Spectral-spatial classification of hyperspectral imagery based on Random Forests

Authors:
Liu Wei;Shaozi Li;Miaohui Zhang;Yundong Wu;Song-zhi Su;Rongrong Ji
Affiliations:
Xiamen University, Xiamen, China;Xiamen University, Xiamen, China;Xiamen University, Xiamen, China;Jimei University, Xiamen, China;Xiamen University, Xiamen, China;Xiamen University, Xiamen, China
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 6
Cited 0

Random Forests

Machine Learning
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Random Forests for land cover classification

Pattern Recognition Letters - Special issue: Pattern recognition in remote sensing (PRRS 2004)
Hyperspectral Data Exploitation: Theory and Applications

Hyperspectral Data Exploitation: Theory and Applications
Segmentation and classification of hyperspectral images using watershed transformation

Pattern Recognition
A morphological gradient approach to color edge detection

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The high dimensionality of hyperspectral images are usually coupled with limited reference data available, which degenerates the performances of supervised classification techniques such as random forests (RF). The commonly used pixel-wise classification lacks information about spatial structures of the image. In order to improve the performances of classification, incorporation of spectral and spatial is needed. This paper proposes a novel scheme for accurate spectral-spatial classification of hyperspectral image. It is based on random forests, followed by majority voting within the superpixels obtained by oversegmentation through a graph-based technique. The scheme combines the result of a pixel-wise RF classification and the segmentation map obtained by oversegmentation. Our experimental results on two hyperspectral images show that the proposed framework combining spectral information with spatial context can greatly improve the final result with respect to pixel-wise classification with Random Forests.