车位图像畸变的矫正与拼接研究

J4 ›› 2014, Vol. 36 ›› Issue (07): 1341-1346.

车位图像畸变的矫正与拼接研究

李宇成，赵兴彩，李国辉

(北方工业大学机电工程学院，北京 100144)

收稿日期:2013-01-21 修回日期:2013-04-27 出版日期:2014-07-25 发布日期:2014-07-25

Research of correction and stitching of parking image distortion

LI Yucheng,ZHAO Xingcai,LI Guohui

(College of Mechanical and Electrical Engineering,North China University of Technology,Beijing 100144,China)

Received:2013-01-21 Revised:2013-04-27 Online:2014-07-25 Published:2014-07-25

摘要/Abstract

摘要：

为了实现停车场空车位的快速检测和查询，提出一种车位图像畸变的矫正与拼接方法，将相邻摄像头拍摄的具有一定重叠区域的视频图像拼接为一幅能够全面描述停车场车位信息的大视场图像，从而为停车场空车位的快速检测做准备。由于停车场摄像头安装的视角偏移和透视效应，造成拍摄的图片存在纵向和横向畸变，为了直观地显示整个停车场各个车位的占用、空闲信息，同时也为了方便车辆管理，先将各个车位逐一矫正成同视角图片，然后再进行拼接，从而便于用户直接观察停车场中的空车位，也有利于需要自动检测车位时进一步进行图像处理。

关键词: 车位检测, 图形畸变, 图形矫正, 图像拼接

Abstract:

In order to achieve the rapid automatic detection and query of the empty parking spaces, a correction and stitching method of parking image distortion is proposed. Images with some overlapped regions captured by adjacent cameras are stitched into a large field image mosaic that comprehensively describes the parking information, so that the empty parking spaces are detected. And pictures show vertical distortion and horizontal distortion due to the camera perspective and perspective effects. For the sake of intuitively displaying the occupation and empty information of all parking spaces and facilitating the vehicle management, all parking images are corrected to be with the same perspective before image mosaic. Experimental results show that the algorithm is convenient for users to directly observe empty parking spaces, and it is conducive to process images further for automatic detection of the parking spaces.

Key words: parking spaces detection;graphic distortion;graphic correction;image stitching

李宇成，赵兴彩，李国辉. 车位图像畸变的矫正与拼接研究[J]. J4, 2014, 36(07): 1341-1346.

LI Yucheng,ZHAO Xingcai,LI Guohui. Research of correction and stitching of parking image distortion [J]. J4, 2014, 36(07): 1341-1346.

参考文献

［1］Zou Beiji, Ruan Peng, Xiang Yao, et al. An automatic panoramic images mosaic algorithm with precise matching ［J］. Computer Engineering and Science, 2010, 32(8):6063. (in Chinese)
［2］Li Xiaoming,Zheng Lian,Hu Zhanyi.SIFT based automatic registration of remotelysensed imagery ［J］. Journal of Remote Sensing, 2006,10(6):885892. (in Chinese)
［3］Cai Lihuan, Liao Yinghao, Guo Donghui. Study on image stitching methods and its key technologies ［J］. Computer Technology and Development, 2008,18(3):14. (in Chinese)
［4］Lowe D G. Object recognition from local scaleinvariant features ［C］∥Proc of the 7th International Conference on Computer Vision, 1999:11501157.
［5］Bay H,Tuytelaars T,Van Gool L.SURF:Speeded up robust features［C］∥Proc of the 9th European Conference on Computer Vision, 2006:404417.
［6］Zhang Z Y. A flexible new technique for camera calibration［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(11):13301334.
［7］Fischler M A, Bolles R C.Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography ［J］.Communications of ACM, 1981,24(6):381395.
［8］Liu Jinlu, Chen Shouyu. Back propagation learning algorithm with Hessian matrix for fuzzy optimal neural networks［J］. Shuili Xuebao, 2004(4):164. (in Chinese)
［9］Szeliski R.Video mosaics for virtual environment［J］. IEEE Computer Graphics and Applications, 1996,16(2):2230.
［10］Hou Shuwei, Guo Baolong. A fast automatic image stitching algorithm ［J］. Computer Engineering, 2005,31(24):7072. (in Chinese)
［11］Li Yucheng, Yan Juanli. Approach for parking spaces detection based on video images［J］. Computer Engineering and Design, 2012,33(1):283285. (in Chinese)
附中文参考文献：
［1］邹北骥,阮鹏,向遥,等. 一种精确匹配的全景图自动拼接算法［J］.计算机工程与科学,2010,32(8):6063.
［2］李晓明,郑链,胡占义.基于 SIFT 特征的遥感影像自动配准［J］.遥感学报,2006,10(6):885892.
［3］蔡丽欢,廖英豪,郭东辉.图像拼接方法及其关键技术研究［J］.计算机技术与发展,2008,18(3):14.
［8］刘金禄,陈守煜.基于Hessian矩阵的模糊优选BP算法及其应用［J］.水利学报,2004(4):164.
［10］侯舒维,郭宝龙. 一种图像自动拼接的快速算法［J］.计算机工程,2005,31(24):7072.
［11］李宇成,严娟莉.利用视频图像检测车位状态的方法［C］.计算机工程与设计,2012,33(1):283285.

[1]	许光宇, 丁健. 基于特征聚类的大视差图像拼接算法 [J]. 计算机工程与科学, 2022, 44(02): 283-290.
[2]	梁中岩, 戚红雨, 王伟良, 胡杰. 无人机载荷图像地理信息拼接及验证算法[J]. 计算机工程与科学, 2020, 42(12): 2208-2216.
[3]	崔克彬1，苑津莎2，李宝树2. 基于Hu向量相似度的图像序列自动排序算法[J]. J4, 2015, 37(08): 1579-1583 .
[4]	孟建良，王雅继. 最佳点平滑法寻找最佳拼接缝[J]. J4, 2015, 37(07): 1387-1392.
[5]	陈为龙1,2，郭黎3. 一种基于膨胀的渐进渐出图像融合算法[J]. J4, 2014, 36(07): 1347-1351.
[6]	张其亮1,2,陈永生2,韩斌1. 基于嵌入式系统的全景图像拼接系统设计[J]. J4, 2012, 34(6): 118-122.
[7]	李欢欢，黄山，张洪斌. 基于Harris与SIFT算法的自动图像拼接[J]. J4, 2012, 34(11): 104-108.
[8]	冷晓艳. 空中侦察图像连续拼接中的平滑算法研究[J]. J4, 2007, 29(2): 53-55.
[9]	杨琳赵建民朱信忠徐慧英郑国强. 虚拟校园三维全景漫游技术研究[J]. J4, 2007, 29(10): 26-28.
[10]	何红太王秀美全茜. 刑事犯罪现场的图像拼接设计与实现[J]. J4, 2004, 26(12): 46-48.