-
摘要: 为了提高智能交通系统中运动车辆检测的准确率, 提出了一种基于张量恢复的APG-TR算法。采用张量表征交通视频图像, 保持视频图像高维结构特征。通过张量恢复, 重建出张量的低秩部分与稀疏部分, 实现交通视频图像中交通背景与运动目标车辆的分离与交通视频内在特征的提取。利用交通监控系统采集到的交通视频106帧图像对本文算法进行了测试。测试结果表明: 在晴天条件下, APG-TR算法的平均正确率为91.4%, 在雨、雾天气条件下, 正确率分别为86.4%、85.2%, 相比帧差法更加稳定与准确。APG-TR算法具有良好的收敛速度与鲁棒性, 在智能交通领域中具有广泛的应用前景。Abstract: In order to improve the accuracy of moving vehicle detection in intelligent transportation system, an accelerated proximal gradient-tensor recovery(APG-TR) algorithm was proposed based on tensor recovery.The traffic video image data were characterized by using tensor in the algorithm, which maintained the high-dimensional structure characteristic of video image.The lower rank part and sparse part in the tensor were effectively reconstructed by tensor recovery, and moving target vehicle and traffic background were separated, therefore the internal properties were easily extracted.The algorithm was tested by using 106 video images collected by traffic monitoring system.Test result shows that the average detection accuracies are 91.4% in fine days, 86.4% and 85.2% under rain and fog conditions respectively, which are more stable and accurate compared with the frame differential method.APG-TR algorithm is proved to have good convergence speed and robust, and has abroad application in the field of intelligent transportation.
-
Key words:
- ITS /
- vehicle detection /
- high-dimensional structure /
- tensor recovery /
- APG-TR /
- matrix recovery
-
[1] 简林莎, 段宗涛, 周兴社. 智能运输系统信息平台[J]. 长安大学学报: 自然科学版, 2006, 26(2): 81-83. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200602019.htmJIAN Lin-sha, DUAN Zong-tao, ZHOU Xing-she. Information platform of intelligent transportation systems[J]. Journal of Chang'an University: Natural Science Edition, 2006, 26(2): 81-83. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200602019.htm [2] 金凌, 陈启美, 王炜. ITS域跨平台应用技术[J]. 交通运输工程学报, 2008, 8(3): 101-107. doi: 10.3321/j.issn:1671-1637.2008.03.022JIN Ling, CHEN Qi-mei, WANG Wei. Cross-platform appli-cation technologies in ITS[J]. Journal of Traffic and Trans-portation Engineering, 2008, 8(3): 101-107. (in Chinese). doi: 10.3321/j.issn:1671-1637.2008.03.022 [3] 李毅, 孙正兴, 远博, 等. 一种改进的帧差和背景减相结合的运动检测方法[J]. 中国图象图形学报, 2009, 14(6): 1162-1168. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200906026.htmLI Yi, SUN Zheng-xing, YUAN Bo, et al. An improved method for motion detection by frame difference and background subtraction[J]. Journal of Image and Graphics, 2009, 14(6): 1162-1168. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200906026.htm [4] 高韬, 刘正光, 岳士宏, 等. 用于智能交通的运动车辆跟踪算法[J]. 中国公路学报, 2010, 23(3): 89-94. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201003015.htmGAO Tao, LIU Zheng-guang, YUE Shi-hong, et al. Moving vehi-cle tracking algorithm used for intelligent traffic[J]. China Journal of Highway and Transport, 2010, 23(3): 89-94. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201003015.htm [5] 冀振元, 李晨雷, 唐文彦. 支持向量机在车辆目标识别中的应用[J]. 系统工程与电子技术, 2010, 32(2): 284-286. https://www.cnki.com.cn/Article/CJFDTOTAL-XTYD201002017.htmJI Zhen-yuan, LI Chen-lei, TANG Wen-yan. Application of SVM in recognition of vehicles[J]. Systems Engineering and Electronics, 2010, 32(2): 284-286. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XTYD201002017.htm [6] 李喜来, 李艾华, 白向峰. 智能交通系统运动车辆的光流法检测[J]. 光电技术应用, 2010, 25(2): 75-78. doi: 10.3969/j.issn.1673-1255.2010.02.021LI Xi-lai, LI Ai-hua, BAI Xiang-feng. Moving vehicles detection in intelligent transportation systems based on optical flow[J]. Electro-Optic Technology Application, 2010, 25(2): 75-78. (in Chinese). doi: 10.3969/j.issn.1673-1255.2010.02.021 [7] SHEN Z, TOH K C, YUN S. An accelerated proximal gradient algorithm for frame-based image restoration via the balanced approach[J]. SIAM Journal on Imaging Sciences, 2011, 4(2): 573-596. doi: 10.1137/090779437 [8] WRIGHT J, GANESH A, RAO S, et al. Robust principal component analysis: exact recovery of corrupted low-rank matri-ces via convex optimization[C]∥BENGIO Y, SCHUURMANS D, LAFFERTY J, et al. Advances in Neural Information Pro-ceeding Systems. Cambridge: MIT Press, 2009: 2080-2088. [9] CANDES E J, LI Xiao-dong, MA Yi, et al. Robust principal component analysis[J]. Journal of the ACM, 2011, 58(3): 1-39. [10] LI Yin, YAN Jun-chi, ZHOU Yue, et al. Optimum subspace learning and error correction for tensors[C]∥DANILLIDIS K, MARAGOS P, PARAGIOS N. Proceedings of the11th European Conference on Computer Vision. Crete: IEEE, 2010: 790-803. [11] TSENG P, YUN S. Block-coordinate gradient descent method for linearly constrained nonsmooth separable optimization[J]. Journal of Optimization Theory and Applications, 2009, 140(3): 513-535. doi: 10.1007/s10957-008-9458-3 [12] ZHOU Zi-han, LI Xiao-dong, WRIGHT J, et al. Stable principal component pursuit[C]∥IEEE. International Symposium on Information Theory. Texas: IEEE, 2010: 1518-1522. [13] CANDES E J, RECHT B. Exact matrix completion via convex optimization[J]. Foundations of Computational Mathematics, 2009, 9(6): 717-772. [14] TSENG P. On accelerated proximal gradient methods for convex-concave optimization[R]. Washington DC: University of Washington, 2008. [15] BECK A, TEBOULLE M. A fast iterative shrinkage-thresh-olding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202. doi: 10.1137/080716542 [16] TSENG P. Convergence of a block coordinate descent method for nondifferentiable minimization[J]. Journal of Optimization Theory and Applications, 2001, 109(3): 475-494. doi: 10.1023/A:1017501703105 [17] HALE E T, YIN Wo-tao, ZHANG Yin. Fixed-point continu-ation for l1-minimization: methodology and convergence[J]. SIAM Journal on Optimization, 2008, 19(3): 1107-1130. https://www.semanticscholar.org/paper/Fixed-Point-Continuation-for-l1-Minimization%3A-and-Hale-Yin/07b5e2f08bc1be6da9269e9c61e113d6e3526ff0 [18] CAI Jian-feng, CANDES E J, SHEN Zuo-wei. A singular value thresholding algorithm for matrix completion[J]. SIAM Journal on Optimization, 2008, 20(4): 1956-1982. doi: 10.1137/080738970 -
下载:
点击查看大图
图(3)
计量
- 文章访问数: 776
- HTML全文浏览量: 107
- PDF下载量: 1108
- 被引次数: 0
