RGB-D Salient Object Detection Method Based on Multi-Modal Fusion and Contour Guidance

Abstract

Salient object detection is a critical task in the field of computer vision. However, existing detection methods still face certain challenges, such as the inability to effectively integrate multimodal features and the blurring of detection result boundaries. To address these issues, this paper proposes a novel RGB-D salient object detection method that combines multimodal feature fusion and contour-guiding techniques. Initially, we employ ResNet50 as the backbone network, and by removing its final pooling layer and fully connected layer, we construct a fully convolutional network specifically for feature extraction from RGB images and depth images. Subsequently, we leverage channel attention mechanism and spatial attention mechanism separately to optimize the RGB image features and depth image features. Following this, we design an interactive feature fusion module to blend the optimized features, thereby obtaining the multimodal fusion features. Furthermore, based on the localization ability of high-level fusion features, we constrain the low-level fusion features, eliminate non-salient objects, and generate salient object contour features. Eventually, we use this contour feature to guide the recognition process of salient objects, resulting in salient objects with clear boundaries. Our approach has been validated across seven RGB-D salient object detection datasets. The experimental results indicate an improvement of 0.21% ~ 1.84% and 0.32% ~ 1.25% respectively in maxF and S metrics, compared to the best competing methods (CMINet, CIR-Net, and CPFP).

Keywords

• RGB-D salient object detection
• multimodal feature fusion
• contour guidance
• attention mechanism
• fully convolutional network