IRST-CGSeg: Infrared Small Target Detection Based on Clustering-Guided Graph Learning and Hierarchical Features

Infrared small target detection (IRSTD) aims to segment small targets from an infrared clutter background. However, the long imaging distance, complex background, and extremely limited number of target pixels pose great challenges for IRSTD. In this paper, we propose a new IRSTD method based on the deep graph neural network to fully extract and fuse the texture and structural information of images. Firstly, a clustering algorithm is designed to divide the image into several subgraphs as a prior knowledge to guide the initialization of the graph structure of the infrared image, and the image texture features are integrated to graph construction. Then, a graph feature extraction module is designed, which guides nodes to interact with features within their subgraph via the adjacency matrix. Finally, a hierarchical graph texture feature fusion module is designed to concatenate and stack the structure and texture information at different levels to realize IRSTD. Extensive experiments have been conducted, and the experimental results demonstrate that the proposed method has high interaction over union (IoU) and probability of detection (Pd) on public datasets and the self-constructed dataset, indicating that it has fine shape segmentation and accurate positioning for infrared small targets.