Title :
Region Growing Tree Delineation in Urban Settlements
Author :
Theng, Lau Bee ; Ling, Choo Ai
Author_Institution :
Sch. of Comput. & Design, Swinburne Univ. of Technol., Kuching, Malaysia
Abstract :
Region growing has been widely used in image segmentation applications. Iovan et al. (2007) has used region growing technique to delineate trees in urban settlements with Quickbird imagery. However, there is a room for improvement in the extraction accuracy. This study attempts to improve the tree crown detections from high resolution satellite imagery with wavelet transform and region growing. We shall discuss how the biorthogonal wavelet transform is utilized in the segmentation first, and then follow by the grass/tree segmentation by region growing. It is proven that accuracy is higher when wavelets are integrated into the segmentation and extraction procedures.
Keywords :
geophysical signal processing; image resolution; image segmentation; object detection; vegetation mapping; wavelet transforms; Quickbird imagery; biorthogonal wavelet transform; grass segmentation; high resolution satellite imagery; image segmentation application; region growing tree delineation; tree crown detection; tree segmentation; urban settlement; wavelet transform; Buildings; Frequency; Image segmentation; Image texture analysis; Object detection; Roads; Satellites; Spatial resolution; Wavelet analysis; Wavelet transforms; Biorthogonal wavelets; Quickbird; satellite imaginary; seed point initialization;
Conference_Titel :
Advanced Computer Theory and Engineering, 2008. ICACTE '08. International Conference on
Conference_Location :
Phuket
Print_ISBN :
978-0-7695-3489-3
DOI :
10.1109/ICACTE.2008.140