Skyline Detection Method Based on Offset Heatmap Network

Skyline detection plays a crucial role in fields such as reconnaissance and photoelectric guidance. This paper presents a deep learning-based skyline detection method utilizing heatmaps as the output of the skyline neural network. To address the downsampling issue prevalent in heatmap-based methods, we propose the use of offset compensation heatmaps to restore the downsampled points. Additionally, we enhance the YOLO network to improve the resolution of the output heatmaps. Experimental results demonstrate that our method is highly adaptable to complex scenes and performs at inference speeds suitable for edge deployment.