Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos

doi:10.1109/TCSVT.2019.2906195

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos
	Liu, Wei1,2 ; Liao, Shengcai3 ; Hu, Weidong 1
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
	2019-12-01
卷号	29 期号:12 页码:3558-3567
通讯作者	Liao, Shengcai(scliao@ieee.org)
摘要	Most existing video-based object detection methods utilize successful image-based object detector as a base network, and additionally exploit temporal information with either bounding-box post-processing or feature enhancement from multiple frames. However, little work has been done on directly modeling temporal motion in an efficient way for detection in surveillance videos. In this paper, a simple but effective module, denoted as motion-from-memory (MFM), is proposed to encode temporal context for improved detection in surveillance videos. With appearance features extracted from a base CNN, the MFM module maintains a dynamic memory for each input sequence and output motion features on each frame. This module costs minor additional model parameters and computations, but is very helpful for moving object detection, especially in surveillance videos. Thanks to the additional MFM module, the performance of a light-weight MobileNet-based Faster RCNN detector is boosted by 13.93 in mAP, achieving comparable performance to that of strong ResNet-50-based. When MFM is integrated into an even weaker but faster single-stage detector, it ranks the second best one among all published works when submitted to the DEETRAC vehicle detection benchmark, with 69.10 mAP, compared to 69.87 of the best one. However, when running speed is considered, the proposed method is the fastest one, running at 33 FPS with 540x960 surveillance videos on a moderate commercial GPU (NVIDIA GTX 1080Ti), which is about 3 times faster than the second fastest one.
关键词	Videos Feature extraction Object detection Detectors Surveillance Proposals Dynamics Object detection surveillance video deep neural network
DOI	10.1109/TCSVT.2019.2906195
关键词[WOS]	TRACKING
收录类别	SCI
语种	英语
资助项目	National Laboratory of Pattern Recognition Independent Research Project[Z-2018008] ; Chinese National Natural Science Foundation Project[61672521] ; National Key Research and Development Plan[2016YFC0801003] ; National Key Research and Development Plan[2016YFC0801003] ; Chinese National Natural Science Foundation Project[61672521] ; National Laboratory of Pattern Recognition Independent Research Project[Z-2018008]
项目资助者	National Key Research and Development Plan ; Chinese National Natural Science Foundation Project ; National Laboratory of Pattern Recognition Independent Research Project
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000502789200008
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/29450
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Liao, Shengcai
作者单位	1.Natl Univ Def Technol, Natl Key Lab Sci & Technol ATR, Coll Elect Sci, Changsha 410073, Hunan, Peoples R China 2.Chinese Acad Sci, Ctr Biometr & Secur Res, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 3.Incept Inst Artificial Intelligence, Abu Dhabi 5151, U Arab Emirates
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Liu, Wei,Liao, Shengcai,Hu, Weidong. Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2019,29(12):3558-3567.
APA	Liu, Wei,Liao, Shengcai,&Hu, Weidong.(2019).Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,29(12),3558-3567.
MLA	Liu, Wei,et al."Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 29.12(2019):3558-3567.