基于场景知识的移动目标检测

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 275-278.

基于场景知识的移动目标检测

史东承, 闫李

长春工业大学计算机科学与工程学院, 长春 130012

收稿日期:2012-06-26 发布日期:2013-06-01
通讯作者: 通讯作者:闫李(1987-),男,硕士研究生.研究方向:图像处理与机器视觉.E-mail:yanlileeyan@sina.com E-mail:yanlileeyan@sina.com
作者简介:史东承(1959-),男,教授.研究方向:图像处理与机器视觉,多媒体信息处理与通信技术.E-mail:dcshi@mail.ccut.edu.cn

Moving object detection based on scene knowledge

SHI Dong-cheng, YAN Li

College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China

Received:2012-06-26 Published:2013-06-01

摘要/Abstract

摘要：

依据背景差法中背景建模的思想,从提取场景知识的角度出发,建立待检测场景的场景知识库,从而提出一种基于场景知识的移动目标检测算法。使用改进的均值漂移算法对待检测场景进行分割,并提取分割后各个区域的底层视觉特征建立场景知识库;从新的场景帧图像中获取各区域的知识特征向量,然后根据和原场景知识库中各特征向量的匹配结果检测出移动目标信息。仿真结果表明,该方法能有效地检测出场景中原有目标和新进入场景目标的移动信息,并在一定程度上改善了目标阴影、形变等噪声对检测结果的干扰。

关键词: 移动目标检测, 场景知识提取, 特征描述, mean shift算法

Abstract:

According to the background modeling thought in background subtraction algorithm and developed from the point of view of extracting scene knowledge to establish the scene knowledge base,an algorithm of moving object detection based on scene knowledge was proposed.In this algorithm,the features of each segmented regions were extracted to build a scene knowledge base after we used an improved mean-shift method to segment the scene image;The feature vectors from the new frame image were extracted,and the information of the moving objects were detected by matching the new feature vectors with the pre-existing feature vectors we can get from the scene knowledge base.The simulation result shows that the proposed method can detect the moving information of original object and new object in the scene effectively and is robust to the noise of shadow and the deformation of the object.

Key words: moving object detection, scene knowledge extraction, feature description, mean shift algorithm

中图分类号:

TP391

史东承, 闫李. 基于场景知识的移动目标检测[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 275-278.

SHI Dong-cheng, YAN Li. Moving object detection based on scene knowledge[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 275-278.

参考文献

[1] Stauffer C,Grimson W.Adaptive background mixture models for real-time tracking[J].Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999,2(6):248-252.

[2] Elgammal A,Harwood D,Davis L.Non-parametric model for background subtraction [C]//Proceedings of International Conference on Computer Vision.1999:751-767.

[3] Rittscher J,Kato J,Joga S.A probabilistic background model for tracking[C]//Proceedings of European Conference on Computer Vision.2000:336-350.

[4] Luo Jie-bo,Guo Chen-gen.Perceptual grouping of segmented regions in color images[J].Pattern Recognition,2003,36(12):2781-2792.

[5] Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.

[6] 叶齐祥,高文,王伟强.一种融合颜色和空间信息的彩色图像分割算法[J].软件学报,2004,15(4):522-530.Ye Qi-xiang,Gao Wen,Wang Wei-qiang.A fusion of color and spatial information for color image segmentation algorithm[J].Journal of Software,2004,15(4):522-530.

[7] Sticker M,Orengo M.Similarity of color image[C]//Proceedings of SPIE Storage and Retrieval for Image and Video Database.1995:381-392.

[8] Manjunath B S,Ma W Y.Texture features for browsing and retrieval of image data[J].IEEE Transactions on Pattern Analysis Machine Intelligence,1996,18(8):837-842.

[9] Hu M K.Visual pattern recognition by moment invariant[J].IEEE Transactions on Information Theory,1962,8(2):179-187.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed