This action might not be possible to undo. Are you sure you want to continue?

# Asian Journal of Control, Vol. 3, No. 1, pp.

64-68, March 2001

64

–Brief Paper–

**APPLICATION OF FUZZY LOGIC TO VEHICLE CLASSIFICATION ALGORITHM IN LOOP/PIEZO-SENSOR FUSION SYSTEMS
**

Sung-Wook Kim, Kwangsoo Kim, Joo-hyung Lee and Dong-il (Dan) Cho ABSTRACT

Individual vehicle information, especially, vehicle classification data play a key role in Advanced Traffic Management and Information Systems (ATMIS). In inductive loop and piezo-sensor fusion systems, traffic data such as the vehicle length and the distance between axles are used for vehicle classification. However, classification errors often occur in distinguishing passenger cars from small trucks and in distinguishing medium-sized trucks from small trucks. It is mainly attributed to the fact that they are similar in lengths and have similar inter-axle distances. To improve the performance in vehicle classification, we develop a new algorithm using a fuzzy logic. Vehicle weight and speed are used as the inputs to the fuzzy logic block. The output of the fuzzy logic block is a weighting factor to modify the calculated vehicle length. Experimental results show that the developed algorithm significantly improves the classification performance. KeyWords: Fuzzy logic, loop/piezo-sensor fusion system, vehicle classification algorithm.

I. INTRODUCTION

Recently, traffic congestion has become a serious problem. However, the construction of new roads alone is not the solution to effective traffic management [1,2]. To manage the traffic congestion effectively, traffic information such as vehicle speed, number of passing vehicles, travel time, and vehicle classification data should be supplied by various traffic detectors. Especially, vehicle classification data can serve as the fundamental data for planning new road constructions, establishing road maintenance policies, and calculating travel times. Many studies have been conducted to identify vehicles using various traffic sensors, such as microwave, ultrasonic, inductive loop, video image, and vehicle sound sensors [18]. One of the most commonly used technologies for

Manuscript received July 19, 2000; accepted September 6, 2000. The authors are with School of Engineering and Computer Engineering, Seoul National University, San 56-1, ShinlimDong, Kwanak-ku, Seoul, 151-742, Korea. This work was supported by the Ministry of Commerce, Industry and Energy from a ITEP program, and the second and third authors were supported in part by BK 21 Project.

vehicle classification is the combined loop and piezoelectric sensor system [2,9]. In this loop/piezo-sensor fusion detector, the vehicle length information is one of the most important data [1,2]. Therefore, obtaining accurate vehicle length data is critical to obtain accurate vehicle classification results. The calculated vehicle length, however, may not be exact, because the outputs of inductive loops may not be sufficiently excited when the variation of inductance is small. Hence, if the outputs of two inductive loops are directly used, the length data can result in underestimating vehicle lengths. Fuzzy algorithms have been successfully applied to a variety of industrial applications, including automobiles, autonomous vehicles, chemical processes, and robotics [10,11]. In the traffic application area, fuzzy logics have also been used to control the traffic signal in intersections and to develop incident detection algorithms [12,13]. These successful applications are attributed to the fact that fuzzy systems are knowledge-based or rule-based systems. In the loop/piezo detector, there is no exact mathematical relationship between the vehicle length and speed, or between the length and shape. However, a heuristic knowledge of how the vehicle speed or shape may have an influence on the measured length is available. This heuristic knowledge can be expressed well in terms of a fuzzy

