WGI-Net: A weighted group integration network for RGB-D salient object detection
Open Access
- 8 January 2021
- journal article
- research article
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 7 (1) , 115-125
Abstract
Salient object detection is used as a pre-process in many computer vision tasks (such as salient object segmentation, video salient object detection, etc.). When performing salient object detection, depth information can provide clues to the location of target objects, so effective fusion of RGB and depth feature information is important. In this paper, we propose a new feature information aggregation approach, weighted group integration (WGI), to effectively integrate RGB and depth feature information. We use a dual-branch structure to slice the input RGB image and depth map separately and then merge the results separately by concatenation. As grouped features may lose global information about the target object, we also make use of the idea of residual learning, taking the features captured by the original fusion method as supplementary information to ensure both accuracy and completeness of the fused information. Experiments on five datasets show that our model performs better than typical existing approaches for four evaluation metrics.Keywords
This publication has 47 references indexed in Scilit:
- Image Co-segmentation via Saliency Co-fusionIEEE Transactions on Multimedia, 2016
- Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues FusionIEEE Signal Processing Letters, 2016
- Depth saliency based on anisotropic center-surround difference2014
- Salient region detection for stereoscopic images2014
- Depth Enhanced Saliency Detection Method2014
- Cluster-Based Co-Saliency DetectionIEEE Transactions on Image Processing, 2013
- Adaptive object tracking by learning background context2012
- 3-D Object Retrieval and Recognition With Hypergraph AnalysisIEEE Transactions on Image Processing, 2012
- Salient Object Detection: A Benchmark2012
- Frequency-tuned salient region detection2009