ISPRS-Annals ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS-Annals ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci. 2194-9050 Copernicus Publications Göttingen, Germany 10.5194/isprs-annals-III-7-111-2016 A MINIMUM SPANNING TREE BASED METHOD FOR UAV IMAGE SEGMENTATION Wang Ping 1 Wei Zheng 1 Cui Weihong 2 Lin Zhiyong 2 South China Sea Institute of Planning and Environment Research, SOA, Guangzhou, China School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China 07 06 2016 III-7 111 117 This article is available from https://isprs-annals.copernicus.org/articles/isprs-annals-III-7-111-2016.html The full text article is available as a PDF file from https://isprs-annals.copernicus.org/articles/isprs-annals-III-7-111-2016.pdf

This paper proposes a Minimum Span Tree (MST) based image segmentation method for UAV images in coastal area. An edge weight based optimal criterion (merging predicate) is defined, which based on statistical learning theory (SLT). And we used a scale control parameter to control the segmentation scale. Experiments based on the high resolution UAV images in coastal area show that the proposed merging predicate can keep the integrity of the objects and prevent results from over segmentation. The segmentation results proves its efficiency in segmenting the rich texture images with good boundary of objects.