[1]曹田,李勃,任福继,等.快速的圆投影图像匹配算法[J].智能系统学报,2020,15(1):84-91.[doi:10.11992/tis.201903037]
　CAO Tian,LI Bo,REN Fuji,et al.Fast image matching algorithm based on circular projection[J].CAAI Transactions on Intelligent Systems,2020,15(1):84-91.[doi:10.11992/tis.201903037]
点击复制

快速的圆投影图像匹配算法

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 15 期数: 2020年第1期 页码: 84-91 栏目: 学术论文—机器感知与模式识别 出版日期: 2020-01-05
Title:
Fast image matching algorithm based on circular projection
作者:
曹田1, 李勃1, 任福继2,3, 董蓉4
1. 南京大学 电子科学与工程学院, 江苏 南京 210046;
2. 合肥工业大学 计算机与信息学院, 安徽 合肥 230009;
3. 德岛大学 智能信息工学部, 日本 德岛 7708500;
4. 南通大学 电子与信息学院, 江苏 南通 226019
Author(s):
CAO Tian1, LI Bo1, REN Fuji2,3, DONG Rong4
1. School of Electronic Science and Engineering, Nanjing University, Nanjing 210046, China;
2. School of Computer and Information Science, Hefei University of Technology, Hefei 230009, China;
3. Department of Information Science and Intelligent Syst
关键词:
圆投影; 模板匹配; 图像匹配; 图像金字塔; 角度直方图; 混合圆投影; 顶层局部聚类; 非极大值抑制
Keywords:
circular projection; template matching; image matching; image pyramid; angle histogram; hybrid circular projection; topmost local clustering; nonmaximal suppression
分类号:
TP391
DOI:
10.11992/tis.201903037
摘要:
针对现有圆投影匹配方法计算复杂度高、对同质区域无法识别的缺点，提出了一种新的图像匹配算法。该算法基于混合圆投影向量，结合塔式分解和角度直方图估计，不仅可以识别出模板在待匹配图像中的准确位置，还可以通过角度估计策略得到模板的旋转角度。通过图像金字塔策略，结合混合圆投影向量快速找到候选点；然后在诸多候选点中精确定位，确定位置；最后通过角度直方图计算出准确的角度。实验结果证明该算法识别率高，且匹配速度快。
Abstract:
In view of the high computational complexity and the incapability to recognize homogeneous regions of existing circular projection matching algorithms, a new image matching algorithm is proposed in this study. On the basis of hybrid circular projection and combined with pyramid decomposition and angle histogram estimation, the proposed algorithm can not only identify the exact position of the template in the image to be matched but also obtain the rotation angle of the template through the angle estimation strategy. First, candidate points are identified by the image pyramid strategy combined with the hybrid circular projection vector. Then, the positions of the candidate points are precisely located and determined. Finally, the exact angle is calculated by the angle histogram algorithm. The experimental results show the high recognition rate and fast matching speed of the proposed algorithm.
参考文献/References:
[1] 周可, 秦世引. SIFT特征匹配的辐射畸变图像相对校正新方法[J]. 智能系统学报, 2011, 6(6): 507–514
ZHOU Ke, QIN Shiyin. A novel method for relative correction of a radiometric distortion image based on SIFT feature matching[J]. CAAI transactions on intelligent systems, 2011, 6(6): 507–514
[2] 阮晓虎, 李卫军, 覃鸿, 等. 一种基于特征匹配的人脸配准判断方法[J]. 智能系统学报, 2015, 10(1): 12–19
RUAN Xiaohu, LI Weijun, QIN Hong, et al. An assessment method for face alignment based on feature matching[J]. CAAI transactions on intelligent systems, 2015, 10(1): 12–19
[3] 李龙, 尹辉, 许宏丽, 等. 一种鲁棒的Multi-Egocentric视频中的多目标检测及匹配算法[J]. 智能系统学报, 2016, 11(5): 619–626
LI Long, YIN Hui, XU Hongli, et al. A robust multi-object detection and matching algorithm for multi-egocentric videos[J]. CAAI transactions on intelligent systems, 2016, 11(5): 619–626
[4] 王杰, 蒋明敏, 花晓慧, 等. 基于投影直方图匹配的双目视觉跟踪算法[J]. 智能系统学报, 2015, 10(5): 775–782
WANG Jie, JIANG Mingmin, HUA Xiaohui, et al. Binocular object tracking method using projection histogram matching[J]. CAAI transactions on intelligent systems, 2015, 10(5): 775–782
[5] ZITOVá B, FLUSSER J. Image registration methods: a survey[J]. Image and vision computing, 2003, 21(11): 977–1000.
[6] AGGARWAL J K, DAVIS L S, MARTIN W N. Correspondence processes in dynamic scene analysis[J]. Proceedings of the IEEE, 1981, 69(5): 562–572.
[7] SECILLA J P, GRACIA N, CARRASCOSA J L. Template location in noisy pictures[J]. Signal processing, 1988, 14(4): 347–361.
[8] TANIMOTO S L. Template matching in pyramids[J]. Computer graphics and image processing, 1981, 16(4): 356–369.
