李珊,饶文碧.基于视频的矿井中人体运动区域检测[J].计算机科学,2018,45(4):291-295
基于视频的矿井中人体运动区域检测
Video-based Detection of Human Motion Area in Mine
投稿时间:2017-01-22  修订日期:2017-04-01
DOI:10.11896/j.issn.1002-137X.2018.04.049
中文关键词:  人体运动区域,时间差分法,TD-HF,AdaBoost
英文关键词:Human motion region,Time difference method,TD-HF,AdaBoost
基金项目:本文受国家自然科学基金项目(61601337),湖北省重大科技创新计划项目(2015BCE068)资助
作者单位E-mail
李珊 武汉理工大学计算机科学与技术学院 武汉430070  
饶文碧 武汉理工大学计算机科学与技术学院 武汉430070 wbrao@whut.edu.cn 
摘要点击次数: 281
全文下载次数: 195
中文摘要:
      将人体运动区域检测技术应用到矿井视频中可以检测矿井下矿工的运动情况,进一步可以智能检测矿工的异常行为,根据反馈的检测结果实现实时报警和联动控制,减少矿井事故的发生。针对矿井场景下的人体运动区域检测,提出了一种实现人体运动区域提取的融合方法TD-HF(Time Difference and Haar Feature),该方法融合了时间差分法和基于Haar特征的人体检测算法。实验表明,所提方法在检测率和误识率方面均比单纯的基于AdaBoost算法的分类器更胜一筹,并且在检测时间上满足实时性要求,适用于矿井视频这种特殊场景下的人体运动区域检测。
英文摘要:
      The human motion area detection technology applied to the mine video can detect motion of miners and intelligently detect abnormal behavior of miners through further analysis.According to the results of feedback detection to achieve real-time alarm and linkage control,it obviously reduces the occurrence of mine accidents.This paper proposed a hybrid method TD-HF(Time Difference and Haar Feature) for extracting human motion area,which integrates the time difference method and the human detection algorithm based on Haar feature especially under the condition of mine.The experiment shows that this method is better than the simple classifier based on AdaBoost algorithm in the detection rate and false recognition rate,at the same time,it can satisfy the real-time requirements in detection time.It’s applicable to the detection of human motion area under the special condition of mine video.
查看全文  查看/发表评论  下载PDF阅读器