You are on page 1of 16

Available online at www.sciencedirect.

com
Available online at www.sciencedirect.com

Procedia
Engineering

Procedia
Engineering
0023
(2011)
000–000
Procedia
Engineering
(2011)
351 – 366
www.elsevier.com/locate/procedia

Review on fruit harvesting method for potential use of
automatic fruit harvesting systems
Peilin Li, Sang-heon Lee, Hung-Yao Hsua*
Student, Division of ITEE,School of AMME,University fo South Australia,Adelaide, South Australia
PHD,Division of ITEE,School of AMME,University of South Australia,Adelaide,South Australia

Abstract
In horticultural industry, conventional harvesting is done by ‘handpicking’ methods to remove hundreds of fruits such
as citrus fruits in random spatial locations on the individual fruit trees. It is well known that harvesting fruits in a
large scale is still inefficient and not cost effective. To solve this challenging task, mechanical harvesting systems
have been investigated and practiced to enhance profitability and efficiency of horticultural businesses. However they
often damage fruits in the harvesting process. Development of efficient fruit removal methods are required to
maintain the fruits quality. This paper reviews fruit harvesting systems from purely mechanical based systems in
which operator involvement is still required, to automatic robotic harvesting systems which require minimal or no
human intervention in their operation. The researches on machine vision system methodologies used in the automatic
detection, inspection and the location of fruits for harvesting are also included. The review is focused on the citrus
fruits due to the fact that the research on citrus fruit harvesting mechanism is a bit more advanced than others. Major
issues are addressed in the camera sensor and filter designs and image segmentation methods used to identify the
fruits within the image. From this review, the major research issues are addressed as future research directions.

© 2011 Published by Elsevier Ltd. Open access under CC BY-NC-ND license.
Keywords: Fruit Harvest; Mechanical Harvest; Automatic Harvest; Physical Sensor; Machine Vision; Image Processing

1. Introduction
In recent years the horticultural industry has funded the research and the development of novel fruit
harvesting systems. Motivation for the research is to decrease harvesting cost and increase the value of
their product to the consumer. Conventional harvesting method is highly labour intensive and inefficient
in terms of both economy and time. Machine harvesting systems are a partial solution to overcome these

* Corresponding author. Tel.: +61-8-83023826; fax: +61-8-83025292.
E-mail address: liypl001@mymail.unisa.edu.au.

1877-7058 © 2011 Published by Elsevier Ltd. Open access under CC BY-NC-ND license.
doi:10.1016/j.proeng.2011.11.2514

lower removal rate in earlier and mid of harvesting season. Another tree shaker with two catching frames each with an inertia type limb shaker was . Last section presents the summary on this review paper with the future directions of the research. limitations of the sensors. the concept of an automatic harvester was proposed and investigated by Schertz and Brown[2] using automatic robotic picking device. Coppock stated that citrus fruit can be harvested by mechanical means after proving that a tree could be mechanically shaken to remove the fruit from the branches without destroying the whole tree. Mechanical harvesting systems are designed to achieve mass removal of the fruit during the harvesting season. the mechanical system operates blind when it come to removing quality ripe fruit. Two streams of harvesting systems have been researched and attempted through years since early 60’s. An alternative tree shaker was represented using fixed stoke. the image sensor for data acquisition and computer aided processing are the main components used to successfully detect the fruit. and large or small immature fruit removal.2352 Peilin al. They are mechanical harvester and automatic harvester. and the use of an abscission chemical agent to loosen the fruits. This section will review those mechanical harvesting methods and others very briefly. Those are detailed in section four and five. the damage to the fruit and trees in some cases and the layout of the grove design for mechanical harvester. In an automatic harvester. canopy shaking. A post selection process can be appended to maintain the aesthetic appearance and value of product for the consumer. 2. and direct impact on trees limbs[6]. 2. They proposed a system which uses a robotic arm to position a manipulator within the picking range of target fruit before detaching the fruit from the tree. Notably some damage was made to the bark of the tree by the clamping mechanism. inertia. It is well known that the robust solutions are still largely underdeveloped. However. a pre-harvest abscission spray was also proposed to loosen the fruits on the tree. Limb Shaker An early limb shaker was represented by Coppock and Jutras[5] using inertia developed by Adrain and Fridley. An eccentric weight about 85 pounds was rotated in the mechanism to produce the shacking action after the shaker was attached to the tree limb. trunk shaking. In order to improve the design of mechanical harvester the biological and physical properties of the fruit were also studied by Coppock et al[4]. There are some issues in mechanical harvesting system such as the quality and size selection. This method has been practiced using such as shaker or air blast with chemical mechanics of abscission as pre-harvest agents to loosen the mature fruits. The issues from this practice included such as fruit damage due to fall foliage. Hence this review paper is focused toward the novel sensor designs and image processing methods which aim to present the reader with an up-to-date account of useful methods found in literature to overcome such issues. Relevant research articles regarding the development of automatic harvesting machines are reviewed in section three. air blasting. and a robust methodology. The guidance for the manipulator is achieved by a machine vision system to detect the fruit. To reduce the physical damage to the tree. Mechanical harvester Mechanical harvesting methods have been investigated and practiced since early 1960s[3]. An overview of the mechanical harvester is outlined in section two. The mechanical harvesting methods reviewed here are limb shaking. In the early 1960s. The issues are multifactor of such as the unstructured environment. The major issues are discussed in section six. The remaining of the paper is organized as follow. / Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 issues by removing fruits from the trees efficiently thus to reduce the harvesting cost to about 35-45% of total production cost[1]. see Sanders[1].1. For a more complete review. However the nature of the horticultural environment makes the fruit detection a challenging task.

