e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

Volume:02/Issue:05/May-2020 www.irjmets.com

COW DETECTION SYSTEM

Miss. Sayali Kale*1, Miss. Toshali Bhadke*2, Miss. Shrushti Hajare*3, Miss. Shivani Watekar*4
Mr. Sumit Pal*5
*1,2,3,4,5
B.E., Students, Datta Meghe Institute of Engineering Technology and Research, Wardha,
Rtmnu University, India.

ABSTRACT
One serious problem that all the developed nations are facing today is death and injuries due to road accidents.
The collision of Cow with the vehicle on the highway is one such big issue, which leads to such road accidents.
In this paper, a simple and a low-cost approach for automatic Cow detection on highways for preventing animal-
vehicle collision using collision detection techniques are proposed. A method for finding the distance of the
Cow in real-world units from the camera mounted vehicle is also proposed. The proposed system is trained on
more number of images consisting of positive and negatives images and tested on various video clips of Cow
on highways with varying vehicle speed. As per the two-second rule, our proposed method can alert the driver
when the vehicle speed is up to 35 km/h. Beyond this speed, though the Cow gets detected correctly, the driver
does not get enough time to prevent a collision.
KEYWORDS: PC Vision, Camera, Image philosophy, Calculation.

I. INTRODUCTION
The present car configuration principally relies upon well being measures, security devices and solace
instrument. The approach has encouraged the advancement of a few vehicles that depend on current apparatuses
and innovation for their execution. The security of a vehicle is the most astounding need as per an ongoing
report [1]. The report appointed by World Health Organization in its Global Status Study on Road Safety 2013,
uncovered that the main source of death for youngsters (15-29 age) all around is because of street car accidents.
Despite the fact that different nations have started and found a way to lessen street car accidents and mishaps,
the aggregate number of accidents and car crashes stay as high as 1.24 million every year [2]. As indicated by
information given in an examination [7], the quantity of individuals who lost their lives in India because of
street mischances was right around 0.11 million passings in 2006, which was roughly 10% of the aggregate
street mishap passings on the planet. As per the mischance inquire about examination led by JP Research India
Pvt. Ltd. for the Ahmedabad-Gandhinagar locale (urban communities of India), for the term February 2014 to
January 2015, add up to 206 street car crashes were recorded and these were affected by three principle factors
i.e. human, vehicle, framework or a mix of them [8]. According to the surveys and report given by the Society
for Prevention of Cruelty to Animals (SPCA) and , the number of accidents on Indian roads has increased due to
increase in a number of vehicles day by day and also due to the presence of animals on the road (mainly two
animal’s dog and Cow). The collision of an animal with the vehicle on the highway is one such big issue apart
from other problems such as over speed, abrupt lane change, and drunk-drive and others which lead to such road
accidents and injuries. The associated number of fatalities and injuries are substantial too. Specific reasons
behind developing automatic Cow detection system in place of any other animal are: India is mainly an
agriculture based country where 70% of people depend on agriculture, and 98% of them depend on Cow based
agriculture. The Cow is a sacred animal in India and nobody wants to hit a Cow. Cow milk is the most useful
and compatible with human mother’s milk than any other animal or so. According to some surveys, Cow’s milk
and Cow dung have many medicinal benefits. Cows, as well as dogs, are found quite often than other animals on
the Indian roads. As Cow is a large (heavy) sized animal, the collision between a Cow and vehicle will be very
much severe. The collision between a small (less weight) sized animal like Dog and car won’t be that much
severe. The speed with which the vehicle is coming and hitting the animal also plays a critical role in deciding
the impact of the collision. Though various practical solutions for automatic lane detection and pedestrian
detection on highways are available still research related to Cow detection on highways is going on. Cow
detection in wildlife (forest) videos or underwater videos (controlled areas) have been tried in past but the
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[45]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
challenges are much more when detecting animals on highways (uncontrolled areas) as both animal as well as a
camera mounted vehicle is moving apart from other obstacles on the road which are also moving or stationary.
There is no issue of speed (vehicle speed as well as animal speed) and detecting distance of animal from the
vehicle in wildlife videos which is crucial and critical in animal detection on highways. The biggest challenge in
detecting Cow compared to pedestrians or other objects is that animals come in various size, shape, pose, color
and their behavior is also not entirely predictable. Though the basic shape and size of a human being are pretty
average and standard, the same is not true for animals. Although various methods and approaches have been
used and are still in progress to detect, solve and reduce the number of Cow-vehicle collisions, the absence of
any practical systems related to a Cow-vehicle collision on highways has delayed any substantial development
in the scenario.

