Hierarchical improvement of foreground segmentation masks in background subtraction
EntityUAM. Departamento de Tecnología Electrónica y de las Comunicaciones
10.1109/TCSVT.2018.2851440IEEE Transactions on Circuits and Systems for Video Technology 29.6 (2019): 1645 - 1658
Funded byThis work was partially supported by the Spanish Government (HAVideo, TEC2014-53176-R)
ProjectGobierno de España. TEC2014-53176-R
SubjectsForeground segmentation improvement; Background subtraction; Foreground quality; Post-processing; Telecomunicaciones
Note© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Rights© 2018 IEEE
A plethora of algorithms have been defined for foreground segmentation, a fundamental stage for many computer vision applications. In this work, we propose a post-processing framework to improve foreground segmentation performance of background subtraction algorithms. We define a hierarchical framework for extending segmented foreground pixels to undetected foreground object areas and for removing erroneously segmented foreground. Firstly, we create a motion-aware hierarchical image segmentation of each frame that prevents merging foreground and background image regions. Then, we estimate the quality of the foreground mask through the fitness of the binary regions in the mask and the hierarchy of segmented regions. Finally, the improved foreground mask is obtained as an optimal labeling by jointly exploiting foreground quality and spatial color relations in a pixel-wise fully-connected Conditional Random Field. Experiments are conducted over four large and heterogeneous datasets with varied challenges (CDNET2014, LASIESTA, SABS and BMC) demonstrating the capability of the proposed framework to improve background subtraction results
This item appears in the following Collection(s)
Showing items related by title, author, creator and subject.