Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing

TL;DR

This paper introduces EGFNet, an advanced neural network for RGB thermal scene parsing that enhances boundary detection and feature fusion by incorporating edge guidance, semantic modules, and deep supervision, leading to superior accuracy.

Contribution

The paper proposes a novel edge-aware guidance fusion network with a multimodal fusion module and semantic modules, improving boundary extraction and feature integration in RGB thermal scene parsing.

Findings

EGFNet outperforms state-of-the-art methods on benchmark datasets.

Incorporating edge guidance improves boundary accuracy.

Multimodal fusion and semantic modules enhance feature richness.

Abstract

RGB thermal scene parsing has recently attracted increasing research interest in the field of computer vision. However, most existing methods fail to perform good boundary extraction for prediction maps and cannot fully use high level features. In addition, these methods simply fuse the features from RGB and thermal modalities but are unable to obtain comprehensive fused features. To address these problems, we propose an edge-aware guidance fusion network (EGFNet) for RGB thermal scene parsing. First, we introduce a prior edge map generated using the RGB and thermal images to capture detailed information in the prediction map and then embed the prior edge information in the feature maps. To effectively fuse the RGB and thermal information, we propose a multimodal fusion module that guarantees adequate cross-modal fusion. Considering the importance of high level semantic information, we propose a global information module and a semantic information module to extract rich semantic information from the high-level features. For decoding, we use simple elementwise addition for cascaded feature fusion. Finally, to improve the parsing accuracy, we apply multitask deep supervision to the semantic and boundary maps. Extensive experiments were performed on benchmark datasets to demonstrate the effectiveness of the proposed EGFNet and its superior performance compared with state of the art methods. The code and results can be found at https://github.com/ShaohuaDong2021/EGFNet.