The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A detecção de comportamento anormal de multidões é um importante tópico de pesquisa em visão computacional para melhorar o tempo de resposta de eventos críticos. Nesta carta, apresentamos um novo método para detectar e localizar multidões reunidas em vídeos de vigilância. O modelo de quietude de primeiro plano proposto é baseado na máscara do objeto em primeiro plano e no fluxo óptico denso para medir o nível instantâneo de quietude da multidão. Além disso, obtemos o nível de quietude da multidão a longo prazo pelo modelo do balde furado, e o comportamento de aglomeração da multidão pode ser detectado pela análise de limiar. Resultados experimentais indicam que a abordagem proposta pode detectar e localizar eventos de aglomeração de multidões, e é capaz de distinguir entre multidões em pé e andando. Os experimentos em cenas realistas com precisão de 88.65% para detecção de quadros de aglomeração mostram que nosso método é eficaz para detecção de comportamento de aglomeração de multidões.
Chun-Yu LIU
National Taiwan University of Science and Technology
Wei-Hao LIAO
National Taiwan University of Science and Technology
Shanq-Jang RUAN
National Taiwan University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Chun-Yu LIU, Wei-Hao LIAO, Shanq-Jang RUAN, "Crowd Gathering Detection Based on the Foreground Stillness Model" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 7, pp. 1968-1971, July 2018, doi: 10.1587/transinf.2018EDL8005.
Abstract: The abnormal crowd behavior detection is an important research topic in computer vision to improve the response time of critical events. In this letter, we introduce a novel method to detect and localize the crowd gathering in surveillance videos. The proposed foreground stillness model is based on the foreground object mask and the dense optical flow to measure the instantaneous crowd stillness level. Further, we obtain the long-term crowd stillness level by the leaky bucket model, and the crowd gathering behavior can be detected by the threshold analysis. Experimental results indicate that our proposed approach can detect and locate crowd gathering events, and it is capable of distinguishing between standing and walking crowd. The experiments in realistic scenes with 88.65% accuracy for detection of gathering frames show that our method is effective for crowd gathering behavior detection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8005/_p
Copiar
@ARTICLE{e101-d_7_1968,
author={Chun-Yu LIU, Wei-Hao LIAO, Shanq-Jang RUAN, },
journal={IEICE TRANSACTIONS on Information},
title={Crowd Gathering Detection Based on the Foreground Stillness Model},
year={2018},
volume={E101-D},
number={7},
pages={1968-1971},
abstract={The abnormal crowd behavior detection is an important research topic in computer vision to improve the response time of critical events. In this letter, we introduce a novel method to detect and localize the crowd gathering in surveillance videos. The proposed foreground stillness model is based on the foreground object mask and the dense optical flow to measure the instantaneous crowd stillness level. Further, we obtain the long-term crowd stillness level by the leaky bucket model, and the crowd gathering behavior can be detected by the threshold analysis. Experimental results indicate that our proposed approach can detect and locate crowd gathering events, and it is capable of distinguishing between standing and walking crowd. The experiments in realistic scenes with 88.65% accuracy for detection of gathering frames show that our method is effective for crowd gathering behavior detection.},
keywords={},
doi={10.1587/transinf.2018EDL8005},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Crowd Gathering Detection Based on the Foreground Stillness Model
T2 - IEICE TRANSACTIONS on Information
SP - 1968
EP - 1971
AU - Chun-Yu LIU
AU - Wei-Hao LIAO
AU - Shanq-Jang RUAN
PY - 2018
DO - 10.1587/transinf.2018EDL8005
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2018
AB - The abnormal crowd behavior detection is an important research topic in computer vision to improve the response time of critical events. In this letter, we introduce a novel method to detect and localize the crowd gathering in surveillance videos. The proposed foreground stillness model is based on the foreground object mask and the dense optical flow to measure the instantaneous crowd stillness level. Further, we obtain the long-term crowd stillness level by the leaky bucket model, and the crowd gathering behavior can be detected by the threshold analysis. Experimental results indicate that our proposed approach can detect and locate crowd gathering events, and it is capable of distinguishing between standing and walking crowd. The experiments in realistic scenes with 88.65% accuracy for detection of gathering frames show that our method is effective for crowd gathering behavior detection.
ER -