the vehicle weight. TP1. and. The fuzzy rules in this paper are as follows: IF weight is very light and speed is slow. positive small(PS). In this paper. and the output of the piezoelectric sensor is an analog signal as shown in Fig. Then. This in turn can result in underestimating the length. speed. as well as the distance between axles can be calculated. passenger cars and small trucks are similar in lengths and have similar inter-axle distances. the cargo area can be far away from the road surface. 1. The organization of this paper is as follows. and the length modification are interpreted as the linguistic variables which have some of linguistic values as follows: Speed = {slow(S).65 S. and medium-size trucks from small trucks. light(L). This modified vehicle length is used to improve the performance in classifying the vehicle into a particular category. OPERATIONAL PRINCIPLES OF LOOP/ PIEZO-SENSOR FUSION SYSTEM In a loop/piezo traffic detector. number of axles. zero(ZE). therefore. the vehicle speed and length. The system configuration can be either two inductive loops and one piezoelectric sensor. A direct consequence of this involves the difficul- Fig. Experimental results are shown in section IV. the developed algorithm can also be applied to the system with one inductive loop and two piezoelectric sensors. Finally. Thus. 3. the final classification result is generated in the vehicle classification block. by the use of fuzzy algorithms. the interaxle spacing information cannot be used to distinguish the vehicle types in this case. which gives only a small inductance change. medium(M). The heuristic knowledge of other factors that can influence the length value is used to modify the length value. The outputs. heuristic knowledge was found that the weight and speed of a vehicle can be effectively used in modifying the length data. TL4. Kim et al. THEN length modification is zero IF weight is very light and speed is medium. The basic idea for the new classification algorithm is to modify the length value output from the loop sensor. 1. DEVELOPED CLASSIFICATION ALGORITHM USING A FUZZY LOGIC To improve the situation. Weight = {very light(VL). the modified length value is generated from the length fuzzy logic block. . The output is a weighting factor for modifying length value. ties in discriminating passenger cars from small trucks.16]. With the modified vehicle length. the vehicle length is calculated directly using the outputs of two inductive loops. Length modification = {negative big(NB). TL3. positive big(PB)}. TL2.-W. From extensive experiments.: Application of Fuzzy Logic to Vehicle Classification Algorithm in Loop/Piezo-Sensor Fusion Systems logic using the so-called fuzzy IF-THEN rules [14]. fast(F)}. and T P3). THEN length modification is negative small II. TP2. medium(M). 2. The dashed box in the middle represents a newly developed fuzzy logic block. A brief operational principle of loop/piezo-sensor fusion vehicle detector systems is explained in section II. and inter-axle distance. In the fuzzy logic block. the inputs to the fuzzy logic block are the vehicle weight and speed. Typical output waveform of two inductive loops and one piezoelectric sensor (3-axle vehicle). the configuration and the methodology of the developed classification algorithm using fuzzy logic are presented in detail in section III. In addition. The fuzzy rule base is an IF-THEN linguistic rule using the fuzzy input and output sets. The total vehicle weight as well as individual axle weight information can also be obtained by processing the piezoelectric sensor signal. In a conventional classification algorithm. From the time data (TL1. heavy(H)}. and the piezoelectric sensor is used to detect a passing vehicle by the pressure generated from tires. Especially for trucks. the use of fuzzy algorithms is targeted at the system with two inductive loops and one piezoelectric sensors. In this paper. Each linguistic value is represented by an appropriate membership function. III. This paper discusses improving the vehicle classification performance of loop/piezo detectors. triangle membership functions are used as shown in Fig. From this weighting factor and the raw length value. the modified length is used to classify the passing vehicle. The typical output of the inductive loop is a digital on-off signal. however. inductive loop coils and piezoelectric sensors are installed under the pavement at each lane. or one inductive loop and two piezoelectric sensors [2. negative small (NS). however. The inductive loop coil is used to detect the presence of a passing vehicle by sensing the inductance change in the loop coil. a new classification algorithm using a fuzzy logic is developed. may not be sufficiently excited when the variation of inductance is small. The configuration of the developed algorithm is shown in Fig.

the computational complexity is not a great disadvantage in the proposed system. The expert thinks. THEN length modification is zero IF weight is light and speed is fast. THEN length modification is negative big IF weight is light and speed is slow. center of largest area. THEN length modification is positive small This rule base is generated based on an expert’s heuristic knowledge. In a similar way. because it is known to have a less mean square error and better steady-state performance. THEN length modification is negative small IF weight is medium and speed is slow. There are some defuzzification methods other than COG. transient performance. Vol. Membership functions for fuzzy inputs. such as the center of sums. the COG is the most widely used in practical applications. Fig. “IF weight is heavy and speed is slow. center of gravity method (COG) is used. because the fuzzy logic system is not used in real time. in the case of the rule. THEN length modification is positive big . The membership functions of output fuzzy sets used in this paper are shown in the Fig. 4. The characteristics of the each method are a little different in the computational complexity. IF weight is very light and speed is fast. IF weight is heavy and speed is medium. and mean square error. The nonlinear transfer characteristic plot of the developed fuzzy logic block is shown in Fig. the Mamdani implication is used in this paper. therefore. the other rules are generated based on human knowledge. THEN length modification is positive big IF weight is heavy and speed is fast. Based on the rule base. THEN length modification is zero IF weight is heavy and speed is slow. March 2001 66 Fig. an expert thinks that the vehicle has a high probability of being a truck rather than a passenger car. (a) Membership functions for vehicle speed. The disadvantage of the COG is that it is computationally more complex. 3.Asian Journal of Control. which is one of the most widely used implications in applications of fuzzy logic [10. THEN length modification is positive small IF weight is light and speed is medium. 5. Among the various mechanisms representing the meaning of IF-THEN rules in the inference step. the output of fuzzy system is computed through two steps: an inference step and a defuzzification step. In the defuzzification step. No. For example. This characteristic plot was constructed with the Fuzzy Logic Toolbox in the MATLAB [17].14. The configuration of the developed algorithm. THEN length modification is positive big”. 1. (b) Membership functions for vehicle weight. 2. THEN length modification is positive small IF weight is medium and speed is fast. THEN length modification is positive big IF weight is medium and speed is medium. 3. and middle of maxima [15]. Among them. the vehicle’s original length value needs to be modified to be longer. However. first of maxima.15].

