Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications. This paper presents a parallel implementation for a recently proposed scale- and rotation-invariant on-line object tracking system. The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads. Specifically, we analyze the original algorithm and propose the GPU-based parallel design. Emphasis is placed on exploiting the data parallelism and memory usage. In addition, we apply optimization technique to maximize the utilization of NVIDIA's GPU and reduce the data transfer time. Experimental results show that our GPGPU-based method running on a GTX480 graphics card could achieve up to 12X speed-up compared with the efficiency equivalence on an Intel E8400 3.0 GHz CPU, including I/O time.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Quan MIAO, Guijin WANG, Xinggang LIN, "Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 12, pp. 2549-2552, December 2011, doi: 10.1587/transinf.E94.D.2549.
Abstract: Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications. This paper presents a parallel implementation for a recently proposed scale- and rotation-invariant on-line object tracking system. The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads. Specifically, we analyze the original algorithm and propose the GPU-based parallel design. Emphasis is placed on exploiting the data parallelism and memory usage. In addition, we apply optimization technique to maximize the utilization of NVIDIA's GPU and reduce the data transfer time. Experimental results show that our GPGPU-based method running on a GTX480 graphics card could achieve up to 12X speed-up compared with the efficiency equivalence on an Intel E8400 3.0 GHz CPU, including I/O time.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.2549/_p
Copy
@ARTICLE{e94-d_12_2549,
author={Quan MIAO, Guijin WANG, Xinggang LIN, },
journal={IEICE TRANSACTIONS on Information},
title={Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA},
year={2011},
volume={E94-D},
number={12},
pages={2549-2552},
abstract={Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications. This paper presents a parallel implementation for a recently proposed scale- and rotation-invariant on-line object tracking system. The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads. Specifically, we analyze the original algorithm and propose the GPU-based parallel design. Emphasis is placed on exploiting the data parallelism and memory usage. In addition, we apply optimization technique to maximize the utilization of NVIDIA's GPU and reduce the data transfer time. Experimental results show that our GPGPU-based method running on a GTX480 graphics card could achieve up to 12X speed-up compared with the efficiency equivalence on an Intel E8400 3.0 GHz CPU, including I/O time.},
keywords={},
doi={10.1587/transinf.E94.D.2549},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA
T2 - IEICE TRANSACTIONS on Information
SP - 2549
EP - 2552
AU - Quan MIAO
AU - Guijin WANG
AU - Xinggang LIN
PY - 2011
DO - 10.1587/transinf.E94.D.2549
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2011
AB - Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications. This paper presents a parallel implementation for a recently proposed scale- and rotation-invariant on-line object tracking system. The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads. Specifically, we analyze the original algorithm and propose the GPU-based parallel design. Emphasis is placed on exploiting the data parallelism and memory usage. In addition, we apply optimization technique to maximize the utilization of NVIDIA's GPU and reduce the data transfer time. Experimental results show that our GPGPU-based method running on a GTX480 graphics card could achieve up to 12X speed-up compared with the efficiency equivalence on an Intel E8400 3.0 GHz CPU, including I/O time.
ER -