[9] ROSENFELD A, KAK A, Digital image processing[M]. 2nd ed. Orlando: Academic Press, 1982.
[10] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91–110.
[11] 郑永斌, 黄新生, 丰松江. SIFT和旋转不变LBP相结合的图像匹配算法[J]. 计算机辅助设计与图形学学报, 2010, 22(2): 286–292
ZHENG Yongbin, HUANG Xinsheng, FENG Songjiang. An image matching algorithm based on combination of SIFT and the rotation invariant LBP[J]. Journal of computer-aided design & computer graphics, 2010, 22(2): 286–292
[12] TANG Y Y, CHENG H D, SUEN C Y. Transformation-ring-projection (TRP) algorithm and its VLSI implementation[J]. International journal of pattern recognition and artificial intelligence, 1991, 5(1/2): 25–56.
[13] TSAI D M, TSAI Y H. Rotation-invariant pattern matching with color ring-projection[J]. Pattern recognition, 2002, 35(1): 131–141.
[14] LEE W C, CHEN C H. A fast template matching method with rotation invariance by combining the circular projection transform process and bounded partial correlation[J]. IEEE signal processing letters, 2012, 19(11): 737–740.
[15] 徐亦斌, 王敬东, 李鹏. 基于圆投影向量的景象匹配方法研究[J]. 系统工程与电子技术, 2005, 27(10): 1725–1728
XU Yibin, WANG Jingdong, LI Peng. Research on scene matching method using circular projection[J]. Systems engineering and electronics, 2005, 27(10): 1725–1728
[16] CHOI M S, KIM W Y. A novel two stage template matching method for rotation and illumination invariance[J]. Pattern recognition, 2002, 35(1): 119–129.
[17] 贾晓芬, 赵佰亭, 周孟然, 等. 采用圆投影和序贯相似检测的图像匹配技术[J]. 哈尔滨商业大学学报(自然科学版), 2015, 31(2): 232–236, 241
JIA Xiafen, ZHAO Baiting, ZHOU Mengran, et al. Fast image matching algorithm based on circular projection and sequential similarity detection[J]. Journal of Harbin University of Commerce (Natural Sciences Edition), 2015, 31(2): 232–236, 241
[18] 于辉, 张忠秋, 何周灿. 用于任意旋转角度景象匹配的圆投影算法[J]. 计算机工程与应用, 2011, 47(5): 172–174
YU Hui, ZHANG Zhongqiu, HE Zhoucan. Ring projection transformation algorithm for arbitrary rotation matching[J]. Computer engineering and applications, 2011, 47(5): 172–174
[19] SASSANAPITAK S, KAEWTRAKULPONG P. An efficient translation-rotation template matching using pre-computed scores of rotated templates[C]//Proceedings of the 6th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. Pattaya, Chonburi, Thailand: IEEE, 2009: 1040–1043.
相似文献/References:
[1]赵军,於俊,汪增福.基于改进逆向运动学的人体运动跟踪[J].智能系统学报,2015,10(4):548.[doi:10.3969/j.issn.1673-4785.201403032]
　ZHAO Jun,YU Jun,WANG Zengfu.Human motion tracking based on an improved inverse kinematics[J].CAAI Transactions on Intelligent Systems,2015,10():548.[doi:10.3969/j.issn.1673-4785.201403032]
[2]王杰,蒋明敏,花晓慧,等.基于投影直方图匹配的双目视觉跟踪算法[J].智能系统学报,2015,10(5):775.[doi:10.11992/tis.201410009]
　WANG Jie,JIANG Mingmin,HUA Xiaohui,et al.Binocular object tracking method using projection histogram matching[J].CAAI Transactions on Intelligent Systems,2015,10():775.[doi:10.11992/tis.201410009]
[3]汪鸿翔,柳培忠,骆炎民,等.高斯核函数卷积神经网络跟踪算法[J].智能系统学报,2018,13(3):388.[doi:10.11992/tis.201612040]
　WANG Hongxiang,LIU Peizhong,LUO Yanmin,et al.Convolutional neutral network tracking algorithm accelerated by Gaussian kernel function[J].CAAI Transactions on Intelligent Systems,2018,13():388.[doi:10.11992/tis.201612040]
[4]秦国威,孙新柱,陈孟元.基于WIFI指纹定位的仿生SLAM研究[J].智能系统学报,2018,13(3):407.[doi:10.11992/tis.201705020]
　QIN Guowei,SUN Xinzhu,CHEN Mengyuan.Bio-inspired SLAM fingerprint location based on WIFI[J].CAAI Transactions on Intelligent Systems,2018,13():407.[doi:10.11992/tis.201705020]

备注/Memo

收稿日期:2019-03-26。
基金项目:国家自然科学基金深圳联合基金重点项目(U1613217)
作者简介:曹田，硕士研究生，主要研究方向为图像处理和计算机视觉;李勃，副教授，主要研究方向为宽带网络通信、人工智能、图像识别。申请国家发明专利11项，授权3件。申请PCT、国家发明专利14项，已授权3项，获奖1项。发表学术论文20余篇;任福继，教授，日本工程院和欧盟科学院院士，中国人工智能学会名誉副理事长，日本工学会、IEICE、CAAI Fellow，日本国际先进信息研究所主席。主要研究方向为人工智能、情感计算、自然言语理解、模式识别。获吴文俊人工智能科学技术奖创新一等奖等，发明专利 10 余项，发表学术论文500 余篇
通讯作者:曹田.E-mail:mg1623063@smail.nju.edu.cn

更新日期/Last Update: 1900-01-01
Copyright © 《 智能系统学报》 编辑部
地址：（150001）黑龙江省哈尔滨市南岗区南通大街145-1号楼 电话：0451- 82534001、82518134　邮箱：tis@vip.sina.com