中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Perceiving Motion From Dynamic Memory for Vehicle Detection in Surveillance Videos

文献类型：期刊论文

作者Liu, Wei1,2; Liao, Shengcai3; Hu, Weidong2
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2019-12-01
卷号29期号:12页码:3558-3567
关键词Videos Feature extraction Object detection Detectors Surveillance Proposals Dynamics Object detection surveillance video deep neural network
ISSN号1051-8215
DOI10.1109/TCSVT.2019.2906195
通讯作者Liao, Shengcai(scliao@ieee.org)
英文摘要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.
WOS关键词TRACKING
资助项目National Key Research and Development Plan[2016YFC0801003] ; Chinese National Natural Science Foundation Project[61672521] ; National Laboratory of Pattern Recognition Independent Research Project[Z-2018008]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000502789200008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Plan ; Chinese National Natural Science Foundation Project ; National Laboratory of Pattern Recognition Independent Research Project
源URL[http://ir.ia.ac.cn/handle/173211/29449]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Liao, Shengcai
作者单位1.Chinese Acad Sci, Ctr Biometr & Secur Res, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.Natl Univ Def Technol, Natl Key Lab Sci & Technol ATR, Coll Elect Sci, Changsha 410073, Hunan, Peoples R China
3.Incept Inst Artificial Intelligence, Abu Dhabi 5151, U Arab Emirates
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。