Towards Real-Time Hyperspectral Image Processing: A GPGPU Implementation of Target Identification

In the quest for real time processing of hyperspectral images, this chapter presents three artificial intelligence algorithms for target detection specially developed for their implementation over GPU and applied to a search-and-rescue scenario. All the algorithms are based on the application of artificial neural networks to the hyperspectral data. In the first algorithm the neural networks are applied at the level of individual pixels of the image. The second algorithm is a multiresolution based approach to scale invariant target identification using a hierarchical artificial neural network architecture. The third algorithm is a refinement of the previous one but including also the ability to detect the orientation of the targets in cases for which this information is relevant. We have studied the main issues for the efficient implementation of the algorithms in GPU: the exploitation of thousands of threads that are available in this architecture and the adequate use of bandwidth of the device. The tests we have performed show both the effectiveness of detection of the algorithms and the efficiency of the GPU implementation in terms of execution times and bandwidth usage. These results bear out that the GPU is an adequate computing platform for on-board processing of hyperspectral information.

keywords: Hyperspectral image, target detection, CUDA, commodity GPU, artificial neural network, multithreaded architecture