您的位置:首页  > 论文页面

一种基于鱼眼全景拍摄的畸变车牌校正方法

发表时间:2018-05-31  浏览量:541  下载量:133
全部作者: 赵麒瑞,刘煜
作者单位: 国防科学技术大学信息系统与管理学院
摘 要: 由于全景图像的采集受到鱼眼镜头和各种因素的干扰,得到的车牌图像经常产生畸变,因此实现车牌图像畸变校正对提高车牌识别准确率具有重要意义。研究提出一种将畸变图像近似分割校正的方法,主要思路是将非线性畸变的车牌图像根据车牌字符特征进行近似分割,用线性近似替代非线性的思想确定角点,采用透视投影模型重构车牌图像,实现非线性畸变的车牌图像校正。实验证明,本文方法针对非线性畸变车牌图像的校正效果较为显著。
关 键 词: 系统工程;非线性畸变;鱼眼全景;图像分割;透视变换
Title: Correcting method of distorted license plates based on fisheye panoramic photography
Author: ZHAO Qirui, LIU Yu
Organization: College of Information System and Management, National University of Defense Technology
Abstract: Since the collection of panoramic images is disturbed by the fisheye lens and various factors, the obtained license plate images are often distorted. It is important to achieve license plate image distortion correction to improve the accuracy of license plate recognition. This paper proposes a new method to segment distorted images for linear approximation. The main idea is to segment the non-linear distorted license plate images into linear parts according to the license plate character, searching for the corners of each part, then reconstructing the non-linear distortion of the license plate image by using the perspective projection model, finally realizing the license plate image correction of non-linear distortion. Experimental results show that the proposed method is effective for the correction of non-linear distortion license plate images.
Key words: system engineering; non-linear distortion; fisheye panorama; image segmentation; perspective transformation
发表期数: 2018年5月第10期
引用格式: 赵麒瑞,刘煜. 一种基于鱼眼全景拍摄的畸变车牌校正方法[J]. 中国科技论文在线精品论文,2018,11(10):1052-1057.
 
0 评论数 0
暂无评论
友情链接