针对自动准确稳健的高速车辆统计问题，模拟视觉机制建立稀疏超完备表示模型，以图像单元作为处理对象，用少量非零响应稀疏系数表达目标图像的内在结构和本质属性，解决不同环境下、不同类别车辆的识别问题. 采用虚拟检测线技术设置动态车道进行在线统计，对多环境状况下车辆统计准确率达98.89%. 结果表明算法能有效抑制外界环境干扰，如光线变化和摄像机抖动等，其鲁棒性和准确率高于传统算法.
To detect and count high-speed vehicles accurately and robustly, a sparse over-complete model is established to simulate the visual mechanism. The model uses image units as processing objects. It expresses the internal structure and essential attributes of the target image with a small amount of non-zero response sparse coefficients, and identifies different types of vehicles in different environments. Online counting of vehicles is achieved by setting dynamic lanes based on virtual detection lines. Accuracy of the vehicle counting reaches 98.89% under a variety of environmental conditions. The results show that the proposed algorithm can effectively suppress interference caused by external factors such as wind, light changes and camera shakes. It
has higher robustness and accuracy than traditional algorithms.
[1] DIMITRAKOPOULOS G, DEMESTICHAS P. Intelligent transportation systems[J]. Vehicular Technology Magazine, Institute of Electrical and Electronics Engineers, 2010, 5(1): 77-84.
[2] HEALEY Christopher G. Attention and visual memory in visualization and computer graphics[J]. IEEE Transactions on Visualization and Computer Graphics, 2012, 18(7): 1170-1188.
[3] SUN Z, BEBIS G, MILLER R. On-road vehicle detection: a review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(5): 694-711.
[4] 张晖，董育宁. 基于视频的车辆检测算法综述[J].南京邮电学报，2006, 27(3): 88-94.
ZHANG H, DONG Y N. Video-based vehicle detection algorithms review[J]. Journal of Nanjing University of Posts, 2006, 27(3): 88-94.
[5] GUO Shenyu. Image modeling and enhancement via structured sparse model selection [C]//IEEE 17th International Conference, 2010, 1641-1644.
[6] 路锦正，张启衡，徐智勇，彭真明. 超完备稀疏表示的图像超分辨率重构方法[J]. 系统工程与电子技术，2012, 34(2): 403-408.
LU Jinzheng, ZHANG Qiheng, XU Zhiyong, PENG Zhenming. Image super-resolution reconstruction algorithm using over-complete sparse representation [J]. Systems Engineering and Electronics, 2012, 34(2): 403-408.
[7] MEI Xue, LING Haibin. Robust visual tracking and vehicle classification via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence 2011, 33(11): 2259-2272.
[8] LU Peng, TANG Yuhe, CHEN Eryan, SHI Huige, ZHANG Shanshan. Unstructured scene object localization algorithm based on sparse overcomplete representation[M]. Intelligent Computing Technology. Berlin Heidelberg: Springer 2012: 618-625.
[9] YANG Shuyuan, WANG min, WEI Meirong, JIAO Licheng. Evolution-enhanced multiscale overcomplete dictionaries learning for image denoising[J]. Engineering Applications of Artificial Intelligence, 2012, 25(6): 1259-1264.
[10] WEI Chen, ODRIGUESMiguel RD R, WASSELL Ian J. On the design of optimized projections for sensing sparse signals in overcomplete dictionaries[C]//Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on. IEEE, 2012: 3457-3460.
[11] ZHANG Shaoting, ZHAN Yiqiang, ZHOU Yan, METAXAS D N. Efficient sparse shape composition with its applications in biomedical image analysis: An overview[C]. Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on. IEEE, 2012: 976-979.
[12] DONOHO D L, TSAIG Y, DRORI I,Drori.I, Starck.J.-L. Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit[J]. Information Theory, IEEE Transactions on, 2012, 58(2): 1094-1121.
[13] WONG Yong Kang, HARANDI M T, SANDERSON C, LOVELL B.C. On robust biometric identity verification via sparse encoding of faces: holistic vs local approaches[C]//Neural Networks (IJCNN), The 2012 International Joint Conference on. IEEE, 2012: 1-8.
[14] YAO Bang Peng, BRADSKI G, LI Fei Fei. A codebook-free and annotation-free approach for fine-grained image categorization[C]//Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on Institute of Electrical and Electronics Engineers, 2012: 3466-3473.
[15] WANG Zhaobin, MA Yide, CHENG Feiyan, YANG Lizhen. review of pulse-coupled neural networks[J]. Image and Vision Computing, 2010, 28(1): 5-13.
