Pedestrian tracking method based on road environment context

doi:10.11772/j.issn.1001-9081.2015.08.2311

Journal of Computer Applications ›› 2015, Vol. 35 ›› Issue (8): 2311-2315.DOI: 10.11772/j.issn.1001-9081.2015.08.2311

Previous Articles Next Articles

Pedestrian tracking method based on road environment context

FANG Yi¹, JI Zhiyuan², SHENG Hao³

1. Department of Technology and Information, Aviation Industry Corporation of China, Beijing 101304, China;
2. High Technology Research and Development Center, Ministry of Science and Technology of the People's Republic of China, Beijing 100044, China;
3. School of Computer Science and Engineering, Beihang University, Beijing 100191, China

Received:2015-01-12 Revised:2015-04-24 Online:2015-08-14 Published:2015-08-10

基于道路环境上下文的行人跟踪方法

方义¹, 嵇智源², 盛浩³

1. 中航发动机控股有限公司科技与信息化部, 北京 101304;
2. 中华人民共和国科学技术部高技术研究发展中心, 北京 100044;
3. 北京航空航天大学计算机学院, 北京 100191

通讯作者: 嵇智源(1956-),男,北京人,高级工程师,主要研究方向:信息领域科技管理、软件工程管理,jzy@htrdc.com
作者简介:方义(1974-),男,安徽池州人,高级工程师,博士,主要研究方向:模式识别、信息系统集成; 盛浩(1981-),男,浙江台州人,副教授,博士,CCF会员,主要研究方向:计算机视觉、模式识别。
基金资助:
国家自然科学基金资助项目(61472019);国家863计划项目(2013AA01A603)。

Abstract

Abstract:

Since tracking pedestrians with car driving is still a problem in multi-object tracking, a pedestrian tracking method based on road environment context was proposed. Firstly, with the analysis of road environment context, an interaction algorithm based on the path model was proposed for pedestrians' motion prediction, then the model of pedestrians pedestrians mixed with vehicles was introduced. Finally, the model was applied in pedestrian tracking. The experimental results show that compared with discrete-continuous tracking approach, Multiple Object Tracking Accuracy (MOTA) of the proposed algorithm grows from 47.6% to 63.2% and Multiple Object Tracking Precision (MOTP) grows from 68.8% to 74.3%. The results prove the effectiveness of road environment context to improve the pedestrian tracking effect in mixed vehicle scene.

Key words: multiple pedestrians tracking, pedestrians mixed with vehicles, environment context, path model, interaction with environment

摘要：

针对目前城市交通中人车混行场景中行人跟踪效果不佳的问题,提出了一种基于道路环境上下文的行人跟踪方法。首先通过对道路环境上下文进行分析,建立道路模型;其次在道路模型的约束下建立行人与环境的交互运动模型;最后利用该模型进行行人的跟踪。在真实场景中的实验表明使用了道路上下文信息的跟踪方法与连续离散连续能量最小化的多行人跟踪方法相比,多目标跟踪准确度从47.6%提升至63.2%,多目标跟踪精度从68.8%提升至74.3%。数值结果表明道路上下文信息对于提高人车混行场景中行人跟踪效果的有效性。

关键词: 多行人跟踪, 人车混行, 环境上下文, 道路模型, 环境交互

CLC Number:

TP391.4

FANG Yi, JI Zhiyuan, SHENG Hao. Pedestrian tracking method based on road environment context[J]. Journal of Computer Applications, 2015, 35(8): 2311-2315.

方义, 嵇智源, 盛浩. 基于道路环境上下文的行人跟踪方法[J]. 计算机应用, 2015, 35(8): 2311-2315.

