摘要
为解决现有视频浓缩在复杂场景下存在的轨迹不完整、交互行为难以保留等问题,提出一种片段-自适应的监控视频浓缩方法.首先,提出一种视频划分模块,对输入视频逐帧进行拥挤度检测,采用自适应阈值将视频划分为稀疏和拥挤片段,并将被中断的轨迹进行链接形成延展拥挤片段;其次,设计交互行为判别模块,结合空间距离和视频自适应阈值判别并保留目标之间的交互行为;最后,提出片段-自适应重排模块,综合碰撞约束、空间占比约束、交互约束和时序约束生成最优时间标签,进而融合背景生成浓缩视频.在数据集VISOR,BEHAVE和CAVIAR上的实验结果表明,该方法比当前主流方法在帧压缩率和碰撞率上分别降低了0.136和0.011,计算时间减少了120.03 s.
To solve the problems of existing video synopsis methods such as incomplete tracks and difficulty to retain interactive behaviors in complex scenes,a segmentation-adaptive video synopsis method is proposed.Firstly,a video segmentation module is proposed,which detects the crowding degree of each frame of the input video,and divides the video into sparse and crowded segmentation using self-adaption threshold,and links the interrupted track to form extending crowded segmentation.Secondly,an interactive behavior judgment module is designed,which combines spatial distance and video self-adaption threshold to comprehensively judge and retain interactive behavior between objects.Finally,a segmentation-adaptive rearrangement module is proposed,which combines collision constraints,space proportion constraint,interactive constraints and temporal constraints to generate the optimal time tag,and fuses the background to generate synopsis video.Experimental results on pub-lic dataset VISOR,BEHAVE and CAVIAR show that compared with the current mainstream methods,the pro-posed method reduces 0.136 and 0.011 frame compression rate and collision rate respectively,and the time cost is reduced by 120.03s.
作者
张云佐
朱鹏飞
郑婷婷
李文博
张天
Zhang Yunzuo;Zhu Pengfei;Zheng Tingting;Li Wenbo;and Zhang Tian(School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2023年第6期944-952,共9页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(61702347,62027801)
河北省自然科学基金(F2022210007,F2017210161)
河北省高等学校科学技术研究项目(ZD2022100,QN2017132)
中央引导地方科技发展资金(226Z0501G)
石家庄铁道大学研究生创新资助项目(YC2023081).
关键词
视频浓缩
监控视频
片段
自适应
交互行为
video synopsis
surveillance video
segmentation
self-adaption
interactive behavior
