CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
Motion Cue Based Instance-level Moving Object Detection
Huang,Junjie1,2; Zou,Wei1,2; Zhu,Zheng1,2; Zhu,Jiagang1,2
2019
Conference Name第31届中国控制与决策会议(2019CCDC)
Conference Date2019年6月3日-5日
Conference Place中国南昌
Abstract

This paper studies the moving object detection, i.e., analyzing the amount, position and size of the moving objects in instance-level, which is meaningful for many computer vision problems. However, the existing methods are still not satisfying in accuracy, portability and speed. In this paper, we propose a novel framework which detects moving objects by analysis the consistency of the moving foreground. Instead of directly performing cluster algorithms on the moving foregound, we take two stages: analyzing the composition according to the local density of the moving foreground points and locating the targets by regressing some anchors. In this way, the proposed method doesn’t need any training processes and can be efficiently performed to detect moving objects with arbitrary classes. Besides, we create our own publicly available dataset PDMOD with sufficient data, general challenges and convictive evaluation protocols to fill the scarcity of the evaluational datasets.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23602
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorHuang,Junjie
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Huang,Junjie,Zou,Wei,Zhu,Zheng,et al. Motion Cue Based Instance-level Moving Object Detection[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
PID5820299.pdf(1769KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang,Junjie]'s Articles
[Zou,Wei]'s Articles
[Zhu,Zheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang,Junjie]'s Articles
[Zou,Wei]'s Articles
[Zhu,Zheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang,Junjie]'s Articles
[Zou,Wei]'s Articles
[Zhu,Zheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PID5820299.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.