首页 | 本学科首页   官方微博 | 高级检索  
     

基于CNN的监控视频事件检测
引用本文:王梦来,李想,陈奇,李澜博,赵衍运.基于CNN的监控视频事件检测[J].自动化学报,2016,42(6):892-903.
作者姓名:王梦来  李想  陈奇  李澜博  赵衍运
作者单位:北京邮电大学信息与通信工程学院多媒体通信与模式识别实验室 北京 100876
摘    要:复杂监控视频中事件检测是一个具有挑战性的难题, 而TRECVID-SED评测使用的数据集取自机场的实际监控视频,以高难度著称. 针对TRECVID-SED评测集, 提出了一种基于卷积神经网络(Convolutional neural network, CNN)级联网络和轨迹分析的监控视频事件检测综合方案. 在该方案中, 引入级联CNN网络在拥挤场景中准确地检测行人, 为跟踪行人奠定了基础; 采用CNN网络检测具有关键姿态的个体事件, 引入轨迹分析方法检测群体事件. 该方案在国际评测中取得了很好的评测排名: 在6个事件检测的评测中, 3个事件检测排名第一.

关 键 词:卷积神经网络    事件检测    行人检测    目标跟踪    轨迹分析
收稿时间:2015-11-03

Surveillance Event Detection Based on CNN
WANG Meng-Lai,LI Xiang,CHEN Qi,LI Lan-Bo,ZHAO Yan-Yun.Surveillance Event Detection Based on CNN[J].Acta Automatica Sinica,2016,42(6):892-903.
Authors:WANG Meng-Lai  LI Xiang  CHEN Qi  LI Lan-Bo  ZHAO Yan-Yun
Affiliation:Multimedia Communication and Pattern Recognition Laboratory, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876
Abstract:It is well-known that event detection in real-world surveillance videos is a challenging task. The corpus of TRECVID-SED evaluation is acquired from the surveillance video of London Gatwick International Airport and it is well known for its high difficulties. We propose a comprehensive event detection framework based on an effective part-based deep network cascade——head-shoulder networks (HsNet) and trajectory analysis. On the one hand, the deep network detects pedestrians very precisely, laying a foundation for tracking pedestrians. On the other hand, convolutional neural networks (CNNs) are good at detecting key-pose-based single events. Trajectory analysis is introduced for group events. In TRECVID-SED15 evaluation, our approach outperformed others in 3 out of 6 events, demonstrating the power of our proposal.
Keywords:Convolutional neural network (CNN)  event detection  pedestrian detection  target tracking  trajectory analysis
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号