However. The efficiency or removal was from 67% on large trees to 98% on small trees. immature fruits were removed with damages to the fruits. The abscission use was subjective to many 3353 . A self-propelling full powered positioning limb shaker was also evaluated with abscission aid by Summer and Hedden[9]. The use of abscission agent was applied as pre-harvest process and constituted part of harvesting such as air shaker[20]. Canopy Shaker A canopy shaker was designed to clamp secondary limbs to shake vertically[13].//Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname developed[7].4. 2. Shaking frequency and stroke are important factors in the performance in this type of harvester and it requires more tests to determine the optimal values. An oscillating air blast machine was tested and practiced by Jutras and Patterson[10]. the fruits picked up from ground had high percentage of bruise. Manual workers were needed to collect the fruits after the harvest. Overall the tractor mounted shaker was more effective with 72% detachment than the hand-held shaker with 57% detachment. Limb shaker used abscission to loosen the fruit on stem[9]. Air shaker was tested with applying abscission agent in advance on FMC-3 by Wilson et al[20]. Later the trunk shakers were tested along with other canopy shakers by Whitney[17].3.5. Hedden and Whitney designed the experiment to evaluate the trunk shaker for earlier season Hamlin orange and late season Valencia orange using different unbalanced mass and multidirectional shakers for years. 2. However still damages to the fruits and leaves were the major issues addressed in the project. It was noted that abscission chemical was inconsistent in practical use[8]. Later. a tractor mounted trunk shaker was tested on varieties of oranges and mandarins in Spain by Torregrosa et al[18] in comparison to a hand-held shaker. Fruit removal was maximized by the oscillation rate. size and weight of fruits. an air shaker was designed and constructed to alleviate issues such as the high power requirement[12]. The air blast model and all the subsequence models were made and named after FMC (Food Machinery Corporation)[11].2. Still. The performance of FMC series was dependent on factors such as structure of tree. 2. These two units were used for juice processing plants. More recently. The linear low frequency shaker with a larger displacement performed better than the canopy shaker machine. An excessive immature oranges were removed during tests conducted by Summer. 2. In test. The shaker was extended into tree with a pantograph lift unit and shake always vertically. Two continuing canopy shakers were reported by Futch and Roka[14].Peilin et al. The bark was more or less damaged during the experiment. one was self-propelled unit and another was tractor-drawn unit. Defoliation was high at high shaking frequency and the bark was damaged in season of May and June. Air Blast The application of force generated by airblast to remove the fruit started in 1961. Trunk Shaker Trunk shaker was used to remove deciduous fruits and nuts but difficult to apply this technique on citrus fruit removal[15. A self-propelled limb shaker was tested on Valencia orange[8]. Abscission Chemical Abscission chemical agent was designed to loosen the mature fruit and improve the rate of removal of fruit in harvesting season. 16]. There are many kinds of abscission agent such as Ethephon and 2-chloroethyl phosphoric acid[19].

A simple black and white(B/W) camera was positioned above the telescope arm aiming fruit horizontally in this model. a tractor pulled rake was made to windrow the fruits to the drip-line and the windrowed machine was used to pick up windrowed fruits[27]. and cost of using chemical such as equipment.4354 Peilin al. For all of these methods mentioned. were studied by Kender et al[21]. However. 3. some other significant robotic harvesting systems for different kinds of fruits harvesting are selected and reviewed as a complementary reference. In addition. The photometric comparisons showed the potential use of the light reflectance for the fruit detection. Then CEMAGREF Montpellier France[31] extended it on the subsequent projects. the fruit rind burn and pre-harvest drop of fruit were observed. High MJ caused great loosening of fruit but excessive defoliation as well. The grove conditions should be considered to maximize the efficiency of all mechanical harvesters based on the comparison study on different mechanical harvesters[28]. The Prosulfuron.6. A camera was fixed in the pathway to detect the fruits and a grasping tool was sent to the fruit within straight line trajectory. Three abscission chemicals and four types of trunk shaker with scissors type clamps were used in the test. Even though the review is majorly focused on the citrus fruit harvester. the video colour camera was applied to replace the B/W camera with a proximity . The automatic individual harvester was considered as an alternative method to the mechanical harvester by Schertz and Brown[2].1. The quality of fruits picked up by a harvesting machine was evaluated. The chemical Methyl Jasmonate (MJ) was tested on whole tree or canopy sectors of Valencia oranges[24]. The study focused on the sensors and the vision system in mechanical manipulator.The state of arts of individual robotic harvesting systems has been reviewed in this section. Also the potential for microbiological contamination to the process was also presented by Goodrich et al[29]. 3. / Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 factors such as weather factors. Post-Harvest Peripheral mechanical harvesting systems such as catching frames have been designed to reduce the damage on falling fruits[26]. MAGALI Project The basic idea of automatic harvesting system was early developed at Montpellier France[32]. This abscission was more effective in Hamlin than others. In the study. The orange removal with various chemicals was discussed in[23]. 2. tree injury. Much concrete works began at around 1983 at Kyoto University at Japan. and at University of Florida. This basic concept was tested on a labouratory prototype in May 1984. Years later. an abscission chemical agent which was used on Hamlin and Valencia oranges loosening. The two detachment devices. These frames also help to collect the fruit efficiently. the consistency of the performance is the major issue. The CMN-P abscission chemical was tested on ‘Hamlin’ orange before the harvesting by trunk shaker[22]. the immature Valencia was loosen before harvest. Usually the chemicals helped to loosen both Hamlin and Valencia oranges and improved the removal rate by 30%. a vacuum twist device and a rotating cutoff device. Both methods were not adaptable to all grove conditions. were used in the research. Automatic harvester The mechanical harvesting system cannot maintain the quality and size selection that the human vision can. The main issue from the test was the pre-harvest drop of fruits. A CMNP abscission chemical was tested on Hamlin and Valencia oranges by Kostenyuk and Burns[25] before the mechanically harvesting. The concepts were further developed by Parrish and Goskel from University of Virgia in 1976[30]. The combined use with other compounds was proposed for later experiment especially on Valencia orange harvest.

The laser ranger finder was sensitive to the outdoor lighting conditions. Then the colour image for the mature fruit detection was used with Bayesian classifier as discrimination function. The gripper was specially designed with the pneumatic suction cup and proximity IR sensor to sense the attached fruit followed by the saw cutter to cut the stem. 38].Peilin et al. The harvesting cycle time for this machine was 2 second. The colour scheme was superior to the monochromatic scheme with over 90% fruits detected. 3. 36]. a single B/W camera of gray level scheme was tested using 635nm wavelength filter and 560nm wavelength filter with a supported flashing light. and the camera positioned in the centre of the manipulator. In average. Two jointed harvesting arms were built and were mounted on the human guided vehicle[39]. 3.//Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname sensor to sense the fruit touch in grasper. each fruit was harvested in around 4 seconds. A Cartesian based manipulator was housed on a vehicle with a caterpillar to maximize the 5355 . CRAM Citrus Picking Robot In Italy. researchers and collabourators from the University of Catania developed a citrus picking robot[40]. Detection was done by the human operator when the vehicle was placed opposite the fruit tree using a joystick to control the pan and tilt mechanism pointing to the target. Inaccuracy of guidance was accounted when the fruit was moved by wind. 34]. Harrel et al overcame this issue by attaching the colour video at the end of the effecter on a spherical manipulator with an ultrasonic transducer to compensate the distance to the fruit[35. The occlusion by leaves was one issue found in the project. The camera was positioned at the centre of rotary joints at the base of the manipulator. The most failures were the distance problem in the approaching stage when it is close to the fruits. Hence the need of knowing distance from manipulator to the fruit target is of all importance in tests. Agribot Project Agribot project from Spain developed a semi-automatic harvester by combining both human and machine functions.2. In vision detection. 3. This “eye-inhand” approach used the contrast colour between the fruit and the background to track the fruit. This first prototype of self-propelled robot was built to harvest the golden apple[33. The prototype used three degrees of freedom and hydraulically powered spherical coordinate with joint position compensation and an end effecter shaped as suction cup.5. 3. The vision coordinates coincided with the robot coordinates making the end effecter in “line of sight”. The manipulator was three degree of freedom(DOF) design with one vertical rotation axes and two horizontal rotation axes and the rotation on the end effecter with gripper. Hence the special goggles were used to block and enhance the red laser spot.3. The gripper was a spherical manipulator with hydraulic power. Florida Citrus Picking Robot Issue for the “line of sight” from MAGALI project was the obscure between the vision and the target during the later picking stage. Eureka Projects Spanish and French research team cooperated on a project to harvest citrus fruits[37. Fruits were localized in spherical coordinates with distance detected by laser telemetry and the angular position by two rotational axes. The cycle for harvesting was about 3 seconds to 7 seconds with 75% fruit detected. More than 50% fruits were detected and harvested with 75% fruits with the stem on.4.