Membership functions for fuzzy output. CONCLUSIONS In this paper. With the developed fuzzy algorithm. the smaller the weighting factor is. The modified vehicle length is calculated as modified length = measured length × (1 + weighting factor ) 100 where measured length is calculated using the raw outputs of two inductive loops. This means that the vehicle length may be slightly modified. and the results of vehicle classification errors are shown in Fig. category III (bus). category VIII (4-axle truck).: Application of Fuzzy Logic to Vehicle Classification Algorithm in Loop/Piezo-Sensor Fusion Systems Fig. category V (medium-size truck). and the final classification result is generated. the classification error for categories IV and V may not be corrected. In our experiments. Also. In accordance with the Ministry of Construction and Transportation (MOCT) standard in Korea.56% (38 errors/579 vehicles). The transfer characteristics for fuzzy logic block.9] and the newly developed fuzzy algorithm are tested together for performance comparison. EXPERIMENTAL RESULTS The developed algorithm is tested at a test site shown in Fig. In Fig. From Fig. piezo sensor loop sensors Fig.-W. It is mainly due to the fact that there is some difference in weight between a passenger car and a truck. 7(b). The representative vehicles of each category are as follows: category I (passenger car). In this algorithm. 5. It is also seen that the faster and the lighter the vehicle is. some vehicles in category V are classified as category IV or vice versa. category XI (more than 6 axles).78% (74 errors/579 vehicles). . The passing vehicles are classified into 11 categories. Some vehicles in category I are classified as category IV. The photograph of the test site. category IV (small truck). IV. but the difference between a loaded small-truck and an unloaded medium-size truck is not distinguishable. IV and V. The modified length is the input to the vehicle classification block. 7. In the experiments.67 S. 6. category II (small bus). The output of the fuzzy logic block is a weighting factor to modify the vehicle length calculated using the raw sensor outputs. Kim et al. so the classification error for categories IV and V decreased less than that of category I. this case occurred frequently. the classification error of category I decreased more significantly than categories IV and V. the classification error is decreased to 6. category VI (3-axle dump truck). the vehicle weight and speed are used as the inputs to the fuzzy logic block. Experimental results show that the proposed classification algorithm using the fuzzy logic significantly reduces the errors in vehicle classification. the larger the weighting factor is. it can be seen that the slower and the heavier the vehicle is. 4. vehicles are categorized into 11 groups. Total number of passing vehicles in the experiment was 579. category X (5-axle truck). category IX (4axle container truck). and the final classification result is generated. V. 10 5 0 -5 -10 12 10 8 80 6 4 2 40 50 60 70 speed (kph) weight (ton) Fig. 5. The classification error using the conventional algorithm is 12. with the developed fuzzy algorithm. or vice versa. Therefore. These properties are well matched with the heuristic knowledge on which the fuzzy rule base is generated. 6. and weighting factor is the output of the fuzzy logic block. a new vehicle classification algorithm using fuzzy logic is developed. The modified length is the input to the vehicle classification block. category VII (3-axle cargo truck). The errors mainly occur in the categories I. the conventional vehicle classification algorithm [2.

