Abstract | ||
---|---|---|
This paper presents a new approach to multiscale segmentation of satellite multispectral imagery using edge information. The Canny edge detector is applied to perform multispectral edge detection. The detected edge features are then utilized in a multiscale segmentation loop, and the merge procedure for adjacent image objects is controlled by a separability criterion that combines edge information with segmentation scale. The significance of the edge is measured by adjacent partitioned regions to perform edge assessment. The present method is based on a half-partition structure, which is composed of three steps: single edge detection, separated pixel grouping, and significant feature calculation. The spectral distance of the half-partitions separated by the edge is calculated, compared, and integrated into the edge information. The results show that the proposed approach works well on satellite multispectral images of a coastal area. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/TGRS.2012.2194502 | IEEE T. Geoscience and Remote Sensing |
Keywords | Field | DocType |
geophysical techniques,scale selection,adjacent image objects,canny edge detector,object-based image analysis,image segmentation,satellite multispectral imagery,edge-guided multiscale segmentation,multispectral edge detection,segmentation scale,geophysical image processing,pixel grouping,edge detection,edge information,multiscale segmentation loop,multiscale segmentation | Canny edge detector,Image gradient,Scale-space segmentation,Edge detection,Remote sensing,Image segmentation,Multispectral pattern recognition,Artificial intelligence,Computer vision,Pattern recognition,Range segmentation,Morphological gradient,Mathematics | Journal |
Volume | Issue | ISSN |
50 | 11 | 0196-2892 |
Citations | PageRank | References |
8 | 0.54 | 16 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianyu Chen | 1 | 17 | 6.41 |
Jonathan Li | 2 | 798 | 119.18 |
Delu Pan | 3 | 24 | 11.67 |
Qiankun Zhu | 4 | 14 | 5.01 |
Zhihua Mao | 5 | 14 | 9.52 |