Segmenting and tracking multiple objects under occlusion using multi-label graph cut | |
Mingjun Wu; Xianrong Peng; Qiheng Zhang; Rujin Zhao | |
Source Publication | Computers and Electrical Engineering
![]() |
Volume | 36Issue:5Pages:927-934 |
2010 | |
Language | 英语 |
Subtype | 期刊论文 |
Abstract | This paper proposes a new method to segment and track multiple objects through occlusion by integrating spatial-color Gaussian mixture model (SCGMM) into an energy minimization framework. When occlusion does not occur, a SCGMM is learned for each object. When the objects are subject to occlusion, energy minimization is used to segment the objects from occlusion. To make the learned SCGMMs suitable for the segmentation of the current occlusion, a displacing procedure is utilized to adapt the SCGMMs to the spatial variations. A multi-label energy function is formulated building on the displaced SCGMMs and then minimized using the multi-label graph cut algorithm, thus leading to both the segmentation and tracking results of the objects with occlusion. Experimental validation of the proposed method is performed and presented on several video sequences. [All rights reserved Elsevier].; This paper proposes a new method to segment and track multiple objects through occlusion by integrating spatial-color Gaussian mixture model (SCGMM) into an energy minimization framework. When occlusion does not occur, a SCGMM is learned for each object. When the objects are subject to occlusion, energy minimization is used to segment the objects from occlusion. To make the learned SCGMMs suitable for the segmentation of the current occlusion, a displacing procedure is utilized to adapt the SCGMMs to the spatial variations. A multi-label energy function is formulated building on the displaced SCGMMs and then minimized using the multi-label graph cut algorithm, thus leading to both the segmentation and tracking results of the objects with occlusion. Experimental validation of the proposed method is performed and presented on several video sequences. [All rights reserved Elsevier]. |
Document Type | 期刊论文 |
Identifier | http://ir.ioe.ac.cn/handle/181551/5016 |
Collection | 光电探测与信号处理研究室(五室) |
Corresponding Author | Mingjun Wu |
Affiliation | 中国科学院光电技术研究所 |
Recommended Citation GB/T 7714 | Mingjun Wu,Xianrong Peng,Qiheng Zhang,et al. Segmenting and tracking multiple objects under occlusion using multi-label graph cut[J]. Computers and Electrical Engineering,2010,36(5):927-934. |
APA | Mingjun Wu,Xianrong Peng,Qiheng Zhang,&Rujin Zhao.(2010).Segmenting and tracking multiple objects under occlusion using multi-label graph cut.Computers and Electrical Engineering,36(5),927-934. |
MLA | Mingjun Wu,et al."Segmenting and tracking multiple objects under occlusion using multi-label graph cut".Computers and Electrical Engineering 36.5(2010):927-934. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment