A parallel approach for initialization of high-order statistics anomaly detection in hyperspectral imagery

Anomaly detection for remote sensing has drawn a lot of attention lately. An anomaly has distinct spectral features from its neighborhood, whose spectral signature is not known a priori, and it usually has small size with only a few pixels. It is very challenge to detect anomalies, especially without any information of the background environment in hyperspectral data with hundreds of co-registered image bands. Several methods are devoted to this problem, including the well-known RX algorithm which takes advantage of the second-order statistics and other algorithms which detect anomaly based on higher order statistics such as skewness and kurtosis. It has been proved that the HighOrder Automatic Anomaly Detection Algorithm can outperform RX algorithm by distinguishing different types of anomalies. However, the initialization of the High-Order Automatic Anomaly Detection Algorithm remains a challenge problem. When the initial vectors are selected randomly for this recursive algorithm, they might be trapped in the local maximums and give different projection directions. But in our experiments, all those directions will show different types of anomalies. Therefore, this algorithm is particular suitable for parallel processing to increase the computing efficiency. In the parallel architecture, we will first randomly generate initial vectors for each process, and then united those output results for the orthogonal projection base. We will also compare the computational efficiency with the number of parallel processes we used.