II. METHODOLOGY
The biggest challenge in detecting animals compared to pedestrians or other objects is that animals come in
various size, shape, pose, color and their behavior is also not entirely predictable. Though the basic shape and
size of a human being are pretty average and standard, the same is not true for animals. Although various
methods and approaches have been used and are still in progress to detect, solve and reduce the number of
animal-vehicle collisions, the absence of any practical systems related to an animal vehicle collision on
highways has delayed any substantial development in the scenario. Following are the methods to solve the
problem.
a) Proposed System:
The image is inputted for object detection in system. Then we are doing preprocessing steps to enhance the
image. For feature extraction and learning of the system, we are using a combination of clustering and
classification for animal detection. All the image processing techniques are implemented in Matlab software.
Once the animal gets detected in the image, the next step is to find the distance of the animal from the testing
vehicle and then alert the driver so that he can apply the brakes or perform any other necessary action which is
displayed on command prompt as a message.
Depending on the distance of the animal from the camera mounted vehicle, three kinds of messages (indication)
are given to the driver i.e. animal very near, if animal is very near to the vehicle, animal little far, if the animal is
little far from the vehicle and very far, if the animal is very far and at a safe distance from the vehicle.
b) System Requirements:
Hardware and Software Requirements:
MATLAB is a high performance language for technical computing. It takes part in computation, visualization,
an d programming in an easy-to-use environment where problems and solutions are expressed in familiar
mathematical code. Typical uses include: Math and computation. MATLAB is programmable software for
multi-paradigm numerical environment. This software is developed by the Math Works. MATLAB also consists
with the Image Processing Toolbox software, which is a collection of functions that extend the capability of the
MATLAB numeric computing environment. The toolbox supports a wide range of image processing operations
including:
• Spatial image transformations
• Morphological operations
• Neighborhood and block operations
• Linear filtering and filter design
• Transforms
• Image analysis and enhancement
• Image registration
• Region of interest operations
Many of the toolbox functions are MATLAB M-files, a series of MATLAB statements that implement
specialized image processing algorithms. It can view the MATLAB code for these functions using the statement
type function name. It can extend the capabilities of the toolbox by writing your own M-files, or by using the
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[46]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
toolbox in combination with other toolboxes, such as the Signal Processing Toolbox software and the Wavelet
Toolbox software.
System Configuration :

Processor Intel® Core™ i3 Processor 2.40 GHz

4 GB
RAM

64 bit
Operating System

l MATLAB R 2015 a
Programming Tool

c) List of Modules: CAO Detection system project comprises of main modules are listed below:
• Object detection map
• Segmented image and final image
• Object detect image and object crop image
• Gray image
• Gradient image
III. MODELING AND ANALYSIS

Figure-1: System Architecture.

Module Description:
• Object detection map:
MAP in object detection is the Mean Average Precision. Its use is different in the field of information retrieval
and multi class classification settings. To calculate it for object detection, you calculate the average precision for
each class in your data based on your model predictions. Average Precision is related to the area under the
precision-recall curve for a class.
Taking the mean of these average individual class-precision gives you the Mean Average Precision.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[47]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
• Segmented image and final image:
Image segmentation is the process of partitioning a digital image into multiple segment. Image segmentation is
typically used to locate objects and boundaries in image. It is process of assigning a label to every pixel in an
image such that pixels with the same label share certain characteristics. Each of the pixels in a region are similar
with respect to some characteristic or computed property, such as color, intensity or texture.

• Object detect image and object crop image :

In object detected image i.e. Cow image is detected by bounding boxes that are around object are check. This is
a 2d coordinate system. So, bounding box is merely the coordinates of the rectangular border that fully encloses
a image. Object cropped image to specified bounding box that cuts a rectangular part of image.