Eng.M. 9.B.. Vol. Lai. Intell. Kim. 45 40 with fuzzy algorithm without fuzzy algorithm number of vehicles 35 30 25 20 15 10 5 0 1 2 3 4 5 6 7 category 8 9 10 11 (b) Results of vehicle classification error. and N. Heidelberg (1993). “Vehicle Sound Signature Recognition by Frequency Vector Principal Component Analysis. Vol. AK (1998).” IEEE Trans.” J. Vol.” IEEE Trans. “Vehicle Signature Detection Using Standard Loop Detectors. 5. Seoul. Cho and D. 2. Addison-Wesley.G. 3. pp. Lachiver.A. IEEE Int.. D.C. K. The MathWorks Inc... Lee.. and G. Kiryu and W.H. 11. 6th World Congr. Reading. “Vehicle Reidentification and Travel Time Measurement in Real-time on Freeways Using the Existing Loop Detector Infrastructure. pp. “Development of a Vehicle Classification Algorithm Using an Inductive Loop Detector on a Freeway. No. Intell. Fuzzy Control. REFERENCES 1. Hellendoorn and M. Meas. pp. Eun. Electron. H. Soc.. 181-191 (1998). 6.S.” Proc. Ind. C. A. Yurkovich. Sumi. 14. Reinfrank. Prentice-Hall. Siegel and P. Choi. H. Instrum. Road Traffic Monitoring. Y. Conf. Izumi. Kim. Yung. 48. and G.S. Cho and K. N. Res. Wang. T. V.J. Transp.. 128-131 (1992). “Vehicletype Identification through Automated Virtual Loop Assignment and Block-based Direction Biased Motion Estimation. Newton. Nakano and G... Fuzzy Syst.. Experimental results on vehicle classification. H. L. M. No. Springer-Verlag. An Introduction to Fuzzy Control.. Weil. IEEE/IEEJ/JSAI Int. Sun. Anchorage. S. IEE 6th Int. “Performance Comparison of Loop/Piezo and Ultrasonic Sensor-based Detection Systems for Collecting Individual Vehicle Information. 7.K.. Gulley. Syst. Transp. Can.. Vol. Takahashi. Fig. 3. Garcia-Ortiz and J. A Course in Fuzzy Systems and Control. MA (1995).. 135-154. pp. No. S. pp. Intell.. Choi. 43. Conf. “Use of Weigh-in-motion Systems to Aid the Selection of Goods Vehicles for Enforcement Weighing.” Proc. Ko. Cho.. 190-193 (1995). U.. 1005-1009 (1999). 12. Syst. Rec. Matsumoto. Wootton. Driankov. Frith and I.” Intellimotion. 5th World Congr.W. Natick. IEE 2nd Int.K. “Detection of Traffic Anomalies Using Fuzzy Logic Based Techniques. 14.I. number of vehicles .” Proc.. N. Electr.I. Compu. Lai. “A New Loop-detector Circuit for Improving low-speed Performance. Korea Transp. Conf.-S.C. Transp. No. Roe. Wu. 24-28 (1989).X. et al. Vol. J. M. Khosla. pp.. Y.” Proc. W. “Fuzzy Logic-based Controller of Traffic Intersection. Kim. Fuzzy Logic Toolbox. Tokyo. H. Toronto. pp.S. Montreal. R. Jerabek.H.” Proc.G. K.” Proc. Res. H. 15. Korean (1996). Passino. 1. 7. Jang. 13. Syst. pp. Korea (1998). U. 10. Chan and A.” Transp.H. W..” Proc. NJ (1997). Cho. 5. H. 6..A. “Method of Measuring Travel Time by Using Ultrasonic Vehicle Profile Classifiers.. “Classification of Road Vehicles from Microwave Profiles. Y. Conf. Conf. 1643. MA (1998). B.K.. 29-32 (1989). S.J. Canada. Ko. Barbour. 16. Road Traffic Monitoring. No. Hsieh. Berlin.” Proc. “Application of Fuzzy Logic in the Phase-Locked Loop Speed Control of Induction Motor Drive. Upper Saddle River.W. and S. London. 630-639 (1996). J. J. Hobson. Coifman. Jung. Road Traffic Monitoring. Cho and D. I.. H. 17. B. 6. 4. U. Canada (1999). IEE 2nd Int. H. Conf. London.. London.. Kim. 2 (1997).Asian Journal of Control. March 2001 68 400 350 80 60 40 20 0 1 2 3 4 5 6 7 category 8 9 10 11 (a) Number of passing vehicles in each category. M. 8. Japan (1999). 1.