计算机科学 ›› 2018, Vol. 45 ›› Issue (9): 283-287.doi: 10.11896/j.issn.1002-137X.2018.09.047

• 图形图像与模式识别 • 上一篇    下一篇

一种基于FAsT-Match算法的多靶位定位方法

陈俊, 郑洪源   

  1. 南京航空航天大学计算机科学与技术学院 南京210016
  • 收稿日期:2017-07-05 出版日期:2018-09-20 发布日期:2018-10-10
  • 通讯作者: 郑洪源(1973-),男,博士,副教授,硕士生导师,主要研究方向为知识工程、信息系统与信息安全、人机交互,E-mail:zixiayedu@126.com
  • 作者简介:陈 俊(1992-),男,硕士生,主要研究方向为信息系统与图像处理等,E-mail:chanjha@foxmail.com
  • 基金资助:
    本文受产学研联合创新资金:基于物联网的智慧车间关键技术研究(BY2013003-06)资助。

Multi-target Localization Method Based on FAsT-Match Algorithm

CHEN Jun, ZHENG Hong-yuan   

  1. College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • Received:2017-07-05 Online:2018-09-20 Published:2018-10-10

摘要: FAsT-Match(Fast Affine Template Matching)算法很好地实现了二维仿射变换情况下的模板在连续图像中的快速、精准定位。该算法对光照变化不敏感,具有较强的鲁棒性,但是对于有多个目标的图像,只能定位到一个近似全局最优解。因此,首先对FAsT-Match算法进行改进,将通过对得到的仿射变换矩阵进行模糊c均值聚类而得到的目标区域作为新的目标图像,然后采用原始的FAsT-Match算法进行定位,最后将新目标位置返回到原始目标图像中。该方法弥补了FAsT-Match算法只能定位单目标的不足,应用到无线激光模拟射击系统中能够降低硬件成本,快速、精确地定位靶位目标。实验结果表明,该方法是有效的,可以在满足定位多个目标的需求的基础上实现多靶位定位,具有一定的实用价值。

关键词: FAsT-Match算法, 多靶位定位, 仿射变换, 激光模拟射击, 均值聚类

Abstract: FAsT-Match algorithm can realize the fast and accurate positioning ofthe template in a continuous image in the case of two-dimensional affine transformation.FAsT-Match algorithm is insensitive to light changes and has strong robustness.However,for images with multiple targets,only an approximate global optimal solution can be located.Therefore,the FAsT-Match algorithm was improved in this paper,and the target region obtained by fuzzy c-means clustering was used as the new target image,and then the original FAst-Match algorithm was used to locate the new target position and return to the original target image.This method can make up the shortcomings of only locating single target in FAsT-Match algorithm,reduce the hardware cost and locate target fast and accurately when it is applied in the wireless laser shooting system.The experimental results show that the method is effective and can meet the needs of positioning multiple targets,and has certain practical value.

Key words: Affine transformation, C-means clustering, FAsT-Match algorithm, Laser simulated shooting, Positioning multiple targets

中图分类号: 

