多特征融合匹配的霍夫森林多目标跟踪

doi:10.3969/j.issn.1001-2400.2018.01.023

Abstract

Abstract:

In order to solve the problem of low accuracy due to target occlusion and deformation in multi-target tracking, this paper proposes a multi-target tracking algorithm based on the multi-feature fusion matching and Hough forest. First, we select positive and negative samples online according to primary association among detection responses and construct the feature model of the target with color histogram, histogram of oriented gradient (HOG) and optical flow information. Then, longer trajectory associations are generated based on the online learned Hough forest framework. Finally, a trajectory matching algorithm based on multi-feature fusion is proposed, and we introduce two methods of similarity measure in color histogram and feature points matching based on the Gabor filter to generate the probability matrix with the weighted factor. Therefore, it can further form the complete trajectories of the targets by associating them gradually. Experimental results show that the proposed algorithm can effectively solve the problems of target deformation and mutual occlusion in the video sequences of complex environments, and realize the robust tracking of multiple targets.

Key words: multiple targets, Hough forest, color histogram, similarity measure, feature point matching

LIANG Fuxin;LIU Hongbin;CHANG Faliang. Multi-target tracking algorithm based on the multi-feature fusion matching and Hough forest[J].Journal of Xidian University, 2018, 45(1): 129-134+161.

References

［1］ HUANG C, LI Y, NEVATIA R. Multiple Target Tracking by Learning-based Hierarchical Association of Detection Responses［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(4): 898-910.
［2］ KUO C H, NEVATIA R. How Does Person Identity Recognition Help Multi-person Tracking?［C］//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2011: 1217-1224.
［3］ YANG B, NEVATIA R. Online Learned Discriminative Part-based Appearance Models for Multi-human Tracking［C］//Lecture Notes in Computer Science: 7572. Heidelberg: Springer Verlag, 2012: 484-498.
［4］ 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.
［5］ HEILI A, LOPEZ-MENDEZ A, ODOBEZ J M. Exploiting Long-term Connectivity and Visual Motion in CRF-based Multi-person Tracking［J］. IEEE Transactions on Image Processing, 2014, 23(7): 3040-3056.
［6］ XIANG J, SANG N, HOU J. An Online Learned Hough Forest Model for Multi-target Tracking［C］//Proceedings of the 2015 IEEE International Conference on Image Processing. Piscataway: IEEE, 2015: 2398-2402.
［7］别秀德, 刘洪彬, 常发亮, 等. 自适应分块的多特征融合多目标跟踪［J］. 西安电子科技大学学报, 2017, 44(2): 163-168.
BIU Xiude, LIU Hongbin, CHANG Faliang, et al. Multi-target Tracking Method Based on Adaptive Fragment and Multi-feature Fusion［J］. Journal of Xidian University, 2017, 44(2): 163-168.
［8］黄奇, 项俊, 侯建华, 等. 联合特征融合和判别性外观模型的多目标跟踪［J］. 中国图象图形学报, 2015, 20(9): 1188-1198.
HUANG Qi, XIANG Jun, HOU Jianhua, et al. Multi-target Tracking Algorithm Based on Feature Fusion and Discriminative Appearance Model［J］. Journal of Image and Graphics, 2015, 20(9): 1188-1198.
［9］ KALAL Z, MIKOLAJCZYK K, MATAS J. Forward-backward Error: Automatic Detection of Tracking Failures［C］//Proceedings of the International Conference on Pattern Recognition. Piscataway: IEEE, 2010: 2756-2759.
［10］ XIANG J, SANG N, HOU J, et al. Hough Forest-based Association Framework with Occlusion Handling for Multi-target Tracking［J］. IEEE Signal Processing Letters, 2016, 23(2): 257-261.
［11］彭志勇, 常发亮, 刘洪彬, 等. 基于HSV模型和特征点匹配的行人重识别算法［J］. 光电子·激光, 2015, 26(8): 1575-1582.
PENG Zhiyong, CHANG Faliang, LIU Hongbin, et al. Person Re-identification Algorithm Based on HSV Model and Key-points Matching［J］. Journal of Optoelectronics·Laser, 2015, 26(8): 1575-1582.
［12］ RISTANI E, SOLERA F, ZOU R, et al. Performance Measures and a Data Set for Multi-target, Multi-camera Tracking［C］//Lecture Notes in Computer Science: 9914. Heidelberg: Springer Verlag, 2016: 17-35.

[1]	TANG Guoliang. Anti-fuzzy local feature descriptor on images [J]. Journal of Xidian University, 2019, 46(1): 39-45.
[2]	WANG Qiang;Guo Lixin;LIU Zhongyu. Hybrid method for transient electromagnetic scattering from multiple targets above the rough sea surface [J]. Journal of Xidian University, 2018, 45(5): 57-63.
[3]	BIE Xiude;LIU Hongbin;CHANG Faliang;PENG Zhiyong. Multi-target tracking method based on the adaptive fragment and multi-feature fusion [J]. Journal of Xidian University, 2017, 44(2): 151-157.
[4]	LIU Han-qiang;JIAO Li-cheng;ZHAO Feng. SAR image multilevel segmentation based on local similarity measure [J]. J4, 2010, 37(6): 1071-1076.
[5]	SHI Yin-shui;JI Hong-bing;YANG Bai-sheng. Multiple passive-radar based time-varying number targets tracking algorithm [J]. J4, 2010, 37(2): 218-223.
[6]	ZHANG Huai-gen;WU Shun-jun;ZHANG Lin-rang;LIU Yin. Multiple targets angle tracking algorithm based on the elements of the covariance matrix [J]. J4, 2008, 35(5): 785-792.
[7]	WANG Shu-peng1.2;JI Hong-bing1. Object tracking based on the spatial color model [J]. J4, 2007, 34(7): 76-79.
[8]	MENG Fan-jie; GUO Bao-long. A novel image retrieval algorithm based on the color and distribution of interest points [J]. J4, 2005, 32(2): 256-259.

Multi-target tracking algorithm based on the multi-feature fusion matching and Hough forest

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 8

Metrics

Comments

Recommended 10