CASIA OpenIR  > 智能感知与计算研究中心
Gestalt laws based tracklets analysis for human crowd understanding
Huang KQ(黄凯奇)1,2,3; zhao, weiqi1,2; zhang, zhang1,2
Source PublicationPattern Recognition
2017
Volume75Issue:0Pages:112-127
AbstractCrowded scene analysis is a popular research topic due to its great application potentials, such as intel- ligent video surveillance and crowd density estimation. In this paper, we propose a novel approach to detecting crowd groups and learning semantic regions with a unified hierarchical clustering framework. According to the Gestalt laws of grouping, we propose three priors to define a unified similarity metric to measure the similarities of pairs of original tracklets and pairs of representative tracklets from dif- ferent crowd groups, so that the short-term crowd groups and the long-term semantic paths commonly composed of several short-term crowd groups can be detected by a bottom-up hierarchical clustering al- gorithm simultaneously. In order to verify our method at the longer time duration video sequences in the crowded scene, we construct a new crowd database (CASIA crowd database 1 ) with various crowd densi- ties in real scenes. Extensive experiments on our CASIA crowd database, Collective Motion Database and CUHK database are performed, and the results demonstrate that our approach is effective and reliable for crowd detection and semantic scene understanding in various crowd densities, especially for the crowd analysis in long temporal video clips.
KeywordGestalt Laws
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20217
Collection智能感知与计算研究中心
Affiliation1.CRIPAC
2.University of Chinese Academy of Sciences
3.CAS Center for Excellence in Brain Science and Intelligence Technology
Recommended Citation
GB/T 7714
Huang KQ,zhao, weiqi,zhang, zhang. Gestalt laws based tracklets analysis for human crowd understanding[J]. Pattern Recognition,2017,75(0):112-127.
APA Huang KQ,zhao, weiqi,&zhang, zhang.(2017).Gestalt laws based tracklets analysis for human crowd understanding.Pattern Recognition,75(0),112-127.
MLA Huang KQ,et al."Gestalt laws based tracklets analysis for human crowd understanding".Pattern Recognition 75.0(2017):112-127.
Files in This Item: Download All
File Name/Size DocType Version Access License
zhaoweiqi-Gestalt la(6952KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang KQ(黄凯奇)]'s Articles
[zhao, weiqi]'s Articles
[zhang, zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang KQ(黄凯奇)]'s Articles
[zhao, weiqi]'s Articles
[zhang, zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang KQ(黄凯奇)]'s Articles
[zhao, weiqi]'s Articles
[zhang, zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: zhaoweiqi-Gestalt laws based tracklets analysis for human crowd understanding.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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