基于自适应分块和SSIM的运动目标检测

计算机科学 ›› 2014, Vol. 41 ›› Issue (2): 119-122.

基于自适应分块和SSIM的运动目标检测

田洪金,战荫伟

广东工业大学计算机学院广州510006;广东工业大学计算机学院广州510006

出版日期:2018-11-14 发布日期:2018-11-14

Moving Object Detection Based on Adaptive Image Blocking and SSIM

TIAN Hong-jin and ZHAN Yin-wei

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 研究了目标检测方法。针对传统背景更新方法易受噪声干扰、算法执行速度慢等弊端,对背景差分法予以改进,提出一种基于自适应图像分块和结构相似性(SSIM)的运动目标检测方法。根据视频最初几帧得到初始背景模型,再对视频后续的每帧进行自适应分块处理,利用相邻帧对应分块的结构相似性计算局部更新率,建立背景模型,将背景与当前帧差分即得到运动目标。实验结果表明,与传统的背景差分法相比,改进后的方法具有更好的检测效果。

关键词: 运动目标检测,自适应分块,结构相似性中图法分类号TP391.4文献标识码A

Abstract: This paper focused on object detection．Motivated by the drawbacks of existing background update algorithms that are noise sensitive and slow in execution,an improvement on moving object detection method was proposed by image adaptive blocking and block-wise structure similarity of inter-frames．An initial background model was obtained with a few beginning frames and every successive frame was divided into blocks．Over corresponding blocks of two neighboring frames,a similarity was defined in order to update the background model．The moving objects were then obtained by subtracting the background model from the current frame．Experimental results demonstrate that the improved method has better performance than traditional methods.

Key words: Moving object detection,Adaptive blocking,Structure similarity of inter-frames

田洪金,战荫伟. 基于自适应分块和SSIM的运动目标检测[J]. 计算机科学, 2014, 41(2): 119-122. https://doi.org/

TIAN Hong-jin and ZHAN Yin-wei. Moving Object Detection Based on Adaptive Image Blocking and SSIM[J]. Computer Science, 2014, 41(2): 119-122. https://doi.org/

参考文献

[1] Elhabian S Y,El-Sayed K M,Ahmed S H．Moving Object Detection in Spatial Domain using Background Removal Techniques－State-of-Art [C]∥Recent Patents on Computer Science．2008,1:32-54
[2] Stauffer C,Grimson E．Learning Patterns of Activity Using RealTime Tracking [J]．IEEE Transactions on Pattern Recognition and Machine Intelligence,2000,22(8):747-757
[3] Stauffer C,Grimson W E L．Adaptive Background MixtureModels for Real-Time Tracking [C]∥Computer Vision and Pattern Recognition．1999
[4] 梁华,刘云辉．自适应多模快速背景差方法[J]．中国图象图形学报,2008,13(2):345-350
[5] Li Li-yuan,Huang Wei-min,Irene Y H,et al.Foreground ObjectDetection from Videos Containing Complex Background [C]∥Proceedings of the eleventh ACM international conference on Multimedia.2003:2-10
[6] 张文涛,李晓峰,李在铭．高速密集视频目标场景下的运动分析[J]．电子学报,2000,28(10):114-117
[7] 杨广林,孔令富．基于图像分块的背景模型构建方法[J]．机器人,2007,29(1):29-34
[8] 姚春莲,周兵．运动对象检测及其在视频压缩与处理中的应用[M]．北京:冶金工业出版社,2010
[9] 李庆武,王敏,陈琦,等．基于图像分块和Hausdorff距离的背景更新方法[J]．测试技术学报,2011,25(6):544-547
[10] Jodoin J P,Bilodeau G A,Saunier N．Background subtraction based on local shape [J]．arXiv preprint arXiv:1204.6326,2012
[11] Wang Zhou,Bovik A C,Sheikh H R,et al．Image quality assessment:From error visibility to structural similarity [J]．IEEE Transactions on Image Processing,2004,13(4):600-612
[12] Wang Zhou,Bovik A C,Simoncelli．Structural approaches to image quality assessment[J]．Handbook of Image and Video Processing,2005,7:18
[13] Loza A,Mihaylova L,Canagarajah N,et al.Structural Similarity-Based Object Tracking in Video Sequences[C]∥20069th International Conference on Information Fusion．IEEE,2006:1-6
[14] oza A,Mihaylova L,Bull D,et al.Structural Similarity-Based Object Tracking in Multimodality Surveillance Videos [J]．Machine Vision and Applications,2009,20(2):71-83
[15] PETS 2006benchmark data．http://www.pets2006.net,2006

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed