Convolutional Residual Learning with Sparse Robust Samples and Multi-feature Fusion for Object Tracking

doi:10.1117/12.2524414

	Convolutional Residual Learning with Sparse Robust Samples and Multi-feature Fusion for Object Tracking
	Gao, Huiling 2; Liu, Jie 1; Liu, Chaorong 3; Li, Binshan 2; Zhao, Zhengtian 2; Liu, Weirong 2
	2019
关键词	Sparse representation deep learning joint detection multiple feature fusion object tracking
卷号	11069
DOI	10.1117/12.2524414
英文摘要	Recently, discriminative object trackers based on deep learning have demonstrated excellent performance. However, the tracking accuracy is facing a challenge due to contaminated training samples and different complex scenarios. For this reason, we propose a tracker based on sparse robust samples and convolutional residual learning with multi-feature fusion (SR_MFCRL). First, a sparse robust sample set (SRSS) is introduced to improve robustness of the network. In this process, we first employ sparse representation to estimate the best candidate and then utilize joint detection with response peak value and occlusion detection to determine the contamination degree of the sample. Second, a multi-feature fusion residual network (MRN) is proposed and its two base branches to capture response output of different features in order to achieve higher positioning accuracy. Extensive experimental results conducted on OTB-2013 illustrate that the proposed tracker achieves outstanding performance in terms of tracking accuracy and robustness.
会议录	TENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2018)
会议录出版者	SPIE-INT SOC OPTICAL ENGINEERING
会议录出版地	1000 20TH ST, PO BOX 10, BELLINGHAM, WA 98227-0010 USA
语种	英语
资助项目	National Natural Science Foundation of China[61861027]
WOS研究方向	Optics ; Imaging Science & Photographic Technology
WOS记录号	WOS:000485096200026
内容类型	会议论文
源URL	[http://119.78.100.223/handle/2XXMBERH/36101]
专题	电气工程与信息工程学院党委教师工作部（人事处、教师发展中心）
通讯作者	Gao, Huiling
作者单位	1.Lanzhou Univ Technol, Natl Demonstrat Ctr Expt Elect & Control Engn Edu, Lanzhou, Gansu, Peoples R China 2.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou, Gansu, Peoples R China 3.Lanzhou Univ Technol, Key Lab Gansu Adv Control Ind Processes, Lanzhou, Gansu, Peoples R China
推荐引用方式 GB/T 7714	Gao, Huiling,Liu, Jie,Liu, Chaorong,et al. Convolutional Residual Learning with Sparse Robust Samples and Multi-feature Fusion for Object Tracking[C]. 见:.