联合多层时空切片和二分思想的视频浓缩  

Video synopsis based on the integration of multiple spatiotemporal slices and dichotomy

作　　者：张云佐 郑婷婷 蔡昭权 ZHANG Yunzuo;ZHENG Tingting;CAI Zhaoquan(School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China;Shanwei Institute of Technology,Shanwei 516600,China)

机构地区：[1]石家庄铁道大学信息科学与技术学院,河北石家庄050043 [2]汕尾职业技术学院,广东汕尾516600

出　　处：《合肥工业大学学报（自然科学版）》2022年第11期1478-1483,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61702347,62027801);广东省重点领域研发计划资助项目(2019B01037002);河北省自然科学基金资助项目(F2022210007,F2017210161);河北省高等学校科学技术研究资助项目(ZD2022100,QN2017132);中央引导地方科技发展资金资助项目(226Z0501G)。

摘　　要：视频浓缩是高效表达监控视频的重要方式,提取目标管是视频浓缩的基本步骤。现有的视频浓缩大多基于目标检测和跟踪生成目标管,应用于包含拥挤场景的监控视频时,性能表现不佳。文章提出一种稀疏-拥挤视频的浓缩框架(sparse-crowed video synopsis,SCVS),将输入视频分为稀疏和拥挤片段分别处理。首先提出一种基于多层时空切片联合的稀疏和拥挤片段划分方法,以二分思想为基础联合多层时空切片分割稀疏和拥挤片段;其次对分割后的稀疏片段提取目标管,进行管优化重排得到稀疏场景的浓缩视频;最后融合稀疏浓缩视频和拥挤片段生成浓缩视频。实验结果表明,SCVS框架有效避免了现有方法在拥挤场景下性能不佳的问题,具有较高的压缩比和目标留存比以及良好的视觉体验。Video synopsis is an important way to express surveillance video efficiently,and the extraction of object tubes is the essential step of video synopsis.Most of the existing video synopsis methods use object detection and object tracking to generate object tubes.The performance is commonly poor when applied to surveillance video containing the crowded scene.To solve this problem,this paper proposes a sparse-crowed video synopsis(SCVS)framework,which divides the input video into sparse and crowded segments and processes them respectively.Firstly,a sparse and crowded clips segmentation method based on the integration of multiple spatiotemporal slices and dichotomy is proposed to divide sparse and crowded clips.Secondly,the object tube is extracted from the segmented sparse clips,and the synopsis video in the sparse clip is obtained by optimizing the rearrangement of the tubes.Finally,sparse synopsis video and crowded clips are fused to generate a complete synopsis video.The experimental results show that SCVS framework can effectively avoid the problem of poor performance of preprocessing technology in a crowded scene,which has higher compression ratio(CR)and object preserving ratio(OPR),and comfortable visual perception.

关 键 词：时空切片 二分思想 拥挤视频 视频浓缩 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]