Edge-guided feature fusion network for RGB-T salient object detection
Authors:
Open Access
- 17 December 2024
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 18, 1489658
Abstract
Introduction: RGB-T Salient Object Detection (SOD) aims to accurately segment salient regions in both visible light and thermal infrared images. However, many existing methods overlook the critical complementarity between these modalities, which can enhance detection accuracy.Methods: We propose the Edge-Guided Feature Fusion Network (EGFF-Net), which consists of cross-modal feature extraction, edge-guided feature fusion, and salience map prediction. Firstly, the cross-modal feature extraction module captures and aggregates united and intersecting information in each local region of RGB and thermal images. Then, the edge-guided feature fusion module enhances the edge features of salient regions, considering that edge information is very helpful in refining significant area details. Moreover, a layer-by-layer decoding structure integrates multi-level features and generates the prediction of salience maps.Results: We conduct extensive experiments on three benchmark datasets and compare EGFF-Net with state-of-the-art methods. Our approach achieves superior performance, demonstrating the effectiveness of the proposed modules in improving both detection accuracy and boundary refinement.Discussion: The results highlight the importance of integrating cross-modal information and edge-guided fusion in RGB-T SOD. Our method outperforms existing techniques and provides a robust framework for future developments in multi-modal saliency detection.Keywords
This publication has 21 references indexed in Scilit:
- RGB-T Salient Object Detection Based on the Segment Anything Model2024
- SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2021
- RGB-T Saliency Detection via Low-Rank Tensor Learning and Unified Collaborative RankingIEEE Signal Processing Letters, 2020
- RGBT Salient Object Detection: Benchmark and A Novel Cooperative Ranking ApproachIEEE Transactions on Circuits and Systems for Video Technology, 2019
- Constrained fixation point based segmentation via deep neural networkNeurocomputing, 2019
- Video Saliency Detection via Sparsity-Based Reconstruction and PropagationIEEE Transactions on Image Processing, 2019
- General fusion method for infrared and visual images via latent low-rank representation and local non-subsampled shearlet transformInfrared Physics & Technology, 2018
- A novel remote-sensing image fusion method based on hybrid visual saliency analysisInternational Journal of Remote Sensing, 2018
- Saliency filters: Contrast based filtering for salient region detection2012
- Frequency-tuned salient region detection2009