1. Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan Hubei 430070, China; 2. Hubei Key Laboratory of Transport Internet of Things Technology, Wuhan Hubei 430070, China
1. Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan Hubei 430070, China; 2. Hubei Key Laboratory of Transport Internet of Things Technology, Wuhan Hubei 430070, China
摘要Reducing traffic accidents and relieving traffic congestion are two main topics for Chinese road traffic management. Vehicle vision-based vehicle detection and tracking technology is the primary link in road environment perception. The detection technology for forward vehicles is becoming increasingly mature, and commercial products have appeared. Detection is more complicated for oblique vehicles. This research mainly studies the detection and tracking of oblique vehicles. The main work is as follows:First, the image preprocessing method in image processing technology is mainly studied. With focus on research of lane line detection algorithm, an improved lane line detection algorithm combining Hough transform and K-means clustering is proposed to improve the accuracy. With the lane line taken as the standard, the vehicle detection area is divided and combined with the ROI area extraction to further narrow the detection range. With the aim of performing vehicle detection, a two-level optimization algorithm is proposed. First, the method of initial inspection and machine learning detection verification of feature detection is presented. The vehicle target feature and image vertical edge feature fusion are used to generate the suspected target region. An improved dual threshold segmentation algorithm is then proposed to improve the effect of shadow feature extraction. The cascading AdaBoost classifier is combined to generate the target verification area. To address the real-time problem, kernel principle component analysis using Gaussian kernel function is applied to reduce the dimensionality of image feature and improve real-time performance. Experimental results show that the identification accuracy is up to 90% for oblique vehicles when the optimization algorithm of the mixing of shadow feature and image vertical edge feature is used. In good weather, the accuracy is up to 95% when using the AdaBoost classifier combined with HOG+Haar-like feature; The detection time is reduced by 26% when kernel principal component analysis is used. The result of this project is valuable for dynamic oblique vehicle detection.
Abstract：Reducing traffic accidents and relieving traffic congestion are two main topics for Chinese road traffic management. Vehicle vision-based vehicle detection and tracking technology is the primary link in road environment perception. The detection technology for forward vehicles is becoming increasingly mature, and commercial products have appeared. Detection is more complicated for oblique vehicles. This research mainly studies the detection and tracking of oblique vehicles. The main work is as follows:First, the image preprocessing method in image processing technology is mainly studied. With focus on research of lane line detection algorithm, an improved lane line detection algorithm combining Hough transform and K-means clustering is proposed to improve the accuracy. With the lane line taken as the standard, the vehicle detection area is divided and combined with the ROI area extraction to further narrow the detection range. With the aim of performing vehicle detection, a two-level optimization algorithm is proposed. First, the method of initial inspection and machine learning detection verification of feature detection is presented. The vehicle target feature and image vertical edge feature fusion are used to generate the suspected target region. An improved dual threshold segmentation algorithm is then proposed to improve the effect of shadow feature extraction. The cascading AdaBoost classifier is combined to generate the target verification area. To address the real-time problem, kernel principle component analysis using Gaussian kernel function is applied to reduce the dimensionality of image feature and improve real-time performance. Experimental results show that the identification accuracy is up to 90% for oblique vehicles when the optimization algorithm of the mixing of shadow feature and image vertical edge feature is used. In good weather, the accuracy is up to 95% when using the AdaBoost classifier combined with HOG+Haar-like feature; The detection time is reduced by 26% when kernel principal component analysis is used. The result of this project is valuable for dynamic oblique vehicle detection.
基金资助:Supported by the National Key R&D Project(2017YFB1402203)
通讯作者:
ZENG Juan
E-mail: zengjuan1973@whut.edu.cn
引用本文:
曾娟, 李守义, 张洪昌. Subregion Multifeature Fusion Oblique Vehicle Detection Algorithm[J]. Journal of Highway and Transportation Research and Development, 2020, 14(3): 86-95.
