Nonlinear regression of saliency guided proposals for unsupervised segmentation of dynamic scenes

Yinhui Zhang, Mohamed Abdel-Mottaleb, Zifen He

Research output: Contribution to journalArticle

Abstract

This paper proposes an efficient video object segmentation approach that is tolerant to complex scene dynamics. Unlike existing approaches that rely on estimating object-like proposals on an intra-frame basis, the proposed approach employs temporally consistent foreground hypothesis using nonlinear regression of saliency guided proposals across a video sequence. For this purpose, we first generate salient foreground proposals at superpixel level by leveraging a saliency signature in the discrete cosine transform domain. We propose to use a random forest based nonlinear regression scheme to learn both appearance and shape features from salient foreground regions in all frames of a sequence. Availability of such features can help rank every foreground proposals of a sequence, and we show that the regions with high ranking scores are well correlated with semantic foreground objects in dynamic scenes. Subsequently, we utilize a Markov Random Field to integrate both appearance and motion coherence of the top-ranked object proposals. A temporal nonlinear regressor for generating salient object support regions significantly improves the segmentation performance compared to using only per-frame objectness cues. Extensive experiments on challenging real-world video sequences are performed to validate the feasibility and superiority of the proposed approach for addressing dynamic scene segmentation.

Original languageEnglish (US)
Pages (from-to)467-474
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE99D
Issue number2
DOIs
StatePublished - Feb 1 2016

Keywords

  • Dynamic scene
  • Nonlinear regressor
  • Random forest
  • Salient object-like proposal
  • Video object segmentation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Nonlinear regression of saliency guided proposals for unsupervised segmentation of dynamic scenes'. Together they form a unique fingerprint.

  • Cite this