| 基于自适应神经网络的双摄像机标定 |
| |
| 引用本文： | 崔岸,袁智,王龙山. 基于自适应神经网络的双摄像机标定[J]. 计算机工程与应用, 2009, 45(21): 55-57. DOI: 10.3778/j.issn.1002-8331.2009.21.014 |
| |
| 作者姓名： | 崔岸 袁智 王龙山 |
| |
| 作者单位： | 吉林大学,汽车工程学院,长春,130025;吉林大学,机械科学与工程学院,长春,130025 |
| |
| 基金项目： | 国家重点实验室资助项目,吉林省科技发展计划 |
| |
| 摘 要： | 摄像机标定是计算机视觉中非常重要的一环,传统标定方法需要求解内外参数,非常繁琐。通过建立自适应神经网络直接学习图像坐标与空间坐标间的关系。该方法对Harris角点提取结果进行增加约束的改进,从而提高网络训练样本精度,通过程序实现隐层神经元的自适应选取,并综合运用正则化、提前终止策略,使网络的泛化能力得到极大的改善。最后通过与经典标定方法进行对比的实验证明基于自适应神经网络具有很好的双摄像机标定精度。
|
| 关 键 词： | 双摄像机标定 自适应 多层前馈网络 Harris角点 |
| 收稿时间： | 2009-01-17 |
| 修稿时间： | 2009-3-24 |
Self-adaptive neural network for binocular camera calibration |
| |
| CUI An,YUAN Zhi,WANG Long-shan. Self-adaptive neural network for binocular camera calibration[J]. Computer Engineering and Applications, 2009, 45(21): 55-57. DOI: 10.3778/j.issn.1002-8331.2009.21.014 |
| |
| Authors: | CUI An YUAN Zhi WANG Long-shan |
| |
| Affiliation: | 1．College of Automotive Engineering,Jilin University,Changchun 130025,China 2.College of Mechanical Engineering,Jilin University,Changchun 130025,China |
| |
| Abstract: | Camera calibration is an important step in computer vision,the traditional calibration methods need to acquire the intrinsic and extrinsic parameters and the process is quite complicated,so self-adaptive neural network is used to learn the relationship between the image coordinates and the space coordinates.The generalization ability is improved a lot by the following methods:modify Harris corner extraction algorithm to improve the training data accuracy,choose the number of the middle layer cells adaptivel... |
| |
| Keywords: | binocular camera calibration self-adaptive Back Propagation(BP) network harris comer |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