Monocular Scheme In applications. 4. The system was based on a vehicle carrying a six DOF of picking arm consisting of gripper and hand. a single gray scale camera or a colour camera has been widely applied on citrus or orange detection[48]. Regunathan and Lee[54] . Machine vision system in automatic harvesting The vision system used in the automatic harvester aims to detect the fruits and provides the information of the location and the distance to the fruits to the robotic controller. Kondo et al[44] has investigated harvesting method with a robot for tomato.1. Henten et al[45] presented a greenhouse robot to harvest the cucumber using an industrial manipulator with 7DOF to position the end effecter. and grape. Other Fruit and Vegetable Robotic Harvester Some other robotic harvesters have been reviewed and listed. The Italian AID robot vision system adopted a colour camera with artificial lighting to detect oranges. Hayashi et al[46] presented an eggplants robotic harvester. A single grayscale camera was tested using 635nm filter for citrus and 560nm filter for leaves. The major achievements of vision systems and the performance of the various sensors in the harvesting have been reviewed by Jimenez et al[48]. Then two cameras with a red filter and a green filter were tested to segment the fruit respectively. The top arm was equipped with a pneumatic piston to extend the gripper far inside the canopy while the lower arm was not equipped the pneumatic extension. The fruit was located by estimating the diameter. and the control system with the image frame grabber and the image processer. Buemi et al[41] from Italy presented a robotic harvesting system on AGROBOT project to harvest the tomato in green house. and laser range finder[48]. spectral. Normally. In the vision system. In Netherland. two micro cameras. the index RG from RGB colour model was adopted to segment fruits from the background. A prototype of robotic melon harvester was developed and practiced by joint researchers from Israel and USA[42. This section will review those approaches. 3.6356 Peilin al. There are three separate vision system development projects found in European Eureka Project[37.93 second. In Belgium. 4. Over 75% orange were detected with some non-fruit part misclassified. the picking time per fruit is about 5. vision cameras are mainly the solution to communicate with the environment. 38]. Finally a colour image for mature fruits was used for fruit identification with over 90% fruits detected. The sensor techniques applied in agricultural applications have also been reviewed by Chen et al[49]. On top of the basic colour processing. 43]. In vision recognition system. cucumber.6. The distance was estimated based on the dynamic incremental movement of manipulator. Slaughter and Harrell[53] used a digital colour camera with a filter of 675nm wavelength to enhance the contrast between orange fruits and others. The visibility of the fruit citrus on canopy has been studied using multiple perspective viewing method analysis as well for a harvesting robot[52]. In Japan. new technologies have also been investigated especially in the measurement and spectral analysis such as the hyperspectral imaging technology(HIS)[50] and the thermal imaging technology[51]. In simulation test. Approximately 70% of the visible fruit were recognized. The components of hue and saturation from HSI colour space were used to perform threshold to segment the image. Baeten et al[47] integrated the industrial manipulator with the newly designed and patented flexible gripper which consisted of the silicon funnel with camera mounted inside the center of the funnel to harvest apples. / Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 reachability. Kalman filter was used to estimate the real dimension of the fruit in the reaching stage in sequential estimation. intensity. the digital image data has been categorized in three types.

two single B/W cameras were positioned as far vision and near vision sensors for planning and controlling level respectively[42]. Up to 92% fruits were detected. In tests. 7357 . both B/W and colour camera were used to detected the apples[33. In the experiments about 41% of visible apples were detected.Peilin et al. The author proposed the improvement by combining infrared and visible image or by merging multiple sensor fusion methods. Issues such as partial occlusion. Similar to this scheme. The success rate was about 75% for picking attempts and about 50% from all fruits[48]. The photogrammetric principle was applied based on a triangulation algorithm. The intensive computation of transforming the disparity between the objects in two images into depth information was costly. Whittacker et al[59] used a greyscale video camera to capture the tomato images. About 80% apples were detected and harvested in the experiment. Harrell et al[35. Grasso et al[61] developed a stereo matching algorithm to recognize oranges using two images captured from different view of angles. Takahashi et al[63] presented another binocular stereo vision system. In Belgium. The 3-dimensional information was then extracted from stereoscope matching of two tomato images on the same scene. A single camera has been applied also in apple detection. 18 apples were recognized out of 20 visible apples. Some other fruits and vegetables have also been practiced using this scheme. The lighting conditions and occlusion problems affected the detection efficiency. Some issues were found commonly. Sites et al[55] used a single CCD camera to catch gray level fruit images of peach and apple with filters. Average 68% tomato was detected with a proper threshold. and clustering of fruit caused errors in both fruit count and size estimation were addressed.//Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname used a colour camera to capture the citrus fruit with an ultrasonic sensor to obtain the distance between fruit and camera. The measured disparity was difficult to guarantee the estimation of the dynamic shape of the natural fruits. 34]. two colour cameras was designed and positioned on two DOF manipulator heads[41]. One of interesting practices with video sequences was presented by Tabb et al[58] to segment the apples fruit in labouratory environment. Later it was also found that the use of stereoscope matching scheme could extract the 3D information of object from both segmented results from two colour images[41]. About 80% melons were detected in experiment. 36] designed the vision system by positioning the colour video at the end of effecter on a spherical manipulator with an ultrasonic transducer to compensate the distance to the fruit. In MAGALI project. In AGROBOT project. In melon harvesting system. Bulanon et al[56] used a colour CCD camera to acquire images and 80% apples were detected under natural lighting condition. Parrish et al[30] used a single gray scale camera with a colour filter attached to detect the fruit apples. Another stereo matching method was presented by Plebe and Grasso[62] in which two cameras were carried in the center of the gripper on each of two robotic arms. Two colour cameras were designed and positioned separately in a distance with an angle converging to the same scene. Up to 95% of apples were identified. 4. variable illumination. two colour cameras were positioned on each of two DOF manipulator head mechanism. The 3D match was done based on disparity constraints. In Italian AGROBOT project. Binocular Stereoscope Scheme An early approach using stereo vision system was presented by Kassay[60] from Hungary AUFO robot project.2. Baeten et al[47] used the colour camera positioned inside the center of the gripper in a funnel shape. Later to overcome the obscure issue of this scheme. Zhao et al[57] used a single colour image to segment the fruit apples using both colour and texture.

