-
摘要: 为提高城市智能交通综合管理能力, 提出了基于视频分析的运动车辆检测与跟踪方法。在城市交通干道路面环境中, 根据运动目标与道路背景统计特性的差异, 基于贝叶斯概率准则, 提出一个自适应背景更新算法, 检测分离运动车辆目标前景, 采用卡尔曼滤波器实现对视频序列中车辆目标的运动检测与实时跟踪, 并对在重庆某交通干道的交通流视频进行检测。试验结果表明: 该方法在常规视频分辨率下能实现实时处理视频, 平均检测准确率为94%, 具有较好的实时性与鲁棒性, 能够实现城市交通环境中各类运动车辆的检测与跟踪。Abstract: In order to improve the comprehensive management ability of intelligent transportation systems in cities, a detecting and tracking method of moving vehicle was presented by using video analysis. Considering the pavement environment of urban transport artery and the difference between moving object and the statistical characteristics for road background, an adaptive background updating algorithm was realized based on Bayesian probability criterion, from which foreground image was extracted. Motion detection and real-time tracking were realized for target vehicle in video sequence based on Kalman filter. The traffic flow video collected from a certain urban transport artery of Chongqing was detected by using the proposed method. Experimental result indicates that the video with normal resolution can be processed in time by using the method, and the average detecting accuracy is 94 %, so the proposed method has good real-time performance and robustness, and meets the requirement of real- time detecting and tracking vehicles in urban traffic arteries. 2 tabs, 5 figs, 15 refs.
-
表 1 高分辨率视频试验结果
Table 1. Experimental result of high resolution video
车型 实际数/veh 检测数/veh 误检数/veh 检测率/% 小车 25 28 3 88 大车 4 5 1 75 摩托车 3 3 0 100 总数 32 36 4 87 
下载: 导出CSV
表 2 低分辨率视频试验结果
Table 2. Experimental result of low resolution video
车型 实际数/veh 检测数/veh 误检数/veh 检测率/% 小车 116 113 3 97 大车 15 12 3 80 摩托车 11 9 2 82 总数 142 134 8 94
下载: 导出CSV
-
[1] 杨国亮, 王志良, 牟世堂, 等. 一种改进的光流算法[J]. 计算机工程, 2006, 32(15): 187-188, 226. doi: 10.3969/j.issn.1000-3428.2006.15.066YANG Guo-liang, WANG Zhi-liang, MU Shi-tang, et al. An improved optical flow algorithm[J]. Computer Engineering, 2006, 32(15): 187-188, 226. (in Chinese) doi: 10.3969/j.issn.1000-3428.2006.15.066 [2] 郑锦, 李波. 视频序列中运动对象检测技术的研究现状与展望[J]. 计算机应用研究, 2008, 25(12): 3534-3540. doi: 10.3969/j.issn.1001-3695.2008.12.004ZHENG Jin, LI Bo. Prospects and current studies on motion object detection in video sequences[J]. Application Research of Computers, 2008, 25(12): 3534-3540. (in Chinese) doi: 10.3969/j.issn.1001-3695.2008.12.004 [3] 查成东, 王长松, 崔巍. 背景差方法在复杂场景条件下的应用[J]. 计算机工程与设计, 2008, 29(4): 894-895. https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ200804040.htmZHA Cheng-dong, WANG Chang-song, CUI Wei. Application of background subtraction under complex scene[J]. Computer Engineering and Design, 2008, 29(4): 894-895. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ200804040.htm [4] 田军, 魏振华, 武思远. 能量法的自适应背景更新算法[J]. 计算机科学与探索, 2009, 3(2): 218-224. doi: 10.3778/j.issn.1673-9418.2009.02.010TIAN Jun, WEI Zhen-hua, WU Si-yuan. A self-adaptive background updating algorithm of energy method[J]. Journal of Frontiers of Computer Science and Technology, 2009, 3(2): 218-224. (in Chinese) doi: 10.3778/j.issn.1673-9418.2009.02.010 [5] SONG K T, TAI J C. Real-time background estimation of traffic imagery using group-based histogram[J]. Journal of Information Science and Engineering, 2008(24): 411-423. [6] TANIGUCHI H, NAKAMURA T, FURUSAWA H. Methods of traffic flow measurement using spatio-temporal image[C]∥ IEEE. Proceedings of 1999 International Conference on Image processing. Kobe: IEEE, 1999: 16-20. [7] WAKABAYASHI Y, AOKI M. Traffic flow measurement using stereo slit camera[C]∥IEEE. Proceedings of the 7th international Conference on Intelligent Transportation Systems. Washington DC: IEEE, 2004: 7-12. [8] KOLLER D, WEBER J, HUANG T, et al. Towards robust automatic traffic scene analysis in real-time[C]∥IEEE. Proceeding of the 33rd of IEEE Conference on Pattern Recognition. Jerusalem: IEEE, 1994: 126-131. [9] JUN G, AGGARWAL J K, GOKMEN M. Tracking and segmentation of highway vehicles in cluttered and crowded scenes[C]∥IEEE. Proceedings of the 2008 IEEE Workshop on Applications of Computer Vision. Copper Mountain: IEEE, 2008: 1-6. [10] 赵宇. 视频处理中的目标分割与跟踪的研究[D]. 北京: 中国科学院, 2004.ZHAO Yu. The research of object segmentation and tracking in video processing[D]. Beijing: Chinese Academy of Sciences, 2004. (in Chinese) [11] TAMERSOY B, AGGARWAL J K. Robust vehicle detection for tracking in highway surveillance videos using unsupervised learning[C]∥IEEE. Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance. Genova: IEEE, 2009: 529-534. [12] LI Li-yuan, HUANG Wei-min, GUI Y, et al. Statistical modeling of complex backgrounds for foreground object detection[J]. IEEE Transactions on Image Processing, 2004, 13(11): 1459-1472. doi: 10.1109/TIP.2004.836169 [13] 袁基炜, 史忠科. 一种基于灰色预测模型GM(1, 1) 的运动车辆跟踪方法[J]. 控制与决策, 2006, 21(3): 300-304. doi: 10.3321/j.issn:1001-0920.2006.03.014YUAN Ji-wei, SHI Zhong-ke. A method of vehicle tracking based on GM(1, 1)[J]. Control and Decision, 2006, 21(3): 300-304. (in Chinese) doi: 10.3321/j.issn:1001-0920.2006.03.014 [14] KALMAN R E. A new approach to linear filtering and prediction problems[J]. Transactions of the ASME—Journal of Basic Engineering, 1960(82): 35-45. [15] STORVIK G. Particle filters for state space models with the presence of unknown static parameters[J]. IEEE Transactions on Signal Processing, 2002, 50(2): 281-289. doi: 10.1109/78.978383 -
点击查看大图
图(5) / 表(2)
计量
- 文章访问数: 814
- HTML全文浏览量: 137
- PDF下载量: 1169
- 被引次数: 0
