Rough Waypoint Extraction Algorithm Based on Mean Shift Clustering Saliency Analysis
Yuzhu Chen, Qingzhong Jia, Yong Jun Zhao · 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 2020
This paper studies the problem of rough extraction of salient waypoints for UAV scene matching navigation, and a saliency analysis algorithm based on mean shift clustering is researched. The input image is preprocessed by color space conversion and Gaussian low-pass filtering. Mean-shift clustering is used to divide the image into sub-regions as the basic unit for candidate waypoint extraction. The Euclidean distance between the pixel color value and the average color value of the full image is used to represent the saliency. The sub-regions with high saliency value in the image are extracted as candidate waypoints.