In the experiment. Tangelo. occlusion. Okamoto et al[71] present a green citrus fruit detection using a hyperspectral imaging camera. The wavebands between 542nm to 752nm gave a great statistical disparity between defect surface and normal surface of apples. a custom built laser range finder was applied by Kondo[44] for tomato. A recent project using thermal infrared imaging in fruit citrus canopy was presented by Bulanon et al[51. Benady and Miles[65] presented the use of the structure light with a laser profiling system to locate the melon. each pixel collects stacks of the waveband segments continually across the whole sensible spectrum. Scanning could be improved by parallelizing the scanning and the analysis process[64]. The time to acquire a hyperspectral image varied from 22s to 65s depending on the scanning area and the image resolution. and Hamlin.5. Three different types of green citrus fruits were captured by this sensor. The main cause of incorrect identification was the similar spectral characteristics between the green leaves and the green fruits. and grape harvesting. Totally four types of images were used in the system. surface type. Saint-Marc et al[66] placed two cameras on both sides of the sheet light plane with an angle to overcome the occlusion problem. Valencia. In the image processing. cucumber. Hyperspectral Scheme Hyperspectral technique has been applied in quality inspection analysis and measurement applications. 4. The thermal sensing was based on the heat emission depending on the exposure time from the sun heat. the waveband ratio and difference were preferable since the classification between the normal and defection areas was more consistent in those two. / Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 4. The camera employed could sense from 369nm to 1042nm waveband areas.8358 Peilin al. The histogram based . The thermal radiation which was based on the Stephan-Boltzman law was used as an indicator of the temperature of the emitting object. The use of structured light had faced some issues such as the sparseness of measurements. Ariana et al[70] used a near infrared hyperspectral imaging to detect the bruises on pickling cucumbers. and the orientation of the sensed points. The range and attenuation data values of scanned surface were identified by the laser energy depending on the distance. the hyperspectral sensor is designed to disperse the whole sensible spectral area into discrete wavebands of spectra. and the reading of the orientation of the surface. A similar idea was found in a cherry robotic harvesting system from Japan by Tanigaki[67]. 10 out of 12 fruits were recognized.4. The custom-built active range finder projected and received two lasers light in the same optical axis and the distance from the sensor to the target was calculated by the demodulated signal from both beams.3. A hyperspectral system was developed by Mehl et al[68] to detect the defects and contaminations on apples. 73]. This sensor gave the spherical coordinates of the scanned scene points. 4. Overall 87% visible fruits were detected without any false detection. Thermal Imaging Scheme The infrared thermograph has been applied in application using sensors responding to longer wavelength. The 3D sensor was custom built and equipped with red and infrared laser diodes to detect the ripe cherry. the shape analysis could detect both mature and green fruits if the contour of the fruit was visual more than 70% of the whole. Structured Light Scheme Jimenez et al[64] presented a laser range finder sensor for AGRIBOT robot on orange detection. Ye et al[69] used an airborne hyperspectral remote sensing to predict the citrus yield. It was found that the large temperature difference between the fruit and the canopy occurred around 4:00 pm. In Japan. In the output image. In the experiment. Generally. Two scanned images from both cameras were matched based on the calibration. Stajnko et al[72] developed a method for estimating the number and the diameter of apples in an orchard using a thermal camera.

The multispectral scheme has been more designed in inspection analysis applications.//Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname algorithm performed well during the selected time. The detection of fruit was about 75% when the sky was overcast. and 950nm wavelength respectively[48]. This scheme initially gave the implication to possibly detect immature green fruits by combining different waveband spectra. segmentation to cluster the image into different classes. Kise et al[80. Three images were calculated and combined to generate a binary image. In general a procedure may be accomplished by several steps: image acquisition followed by the feature construction. In Spain. The registration was required to align two different images from thermal sensor and the visible camera by a half-meter PVC pipe frame. The fusion technique using thermal imaging and colour imaging could be a practical alternative during an appropriate time period. More recently. Kane and Lee[75] used a monochromatic near infrared camera equipped with multi waveband pass filters to capture citrus fruit tree images. Regarding the nature of the task in the fruit image analysis. preprocessing to improve the quality of images by such as noise removal. 5. It was proposed that the multispectral images should be captured at the same time with capability of acquiring more wavebands and a smarter image processing technique. Later the author developed a fusion technique to improve the fruit detection using both colour image and thermal image. 81] has developed two types of portable multispectral imaging system. The custom built camera consisted of three CCD micro cameras side by side with three different optical waveband filters in terms of 550nm. a dual-band spectral imaging system and three-band spectral imaging system for contaminant detection in food inspection industry.6. The reason that the number of leaves caused the diffuse reflectance was theoretically studied[76]. 9359 . Three waveband filters were attached to the camera respectively to catch waveband spectral area images. Averagely 84. Some of the analyses have been further discussed in this section.Peilin et al. 4. Methods in image data analysis on fruit harvesting Image processing schemes applied to the images are basically a recognition problem to recognize the fruits. and classification or interpretation by assigning meaning to classes. In the experiment. Lu et al[79] presented a multispectral scheme to predict the firmness and the soluble solids content of the fruit apples. Multispectral Scheme Instead of dispersing spectrum into the discrete numerous wavebands. 650nm. the success rate was high when the temperature of fruit was warmer than the canopy. Another issue was the saturation of sensor value and the dark area on the image. They proposed the method by combining the infrared and visible image to improve the detection result. This work was extended after the measurements on the green leaves and the green citrus fruits through types of citrus and seasons[76]. Dobrusin et al[77] carried out their preliminary investigation on the detection of melon using infrared image. multispectral image capture the specific across wavelength area in the spectrum. The early multispectral scheme was presented by Rabatel[74]. the segmentation part seems to be the centrepiece of all other tasks in analysis. Aleixos et al[78] presented a machine vision scheme on citrus online inspection using two CCD cameras with one camera for visible area detection and the second for infrared area detection. In[48] the methods have been categorized into two groups as local based and shape based.5% correct citrus pixels were identified. However the resultant multispectral images were not well synchronized and matched in dynamic scenes.

