|
|||||
|
|
| 基于形状上下文和方向梯度直方图特征的异源图像配准 | |
| 引用本文： | 黄微,任卫红,朱琳琳,田建东. 基于形状上下文和方向梯度直方图特征的异源图像配准[J]. 信息与控制, 2019, 48(2): 149-155. DOI: 10.13976/j.cnki.xk.2019.8210 |
| 作者姓名： | 黄微 任卫红 朱琳琳 田建东 |
| 作者单位： | 1. 中国科学院沈阳自动化研究所机器人学国家重点实验室, 辽宁 沈阳 110016; 2. 中国科学院机器人与智能制造创新研究院, 辽宁 沈阳 110016; 3. 中国科学院大学, 北京 100049; 4. 沈阳航空航天大学, 辽宁 沈阳 110136 |
| 基金项目： | 国家自然科学基金资助项目（91648118，61503256） |
| 摘 要： | 针对单模态图像包含的信息存在局限性的问题，提出了一种基于形状上下文和HOG（histogram of oriented gradient）特征的红外和可见光图像配准方法.在混合高斯模型前景检测的基础上，通过提出的形状上下文和HOG特征结合的方法实现轮廓特征匹配，再利用TPS（thin plate spline）转换模型将匹配延伸到整个形状，并使用正则化和缩放特性迭代重组对应关系及估计转换降低估计误差.最后，采用RANSAC（random sample consensus）算法去除错误匹配点.与已有的形状上下文方法相比，此方法结合了边缘和轮廓特征信息，降低了误差，鲁棒性更好. |
| 关 键 词： | 图像配准 前景检测 形状上下文 方向梯度直方图(HOG)特征 |
| 收稿时间： | 2018-04-18 |
Multi-sensor Image Registration Based on Shape Context and Histograms of Oriented Gradient Feature |
|
| HUANG Wei,REN Weihong,ZHU Linlin,TIAN Jiandong. Multi-sensor Image Registration Based on Shape Context and Histograms of Oriented Gradient Feature[J]. Information and Control, 2019, 48(2): 149-155. DOI: 10.13976/j.cnki.xk.2019.8210 | |
| Authors: | HUANG Wei REN Weihong ZHU Linlin TIAN Jiandong |
| Affiliation: | 1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; 2. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China; 3. University of Chinese Academy of Sciences, Beijing 100049, China; 4. Shenyang Aerospace University, Shenyang 110136, China |
| Abstract: | We propose a registration method for infrared and visible images based on shape context and histogram of oriented gradient (HOG) feature to overcome the limitations of single-mode image information. On the basis of foreground detection by Gaussian mixture model, we realize the contour feature matching using the proposed shape context and HOG feature. Matching is extended to the whole shape through a thin plate spline (TPS) transformation model. Then, we use the regularization and scaling characteristics to reorganize the corresponding relationship and estimate the transformation in order to reduce the estimation error. Finally, the random sample consensus (RANSAC) algorithm is used to remove the error matching points. Compared with existing shape context methods, this method combines edge and contour feature information with lower error and better robustness. |
| Keywords: | image registration foreground detection shape context histogram of oriented gradient (HOG) feature |
| 点击此处可从《信息与控制》浏览原始摘要信息 | |
| 点击此处可从《信息与控制》下载全文 | |