Band Selection for Hyperspectral Image Classification by a Sliding Window Model
We investigate how to better use mutual information (MI) to select bands for hyperspectral image classi.cation with less human intervention. Mutual information e.ectively measures the statistical dependence between two random variables. By modeling ground truth (e.g., a reference map) as one of the two random variables, MI can be used to .nd the spectral bands that contribute most to image classi.cation. Extending our earlier work, we propose a sliding window model and apply mutual information to construct the estimated reference map, which need less human intervention. Experiments on the AVIRIS 92AV3C data set show that the proposed approach outperformed the benchmark methods, removing up to 55％ of bands without signi.cant loss of classi.cation accuracy, compared to the 40％ from that using the reference map accompanied with the data set. Meanwhile, its performance is found to be much robust to accuracy degradation when bands are cut o. beyond 60％, revealing a better agreement in the mutual information estimation.
Hyperspectral image classi.cation band selection mutual information
Baofeng Guo Yuesong Lin Dongliang Peng Anke Xue
Institute of Information and Control, School of Automation, Hangzhou Dianzi UniversityHangzhou, Zhej Institute of Information and Control, School of Automation, Hangzhou Dianzi University Hangzhou, Zhe
国际会议
桂林
英文
1-7
2011-11-01（万方平台首次上网日期，不代表论文的发表时间）