Sea-skyline extraction is an important research subject in the development of infrared search-and-rescue equipment for offshore target detection and tracking. This study investigates sea-sky background target-extraction technology and develops a practical sea–skyline extraction algorithm. First, this work uses spatial filtering to eliminate the interference of a small-vessel target and near-domain sea clutter; it then performs a morphological gradient operation, obtains the edge contour of the sea–skyline using the Ostu threshold-segmentation method, obtains a point group using the Hough transform, and extracts the sea-skyline using the least square method. The experimental results show that the algorithm can accurately and quickly extract the sea-skyline. This study provides a foundation for the rapid detection and tracking of offshore targets.