Urban change detection based on self-organizing feature map neural network

Change detection is a newly developed method for identifying land surface changes recorded in temporal remote sensing data. When traditional statistic classification algorithms are normally used in change detection for temporal multi-spectral remote sensing data, a singularity structure problem should occur if performing direct classification change detection approach, which is caused by different spectrum come from the same training area. In order to solve this problem a self-organizing feature map neural network is developed, which is based on the weight of samplings and data. The result indicates direct classification change detection is better than that of post classification comparison based on maximum likelihood classification algorithm.