  • TP391
[1]LIN Y G,HE X H,ZHANG S J.Real-time Multi-targets Tra-cking Based on Region Template Matching [J].Computer Simulation,2011,28(1):277-280.(in Chinese)
林月贡,何小海,张生军.基于区域模板匹配的多目标实时跟踪[J].计算机仿真,2011,28(1):277-280.
[2]XIN N F,QIAN Q C,PENG H D,et al.Design of automatic target-scoring system of shooting game based on computer vision[C]∥Proceedings of the IEEE International Conference on Automation and Logistics.Shenyang,China,2009.
[3]ALI F,MANSOOR A B.Computer vision based automatic scoring of shooting targets[C]∥Multitopic Conference,2008(INMIC 2008),IEEE International.IEEE,2008:515-519.
[4]LEE W C,CHEN C H.A fast template matching method for rotation invariance using two-stage process[C]∥Proceeding of IEEE Conference on Intelligent Information Hiding and Multimedia Signal Processing.Kyoto,Japan,2009:9-12.
[5]LV J,WANG B,GAO H M,et al.Separate of Multi objects in Image Recognition by Local Features[J].Acta Photonica Sinica,2008,37(8):1708-1712.(in Chinese)
吕冀,汪渤,高洪民,等.图像局部特征识别中的多目标分离[J].光子学报,2008,37(8):1708-1712.
[6]GAO W,ZHU M,HE B G,et al.Overview of target tracking technology[J].Chinese Optics,2014,7(3):366-375.(in Chinese)
高文,朱明,贺柏根,等.目标跟踪技术综述[J].中国光学,2014,7(3):366-375.
[7]KORMAN S,REICHMAN D,TSUR G,et al.FAsT-Match:
Fast Affine Template Matching [J].International Journal of Computer Vision,2017,121(1):111-125.
[8]LEI L,LI Z Y,SU Y.Multi-target Tracking Based on Fusion of ROI Feature Matching [J].Journal of Image and Graphics,2008,13(3):580-585.(in Chinese)
雷琳,李智勇,粟毅.基于ROI特征匹配融合的图像多目标跟踪算法[J].中国图象图形学报,2008,13(3):580-585.
[9]ZOU H,HUANG F Z.Infrared Image Segmentation for Electrical Equipment Based on FAsT-Match Algorithm[J].Infrared Technology,2016,38(1):21-27.(in Chinese)
邹辉,黄福珍.基于FAsT-Match算法的电力设备红外图像分割[J].红外技术,2016,38(1):21-27.
[10]冈萨,雷斯.数字图像处理(第二版)[M].北京:电子工业出版社,2007.
[11]ZHAO L L,GENG G H,LI K,et al.Images matching algorithm based on SURF and fast approximate nearest neighbor search[J].Application Research of Computers,2013,30(3):921-923.(in Chinese)
赵璐璐,耿国华,李康,等.基于SURF 和快速近似最近邻搜索的图像匹配算法[J].计算机应用研究,2013,30(3):921-923.
[12]HOU Y M,DI J M.Application of Improved Scale Invariant
Feature Transform Accurate Image Matching in Target Positioning of Electric Power Equipment[J].Proceedings of the CSEE,2012,32(10):134-139.(in Chinese)
侯一民,邸建铭.改进的尺度不变特征转换精确图像匹配在电力设备目标定位中的应用[J].中国电机工程学报,2012,32(10):134-139.
[13]LI G,FENG Y.Moving object detection based on SFT features matching and k-means clustering [J].Journal of Computer Applications,2012,32(10):2824-2826.(in Chinese)
李广,冯燕.基于SIFT特征匹配与K-均值聚类的运动目标检测[J].计算机应用,2012,32(10):2824-2826.
[1] 毛森林, 夏镇, 耿新宇, 陈剑辉, 蒋宏霞.
基于密度敏感距离和模糊划分的改进FCM算法
FCM Algorithm Based on Density Sensitive Distance and Fuzzy Partition
计算机科学, 2022, 49(6A): 285-290. https://doi.org/10.11896/jsjkx.210700042
[2] 胡士娟, 鲁海燕, 向蕾, 沈莞蔷.
求解MMTSP的模糊聚类单亲遗传算法
Fuzzy C-means Clustering Based Partheno-genetic Algorithm for Solving MMTSP
计算机科学, 2020, 47(6): 219-224. https://doi.org/10.11896/jsjkx.190500137
[3] 姚立霜, 刘丹, 裴作飞, 王云锋.
基于EMD聚类的实时网络流量预测模型
Real-time Network Traffic Prediction Model Based on EMD and Clustering
计算机科学, 2020, 47(11A): 316-320. https://doi.org/10.11896/jsjkx.200100085
[4] 雒僖, 范九伦, 于海燕, 梁丹.
基于阴影集的截集式可能性C-均值聚类截集门限的选取
Selection of Cutset Threshold for Cutset-type Possibilistic C-means Clustering Based on Shadowed Set
计算机科学, 2019, 46(8): 249-254. https://doi.org/10.11896/j.issn.1002-137X.2019.08.041
[5] 李鹏清, 李扬定, 邓雪莲, 李永钢, 方月.
一种基于SimRank得分的谱聚类算法
Spectral Clustering Algorithm Based on SimRank Score
计算机科学, 2018, 45(11A): 458-461.
[6] 贾娟娟, 贾富杰.
结合爬山法的模糊C均值彩色图像分割方法
Fuzzy C-means Color Image Segmentation Algorithm Combining Hill-climbing Algorithm
计算机科学, 2018, 45(11A): 247-250.
[7] 朱春,李林国,郭剑.
基于改进布谷鸟优化的模糊聚类图像分割
Fuzzy Clustering Image Segmentation Algorithm Based on Improved Cuckoo Search
计算机科学, 2017, 44(6): 278-282. https://doi.org/10.11896/j.issn.1002-137X.2017.06.049
[8] 耿艳萍,郭小英,王华夏,陈磊,李雪梅.
基于小波图像融合算法和改进FCM聚类的MR脑部图像分割算法
MR Brain Image Segmentation Method Based on Wavelet Transform Image Fusion Algorithm and Improved FCM Clustering
计算机科学, 2017, 44(12): 260-265. https://doi.org/10.11896/j.issn.1002-137X.2017.12.047
[9] 高曼,韩勇,陈戈,张小垒,李洁.
基于K-means聚类算法的公交行程速度计算模型
Computational Model of Average Travel Speed Based on K-means Algorithms
计算机科学, 2016, 43(Z6): 422-424. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.100
[10] 蒋泳森,肖泉,王守觉.
基于矢量方向特征的非参数动态背景建模
Non-parametric Dynamic Background Modeling Based on Direction Feature of Vector
计算机科学, 2016, 43(3): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2016.03.054
[11] 侯晓凡,吴成茂.
一种快速的模糊局部C-均值聚类分割算法
Fast Fuzzy Local Information C-means Clustering Segmentation Algorithm
计算机科学, 2016, 43(10): 297-303. https://doi.org/10.11896/j.issn.1002-137X.2016.10.056
[12] 吴杰,朱家明,陈静.
基于模糊聚类水平集的医学图像分割方法
Fuzzy Clustering Level Set Based Medical Image Segmentation Method
计算机科学, 2015, 42(Z11): 155-159.
[13] 张焕龙,郑卫东,舒云星,蒋 斌.
基于区域协方差矩阵和2DPCA学习的视频跟踪方法研究
Visual Object Tracking Algorithm Based on Region Covariance Matrix and 2DPCA Learning
计算机科学, 2015, 42(9): 278-281. https://doi.org/10.11896/j.issn.1002-137X.2015.09.054
[14] 岳昕,尚振宏,强振平,刘 辉,付晓东,张志华.
基于信息熵与SIFT算法的天文图像配准
Astronomical Image Registration Combining Information Entropy and SIFT Algorithm
计算机科学, 2015, 42(6): 57-60. https://doi.org/10.11896/j.issn.1002-137X.2015.06.013
[15] 李书玲,刘 蓉,刘 红.
改进型RBF神经网络的多标签算法研究
Multi-label Learning for Improved RBF Neural Networks
计算机科学, 2015, 42(4): 316-320. https://doi.org/10.11896/j.issn.1002-137X.2015.04.065
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!