Application of Multi-Class AdaBoost Algorithm to Terrain Classification of Satellite Images
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Terrain classification is still a challenging issue in image processing, especially with high resolution satellite images. The well-known obstacles include low accuracy in the detection of targets, especially for the case of man-made structures, such as buildings and roads. In this paper, we present an efficient approach to classify and detect building footprints, foliage, grass and road from high resolution grayscale satellite images. Our contribution is to build a strong classifier using AdaBoost based on a combination of co-occurrence and Haar-like features. We expect that the inclusion of Harr-like feature improves the classification performance of the man-made structures, since Haar-like feature is extracted from corner features and rectangle features. Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier. Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm. Also, the inclusion of Harr-like feature significantly improves the classification accuracy. The accuracy of the proposed method is 98.4% for the target detection and 92.8% for the classification on high resolution satellite images.
Abstract
Terrain classification is still a challenging issue in image processing, especially with high resolution satellite images. The well-known obstacles include low accuracy in the detection of targets, especially for the case of man-made structures, such as buildings and roads. In this paper, we present an efficient approach to classify and detect building footprints, foliage, grass and road from high resolution grayscale satellite images. Our contribution is to build a strong classifier using AdaBoost based on a combination of co-occurrence and Haar-like features. We expect that the inclusion of Harr-like feature improves the classification performance of the man-made structures, since Haar-like feature is extracted from corner features and rectangle features. Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier. Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm. Also, the inclusion of Harr-like feature significantly improves the classification accuracy. The accuracy of the proposed method is 98.4% for the target detection and 92.8% for the classification on high resolution satellite images.
참고문헌 (12)
- R. M. Haralick, "Textural features for image classification", IEEE Trans. Systems, Man and Cybernetics, SMC-3(6), pp.610~621 (1973)
- Paul Viola, "Robust real-time face detection", International Journal of Computer Vision, 57(2), pp.137~154 (2004)
- David. A. Clausi, "Design-based texture feature fusion using Gabor filters and co-occurrence probabilities", IEEE Tran. Image Processing, 14(7), pp.925~936 (2005)
- Y. Freund, "A decision-theoretic generalization of on-line learning and an application to boosting", Journal of Computer and System Sciences, 55(1), pp.119~139 (1997)
- J. A. Benediktsson, "Classification and feature extraction for remote sensing images from urban areas based on morphological transformations", IEEE Trans. Geoscience and Remote Sensing, pp.1940~1949 (2003)
- David. A. Clausi, "Comparison and fusion of co-occurrence, Gabor, and MRF texture features for classification of SAR sea-ice imagery", Atmos.-Ocean, 39(3), pp.183~194 (2001)
- Dong-Min Woo, "Terrain classification using 3D co-occurrence features and neural networks", International Journal of Information Acquisition, 4(4), pp.1~9 (2007)
- C. Iovan, "Automatic extraction and classification of vegetation areas from high resolution images in urban areas", Springer, Lecture Notes in Computer Science, 4522, pp.858~867 (2007)
- Lei Zhang, "An ontology-based multi-class terrain surface classification System For Aerial Imagery", Proc. IEEE ESPA, pp.95~ (2012)
- Abou-Nasr, "Terrain identification in grayscale images with recurrent neural networks", Proc. IJCNN, pp.1~5 (2010)
- Md. Ali Hossain, "Implementation of back-propagation neural network for isolated bangla speech recognition", International Journal of Information Sciences and Techniques, 3(4), pp.1~9 (2013)
- Ryan Rifkin, "In defense of one-vs-all classification", Journal of Machine Learning Research, 5, pp.101~141 (2004)