55. The interference of background. Benady[65] applied a modified CHT on laser range image data of melon.360 10 Peilin al. Pla[89] developed a method for a partial circle recognition using the segment contours information. 56. the use of threshold or index is considered as a fast way of segmentation. Parrish et al[30] used a No. For example. A large handful work has been applied on citrus fruit images. Similar approaches on citrus images have been reviewed and detailed in[78. the first approach used a fast threshold algorithm on the data acquired from a B/W camera with 630nm wavelength filter and achieved 80% visible fruits detected. Color Based Analysis In colour based analysis. A normalized difference index NDI ( g − r ) / ( g + r ) was also adopted to contrast the image[86]. The global threshold was then applied to segment the fruits form the background. The physical optical filters have been widely adopted to enhance the specific area for the threshold purpose with improvement on the non-uniform distribution. 74. Totally 75% visible fruits were detected and false detection was also caused by occlusion issue. Based on the study on the spectral measurement using spectrophotometer[76]. The shape analysis could be integrated with the advanced technique for the acquisition of multi channel images on the same scene. The index r = 3R − (G + B ) gave high contrast values for red apples. The physical method has also been applied on fruit apples and other vegetables. For example. From European Eureka project. Some colour indices have been applied to segment the image data. A similar method has also been applied on hyperspectral images[71] to detected the green citrus and on a thermal images[73] to detect the citrus fruits. About 80% visible fruit were detected finally[38]. Later. 83]. two cameras were equipped with 630nm and 560nm wavelength filters on each of them. Shape Based Analysis Whittaker[59] applied a circular Hough transform on tomato image segmentation. The ellipsoidal mathematical model on image was based on the illumination function received relative to the position of object and intensity. For example. Pla et al[88] presented a study on the characterization of spherical objects on monochrome images based on Lambert law of diffuse reflector. In the algorithm. the quantification of parameters like circle parameters was based on a minimization criterion using the tangent at each point. In the second approach. a method by fusing the visible image and the thermal image was developed to improve the fruit detection in[51]. . A dynamic threshold value was calculated based on the image maximum and minimum intensity to classify the citrus fruits and the background after segmentation. The ratio between both images was calculated and used. leaves. Slaughter et al[53] used the hue and saturation components as chrominance information to segment the oranges from the background.1. This circular Hough transform (CHT) uses the shape information which is independent of the colour difference between the fruits and foliages. The detection rate was 68% with respect to percentile classification of 99%. Jimenez[64] used a range sensor to acquire the multi images on the same scene and a dual colour and shape methods were employed on different images from the same scene to locate the fruits. Another issue was the intensive computation by CHT[87]. 43. / Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 5. An index R − B was used on citrus fruit image segmentation by Xu et al[85]. Some similar approaches on other fruits and vegetables are reviewed and detailed in works[41. 82. or curvature from the other non-fruit features would be misinterpreted.29 red filter to enhance the apples in image. Kane and Lee[75] applied a normalized difference index similar to NDI on three waveband images instead of RGB. A logical approach was used to find the region of the apples by comparing to the defined region of the apple templates. Zhao et al[57] approached an algorithm on apple images using the texture properties. Stajnko[72] used a thermal imaging camera to estimate the number and diameter of the apple. 84].2. This method could be considered in the case that the contour could be extracted on for example the green mature fruits. 5.

Statistical Based Analysis One of the multivariate statistical pattern classification techniques. the machine learning has been researched to predict the fruit image data distribution using computational learning theory such as statistical tool method.3. The author concluded that the LVQ was not adaptable for real time applications. Jan-jun et al[94] studied and compared a linear vector quantization (LVQ) network based segmentation method with other three methods: dynamic threshold segmentation. The segmentation based on LVQ generated a poor result due to the nonuniform reflection and the high bright area. Both methods achieved 80% fruits detected. Kane and Lee[76] used a spectrometer to measure the different citrus fruits through seasons.D. The principle component analysis(PCA) was employed in this scheme. About 67% orange were detected with 54% accurate detection in the results. Machine Learning Based Analysis The difficulty underlying in the fruit image data is essentially the unpredictable distribution. more literature can be found for analytical or inspection purpose applications using artificial neural network[95].I. The Bayesian discriminant correctly classified 75% of oranges. Ferri et al[91] presented a method based on the nearest neighbor classification and multieditcondensing technique in a vision system for citrus harvesting. However. The multiedit algorithm allowed to select prototypes which belong to Bayes accepted region while the condensing algorithm attempted to eliminate those multiedit references which embedded in the internal regions of Voronoi polygons of each class.Peilin et al. and improved Otsu method combined with genetic algorithm on fruit image.//Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname 5. has been widely applied on the classification based on posterior probability theory. PCA was applied to discriminate the classes between the fruits and the background. On top of that. project from Italy. Slaughter et al[90] presented the Bayes’ classifier on the orange images. Bayes parametric optimal classifier. the neural network performed better in fruit size estimation. In the experiments. The result showed that the traditional Otsu method was faster than other two Otsu methods. Grasso[61] transferred RGB to a modified HSV colour space. Regunathan[54] employed a colour camera and an ultrasonic sensor with a neural network to compare with Bayesian and Fisher linear discriminant methods. 11361 . Juste et al[38] used a pattern classification method of Bayes’ rules which was similar to the method by Slaughter. The Fisher linear discriminant was also used to find the direction of the major eigenvector for the projection of the low dimension space. Bulanon[93] reported that both artificial neural network (ANN) and decision theoretic classifier were used on the segmentation of apples in image for the harvesting robot. about 88% fruits were detected.3.3. A modified K-means algorithm approach was presented by Weeks et al[92] on orange image segmentation. 5. In addition. The success rate was reported up to 90% fruits detected. the time cost of LVQ was higher than Otsu methods. Mehl[68] used a hyperspectral camera on apple surface defects analysis. The study indicated that the hyperspectral data in May had high correlation with the yield. Based on the empirical data. Ye[69] approached a neural network via backpropagation learning algorithm on airborne hyperspectral images to estimate the citrus yield.2. the parametric adjustment for estimation functions in learning algorithm barrier the use of such advanced method in real time harvesting application. Neural Network Approach In A. In European Eureka project. In the experiment. extended Otsu method. 5. A multilayer perceptron trained by backpropagation error algorithm was employed on the segmentation of orange tree images.1.

/ Procedia Engineering 23 (2011) 351 – 366 Author nameLi/ et Procedia Engineering 00 (2011) 000–000 6. Obviously the final fully autonomous fruit picking robot would be based on the integration of developments of those components under the principles for agricultural robotics[98]. Still none of those systems match the capability of the human labour faultlessly. from this review. The degree of freedom of manipulator is still limited in reachability on positioning and extending further inside of the fruit tree canopy since the natural pose of fruits on trees requires a wide degree of the orientation of the end-effecter. Even though mechanical harvesters. However. An efficient method needs to be developed to extract the information of the fruit object accurately from the image for the manipulator. due to the space requirements by the mechanical harvester. In addition. Research issues and discussion Although it is difficult to cover all materials on top of the projects undergoing to the data. The main applications from both mechanical harvesting systems and automatic harvesting systems have been collected. occlusion. The premature dropping of underdeveloped fruit will affect the subsequent seasons harvest[97]. Conclusion The fruit harvesting systems have been reviewed in this paper. mechanical harvesting systems show the advantage in mass production. the fruits must be identified accurately and rapidly. mapping or position in the grove. the successful fruit identification rate is averagely around 70% and up to 90% with variations in some cases. The recent prominent achievements in research have provided a vision for the potential use of automatic harvesters. the operations under the open dynamic natural environment with potential multi-factor make practical applications of automatic harvesters challenging and even unacceptable. The . the issue of the size and quality selection still limits the capability of the mechanical harvesters. On top of it. A mobile locomotive system would be self-navigated with the capability of automatic path planning. Hence this is also another major issue for the mechanical harvester. can provide an efficient and economical way to replace the human labour. the end-effecter design could be customized to be interchangeable grippers. Hence those issues should be solved before any automatic harvester could be used in the practice. the ripeness study[76] on specific fruit spectral could be quantified as well to cooperate with the vision system and methodology development. On top of all. To make the automatic harvesting robot be used in real application. In most literatures. especially for citrus fruits. In addition. The inaccuracy of identification usually comes from inefficient illumination. there is a need for the much further improvement to develop more practical and efficient fruit harvesters.362 12 Peilin al. the machine vision system has been focused covering the sensor schemes and methods behind them. The automatic harvesting systems have been practiced to tradeoff the selection capability between the conventional labour harvester and mechanical harvester. the grove design and the tree locations should be considered in advance to better suit for the harvesting. This is actually a major challenging issue of the fruit picking robot. especially in the vision and the recognition capability. From the literature. With the consideration of the multi-purpose application in mind. The abscission chemical applied to help to increase the efficiency of the mechanical harvesters might also be a critical issue due to the health regulation[1]. Despite undergoing improvement on mechanical shakers and the post selection. However some interests for future research to develop the potential use of this automatic harvester is possible. 7. In addition. the speed of response is critical and challenging for the vision system in dynamic such as in a rapid motion. the costbenefit issue will make the automatic fruit picking robot impracticable if the fruit identification and picking speed is slower than those of picking by the conventional human labour. the damage sustained to the fruits during the harvesting is a major issue that needs to be solved[96]. or inaccurate distance estimation. The real time cost-effective and fully automatic robotic harvester might have a long way from the final prototype yet.