ZENG Juan, LI Shou-yi, ZHANG Hong-chang. Subregion Multifeature Fusion Oblique Vehicle Detection Algorithm. Journal of Highway and Transportation Research and Development, 2020, 14(3): 86-95.
[1] PENG Jun, WANG Jiang-feng, WANG Na. Intelligent Vehicle Collision Warning Algorithm Based on Machine Vision[J]. Journal of Highway and Transportation Research and Development, 2011,28(S1):124-128. (in Chinese) [2] BAUTISTA C M, DY C A, MA? ALAC M I, et al. Convolutional Neural Network for Vehicle Detection in Low Resolution Traffic Videos[C]//2016 IEEE Region 10 Symposium. Bali, Indonesia:IEEE, 2016:277-281. [3] LI Yun-chong, HE Ke-zhong, JIA Pei-fa. Forward Vehicle Detection Based on Shadow Features and Adaboost[J]. Journal of Tsinghua University:Science and Technology Edition, 2007, 47(10):1713-1716. (in Chinese) [4] CHANG W C, CHO C W. Online Boosting for Vehicle Detection[J].IEEE Transactions on Systems, Man, and Cybernetics, Part B,2010, 40(3):892-902. [5] SIVARAMAN S, TRIVEDI M M. A General Active-Learning Framework for On-road Vehicle Recognition and Tracking[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(2):267-276. [6] WANG Ning. Design of Vision-based Frontal Vehicle Detection and Tracking System[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2016. (in Chinese) [7] YUAN X, LI C N, XU X L, et al. A Two-stage Hog Feature Extraction Processor Embedded with SVM for Pedestrian Detection[C]//2015 IEEE International Conference on Image Processing. Quebec City:IEEE, 2015. [8] LI X, GUO X. Vision-based Method for Forward Vehicle Detection and Tracking[C]//2013 International Conference on Mechanical and Automation Engineering. Jiujiang:IEEE, 2013. [9] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Visual Object Detection with Deformable Part Models[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco:IEEE, 2010. [10] HAN Zhi-gang. Research on HOG and SVM Based Car Detection Method[D]. Xiamen:Xiamen University, 2015. (in Chinese) [11] LIU Dong-jun, XU Mei-hua, GONG Lu-ming. Feature Fusion for Front Vehicle Detection and Implementation[J]. Journal of Shanghai University:Natural Science Edition, 2017,23(6):12-24. (in Chinese) [12] LIN B F, CHAN Y M, FU L C, et al. Incorporating Appearance and Edge Features for Vehicle Detection in the Blind-spot Area[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2):737-747. [13] ZHU Bin, WANG Shao-ping, LIANG Hua-wei. Sub-regional and Multi-classifier Vehicle Detection Based on Haar-like and MB-LBP Features[J]. Pattern Recognition and Artificial Intelligence, 2017,30(6):91-98. (in Chinese) [14] YAN Xiao-juan. Research on Detection Method of Backside Target and Lane Change Early-warning System Based on Machine Vision[D]. Zhenjiang:Jiangsu University,2017. (in Chinese) [15] CAI Ying-feng, GAO Li, CHEN Long, et al. Lane Detection Method Based on Clustering Algorithm[J]. Journal of Jiangsu University:Natural Science Edition, 2017, 38(6):6-10. (in Chinese) [16] QI Mei-bin, PAN Yan, ZHANG Yin-xia. Preceding Moving Vehicle Detection Based on Shadow of Chassis[J]. Journal of Electronic Measurement and Instrument, 2012,26(1):54-60. (in Chinese) [17] YU Tian-hong, WANG Rong-ben, GU Bai-yuan, et al. Survey on the Vision-based Recognition Methods of Intelligent Vehicle Road Boundaries and Lane Markings[J]. Journal of Highway and Transportation Research and Development, 2006, 23(1):139-142. (in Chinese) [18] 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, USA:IEEE, 2005:886-893. [19] VIOLA P, JONES M J. Robust Real-time Face Detection[J]. International Journal of Computer Vision, 2004, 57(2):137-154.
2020, Vol. 14 
