TY - GEN
T1 - Using GPUs to improve system performance in visual servo systems
AU - Zang, Chuantao
AU - Hashimoto, Koichi
PY - 2010/12/1
Y1 - 2010/12/1
N2 - This paper describes our novel work of using GPUs to improve the performance of a homography-based visual servo system. We present our novel implementations of a GPU based Efficient Second-order Minimization (GPU-ESM) algorithm. By utilizing the tremendous parallel processing capability of a GPU, we have obtained significant acceleration over its CPU counterpart. Currently our GPU-ESM algorithm can process a 360 x 360 pixels tracking area at 145 fps on a NVIDIA GTX295 board and Intel Core i7 920, approximately 30 times faster than a CPU implementation. This speedup substantially improves the realtime performance of our system. System reliability and stability are also greatly enhanced by a GPU based Scale Invariant Feature Transform (SIFT) algorithm, which is used to deal with such cases where ESM tracking failure happens, such as due to large image difference, occlusion and so on. In this paper, translation details of the ESM algorithm from CPU to GPU implementation and novel optimizations are presented. The co-processing model of multiple GPUs and multiple CPU threads is described in this paper. The performance of our GPU accelerated system is evaluated with experimental data.
AB - This paper describes our novel work of using GPUs to improve the performance of a homography-based visual servo system. We present our novel implementations of a GPU based Efficient Second-order Minimization (GPU-ESM) algorithm. By utilizing the tremendous parallel processing capability of a GPU, we have obtained significant acceleration over its CPU counterpart. Currently our GPU-ESM algorithm can process a 360 x 360 pixels tracking area at 145 fps on a NVIDIA GTX295 board and Intel Core i7 920, approximately 30 times faster than a CPU implementation. This speedup substantially improves the realtime performance of our system. System reliability and stability are also greatly enhanced by a GPU based Scale Invariant Feature Transform (SIFT) algorithm, which is used to deal with such cases where ESM tracking failure happens, such as due to large image difference, occlusion and so on. In this paper, translation details of the ESM algorithm from CPU to GPU implementation and novel optimizations are presented. The co-processing model of multiple GPUs and multiple CPU threads is described in this paper. The performance of our GPU accelerated system is evaluated with experimental data.
UR - http://www.scopus.com/inward/record.url?scp=78651496224&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78651496224&partnerID=8YFLogxK
U2 - 10.1109/IROS.2010.5650418
DO - 10.1109/IROS.2010.5650418
M3 - Conference contribution
AN - SCOPUS:78651496224
SN - 9781424466757
T3 - IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings
SP - 3937
EP - 3942
BT - IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings
T2 - 23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010
Y2 - 18 October 2010 through 22 October 2010
ER -