1971. vol. Churchill D B. vol. Soc. vol. University of Florida.4217. pp. [12] Whitney J D. no. 1977. Institute of Food and Agricultural Sciences. [18] Torregrosa A. Florida Cooperative Extension Service. Development of citrus removal device using oscillating forced air./ /Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname navigation is yet developed for the base of the manipulator. [10] Jutras P J. vol. Coppock G E. vol. no. 1967. no. Floriad Agricultural Experiment Stations Journal Series. Design and development of a tree-shaker harvest system for citrus fruit. Picking citrus fruit by mechanical means. Transaction of the ASAE.2824. [20] Wilson W C. vol. vol.4. pp. 1968. The robust sensor development should include the integration of types of data. Proc. Applied Engineering in Agriculture. Florida State Horticultural Society. Harvesting oranges with a full-powered positioning limb shaker. vol.Peilin et al.16. Harvesting early and midseason citrus fruit with tree shaker harvest systems. [19] Wilson W C.. 1984. Soc. Mechanical harvesting of oranges and mandarins in Spain.56-58. Transaction of the ASAE. Floriad Agricultural Experiment Stations Journal Series. Hedden Scott L. 1968.561-563. [7] Coppock G E . fruit yield and removal. [5] Coppock G E .372-374. 1961. Trunk shakers for citrus harvesting part II: tree growth. [14] Futch S H . vol.2. 1969. vol. Harvesting 'Valencia' oranges with a limb shaker. Abscission chemicals aid to citrus fruit removal. 1972. pp.52-56.2.1. pp.522. 2005.1362. in Horticultural Sciences Department. [13] Summer H R. Churchill D B. 1997. 1979. pp. The measurement on special fruits for ripeness study could be helpful in cooperation of the recognition vision system development. Lenker D H. Coppock G E.90. Biosystems Engineering. [4] Coppock G E. Brown G K. Hedden S L.1538. vol. Harvesting citrus fruit with an inertia shaker.18-24. pp. Orange Harvesting Systems Review.104. 1977. [3] Coppock G E. 2005 [15] Hedden S L. Transaction of the ASAE. Transaction of the ASAE. 2009. Chemical and air shaker orange removal in South Florida (Labelle). pp.89-92. Selective harvesting of Valencia oranges with a vertical canopy shaker.2. Whitney J D.117-120. no.849-860. no.12. pp. Floriad Agricultural Experiment Stations Journal Series. Harvesting citrus fruit with an oscillating air blast. Hedden S L. Patterson J M.110. [8] Coppock G E. 1973. vol. Jutras P J. This literature review commenced and based on the valuable project report for robotic citrus harvesting from the centre of Advanced Manufacturing Research at University of South Australia. Field test results with mechanical citrus fruit removal devices. Basic considerations in mechanizing citrus harvest. vol. [2] Schertz C E . et al. The manipulator and gripper could be innovated for multipurpose flexibility. 1962. [16] Hedden S L.5. Whitney J D. pp. no.102-106. no. in American Society of Agricultural Engineers. Int.62-155. pp. Roka F M. vol. vol. no.15.. Donhaiser J R. [17] Whitney Jodie D. no. Transaction of the ASAE. 1989. [6] Coppock G E. Patterson J M. pp.6.4. Acknowledgements The author is indebted to all researchers for their achievements and for all the materials that have been reviewed in this paper and beyond. Floriad State Horticultural Society. Transaction of the ASAE.HS1006. 1962 [11] Whitney J D . Fla.115-125.92. Continuous canopy shake mechanical harvesting systems. Transaction of the ASAE. 1975. Biosystems Engineering. pp.1024-1026. Biophysical properties of citrus fruit related to mechanical harvesting.343-346. no. Design and performance of an air shaker for citrus fruit removal. 13363 . Floriad Agricultural Experiment Stations Journal Series. Trunk shaker removal of oranges. Proc. pp.11. vol. State Hort.20. Citriculture.27.339-342. [9] Sumer Harold R . References [1] Sanders K F.3.