• Gray image:
A gray scale digital image is an image in which the value of each pixel is a single sample. Displayed images of
this sort the typically composed of shades of gray, varying from black at the weakest intensity to white at the
strongest. The values of intensity image ranges from 0 to 255.

• Gradient image:
Gradient operators are based on local derivatives of the image function. Derivatives are biggest at locations of
the image where the image function undergoes rapid changes. The aim of gradient operators is to indicate such
locations in the image. Gradient operators have a similar effect as suppressing low frequencies in the frequency
domain.

Figure-2

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[48]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
IV. RESULTS AND DISCUSSION
1. First we have to apply object detection mapping method where we average mean precision is used. To
calculate it for object Detection,you calculate the average precision for each class in your database done your
model predictions.

Fig-4.1: Object Detection Map

2. Image segmentation typically used to locate objects and boundaries in image.

Fig-4.2: Segmented Image and Final Segmented Image

3. Here object cropped image to specified bounding box that cuts a rectangular par to fix image.

Fig-4.3: Object Detected Image and Object Cropped Image

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[49]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
4. Displayed images of this sort the typically composed of shades of gray, varying from black at the weakest
intensity to white at the strongest.

Fig-4.4: Gray Image

5. At last the image is converted from gray to gradient image to measure the change intensity of that same point
in the original image in a given direction.

Fig-4.5: Gradient Image

V. CONCLUSION
An efficient Cow detection and a warning system can help drivers in reducing the number of collisions
occurring between the Cow and the vehicle on roads and highways. In this paper, we discussed the necessity of
Cow detection system and our algorithm for Cow detection based on HOG and cascade classifier. The algorithm
can detect a Cow in different conditions on highways. The proposed system can be used with other available,
efficient Cost 50 % regarding animal (Cow) detection. Estimation of approximate Cow distance from the testing
vehicle is also done. Though the proposed work has been focused on Cow detection in context to Indian
highways, it will work in other countries also. The proposed method can easily be extended for detection of the
cow detection systems and can be offered as a complete solution (package) for preventing collisions and loss
Human life on highways.

VI. REFERENCES
[1] Sachin Umesh Sharma And Dharmesh J. Shah”,A Practical Animal Detection And Collision Avoidance
System Using Computer Vision Technique” Special Section On Innovations In Electrical And Computer
Engineering Education IEEE 2018,pp.128- 131.
[2] Prof. Latha Venkatesan, S.Omar Farooq ,Animals And Vehicle Collision Avoidance Using Wireless
Sensor Actuator Network, International Journal Of Scientific & Engineering Research, Volume 4,
pp.100-101,May-2013.
[3] Dr. C. Li And Dr. R. Venkatesan ,Enabling A Wildlife-Roadway Collision Warning And Mitigation
System Using Wireless Sensor Networking Technologies ,March 2013.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[50]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:05/May-2020 www.irjmets.com
[4] Khaled Ragab ,Simulating Camel-Vehicle Accidents Avoidance System, International Journal Of Future
Generation Communication And Networking Vol. 4, pp.98-99, December 2011.
[5] Norris L. Dodd ,Evaluation Of Measures To Minimize Wildlife-Vehicle Collisions And Maintain
Wildlife Permeability ACROSS HIGHWAYS IN ARIZONA, USA Animal-Vehicle Collision Reduction,
ISBN, 2014.
[6] J. Padmanaban, R. Rajaraman, G. Stadter, S. Narayan, and B. Ramesh, ‘‘Analysis of in-depth crash data
on Indian national highways and impact of road design on crashes and injury severity’’, in Proc. 4th Int.
Conf. ESAR ‘Expert Symp. Accident Res’, Hanover, Germany, pp. 170–183 ,Sep 2010.
[7] Ministry of Home Affairs. Accidental Deaths & Suicides in India 2006, Nat. Crime Records Bureau, New
Delhi, India, Jun 2007.
[8] Accident Research Study on the Ahmedabad–Gandhinagar Highway for the Duration February 2014 to
January 2015, JP Res. India Pvt Ltd,Mar 2015.
[9] S. Sharma and D. J. Shah, ‘‘A brief overview on different animal detection method’’, Signal Image
Process, Int. J, vol. 4, pp. 77–81, Jun 2013.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[51]