Abstract
In classifying very high spatial resolution (VHR) hyperspectral imagery, intra-class variation often adversely affects classification accuracy, mainly due to a low signal-to-noise ratio (SNR) and high spatial heterogeneity. To address this problem, this article develops a neighbourhood-constrained k-means (NC-k-means) algorithm by incorporating the pure neighbourhood index into the traditional k-means algorithm. The performance of the NC-k-means algorithm was assessed through a series of simulated images and a real hyperspectral image. The results indicate that the classification accuracy of NC-k-means algorithm is consistently better than that of the traditional k-means algorithm, in particular for the images with significant spatial autocorrelations among neighbouring pixels.
Acknowledgements
The authors are grateful to Prof. Tim Warner from West Virginia University and two anonymous referees for their constructive comments. This work was supported by Director Foundation of Center for Earth Observation and Digital Earth, Chinese Academy of Sciences and National Key Technology R&D Program of China under Grant No. 2011BAH12B04.