您的位置:首页  > 论文页面

基于手持终端采集全景图像中的车牌定位算法

发表时间:2017-08-31  浏览量:1918  下载量:198
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: 针对出现的复杂背景干扰,结合马尔可夫随机场图像分割理论,构建前景-背景分割模型,提取前景中的车辆区域,实现复杂背景干扰的去除。针对不同拍照角度和距离产生的影响,提取车牌色调特征信息,建立色调阈值区间,使用反馈调节的算法,得到所有可能的车牌区域。再利用车牌特有的字符特征,去除伪车牌,实现准确定位。基于手持终端的车牌定位方法,能较好地去除背景干扰,克服手持终端拍摄角度和距离的影响,具有较高的车牌定位准确率。
关 键 词: 控制理论其他学科;全景图像;前景分割;车牌定位
Title: Panorama image license plate locating method based on the handheld terminals
Author: ZHAO Qirui, LIU Yu
Organization: College of Information System and Management, National University of Defense Technology
Abstract: To cope with the complex background interference, we build a foreground-background segmentation model combining the theory of Markov random field image segmentation. Vehicles in the foreground area are extracted, thus to achieve the removal of complex background interference. Considering the impact of different photo angles and distances, we extract license plate color characteristic information and find a tonal threshold value interval. By using feedback control algorithm, we get all potential license plate areas. By utilizing characteristic of the license plates, we can remove the false license plates, achieving the ultimate localization. Our method can better remove the background interference, overcome the influence of the handset camera angles and distances and achieve the high accuracy of license plate localization.
Key words: control theory other disciplines; panoramic image; foreground segmentation; license plate locating
发表期数: 2017年8月第16期
引用格式: 赵麒瑞,刘煜. 基于手持终端采集全景图像中的车牌定位算法[J]. 中国科技论文在线精品论文,2017,10(16):1885-1891.
 
1 评论数 0
暂无评论
友情链接