Tracking objects with occlusion based on geometry layout and activity detection

Computer Engineering and Applications ›› 2015, Vol. 51 ›› Issue (13): 42-46.

Previous Articles Next Articles

Tracking objects with occlusion based on geometry layout and activity detection

WU Xuegang1，3, TAN Yuanyan1，2, FANG Bin1, ZHAO Shuangwen4, LI Liubai3, TAN Yong3, XING Changyuan1，3

1.College of Computer, Chongqing University, Chongqing 400044, China
2.Department of Computer and Information Science, the University of Macao, Macao, China
3.Department of Mathematics and Computer, Yangtze Normal University, Chongqing 408100, China
4.Fuling District Economic and Information Commission, Chongqing 408000, China

Online:2015-07-01 Published:2015-06-30

几何布局和行为检测相结合的遮挡目标跟踪

吴雪刚1，3，唐远炎1，2，房斌1，赵爽文4，李柳柏3，谭勇3，邢昌元1，3

1.重庆大学计算机学院，重庆 400044
2.澳门大学计算机信息科学系，中国澳门
3.长江师范学院数学与计算机系，重庆 408100
4.涪陵区经济和信息化委员会，重庆 408000

Abstract

Abstract: Based on geometry layout and particle filter, this paper proposes a method to solve the problem of object tracking. Prior knowledge from interesting object and its perspective effect, the region of different shapes is investigated. When occlusion happens between different objects, it firstly measures the distance between camera and object, and then gets the relative height of object, further ensures the accurate site of the object. At last, it is known that different objects belong to their regions. And then, using particle filter to tracking different occlusion objects, the weight will be increased when objects in different region move to their rails, the accurate rate will be advanced. The experimental results show the method is with practical effect.

Key words: object tracking, Kalman Filter（KF）, Particle Filter（PF）, particle degenerating, occlusion

摘要： 提出一种基于本地环境几何结构信息并结合行为识别的粒子滤波器来解决行进中被跟踪目标的遮挡问题。当发生遮挡情况时，先测定目标在环境中的相对位置信息，根据先验知识确定此位置目标的相对高度，进一步确定目标地面着力点的位置坐标；根据着力点的位置确定不同目标分属的相对不同的环境区域；再利用行为识别算法的对不同行为（跑、跳、走等）进行判断；将这些参数结合到粒子滤波器中进行预测跟踪。此时，不同位置区域目标在不同轨道上的粒子权重就会增加，不同特征的行为在运动过程的粒子权重也会增加，从而提高了遮挡情况下目标跟踪的准确率。仿真实验结果表明，该方法具有较好的实用性和研究价值。

关键词: 目标跟踪, 卡尔曼滤波器, 粒子滤波, 粒子退化, 遮挡

WU Xuegang1，3, TAN Yuanyan1，2, FANG Bin1, ZHAO Shuangwen4, LI Liubai3, TAN Yong3, XING Changyuan1，3. Tracking objects with occlusion based on geometry layout and activity detection[J]. Computer Engineering and Applications, 2015, 51(13): 42-46.

吴雪刚1，3，唐远炎1，2，房斌1，赵爽文4，李柳柏3，谭勇3，邢昌元1，3. 几何布局和行为检测相结合的遮挡目标跟踪[J]. 计算机工程与应用, 2015, 51(13): 42-46.

[1]	MA Jun，WANG Yuhao. Object Tracking Algorithm Based on Adaptive Update Strategy and Re-detection Technology [J]. Computer Engineering and Applications, 2021, 57(9): 217-224.
[2]	LI Zhenxiao, SUN Wei, LIU Mingming, ZHENG Lili, CHEN Shaoying. Research on Vehicle Detection and Tracking Algorithms in Traffic Monitoring Scenes [J]. Computer Engineering and Applications, 2021, 57(8): 103-111.
[3]	WANG Ling, WANG Jiapei, WANG Peng, SUN Shuangzi. Siamese Network Tracking Algorithms for Hierarchical Fusion of Attention Mechanism [J]. Computer Engineering and Applications, 2021, 57(8): 169-174.
[4]	LI Songjiang, WU Ning, WANG Peng, LI Hailan. Vehicle Target Detection Method Based on Improved Cascade RCNN [J]. Computer Engineering and Applications, 2021, 57(5): 123-130.
[5]	CUI Zhoujuan, AN Junshe, CHEN Changlong, CUI Tianshu. Deep Convolutional Features Heterogeneous Tracking System Based on PYNQ Framework [J]. Computer Engineering and Applications, 2021, 57(4): 120-126.
[6]	LI Zuolong, WANG Banghai, LU Zeng. Pedestrian Detection Method Based on Multi-scale Feature Fusion and Reconstruction [J]. Computer Engineering and Applications, 2021, 57(4): 176-182.
[7]	LIN Shubin, WU Guishan, XU Jiayun, YANG Wenyuan. Multi-frame Surveillance of Correlation Filter in UAV Object Tracking [J]. Computer Engineering and Applications, 2021, 57(24): 152-160.
[8]	YANG Luyue, ZHANG Shumei, ZHAO Junli. Dynamic Expression Recognition with Partial Occlusion Based on Parallel Gan [J]. Computer Engineering and Applications, 2021, 57(24): 168-178.
[9]	CHEN Fujian, XIE Weixin, XIA Ting. Adaptive Anti-occlusion Target Tracking Algorithm Based on LCT+ [J]. Computer Engineering and Applications, 2021, 57(22): 190-198.
[10]	WU Zhewei, ZHOU Shijie, LIU Qihe. Review on Object Tracking Methods for Restricted Computing Resources [J]. Computer Engineering and Applications, 2021, 57(21): 24-40.
[11]	XU Xialing, LIU Tao, TIAN Guohui, YU Wenjuan, XIAO Dajun, LIANG Shanpeng. Review of Occlusion Face Recognition Methods [J]. Computer Engineering and Applications, 2021, 57(17): 46-60.
[12]	HUANG Tongyu, HU Binjie, ZHU Tingting, HUANG Zhewen. Object Detection Method Based on Multi-scale Feature Fusion for Driving Scene [J]. Computer Engineering and Applications, 2021, 57(14): 134-141.
[13]	ZHANG Yao, LU Huanzhang, ZHANG Luping, HU Moufa. Overview of Visual Multi-object Tracking Algorithms with Deep Learning [J]. Computer Engineering and Applications, 2021, 57(13): 55-66.
[14]	LIU Yun, QIAN Meiyi, LI Hui, WANG Chuanxu. Efficient Object Tracking with Feature Fusion and Training Acceleration [J]. Computer Engineering and Applications, 2021, 57(10): 101-109.
[15]	DONG Yanhua, ZHANG Shumei, ZHAO Junli. Review of Occlusion Face Recognition Method [J]. Computer Engineering and Applications, 2020, 56(9): 1-12.

Tracking objects with occlusion based on geometry layout and activity detection

几何布局和行为检测相结合的遮挡目标跟踪

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics