Skyline Extraction Using A Multistage Edge Filtering

Byung-Ju Kim, Jong-Jin Shin, Hwa-Jin Nam, Jin-Soo Kim
2011 Zenodo  
Skyline extraction in mountainous images can be used for navigation of vehicles or UAV(unmanned air vehicles), but it is very hard to extract skyline shape because of clutters like clouds, sea lines and field borders in images. We developed the edge-based skyline extraction algorithm using a proposed multistage edge filtering (MEF) technique. In this method, characteristics of clutters in the image are first defined and then the lines classified as clutters are eliminated by stages using the
more » ... posed MEF technique. After this processing, we select the last line using skyline measures among the remained lines. This proposed algorithm is robust under severe environments with clutters and has even good performance for infrared sensor images with a low resolution. We tested this proposed algorithm for images obtained in the field by an infrared camera and confirmed that the proposed algorithm produced a better performance and faster processing time than conventional algorithms.
doi:10.5281/zenodo.1075237 fatcat:53aopojzuratpcejisfz44fzna