1998. [45] Henten E J Van. 331-338. vol. vol. 2002.1037. Robotic Manipulators in Horticulture: A Review.122. 2000. Ishii Yukitsugu. Amer. no. American Society of Agricultural Engineers. in ASAE. Soc.2. [27] Hedden Scott L. vol. no. Citrus: An European Project to Study the Robotic Harvesting of Oranges. Fla.173-191.41-50.28-33.): Field and Service Robotics. Friedrich Loretta M.119.agric. vol. no.67. [41] Buemi F. 2004. IEEE Transactions on Robotics and Automation. Applied Engineering in Agriculture. Soc. A prototype of an orange picking robot: past history. 1993. Robotic Melon Harvesting. [32] D'Esnon A Grand. Design of an autonomous agricultural robot. Int. [39] Ceres R..113.92. Miles Gaines E. 1977. 1995. Int. Chao Kuanglin. J. Proc. Goksel A K. Ganno Katsunobu. pp. 2000.RA-3. pp.. pp. vol. Proc.5. Fruit harvesting robots in Japan. A Survey of Computer Vision Methods for Locating Fruit on Trees. no. vol. Brisbane. Ehsani Reza. 2006. et al.55. Effects of concentration and application time of 'Prosulfuron' on the abscission of 'Hamlin' and 'Valencia' oranges. 1996. Pictorial Pattern Recognition Applied to Fruit Harvesting. [34] Tillett N D. State Hort.36.20. Sevila F. Effects of abscission chemical spray deposition on mechanical harvest efficacy of 'Hamlin' orange. Slaughter D C. Industrial Robot. State Hort. vol. Applied Intelligence. Abscission chemicals affect trunk shaker orange removal.01-85. Collecting and handling mechanically removed citrus fruit. Soc. et al. 1977. pp. Fla.93-96.13. [28] Whitney J D. et al. 1995. pp. [33] D'Esnon A Grand.269-278. Citriculture. Collecting and handling mechanically harvested oranges in South Florida (Labelle). Juste F. 1990.6. Hort. [24] Hartmond Ulrich. Munilla R D. Computers and Electronics in Agriculture.43. Space Res. Soc. 2002.8. / Procedia Engineering 23 (2011) 351 – 366 AuthorPeilin nameLi/ Procedia Engineering 00 (2011) 000–000 [21] Kender W J. et al. A Fruit-Tacking System for Robotic Harvesting. pp. 1992.1. Soc. vol. Citrus fruit abscission induced by Methyl-jasmonate.59-61. Industrial Robot: An International Journal. Burns Jacqueline K. Robotica. vol.25. no. J. pp. Bourely A. Spatial Distribution Mapping of Pasture Herbage Mass by Hyperspectral Imaging. pp. 1985. pp. Mechanical wounding and abscission in citrus. [25] Kostenyuk Igor A .. Churchill D B. 1999... no. Sandini G. vol.5. pp. [35] Harrell R C. Ieee Journal of Robotics and Automation. pp.531-539. pp. pp. Robotics in Agriculture & The Food Industry. Sumner H R. 1979. Nut.6. Ceres R. pp. Flash Tamar. vol. pp. 210-214. no. 2000. Magali: a Self-Propelled Robot to Pick Apples. vol.108-112. Fujiura T. no. Proc.18. [30] Parrish E A. Transactions of the ASAE. [48] Jimenez A R.4. Australia. Autonomous fruit picking machine: a robotic apple harvester. Robotic Harvesting of Citrus: State-Of-Art and Development of the French Spansh EUREKA Project.89-105. Adsit P D. no. 1987.2..831-834.1/2. Robotic picking of citrus. An autonomous robot for harvesting cucumbers in greenhouses. Design and implementation of an aided fruit-harvesting robot(Agribot).112. Tanaka Itsuo. 1987.413-418.5. 2008.128-138.STAR 42. Machine Vision and Applications. [36] Harrell R C. vol. vol. vol. pp. [43] Edan Yael.. 1995. Fla. Laugier and R. pp. 1998. [46] Hayashi Shigehiko.69-80.36. Jr... Proc. Robotic harvesting system for eggplants.1911-1920. in Proceedings of the 3. 2002. and Vegetable Harvesting Mechanization Jordbrugsteknik Agricultural Engineering. [23] Whitney J D. vol. [29] Goodrich Renee M. Massa M. [44] Kondo N.. Sci.195-197. Slaughter D C. Churchill D B. pp. Citriculture. Proc.3. vol.125. Monta M. [42] Edan Yael. SME.111. et al. Adv.32.241-258. pp.2. Rogozin Dima. 2009 .163-168.3. State Hort. vol.. Pons J L. pp. vol. 2000. pp. Kim Moon S. [37] Rabatel G. vol.822-827.364 14 et al. International Symposium on: Fruit. Soc. [31] Sistler Fred E.205-210. pp.354-361. Prestifilippo M. no. JARQ. Physiologia Plantarum. 1989. 1999. Transactions of the ASAE. vol.. no. et al.547-552. [47] Baeten Johan. no.3-6. vol..16. pp. vol. Sevila F. et al. the new robot and experimental results.5. vol. Engng Res. Robotics and Intelligent Machines in Agriculture. [40] Muscato G . Soc. Fla. Robotic Harvesting of Apples. Adsit P D. Autonomous Robots. [38] Juste F . pp. Proc.337-346. vol.172-184. in Biennial Conference of the Australian Society for Engineering in Agriculture (SEAg). Machine Vision Technology for Agricultural Applications. [49] Chen Yud-Ren. Salyani Masoud. no. State Hort. pp. et al.181-184. [50] Suzuki Y. [26] Sumner H R . 2005. [22] Koo Young M.87.15. Field test results with mechanical harvesting equipment in Florida oranges. vol.. Effect of fruit pick up systems on the microbial quality of citrus fruit surfaces. Siegwart (Eds. Whitney Jodie D. Agrobot: A Robotic System for Greenhouse Operations.

