Paper Info
Title
Terrain segmentation of high resolution satellite images using multi-class AdaBoost algorithm
Abstract
Terrain segmentation is still a challenging issue in pattern recognition, especially in the application of high resolution satellite images. Among the various segmentation approaches are those based on graph partitioning, which present some drawbacks such as high processing time, low accuracy on detection of targets on the large scaled images such as high resolution satellite images. In this paper, we focus on the computational intelligence approach to classify and detect building, foliage, grass, bare-ground, and road of land cover. We propose a method, which has a high accuracy on classification and object detection by using multi-class AdaBoost algorithm based on a combination of two extracted features, which are cooccurrence and Haar-like features. With all features, multi-class Adaboost selects only critical features and performs as an extremely efficient classifier. Experimental results show that the classification accuracy is over 91% with a high resolution satellite image.
Year
DOI
Venue
2014
10.1109/ICNC.2014.6975970
ICNC
Keywords
DocType
ISSN
high resolution satellite image terrain segmentation,building classification,remote sensing,foliage detection,pattern recognition,Haar-like features,computational intelligence approach,learning (artificial intelligence),image resolution,image segmentation,segmentation,grass detection,land cover road detection,land cover road classification,building detection,feature extraction,image classification,geophysical image processing,target detection,object detection,satellite image,grass classification,multiclass AdaBoost algorithm,graph theory,classification,Haar transforms,graph partitioning,Terrain,bare-ground classification,bare-ground detection
Conference
2469-8814
Citations 
PageRank 
References 
0
0.34
0
Authors
4
Name
Order
Citations
PageRank
Ngoc-hoa Nguyen162.43
Dong-min Woo25416.85
Seungwoo Kim301.35
Minkee Park437525.10