Fast hog feature computation based on CUDA | |
Chen, Yan-Pi ; Li, Shao-Zi ; Lin, Xian-Min ; Li SZ(李绍滋) ; Chen YP(陈延平) ; Lin XM(林贤明) | |
2011 | |
关键词 | Algorithms Parallel architectures |
英文摘要 | Conference Name:2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011. Conference Address: Shanghai, China. Time:June 10, 2011 - June 12, 2011.; IEEE Beijing Section; Pudong New Area Association for Computer; Pudong New Area Science and Technology Development Fund; Tongji University; Xiamen University; Histogram of oriented gradients (HOG) is one of the most popular descriptors used for pedestrian detection, but this descriptor has its own drawback. Like most sliding window algorithms it is very slow, making it unsuitable for many real-time applications. This paper proposes a parallel implementation of the HOG algorithm. It bases on CUDA (compute unified device architecture) platform that could use parallel computing of graphic processing unit (GPU). The time consumption of HOG running on the GPU and on the CPU is compared by experiments in this paper. The results demonstrate that the HOG on GPU performs better than the HOG running on CPU, and is approximate 10 times speedup. ? 2011 IEEE. |
语种 | 英语 |
出处 | http://dx.doi.org/10.1109/CSAE.2011.5952952 |
出版者 | IEEE Computer Society |
内容类型 | 其他 |
源URL | [http://dspace.xmu.edu.cn/handle/2288/86994] |
专题 | 信息技术-会议论文 |
推荐引用方式 GB/T 7714 | Chen, Yan-Pi,Li, Shao-Zi,Lin, Xian-Min,et al. Fast hog feature computation based on CUDA. 2011-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论