视频拼接中最优自适应单应性矩阵求解算法

doi:10.7964/jdxbgxb201304043

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (04): 1116-1120.doi: 10.7964/jdxbgxb201304043

视频拼接中最优自适应单应性矩阵求解算法

张春雨¹, 王文¹, 邱亚特¹, 郭克友²

1. 交通运输部公路科学研究所北京诚达交通科技有限公司,北京 100088;
2. 北京工商大学机械工程学院北京 100037

收稿日期:2012-12-22 出版日期:2013-07-01 发布日期:2013-07-01
作者简介:张春雨(1974-),女,副研究员,博士.研究方向:多媒体信号处理,智能车辆驾驶辅助技术. E-mail:chunyuzhang0320@hotmail.com
基金资助:
中央级公益型科研院所基本科研业务费项目.

Algorithm for optimal homography matrix in video mosaic

ZHANG Chun-yu¹, WANG Wen¹, QIU Ya-te¹, GUO Ke-you²

1. Research Institute of Highway, Ministry of Transportation, Beijing Chengda Traffic Technology Co.Ltd,Beijing 100088,China;
2. College of Mechanical Engineering and Automation,Beijing Technology and Business University, Beijing 100037,China

Received:2012-12-22 Online:2013-07-01 Published:2013-07-01

摘要/Abstract

摘要：

针对交通场景中对视频拼接速度要求较高的特点,提出了利用视频帧最优单应性矩阵进行实时拼接的双线程快速算法。首先,利用SURF(Speeded up robust features)算法提取图像特征点;其次,通过NN(Nearest neighbor)算法以及优化的RANSAC(Random sample consensus)算法进行特征点的匹配,并去除误匹配点对;再次,利用重叠区域的归一化协方差相关函数最大化得到视频前k帧配准效果最佳的单应性矩阵,作为后继视频帧场景拼接的映射矩阵;同时,采用KLT算法对k+1的后继视频帧特征点进行动态跟踪,若匹配点对的数量变化超过了给定的阈值,则认为当前的最优单应性矩阵需要进行优化和变换,重新计算k幅视频帧中新的特征点对,经匹配后求取新的最优单应性矩阵。在交通场景中的拼接实验证明,该快速算法平均视频帧的拼接处理速度小于100 ms,对存在旋转、尺度缩放、视角以及光照变化的图像都具有良好的拼接效果,具有参数估算准确,计算量小、速度快的优点,能够满足系统对视频拼接的实时性和精确性要求。

关键词: 信息处理技术, 视频拼接, SURF, 最优单应性矩阵

Abstract:

We propose an algorithm for optimal homography matrix in video mosaic using double thread. First, the characteristic points are extracted using Speeded Up Robust Feature (SURF) method. Second, the corresponding characteristic points are matched using Nearest Neighbor (NN) and Random Sample Consensus (RANSAC) methods. Third, the optimal homography matrix of first k video frames is calculated using the normal covariance correlation of overlapped area between corresponding frames. The optimal homography matrix is taken as the mapping matrix of the succeeding frames. Meanwhile, the KLT algorithm is used for feature dynamic tracking of the frames succeeding k+1 frame. If the change of amount of the tracked feature points exceeds the given threshold, the current optimal homgoraphy matrix needs re-optimization and transformation; the pairs of feature points of k video frames are recalculated and matched to obtain the new optimal homgoraphy matrix. Image matching tests in traffic surveillance demonstrate that the average matching speed of the proposed algorithm is less than 100 ms; good matching quality is achieved for images with variable rotation, scaling, visual angle and illumination; parameter estimation is accurate and high speed with less computation, which meets the requirements of real-time and high accurate matching of the system.

Key words: information processing, video image mosaic system, speeded up robust features(SURF), optimal homography matrix

中图分类号:

TN911

张春雨, 王文, 邱亚特, 郭克友. 视频拼接中最优自适应单应性矩阵求解算法[J]. 吉林大学学报(工学版), 2013, 43(04): 1116-1120.

