| 基于 GPU 的 Harris 图像特征提取 |
| |
| 引用本文： | 王直,汤宁宁.基于 GPU 的 Harris 图像特征提取[J].江苏科技大学学报(社会科学版),2014(3):277-279. |
| |
| 作者姓名： | 王直 汤宁宁 |
| |
| 作者单位： | 江苏科技大学计算机科学与工程学院,江苏镇江212003 |
| |
| 摘 要： | 船用钢板的加工制造主要采用水火弯板的加工过程，随着三维测量技术的发展，现代工业系统主要采用视觉测量技术，它针对目标钢板的纹理特征不明显的特点，提出了一种点阵结构光的方法来测量钢板的三维形状.通过对钢板投影一些点阵，采用基于 GPU 的 Harris 加速角点检测算法提取投影特征点.实验结果表明，对于分辨率为995＆#215;646大小的图像加速比提高了26.36倍.
|
| 关 键 词： | 点阵结构光 GPU Harris 特征点提取 |
Harris image feature extraction based on GPU |
| |
| Wang Zhi,Tang Ningning.Harris image feature extraction based on GPU[J].Journal of Jiangsu University of Science and Technology:Natural Science Edition,2014(3):277-279. |
| |
| Authors: | Wang Zhi Tang Ningning |
| |
| Institution: | (School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang Jiangsu 212003, China) |
| |
| Abstract: | The manufacturing of hull steel is mainly adopted for line heating. With the technology innovation and the development of 3D measurement techniques,modern industrial system is mainly used for visual measurement technology. Because of unclear texture of the target steel,a point-array structured light method is used for the measurement of 3D shape. This paper uses the algorithm of Harris corner detection based on GPU to extract these projected feature points on the steel plate. Experimental results show that GPU can implement nearly 26. 36 times speedup rate for the resolution of 995 ＆#215; 646. |
| |
| Keywords: | point-array structured light GPU Harris feature points extraction |
| 本文献已被 维普 等数据库收录！ |
