High Performance Computing for Image Classification

We present the overall goals of our research program on the application of high performance computing to remote sensing applications, specifically applications in land cover dynamics. This involves developing scalable and portable programs for a variety of image and map data processing applications, eventually integrated with new models for parallel I/O of large scale images and maps. Here, we focus on our research in classification of remotely sensed images, describing new parallel algorithms for classification using Markov Random Fields and for classifying segmentations of images using a multistage decision procedure. 1 Introduction We describe the results of our research program on the application of high performance computing to the analysis of remotely sensed imagery. The specific application area that we are focusing on, initially, is generating maps of the world's tropical rain forest during the past three decades. This is currently being done using manually labor intensive te..