MS-AFF: a novel semantic segmentation approach for buried object based on multi-scale attentional feature fusion

Infrared technology is widely used in buried object detection since it can capture the heat radiated outward from target objects. Compared to visible images, infrared images present poor resolution, low contrast, and fuzzy visual effect, making challenging detect objects, specifically complex backgrounds. In recent years, deep learning-based methods have made significant improvements tasks. However, of objects are difficult obtain. Less training samples, worse performance deep-learning based detection. We raise a multi-scale attentional feature fusion module for image semantic segmentation solve this problem. Precisely, we integrate series maps different levels by an atrous spatial pyramid structure. way, model obtain rich representation ability on images. Besides, global information attention employed let focus region reduce disturbance images’ background. addition, propose dataset thermal imaging system. Finally, use state-of-the-art train compare them with our proposed method. Extensive experiments demonstrate superiority