Method of moving pedestrian detection and tracking based on monocular vision technology
-
摘要: 为了有效检测与跟踪城市交通环境中的行人, 提出了一种在摄像机静止情况下基于单目视觉的运动行人检测与跟踪方法。检测阶段通过自适应背景模型快速提取背景图像, 用动态多阈值方法二值化差分图分割运动行人; 跟踪阶段引入灰色模型作为行人运动模型, 预测行人运动, 融合行人多种特征建立目标匹配模板, 对行人连续跟踪。通过单个行人通行和多个行人同时出现这两种交通环境下的视频图像对本方法进行了验证, 单个行人通行时, 跟踪的正确率为95%;多个行人同时通行时, 识别每个行人并分别跟踪的正确率为87%。Abstract: In order to effectively detect and track moving pedestrian in urban traffic scenes, a method of moving pedestrian detection and tracking by using the data from a fixed CCD camera was presented. Self-adaptive background subtraction method and dynamic multi-threshold method were adopted for background subtraction and image segmentation respectively. During the process of tracking, a new method based on gray model GM (1, 1) was proposed to predict pedestrian motion, a template of pedestrian continuous tracking was presented by fusing several characters of targets. Experimental results of two real urban traffic scenes show that 95% of single pedestrians can be detected and tracked, 87% of multi-pedestrians can be detected and tracked.
-
Key words:
- traffic control /
- pedestrian detection /
- pedestrian tracking /
- monocular vision /
- background difference /
- GM (1 /
- 1) prediction
-
[1] 刘广萍, 裴玉龙. 信号控制下交叉口延误计算方法研究[J]. 中国公路学报, 2005, 18(1): 104-108. doi: 10.3321/j.issn:1001-7372.2005.01.021Liu Guang-ping, Pei Yu-long. Study of calculation method of intersection delay under signal control[J]. China Journal of Highway and Transport, 2005, 18(1): 104-108. (in Chinese) doi: 10.3321/j.issn:1001-7372.2005.01.021 [2] 郑长江, 王炜, 陈淑燕. 行人过街信号与交叉口信号的协调控制[J]. 交通运输工程学报, 2004, 4(4): 106-109. doi: 10.3321/j.issn:1671-1637.2004.04.026Zheng Chang-jiang, Wang Wei, Chen Shu-yan. Coordination control of crossing pedestrian signal and crossroad signal[J]. Journal of Traffic and Transportation Engineering, 2004, 4(4): 106-109. (in Chinese) doi: 10.3321/j.issn:1671-1637.2004.04.026 [3] Surendra G, Osama M, Robert F, et al. Detection and classification of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(1): 37-47. doi: 10.1109/6979.994794 [4] Osama M, Nikolaos P P. A novel method for tracking and counting pedestrians in real-time using a single camera[J]. IEEE Transactions on Vehicles Technology, 2001, 50(5): 1 267-1 278. doi: 10.1109/25.950328 [5] 王建军, 王军峰, 毕明涛. 区域公路交通事故及高速公路交通事故特征[J]. 长安大学学报: 自然科学版, 2005, 25(3): 66-69. doi: 10.3321/j.issn:1671-8879.2005.03.016Wang Jian-jun, Wang Jun-feng, Bi Ming-tao. Characteristics of traffic accidents on highway and expressway[J]. Journal of Chang'an University: Natural Science Edition, 2005, 25(3): 66-69. (in Chinese) doi: 10.3321/j.issn:1671-8879.2005.03.016 [6] Zhao L, Thorpe C. Stereo and neural network-based pedestrian detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2000, 3(1): 148-154. [7] Pai C J, Tyan H R, Liang Y M. Pedestrian detection and tracking at crossroads[J]. Pattern Recognition, 2004, 37(5): 1 025-1 034. doi: 10.1016/j.patcog.2003.10.005 [8] Cristovbal C, Johann E, Thomas K. Walking pedestrian recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2000, 3(1): 155-163. [9] 魏朗, 高丽敏, 余强, 等. 驾驶员道路安全感受模糊评判模型[J]. 交通运输工程学报, 2004, 4(1): 102-105. http://transport.chd.edu.cn/article/id/200401025Wei Lang, Gao Li-min, Yu Qiang, et al. Fuzzy evaluating model of driver's road safety perception[J]. Journal of Traffic and Transportation Engineering, 2004, 4(1): 102-105. (in Chinese) http://transport.chd.edu.cn/article/id/200401025 [10] 马万经, 林瑜, 杨晓光. 多相位信号控制交叉口行人相位设置方法[J]. 交通运输工程学报, 2004, 4(2): 103-106. http://transport.chd.edu.cn/article/id/200402024Ma Wan-jing, Lin Yu, Yang Xiao-guang. Design method of pedestrian phases at multi-fractal dimension[J]. Journal of Traffic and Transportation Engineering, 2004, 4(2): 103-106. (in Chinese) http://transport.chd.edu.cn/article/id/200402024 -
下载:
点击查看大图
图(4)
计量
- 文章访问数: 255
- HTML全文浏览量: 70
- PDF下载量: 759
- 被引次数: 0
