Publications

Guo, Zhen G.; Song, Jung K.; Barbastathis, George B.; Vaughan, Courtenay T.; Larson, K.W.; Alpert, Bradley K.; Levine, Zachary L.; Glinsky, Michael E.

Abstract not provided.

Mounce, Andrew M.; Monical, Cara P.; Lewis, Phillip J.; Jacobson, Noah T.; Jock, Ryan M.; Wendt, J.R.; Pluym, Tammy P.; Ward, Daniel R.; Larson, K.W.; Lilly, Michael L.; Luhman, Dwight R.

Abstract not provided.

Mounce, Andrew M.; Lewis, Phillip J.; Monical, Cara P.; Jacobson, Noah T.; Rudolph, Martin R.; Anderson, John M.; Wendt, J.R.; Pluym, Tammy P.; Ward, Daniel R.; Larson, K.W.; Lilly, Michael L.; Carroll, Malcolm

Abstract not provided.

Anderson, Hyrum A.; Helms, Jovana H.; Rohrer, Brandon R.; Wheeler, Jason W.; Larson, K.W.

Abstract not provided.

Myers, Daniel S.; Rothganger, Fredrick R.; Larson, K.W.

Wide baseline matching is the state of the art for object recognition and image registration problems in computer vision. Though effective, the computational expense of these algorithms limits their application to many real-world problems. The performance of wide baseline matching algorithms may be improved by using a graphical processing unit as a fast multithreaded co-processor. In this paper, we present an implementation of the difference of Gaussian feature extractor, based on the CUDA system of GPU programming developed by NVIDIA, and implemented on their hardware. For a 2000x2000 pixel image, the GPU-based method executes nearly thirteen times faster than a comparable CPU-based method, with no significant loss of accuracy.