Video Salient Object Detection Using Spatiotemporal Deep Features

TL;DR

This paper introduces a novel spatiotemporal deep feature-based method for video salient object detection, utilizing a new STCRF model to achieve temporally consistent and accurate saliency maps, outperforming existing methods.

Contribution

It proposes a new set of STD features and an extended CRF model (STCRF) for improved video saliency detection with temporal consistency.

Findings

Outperforms state-of-the-art video saliency detection methods

Achieves more accurate and temporally consistent saliency maps

Improves video object segmentation results

Abstract

This paper presents a method for detecting salient objects in videos where temporal information in addition to spatial information is fully taken into account. Following recent reports on the advantage of deep features over conventional hand-crafted features, we propose a new set of SpatioTemporal Deep (STD) features that utilize local and global contexts over frames. We also propose new SpatioTemporal Conditional Random Field (STCRF) to compute saliency from STD features. STCRF is our extension of CRF to the temporal domain and describes the relationships among neighboring regions both in a frame and over frames. STCRF leads to temporally consistent saliency maps over frames, contributing to the accurate detection of salient objects' boundaries and noise reduction during detection. Our proposed method first segments an input video into multiple scales and then computes a saliency map at each scale level using STD features with STCRF. The final saliency map is computed by fusing saliency maps at different scale levels. Our experiments, using publicly available benchmark datasets, confirm that the proposed method significantly outperforms state-of-the-art methods. We also applied our saliency computation to the video object segmentation task, showing that our method outperforms existing video object segmentation methods.