ZHANG Chun-yu, WANG Wen, QIU Ya-te, GUO Ke-you. Algorithm for optimal homography matrix in video mosaic[J]. 吉林大学学报(工学版), 2013, 43(04): 1116-1120.

参考文献

[1] Smith S, Susan Brady M. A new approach to low level image processing[J]. International Journal of Computer Vision, 1997, 23(1):45-78.

[2] Lemeshewsky G P. Multispectral multi-sensor image fusion using wavelet transforms[J]. Pro SPIE, 1999, 3716:214-222.

[3] Luo Zhong-xuan, Liu Cheng-ming. Fast algorithm of image matching[J]. Journal of Computer-Aided Design & Computer Graphics, 2005, 17(5):966-969.

[4] Lowe D G. Object recognition from local scale-invariant features//International Conference on Computer Vision, Corfu, Greece,1999:1150-1157.

[5] Brown M, Lowe D G. Automatic panoramic image stitching using invariant features[J]. International Journal of Computer Vision,2007,74(1):59-73.

[6] Lowe D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004,60(2):91-110.

[7] 陈昱, 庄天戈 . 基于灰度值相应概率的非刚性图像配准[J]. 上海交通大学学报,1999:33(9):1128-1130. Chen Yu,Zhuang Tian-ge. Non-rigid registration for multi-modal medical images based on gray value correspondence probability[J]. Journal of Shanghai Jiaotong University,1999,33(9):1128-1130.

[8] 董瑞,梁栋. 基于颜色梯度的图像特征点匹配算法[J]. 计算机工程,2007,33(16):178-180. Dong Rui,Liang Dong. Image feature points match algorithm based on color gradient,computer engineering[J]. Computer Engeering, 2007,33(16):178-180.

[9] 李广儒, 张闯. 基于Harris 特征点检测法的雷达图像与电子海图的数据融合[J].大连海事大学学报, 2009,35(2):55-58. Li Guang-ru, Zhang Chuang. Data mining of radar image and electronic chart based on Harris feature point detection[J]. Journal of Dalian Maritime University, 2009,35(2):55-58.

[10] 许俊泽,胡波. 对数极坐标变换域下互信息图像配准方法[J]. 信息与电子工程,2009,7(4):289-293. Xu Jun-ze, Hu Bo. Mutual information image registration based on log-polar transform[J]. Information and Electronic Engineering, 2009,7(4):289-293.

[11] 李根,李文辉.基于尺度不变特征变换的平面旋转人脸检测[J].吉林大学学报:工学版,2013,43(1):186-191. Li Gen, Li Wen-hui. Face detection under rotation in image plane based on scale invariant feature transform[J]. Journal of Jilin University(Engineering and Technology Edition),2013,43(1):186-191.

[12] Bay H, Tuvtellars T, Van Gool L. SURF: speeded up robust features//Proceedings of the European Conference on Computer Vision, 2006:404-417.

[13] Jain P K, Jawahar C V. Homography estimation from planar contours[J]. Third International Symposium, 2006, 77(15):877-884.

相关文章 15

[1]	苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[3]	黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[4]	李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[5]	应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[6]	陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[7]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[8]	单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[9]	姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[10]	全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[11]	陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[12]	陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[13]	孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
[14]	林金花, 王延杰, 孙宏海. 改进的自适应特征细分方法及其对Catmull-Clark曲面的实时绘制[J]. 吉林大学学报(工学版), 2018, 48(2): 625-632.
[15]	王柯, 刘富, 康冰, 霍彤彤, 周求湛. 基于沙蝎定位猎物的仿生震源定位方法[J]. 吉林大学学报(工学版), 2018, 48(2): 633-639.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

视频拼接中最优自适应单应性矩阵求解算法

Algorithm for optimal homography matrix in video mosaic

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10