基于场景感知的运动目标检测方法

doi:10.3969/j.issn.0372-2112.2016.11.009

PDF(3878 KB)

电子学报 ›› 2016, Vol. 44 ›› Issue (11) : 2625-2632. DOI: 10.3969/j.issn.0372-2112.2016.11.009

学术论文

基于场景感知的运动目标检测方法

宋涛¹, 李鸥¹, 崔弘亮²

作者信息 +

A Moving Object Detection Method Based on Scene Perception

SONG Tao¹, LI Ou¹, CUI Hong-liang²

Author information +

文章历史 +

摘要

背景减除法是一种主要的运动目标检测框架，但在复杂环境中构建一种初始模型建立周期短、可靠性高、鲁棒性好的模型仍是一大难题.本文从场景感知的角度出发，在背景减除框架的基础上提出一种目标检测方法.该方法根据前两帧中稳定的结构信息感知背景中潜在的前景区域，在第二帧建立初始模型时利用最近邻域背景像素点代替可能的前景像素点，提高了初始模型可靠性；结合颜色信息和二进制特征提出了像素点二级分类判决机制，并通过感知像素点邻域内的纹理复杂度自适应调整局部判决阈值和更新频率；在模型更新阶段提出处理误判的反馈机制.在公开视频序列上同几种流行检测算法的实验对比结果证明了本文算法的有效性和优越性.

Abstract

Background subtraction algorithm is a kind of main moving object detection framework,but it is too difficult to build a model with short establishing period,high reliability and good robustness.From the perspective of scene perception,a technique for object detection based on the framework of background subtraction is proposed.To improve the reliability of initial model,the potential foreground pixels in background,which are obtained on the basis of stable structural information in the former two frames,are replaced by the nearest neighbor pixels belonging to background,when the initial model is being established in the second frame.Integrating color information with binary feature,a two-stage classification decision mechanism is proposed,meanwhile the local decision threshold and update frequency are adaptively adjusted in accordance with the texture complexity of pixels neighborhood.Subsequently,a feedback mechanism for misclassification is presented in the update model phase.Experimental results using challenging public video sequences show the effectiveness and superiority of the proposed method,compared with other state-of-the-art tracking approaches.

导出引用

宋涛, 李鸥, 崔弘亮. 基于场景感知的运动目标检测方法[J]. 电子学报, 2016, 44(11): 2625-2632. https://doi.org/10.3969/j.issn.0372-2112.2016.11.009

SONG Tao, LI Ou, CUI Hong-liang. A Moving Object Detection Method Based on Scene Perception[J]. Acta Electronica Sinica, 2016, 44(11): 2625-2632. https://doi.org/10.3969/j.issn.0372-2112.2016.11.009

中图分类号： TP319

参考文献

[1] Radke R J,Andra S,Al-Kofahi O.Image change detection algorithms:a systematic survey[J].IEEE Transactions on Image Processing,2005,14(3):294-307.
[2] Wang B,Dudek P.A fast self-tuning background subtraction algorithm[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops[C].Columbus OH:IEEE Press,2014.401-404.
[3] Van Droogenbroeck M,Barnich O.ViBe:a disruptive method for background subtraction[A].Proceedings of the Background Modeling and Foreground Detection for Video Surveillance[C].USA:CRC Press,2014.1-23.
[4] Stauffer C,Grimson W.Adaptive background mixture models for real-time tracking[A].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].Fort Collins:IEEE Press,1999.246-252.
[5] Martins P,Caseiro R,Batista J.Non-parametric Bayesian constrained local models[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Columbus OH:IEEE Press,2014.1797-1804.
[6] Chen S Y,Zhang J H,Li Y F.A hierarchical model incorporating segmented regions and pixel descriptors for video background subtraction[J].IEEE Transactions on Industrial Informatics,2012,8(1):118-127.
[7] Jodoin P,Mignotte M,Konrad J.Statistical background subtraction using spatial cues[J].IEEE Transactions on Circuits and Systems for Video Technology,2007,17(12):1758-1763.
[8] St-Charles P,Bilodeau G,Bergevin R.SuBSENSE:a universal change detection method with local adaptive sensitivity[J].IEEE Transactions on Image Processing,2015,24(1):359-373.
[9] Cuevas C,Mohedano R,Garcia N.VersatileBayesian classifier for moving object detection by non-parametric background-foreground modeling[A].Proceedings of the 19^th IEEE International Conference on Image Processing[C].Orlando FL:IEEE Press,2012.313-316.
[10] Van Droogenbroeck M,Paquot O.Background subtraction:experiments and improvements for ViBe[A].Proceedings of the IEEE Computer Vision and Pattern Recognition Workshops[C].Providence RI:IEEE Press,2012.32-37.
[11] Wu J,Rehg J M.CENTRIST:a visual descriptor for scene categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1489-1501.
[12] St-Charles P L,Bilodeau G A.Improving background subtraction using local binary similarity patterns[A].Proceedings of the IEEE Winter Conference on Applications of Computer Vision[C].Steamboat Springs CO:IEEE Press,2014.509-515.
[13] Wang Y,Jodoin P M,Porikli F.CDnet 2014:an expanded change detection benchmark dataset[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops[C].Columbus OH:IEEE Press,2014.393-400.