References

[1] National Bureau of Statistics of China. China's total population and structural changes in 2011 [EB/OL]. (2012-01-20) [2014-11-13]. http://www.stats.gov.cn/english/pressrelease/201201/t20120120_72112.html.
[2] ALUSI A, ECCLES R G, EDMONDSON A C, et al. Sustainable cities: oxymoron or the shape of the future? Harvard Business School Organizational Behavior Unit Working Paper No. 11-062 [EB/OL]. Boston: Harvard Business School, 2011 [2015-02-09]. http://ssrn.com/abstract=1726484 or http://dx.doi.org/10.2139/ssrn.1726484.
[3] CHEN Z, FAN W, XIONG Z, et al. Visual data security and management for smart cities [J]. Frontiers of Computer Science in China, 2010, 4(3): 386-393.
[4] GAO Y. Research and implementation of intelligent control for pedestrians and vehicles mixed environment [D]. Chengdu: University of Electronic Science and Technology of China, 2012: 31-57. (高杨.人车混合环境智能控制研究与实现[D].成都:电子科技大学,2012:31-57.)
[5] XIAO J, CHENG H, HAN F, et al. Geo-spatial aerial video processing for scene understanding and object tracking [C]//CVPR 2008: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2008: 1-8.
[6] COX I J, HINGORANI S L. An efficient implementation of Reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(2): 138-150.
[7] BRENDEL W, AMER M, TODOROVIC S. Multiobject tracking as maximum weight independent set [C]//CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2011: 1273-1280.
[8] WANG X, ZHAO R. Person re-identification: system design and evaluation overview [M]//Person Re-Identification. Berlin: Springer, 2014: 351-370.
[9] GONCZAREK A, TOMCZAK J M. Manifold regularized particle filter for articulated human motion tracking [C]//ICSS 2013: Proceedings of the International Conference on Systems Science. Berlin: Springer, 2014: 283-293.
[10] LUBER M, STORK J A, TIPALDI G D, et al. People tracking with human motion predictions from social forces [C]//Proceedings of the 2010 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2010: 464-469.
[11] WU B, NEVATIA R. Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors [J]. International Journal of Computer Vision, 2007, 75(2): 247-266.
[12] MILAN A, SCHINDLER K, ROTH S. Detection-and trajectory-level exclusion in multiple object tracking [C]//CVPR 2013: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2013: 3682-3689.
[13] LI H, ZHAO R, WANG X. Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification [J/OL]. arXiv preprint arXiv: 1412.4526, 2014 [2014-12-16]. http://arxiv.org/abs/1412.4526.
[14] YANG B, NEVATIA R. Multi-target tracking by online learning a CRF model of appearance and motion patterns [J]. International Journal of Computer Vision, 2014, 107(2): 203-217.
[15] HELBING D, MOLNÁR P. Social force model for pedestrian dynamics [J]. Physical Review E, 1995, 51(5): 4282-4286.
[16] PELLEGRINI S, ESS A, SCHINDLER K, et al. You'll never walk alone: modeling social behavior for multi-target tracking [C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway: IEEE, 2009: 261-268.
[17] ANDRIYENKO A, SCHINDLER K, ROTH S. Discrete-continuous optimization for multi-target tracking [C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2012: 1926-1933.
[18] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[19] WANG X, MA X, GRIMSON W E L. Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 539-555.
[20] LI Y, HUANG C, NEVATIA R. Learning to associate: Hybridboosted multi-target tracker for crowded scene [C]//CVPR 2009: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2009: 2953-2960.
[21] STIEFELHAGEN R, BERNARDIN K, BOWERS R, et al. The CLEAR 2006 evaluation [C]//CLEAR '06: Proceedings of the 1st International Evaluation Conference on Classification of Events, Activities and Relationships. Berlin: Springer, 2007: 1-44.

Pedestrian tracking method based on road environment context

基于道路环境上下文的行人跟踪方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	YANG Jianfeng, CHEN Bin, LI Yuxuan. Self-supervised point cloud anomaly detection method based on point cloud reconstruction [J]. Journal of Computer Applications, 0, (): 0-0.
[2]	. Multi-attention contrastive learning for infrared small target detection [J]. Journal of Computer Applications, 0, (): 0-0.
[3]	LI Zhonghua, ZHONG Gengxin, FAN Ping, ZHU Hengliang. Camouflaged object detection by boundary mining and background guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Multi-view difficult airway recognition based on discriminant region guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	. Privacy preserving localization of surveillance images based on large vision models [J]. Journal of Computer Applications, 0, (): 0-0.
[6]	. Data augmentation method for abnormal passenger behavior in elevators based on dynamic graph convolutional network [J]. Journal of Computer Applications, 0, (): 0-0.
[7]	. Text-based person retrieval method based on multi-granularity shared semantic center association [J]. Journal of Computer Applications, 0, (): 0-0.
[8]	. Distribution adaptation and dynamic curriculum pseudo-labeling framework for semi-supervised fire detection [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Image Caption Method Based on Swin-Transformer and Multi-Scale Feature Fusion [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	Wei XIONG, Yibo CHEN, Lizhen ZHANG, Qian YANG, Qin ZOU. Self-supervised monocular depth estimation using multi-frame sequence images [J]. Journal of Computer Applications, 2024, 44(12): 3907-3914.
[11]	Keyi FU, Gaocai WANG, Man WU. Few-shot object detection method based on improved region proposal network and feature aggregation [J]. Journal of Computer Applications, 2024, 44(12): 3790-3797.
[12]	Chenghao YANG, Jie HU, Hongjun WANG, Bo PENG. Incomplete multi-view clustering algorithm based on attention mechanism [J]. Journal of Computer Applications, 2024, 44(12): 3784-3789.
[13]	Peng FANG, Fan ZHAO, Baoquan WANG, Yi WANG, Tonghai JIANG. Development， technologies and applications of blockchain 3.0 [J]. Journal of Computer Applications, 2024, 44(12): 3647-3657.
[14]	Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929.
[15]	Xin ZHAO, Xinjie LI, Jian XU, Buyun LIU, Xiang BI. Parallel medical image registration model based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3915-3921.