Multiscale tree analysis from satellite images

作者: Abdullah H. Ozcan , Yetkin Sayar , Dilara Hisar , Cem Unsalan

DOI: 10.1109/RAST.2015.7208353

关键词: Boundary (topology)PixelRemote sensingImage resolutionMinimum spanning tree-based segmentationTree (data structure)Computer scienceScale-space segmentationSatelliteImage segmentation

摘要: As satellite images cover wide areas and obtaining them has become easier, using these in agriculture an important research area. Especially, can be used seasonal crop estimation. In this study, we focused on estimation from trees. The boundary of a tree is proportional to its age which gives information the approximate that obtained it. Obtaining number trees region, with size each tree, amount harvested region. propose method based multiple filtering, watershed segmentation, Otsu thresholding detect their boundaries. To test proposed method, picked three containing 6928 These have diameters between 2 30 pixels. We compared two other methods literature. summarized results study.

参考文章(1)
John Secord, Avideh Zakhor, Tree Detection in Urban Regions Using Aerial Lidar and Image Data IEEE Geoscience and Remote Sensing Letters. ,vol. 4, pp. 196- 200 ,(2007) , 10.1109/LGRS.2006.888107