250-256. pp. in American Society of Agricultural Engineers. vol. Tow Joel.30. Jezouin J-L. pp. On-tree Fruit Recognition Using Texture Properties and Color Data.198. Netherlands. vol. 15365 .31-42. Wageningen. Recce Michael.92-7021. [54] Regunathan Murali . [70] Ariana Diwan P. in American Society of Agricultural Engineers. Computers and Electronics in Agriculture. Spectral Sensing of Different Citrus Varieties for Precision Agriculture. pp. pp. Society for Engineering in Agricultural. [68] Mehl Patrick M. pp. vol. 1-14.. no. Food. Gaultney L D. Medioni G. [67] Tanigaki Kanae. A Versatile PC-Based Range Finding System.31.. 2008. Cherry-harvesting robot. Multispectral Imaging for In-field Green Citrus Identification. [61] Grasso Giorgio M . Computers and Electronics in Agriculture. Ceres R.52. 1992 [66] Saint-Marc P. 2009.12-22. vol.1-8. [65] Benady Meny . [52] Bulanon D M. Navarron F.53. [74] Rabatel G. [73] Bulanon D M.053017.92-3515.061065. Miles G E. pp. 2004. vol. Citrus Fruit Identification and Size Determination Using Machine Vision and Ultrasonic Sensors. 1991. [72] Stajnko D.32. pp. Journal of Food Engineering. no.COMPAG-2106. Segmentation of Apple Fruit from Video via Background Modeling.073025. [75] Kane Kevin E . 1992 [78] Aleixos N. Near infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers. Blasco J. Lakota M. Lee Won Suk. 1988. [63] Takahashi Teruo. vol. 2006 [77] Dobrusin Yuri. Peterson Donald L. Computers and Electronics in Agriculture.161-171. American Society of Agricultural Engineers. Imagawa Junichi. in American Society of Agricultural Engineers. 2008.147-157.III. Lee Won Suk. in 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2002. Hiroma T.1144-1148. 2005 [55] Sites Peter W . 2004. pp. and Biolo. 1987. no.66. in American Society of Agrigultural Engineers. no.33. 1987. vol. pp. Pons J L. [53] Slaughter David C . vol. Computer Vision to Locate Fruit on a Tree. Lu Renfu. Multispectral Inspection of Citrus in Real-time Using Machine Vision and Digital Signal. Netherlands.121-137. VIAS Wageningen. Fujiura Tateshi. Estimation of citrus yield from airborne hypersepctral images using a neural network model. no. 2009.1. 2001. Guyer Daniel E. pp. vol.61. Ecological Modelling. IEEE Transactions on Robotics and Automation.1-11.. Localization of spherical fruits for robotic harvesting. Chan Diane E. Hungarian robotic apple harvester. Chen Yud-Ren.101. Scene Analysis for an Orange Picking Robot. Harrell Roy C. Study on temporal variation in citrus canopy using thermal imaging for citrus fruit detection. Computer and Electronics in Agriculture. Fruit Location in a Partially Occluded Image. American Society of Agricultural Engineers. pp.70-79. no. Measurement of 3-D Locations of Fruit by Binocular Stereo Vision for Apple Harvesting in an Orchard. Park Johnny. Image fusion of visible and thermal images for fruit detection.591-597.2.1719-1736. no. pp.426-432. in American Society of Agricultural and Biological Engineers. Agricultural Engineering International: the CIGR Journal of Scientific Research and Development. pp. Fukuchi Hiroshi. et al. no.13.257-263. A Machine Vision System for the Apple Harvesting Robot.103. Locating melons for robotic harvesting using structured light. Fruit Visibility Analysis for Robotic Citrus Harvesting. Molto E.277-283. no.31. Computer and Electronics in Agriculture. Rostharvest Biology and Technology. 2006. pp. pp. Automatic fruit recognition: a survey and new results using Range/Attenuation images. no. Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging. in Agricultural Engineering. in American Society of Agricultural and Biological Engineers. Biosystems Engineering. vol. Jain A K. Akase Akira. Alchanatis V. in International Congress for Computer Technology in Agriculture. Lee Won Suk. 2009. 2001. the fruit picking robot.7.201-208. 2002 [64] Jimenez A R. Zhang Shuhuai. Burks T F. [69] Ye Xujun. Real-time image processing for robotic melon harvesting. Pattern Recognition. vol. Lee Won Suk. in American Society of Agricultural and Biological Engineers. 2006 [59] Whittaker A Dale. 2004.1. Biosystems Engineering. pp. Burks T F. vol.Peilin et al.30.4. no. 1992. vol.021102. Burks T F. [56] Bulanon D M. pp. 2005 [58] Tabb Amy L. Alchanatis V. pp. no.42.67-81. 1999. et al. vol. American Society of Agricultural Engineers. Grasso Giorgio. [60] Kassay L. no. 1988: Paris. Color vision in robotic fruit harvesting. Hocevar M. Green citrus detection using hyperspectral imaging. Delwiche Michael J. Mitchell O R. [79] Lu Renfu. Alchanatis V. vol. Miles Gaines E.063060.92-7042. 2006. Multispectral imaging for predicting firmness and soluble solids content of apple fruit. A vision system for Magali. 1996 [62] Plebe Alessio . vol. in American Society of Agricultural Engineers./ /Procedia ProcediaEngineering Engineering00 23(2011) (2011)000–000 351 – 366 AuthorLiname [51] Bulanon D M. Machine Vision and Applications. vol.3. American Society of Agricultural and Biological Engineers. vol. Kataoka T. [71] Okamoto Hiroshi . 2007 [76] Kane Kevin E . Development of Hyperspectral Imaging Technique for the Detection of Apple Surface Defects and Contaminations.60-70. Katupitiya Jayantha. Ota Y. Kim Moon S. [57] Zhao Jun.

87-116. 1991 [85] Xu Huirong . pp. [81] Kise Michio. 2002. State Hort.2. Segmentation methods of fruit image based on color difference. no. Park Bosoon. Design and calibration of a dual-band imaging system.1. Su-yu Zhong. Computers and Electronics in Agriculture. Proc.63. Detection of Oranges from a Color Image of an Orange Tree. no. [93] Bulanon D M. Alchanatis V. Miles Gaines E. et al. vol. Proc. vol. Handels H. in American Society of Agricultural and Biological Engineers.2. no. Bargen Kenneth Von. Editor.1. Amsterdam. 2007 [83] Hannan M V. Burns Jackie. Hata S. Citriculture. in Proceedings of SPIE . Juste F. pp. Pattern Recognition vol.6. 1999. [91] Ferri Francisco . A Survey of the Hough Transform.366 16 et al.118.208. size. Sens. vol..61-68.073124. [82] Bulanon D M. 2004 [94] Jian-jun Yin. Computer Vision and Image Understanding. John Wiley & Sons.. Burks T F.757-763. no. Eriksson J. Nof. 1989. 2010. Machine vision to locate melons and guide robotic harvesting. 1988.13.. vol.22-24. no. vol. Food and Agriculture Robotics. [95] Egmont-Petersen M.8. Lawrence Kurt c. Elsevier Science Publishers B. vol. Inc. and Active Vision. 1977. no. pp.7.334-343. Citrus fruit recognition using color image analysis.44.1836. 1996. Graphics and Image Processing. Ferri F. pp.Y. in American Society of Agricultural and Biological Engineers. Gallagher A. Recognition of Partial Circular Shapes from Segmented Contours. SPIE. pp. Multispectral imaging system with interchangeable filter design.5608. Bulanon D M. pp. and enumeration using machine vision techniques on near-binary images. Syvertsen Jim.561-568. pp. Burks T F. [92] Weeks A R. Soc. Kittler J.57-72. vol.V. [86] Woebbecke David M. Pattern Recognition. Plant species identification. no. Image Processing with Neural Networks . Int. Determining the 3-D location of the apple fruit during harvest. 2005.2. American Society of Agricultural Engineers. [87] Illingworth J .the International Society for Optical Engineering. Fla.91-7006. Ying Yibin. vol. [89] Pla Filiberto. [90] Slaughter David C . Ridder D de. & Instrumen. in Handbook of Industrial Robotics. pp. pp. Meyer George E. 2009.701P1004. Hezroni Amots. American Society of Agricultural Engineers. Discriminating Fruit for Robotic Harvest Using Color in Natural Outdoor Scenes. no. Mortensen David A. Mechanical harvesting of Florida citrus trees has little effect on leaf water relations or return bloom. vol. Kataoka T.32. [97] Li Kuo-Tan.321-328. Techniques. pp. [98] Edan Yael. Study on Fruit Visibility for Robotic Harvesting. Intelligent Robots and Computer Vision XXII: Algorithms. Feature extraction of spherical objects in image analysis: an application to robotic citrus harvesting. Vidal Enrique. Computer Vision. Harrell Roy C. 2004. Han-ping Mao. / Procedia Engineering 23 (2011) 351 – 366 AuthorPeilin nameLi/ Procedia Engineering 00 (2011) 000–000 [80] Kise Michio.113-121.35. vol. in American Society of Agricultural Engineers. [88] Pla F.A Review. 2007 [84] Cardenas-Weber Martha. pp. no. . vol. Colour image segmentation and labeling through multiedit-condensing. 2007. no. 1992. Soc. 1993.2279-2301. Windham William R.72. Mechanical removal of fruit from citrus trees. Journal of Communication and Computer. [96] Whitney J D.40-45. Food Qual. A Real-time Machine Vision Algorithm for Robotic Citrus. 1993. Okamoto H. Proc. S.073125. 1999.