Unsupervised Online Video Object Segmentation with Motion Property Understanding

TL;DR

This paper introduces a novel unsupervised online video object segmentation framework that leverages motion properties, salient motion detection, and object proposals to improve accuracy and outperform existing methods.

Contribution

The paper proposes a new unsupervised online segmentation method using motion properties, pixel-wise fusion, and forward propagation to enhance segmentation accuracy.

Findings

Achieves 6.2% absolute gain over state-of-the-art online methods

Outperforms the best offline unsupervised algorithm on DAVIS-2016

Effective in removing dynamic background and stationary objects

Abstract

Unsupervised video object segmentation aims to automatically segment moving objects over an unconstrained video without any user annotation. So far, only few unsupervised online methods have been reported in literature and their performance is still far from satisfactory, because the complementary information from future frames cannot be processed under online setting. To solve this challenging problem, in this paper, we propose a novel Unsupervised Online Video Object Segmentation (UOVOS) framework by construing the motion property to mean moving in concurrence with a generic object for segmented regions. By incorporating salient motion detection and object proposal, a pixel-wise fusion strategy is developed to effectively remove detection noise such as dynamic background and stationary objects. Furthermore, by leveraging the obtained segmentation from immediately preceding frames, a forward propagation algorithm is employed to deal with unreliable motion detection and object proposals. Experimental results on several benchmark datasets demonstrate the efficacy of the proposed method. Compared to the state-of-the-art unsupervised online segmentation algorithms, the proposed method achieves an absolute gain of 6.2%. Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset. Our code is available on the project website: https://github.com/visiontao/uovos.