Detection of Abnormal behavior in Dynamic Crowded Gatherings.
AIPR（2013）
摘要
People gather for parades, sports, musical events, and mass gatherings for pilgrimage at religious places like Mecca, Jerusalem, Vatican, etc. Most often, these mass gatherings lead to crowd disasters. In this research, a new automated algorithm for the Detection of Abnormal behavior in Dynamic Crowded Gatherings (DADCG) is proposed that has reduced processing speed, sensitivity to noise, and improved accuracy. Initially, the temporal features of the scenes are extracted using Motion History Image (MHI) technique. Then the Optical Flow (OF) vectors are calculated for each MHI image using Lucas-Kanade method to obtain the spatial features. This Optical flow image is segmented into four equal-sized blocks. Finally, a two dimensional histogram is generated with motion direction and motion magnitude for each block. Stampede and congestion areas can be detected by comparing the mean value of the histogram of each segmented optical flow image. Based on this result, an alarm may be generated for the security personnel to take appropriate actions.
更多查看译文
关键词
behavioural sciences computing,feature extraction,image motion analysis,image segmentation,image sequences,natural scenes,object detection,video surveillance,DADCG,Lucas-Kanade method,MHI image,MHI technique,OF vectors,accuracy improvement,alarm generation,congestion area detection,crowd disasters,detection-of abnormal behavior-in-dynamic crowded gatherings,mass gatherings,mean histogram value,motion direction,motion history image technique,motion magnitude,noise sensitivity reduction,optical flow image segmentation,optical flow vectors,processing speed reduction,scene temporal feature extraction,security personnel,spatial features,stampede detection,temporal features,two-dimensional histogram generation,Dynamic crowd scene,Motion History Image,abnormal behavior detection,optical flow,video surveillance system
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要