End -to -end video text detection with online tracking

doi:10.1016/j.patcog.2020.107791

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	End -to -end video text detection with online tracking
	Yu, Hongyuan 4,5; Huang, Yan 4,5; Pi, Lihong 1; Zhang, Chengquan 2; Li, Xuan 2; Wang, Liang 3,4,5
刊名	PATTERN RECOGNITION
	2021-05-01
卷号	113 页码:12
关键词	End-to-end Video text detection Online tracking
ISSN号	0031-3203
DOI	10.1016/j.patcog.2020.107791
通讯作者	Wang, Liang(wangliang@nlpr.ia.ac.cn)
英文摘要	Text in videos usually acts as important semantic cues, which is helpful to video analysis. Video text detection is considered as one of the most difficult tasks in document analysis due to the following two challenges: 1) the difficulties caused by video scenes, i.e., motion blur, illumination changes, and occlusion; 2) the properties of text including variants of fonts, languages, orientations, and shapes. Most existing methods try to improve the video text detection through video text tracking, but treat these two tasks separately. This can significantly increase the amount of calculations and cannot take full advantage of the supervisory information of both tasks. In this work, we introduce explainable descriptor, combines appearance, geometry and PHOC features, to establish a bridge between detection and tracking and build an end-to-end video text detection model with online tracking to address these challenges together. By integrating these two branches into one trainable framework, they can promote each other and the computational cost is significantly reduced. Besides, the introduce explainable descriptor also make our end-to-end model have inherent interpretability. Experiments on existing video text benchmarks including ICDAR 2013 Video, DOST, Minetto and YVT verify the role of explainable descriptors in improving model expression ability and the proposed method significantly outperforms state-of-the-art methods. Our method improves F-score by more than 2% on all datasets and achieves 81 . 52% on the MOTA of the Minetto dataset. (c) 2021 Elsevier Ltd. All rights reserved.
资助项目	National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61525306] ; National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015] ; National Natural Science Foundation of China[61806194] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Beijing Science and Technology Project[Z181100008918010]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000626268400011
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Capital Science and Technology Leading Talent Training Project ; Beijing Science and Technology Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44142]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Wang, Liang
作者单位	1.Tsinghua Univ THU, Inst Microelect, Beijing 100084, Peoples R China 2.Baidu Inc, Dept Comp Vis Technol VIS, Beijing 100085, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, Ctr Excellence Brain Sci & Intelligence Technol C, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci UCAS, Beijing 100049, Peoples R China 5.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit NLPR, Ctr Res Intelligent Percept & Comp CRIPAC, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yu, Hongyuan,Huang, Yan,Pi, Lihong,et al. End -to -end video text detection with online tracking[J]. PATTERN RECOGNITION,2021,113:12.
APA	Yu, Hongyuan,Huang, Yan,Pi, Lihong,Zhang, Chengquan,Li, Xuan,&Wang, Liang.(2021).End -to -end video text detection with online tracking.PATTERN RECOGNITION,113,12.
MLA	Yu, Hongyuan,et al."End -to -end video text detection with online tracking".PATTERN RECOGNITION 113(2021):12.