基于目标轨迹空间关系的视频摘要方法

doi:10.11896/jsjkx.210100125

计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 404-408.doi: 10.11896/jsjkx.210100125

• 图像处理& 多媒体技术 • 上一篇下一篇

基于目标轨迹空间关系的视频摘要方法

曲智国, 谭贤四, 唐瑭, 郑建成, 费太勇

空军预警学院武汉430019

出版日期:2021-11-10 发布日期:2021-11-12
通讯作者: 曲智国(670644428@qq.com)
基金资助:
国家自然科学基金 (61401504);博士后科学基金(2014M562562)

Video Synopsis Based on Trajectory Spatial Relationship Analysis

QU Zhi-guo, TAN Xian-si, TANG Tang, ZHENG Jian-cheng, FEI Tai-yong

Air Force Early Warning Academy,Wuhan 430019,China

Online:2021-11-10 Published:2021-11-12
About author:QU Zhi-guo,born in 1982,postgraduate,Ph.D,vice professor.His main research interests include early-warning surveillance,image processing and object recognition,etc.
Supported by:
National Natural Science Foundation of China(61401504) and China Postdoctoral Science Foundation(2014M562562).

摘要/Abstract

摘要： 碰撞现象是视频摘要中需要避免的问题,在轨迹重排时一般通过碰撞代价函数进行约束,但是现有视频摘要方法在轨迹重排优化过程中需要重复计算轨迹间的碰撞代价,存在大量冗余运算量,为此提出了一种基于目标轨迹空间关系的视频摘要方法。该方法通过分析目标轨迹间的空间关系,可以在轨迹重排前预先判断两条轨迹是否会发生碰撞,据此定义了3种轨迹关系,并给出了碰撞代价的快速计算方法,从而较好地降低了现有视频摘要方法优化过程中的冗余计算,提高了视频摘要中轨迹重排的运算速度。实验结果验证了所提方法的有效性。

关键词: 轨迹关系, 轨迹重排, 碰撞现象, 视频处理, 视频摘要

Abstract: Collision phenomenon is an unpleasant issue that needs to be addressed during trajectory rearrangement in video synopsis.It is usually constrained by some collision cost in the final energy function to be optimized.However,most synopsis methods compute the collision cost term repeatedly in the iterative optimization process,leading to serious computation redundancy.To solve that,a novel synopsis method based on spatial relationships between trajectories is proposed in this paper.It turns out whether two trajectories will collide or not can be determined beforehand by analyzing their spatial relationships.Accordingly,three kinds of relationship are defined and corresponding fast computation of collision cost are given.In this way,the redundancy in collision cost computation is decreased and thus improving the speed of traditional methods obviously.Experimental results demonstrate the effectiveness of the proposed method.

Key words: Collision phenomenon, Trajectory rearrangement, Trajectory relationship, Video processing, Video synopsis

中图分类号:

TP391.4

曲智国, 谭贤四, 唐瑭, 郑建成, 费太勇. 基于目标轨迹空间关系的视频摘要方法[J]. 计算机科学, 2021, 48(11A): 404-408. https://doi.org/10.11896/jsjkx.210100125

QU Zhi-guo, TAN Xian-si, TANG Tang, ZHENG Jian-cheng, FEI Tai-yong. Video Synopsis Based on Trajectory Spatial Relationship Analysis[J]. Computer Science, 2021, 48(11A): 404-408. https://doi.org/10.11896/jsjkx.210100125

