摘要Detection technology based on machine vision is one of the important means of road environment perception. At present, detection technologies for vehicles and pedestrians increasingly mature, and many commercial products have been used. But machine vision in the dynamic weighing still needs to be further explored. This paper proposes a wheel recognition method based on machine vision technology used in Weigh in motion. Aiming at deal with the traditional Hough Transform is not robustness on detecting circle targets, we proposed a wheel detection method based on Histogram of Oriented Gradient (HOG) and Support Vector Machine (SVM). Firstly, HOG is used to extract the image features of the wheels. Secondly, positive and negative samples are sent to the SVM for training the classifier. Finally, the trained SVM classifier is employed for wheel detection. Experimental shows that the proposed method had higher performance compared with the traditional Hough transform, and the detection rate is over 96%, which can meet the requirements of vehicle wheel detection. In the engineering test, our method's detection rate has been improved by about 5% compared with the traditional piezoelectric wheel recognition sensor.
Abstract：Detection technology based on machine vision is one of the important means of road environment perception. At present, detection technologies for vehicles and pedestrians increasingly mature, and many commercial products have been used. But machine vision in the dynamic weighing still needs to be further explored. This paper proposes a wheel recognition method based on machine vision technology used in Weigh in motion. Aiming at deal with the traditional Hough Transform is not robustness on detecting circle targets, we proposed a wheel detection method based on Histogram of Oriented Gradient (HOG) and Support Vector Machine (SVM). Firstly, HOG is used to extract the image features of the wheels. Secondly, positive and negative samples are sent to the SVM for training the classifier. Finally, the trained SVM classifier is employed for wheel detection. Experimental shows that the proposed method had higher performance compared with the traditional Hough transform, and the detection rate is over 96%, which can meet the requirements of vehicle wheel detection. In the engineering test, our method's detection rate has been improved by about 5% compared with the traditional piezoelectric wheel recognition sensor.
基金资助:Supported by the Guangxi Science and Technology Planning Project (No.AB17292006), the Central Government Guides the Development of Local Science and Technology (No.Guike ZY20111015)
通讯作者:
LI Xiao-yong
E-mail: 526487861@qq.com
引用本文:
李小勇, 韦泽贤, 杨玉琳. Research on the Application of HOG and SVM for Wheel Recognition in Weigh in Motion[J]. Journal of Highway and Transportation Research and Development, 2021, 15(3): 102-110.
LI Xiao-yong, WEI Ze-xian, YANG Yu-lin. Research on the Application of HOG and SVM for Wheel Recognition in Weigh in Motion. Journal of Highway and Transportation Research and Development, 2021, 15(3): 102-110.
[1] LI Xiao-song. The Application of Weighing in Moving Technique[J]. Journal of Highway and Transportation Research and Development, 1991, 8(3):65-67. (in Chinese)
[2] XU Gang. Application of Expressway Weighing System[J]. Journal of Highway and Transportation Research and Development, 2003, 20(S1):65-68. (in Chinese)
[3] HANG Wen, LI Xu-hong, HE Jie, et.al. Overloading Vehicles Axle-loads Survey and Analysis[J]. Journal of Highway and Transportation Research and Development, 2005,22(8):145-148. (in Chinese)
[4] YANG De, DENG Guo-qiang, CHANG Fu-shan. Design of Non-stop and Whole Vehicle Weighing System[J]. Control Engineering of China, 2015, 22(6):1114-1117. (in Chinese)
[5] WANG Lei, YIN Yan, ZHOU Wei, et al. Research on Intelligent Electronic Weight Tolling System for Heavy Loaded Vehicles[J]. Highway, 2017,62(3):154-160. (in Chinese)
[6] WANG Lei, ZHOU Wei, DONG Min-yi, et al. Study on Station Arrangement for Expressway EWTC System[J]. Journal of Highway and Transportation Research and Development, 2016, 33(9):120-126. (in Chinese)
[7] WANG Lei, YIN Yan, ZHOU Wei, et al. Study on Dynamic Weighing System of High Precision Array Piezoelectric Quartz[J]. China Journal of Highway and Transport, 2016, 29(5):137-143. (in Chinese)
[8] WANG Qiang, LIU Yang-guang, ZHANG Wen-zhong, et al. High speed WIM based on FBG for vehicles[J]. Journal of Chang'an University:Natural Science Edition, 2014, 34(3):145-150. (in Chinese)
[9] LI yan-di, XU Xi-ping, ZHONG Yan. Application of RHT Based on Character String Constraint in Ellipse Detection[J]. Chinese Journal of Scientific Instrument, 2017, 38(1):50-56. (in Chinese)
[10] WANG Hong-liang, HUANG Yang-wen, LI Jian-nan. A Localization Method of Vehicle Wheels Based on Hough Transform[J]. Fire Control & commend Control, 2011, 36(11):25-27. (in Chinese)
[11] MI Wei-jian, XUE Run, SHEN Yang, et al. Wheel Detection Algorithm in Automatic Vehicle Recognition System for Highway Toll Lanes[J]. Journal of Shanghai Maritime University, 2014, 35(4):79-84. (in Chinese)
[12] WANG Qiang, LIU Yang-shao. Characters of Wheel Axles of Vehicles on Highway Bridge[J]. Journal of Highway and Transportation Research and Development, 2013, 30(11):41-52. (in Chinese)
[13] DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego:IEEE, 2005.
[14] LIU Cao, ZHENG Hong, LI Xi, et al. A Method of Moving Vehicle Detection in All-weather Based on Melted Multi-channel HOG Feature[J]. Geomatics and Information Science of Wuhan University, 2015, 40(8):1048-1053. (in Chinese)
[15] ZHANG Rui, LÜ Wen-hong, ZHANG Rui-xi. Research of Vehicle Weigh-in-Motion System Based on Neural Network Self-adaptive Filtering[J]. Journal of Highway and Transportation Research and Development, 2010, 7(27):138-146. (in Chinese)
[16] CHEN Chao-bo, YANG Nan. Application of RBF Neural Network Algorithm in Dynamic Weighing[J]. Electronic Measurement Technology, 2016, 39(5):187-190. (in Chinese)
[17] CORTES C, VAPNIK V. Support-vector Networks[J]. Machine Learning, 1995, 20(3):273-297.
[18] FAN Xin-wei, Support Vector Machine and Its Applications[D]. Hangzhou:Zhejiang University, 2003. (in Chinese)
[19] XU Chao, GAO Meng-zhu, ZHA Yu-feng, et.al. Bus Passenger Flow Calculation Algorithm Based on HOG and SVM[J]. Chinese Journal of Scientific Instrument, 2015, 36(2):446-452. (in Chinese)
[20] LI Lin, WU Yue, YE Mao. Effective Image Classification Method Based on HOG-PCA[J]. Application Research of Computers, 2013, 30(11):3476-3479. (in Chinese)
2021, Vol. 15 
