CHFNet: Curvature Half-Level Fusion Network for Single-Frame Infrared Small Target Detection

Single-frame infrared small target detection (IRSTD) aims to extract targets from background clutter and distinguish them noise. In recent years, semantic segmentation deep learning methods such as CNNs have made many breakthroughs in the field of IRSTD. However, there are limitations this method; for example, tend be too dim, heavy exists. To further improve accuracy IRSTD, we propose a novel curvature half-level fusion network (CHFNet) First, developed (HLF) block new cross-layer feature module. With HLF block, excavates features between two levels features, thus ensuring that each has minimal distortion. Given even dim certain calculated weighted mean image obtain attention boundary, then fused it with level detect edges targets. comparison, prediction results proposed CHFNet on NUAA-SIRST dataset were more complete better preserved edge