参考文献

[1]HÖFERLIN B,HÖFERLIN M,WEISKOPF D,et al.InformaTion-Based Adaptive Fast-forward for Visual Surveillance[J].Multimedia and Tools Applications,2011,55(1):127-150.
[2]EJAZ N,TARIQ T B,BAIK S W.Adaptive Key Frame Extraction for Video Summarization Using an Aggregation Mechanism[J].Journal of Visual Communications and Image Representation,2012,23(7):1031-1040.
[3]PETROVIC N,JOJIC N,HUANG T S.Adaptive Video Fast Forward[J].Multimedia Tools and Applications,2005,26(3):327-344.
[4]ZHU X,WU X,FAN J,et al.Exploring Video Content Structure for Hierarchical Summarization[J].Multimedia Systems,2004,10(2):98-115.
[5]CHEN Z Y.Key-Frame Extraction Using Nonparametric Clustering Based on Density Estimation[J].Computer Science,2007,34(4):119-120,162.
[6]BELO L D S,CAETANO C A,PATROCíNIO Z K G D,et al.Summarizing Video Sequence Using a Graph-Based Hierarchical Approach[J].Neurocomputing,2016(173):1001-1016.
[7]PRITCH Y,RAV-ACHA A,PELEG S.Nonchronological Video Synopsis and Indexing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11):1971-1984.
[8]HUANG C R,CHUNG P C J,YANG D K,et al.Maximum A Posteriori Probability Estimation for Online Surveillance Video Synopsis[J].IEEE Transactions on Circuits Systems and Video Technology,2014,24(8):1417-1429.
[9]NIE Y,XIAO C,SUN H,et al.Compact Video Synopsis viaGlobal Spatiotemporal Optimization[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(10):1664-1676.
[10]ZHONG R,HU R,WANG Z,et al.Fast Synopsis for Moving Objects Using Compressed Video[J].IEEE Signal Processing Letters,2014,21(7):834-838.
[11]FU W,WANG J,GUI L,et al.Online Video Synopsis of Structured Motion[J].Neurocomputing,2014,135:155-162.
[12]ZHU J,FENG S,YI D,et al.High-Performance Video Condensation System[J].IEEE Transactions on Circuits Systems and Video Technology,2015,25(7):1113-1124.
[13]ZHU J,LIAO S,LI S Z.Multicamera Joint Video Synopsis[J].IEEE Transactions on Circuits Systems and Video Technology,2016,26 (6):1058-1069.
[14]LI X L,WANG Z G,LU X Q.Surveillance Video Synopsis via Scaling Down Objects[J].IEEE Transactions on image Processing,2016,25(2):740-755.
[15]HE Y,GAO C X,SANG N,et al.Graph Coloring Based Surveillance Video Synopsis[J].Neurocomputing,2017,225:64-79.
[16]HE Y,QU Z G,GAO C X,et al.Fast Online Video Synopsis Based on Potential Collision Graph[J].IEEE Signal Processing Letters,2017,24(1):22-26.
[17]TIAN H L,DING S,YU C W,et al.Research of Video Abstraction Based on Object Detection and Tracking[J].Computer Science,2016,43(11):297-299,312.
[18]ZHAO L,HUANG H.Compressed Domain Synopsis Research in AVS Surveillance Profile[J].Computer Science,2016,43(7):46-50.
[19]BARNICH O,DROOGENBROECK M V.Vibe:A UniversalBackground Subtraction Algorithm for Video Sequences[J].IEEE Trans.On Image Processing,2011,20(6):1709-1724.
[20]YANG T,LI S Z,PAN Q,et al.Real-Time Multiple Objects Tracking with Occlusion Handling in Dynamic Scenes[C]//Proceedings IEEE Conference on Computer Vision and Pattern Recognition.2005:970-975.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于目标轨迹空间关系的视频摘要方法

Video Synopsis Based on Trajectory Spatial Relationship Analysis

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

Metrics

本文评价

推荐阅读 0

[1]	张开强, 蒋从锋, 程小兰, 贾刚勇, 张纪林, 万健. 多分辨率下资源感知的图像目标自适应缩放检测 Resource-aware Based Adaptive-scaling Image Target Detection Under Multi-resolution Scenario 计算机科学, 2021, 48(4): 180-186. https://doi.org/10.11896/jsjkx.201200116
[2]	赵磊,黄华. AVS监控档视频的压缩域摘要研究 Compressed Domain Synopsis Research in AVS Surveillance Profile 计算机科学, 2016, 43(7): 46-50. https://doi.org/10.11896/j.issn.1002-137X.2016.07.007
[3]	田合雷,丁胜,于长伟,周立. 基于目标检测及跟踪的视频摘要技术研究 Research of Video Abstraction Based on Object Detection and Tracking 计算机科学, 2016, 43(11): 297-299. https://doi.org/10.11896/j.issn.1002-137X.2016.11.057
[4]	李晓光,刘宏哲,袁家政. 基于GPU实时视频处理的多投影融合系统研究 Multi-projector Displays System Research Based on GPU Real-time Video Processing 计算机科学, 2015, 42(9): 285-288. https://doi.org/10.11896/j.issn.1002-137X.2015.09.056
[5]	陈卓夷. 基于非参数密度估计聚类的关键帧提取方法计算机科学, 2007, 34(4): 119-120.
[6]	栾悉道谢毓湘韩智广吴玲达. 新闻视频挖掘技术研究计算机科学, 2007, 34(2): 1-6.