| 基于改进的尺度不变特征变换特征点匹配的电子稳像算法 |
| |
| 引用本文： | 孟勃,韩广良.基于改进的尺度不变特征变换特征点匹配的电子稳像算法[J].计算机应用,2012,32(10):2817-2820. |
| |
| 作者姓名： | 孟勃 韩广良 |
| |
| 作者单位： | 1. 东北电力大学 信息工程学院,吉林 吉林 1320122. 中国科学院 长春光学精密机械与物理研究所, 长春 130033 |
| |
| 基金项目： | 国家自然科学基金资助项目(61172111);东北电力大学博士科研启动基金资助项目(BSJXM-201111) |
| |
| 摘 要： | 针对传统尺度不变特征变换（SIFT）算法运算量大的问题,提出了一种改进的SIFT特征点匹配算法。首先介绍了SIFT特征向量的提取过程,并对算法进行了改进,在单尺度空间内提取目标的关键点,并形成34维特征向量,来代替传统SIFT算法生成的128维特征向量,使算法的实时性得到较大的提高,同时又保持了配准精度,最后将提出的改进SIFT特征应用于电子稳像中的全局运动估计中,并通过实验验证了算法的性能。
|
| 关 键 词： | 电子稳像 全局运动估计 尺度不变特征变换 特征匹配 准确性 |
| 收稿时间： | 2012-04-27 |
| 修稿时间： | 2012-06-13 |
Electronic image stabilization algorithm using improved scale invariant feature transform |
| |
| MENG Bo,HAN Guang-liang.Electronic image stabilization algorithm using improved scale invariant feature transform[J].journal of Computer Applications,2012,32(10):2817-2820. |
| |
| Authors: | MENG Bo HAN Guang-liang |
| |
| Affiliation: | 1. Academy of Information Engineer, Northeast Dianli University, Jilin Jilin 132012, China2. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun Jilin 130033, China |
| |
| Abstract: | In order to satisfy the real-time requirement of image stabilization,this paper proposed a new matching method based on the improved Scale Invariant Feature Transform(SIFT) features.The presented method extract the key points of the target within the space of a single scale,and the formation of 34-dimensional feature vector,instead of the traditional SIFT algorithm to generate the 128-dimensional feature vector,so that the real-time of the algorithm was greatly improved,while maintaining the registration accuracy.At last,the improved SIFT features were used in the global motion estimation of the electronic image stabilization.The experiments verified the performance of the algorithm. |
| |
| Keywords: | electronic image stabilization global motion estimation Scale Invariant Feature Transform(SIFT) image matching accuracy |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
