基于显著性和ORB的红外和可见光图像配准算法
|
摘要
针对红外与可见光图像配准过程过受灰度差异影响大、特征点难配准的问题,提出基于显著性检测和ORB特征点的图像配准算法。首先利用优化的HC-GHS显著性检测算法得到图像的显著性结构图;其次利用ORB算法在显著性结构图上进行特征点检测,利用泰勒级数筛选出鲁棒性强的特征点,并根据特征点的方向进行分组匹配的策略;最后利用汉明距离实现特征点的匹配。实验表明本文算法能准确实现红外与可见光图像之间的配准,在红外噪声干扰、尺度变化下都具有良好效果。
Aiming at the problem that the registration process of infrared and visible images is greatly affected by the difference of gray level and the registration of feature points is difficult,an image registration algorithm based on saliency detection and ORB feature points is proposed. Firstly,the optimized HC-GHS saliency detection algorithm is used to obtain the saliency map of the image. Secondly,ORB algorithm was used to detect the feature points on the saliency map,and the robust feature points were screened by Taylor series,and the grouping matching strategy was carried out according to the direction of feature points. Finally,hamming distance is used to match the feature points. Experiments show that the proposed algorithm can achieve the registration between the infrared and visible images accurately,and it has good effect under the infrared noise interference and scale changes.
Aiming at the problem that the registration process of infrared and visible images is greatly affected by the difference of gray level and the registration of feature points is difficult,an image registration algorithm based on saliency detection and ORB feature points is proposed. Firstly,the optimized HC-GHS saliency detection algorithm is used to obtain the saliency map of the image. Secondly,ORB algorithm was used to detect the feature points on the saliency map,and the robust feature points were screened by Taylor series,and the grouping matching strategy was carried out according to the direction of feature points. Finally,hamming distance is used to match the feature points. Experiments show that the proposed algorithm can achieve the registration between the infrared and visible images accurately,and it has good effect under the infrared noise interference and scale changes.
引文
[1] Yuan Jinsha,Zhao Zhenbing,Gao Qiang. Current statusand prospects of infrared and visible image registration research[J].Laser & Infrared,2009,39(7):693-699.(in Chinese)苑津莎,赵振兵,高强.红外与可见光图像配准研究现状与展望[J].激光与红外,2009,39(7):693-699.
[2] Dong Xiaojie,Liu Erqi,Yang Jie,Wu Qiang.Visible and infrared automatic image registration based on SLER[J].Journal of Infrared and Millimeter Waves,2014,33(1):90-97.
[3] Shan-e-Ahmed Raze,Victor Sanchez,Gillian Prince.et al.Registration of thermal and visible light images if diseased plants using silhouette extraction in the wavelet domain[J].Pattern Registration,2015,48:2119-2129.
[4] Chaoqing Tang,GuiYun Tian,Xiaotian Chen,et al.Infrared and visible images registration with adaptable local-global feature integration for rail inspection[J].Infrared Physics & Technology,2017,(87):31-39.
[5] Hu Yongli,Wang Liang,Liu Rong,et al.A Method of Infrared and Visible Satellite Image Registration from Rough to Fine[J].Spectroscopy and Spectral Analysis,2013,33(11):2968.(in Chinese)胡永利,王亮,刘蓉,等.一种从粗到精的红外和可见光卫星图像配准方法[J].光谱学与光谱分析,2013,33(11):2968-2972.
[6] Bai Lianfa,Han Jing,Zhang Yi,et al. Infrared and visible light image registration algorithm using improved gradient mutual information and particle swarm optimization algorithm[J].Infrared and Laser Engineering,2012,41(01):248-254.(in Chinese)柏连发,韩静,张毅,等.采用改进梯度互信息和粒子群优化算法的红外与可见光图像配准算法[J].红外与激光工程,2012,41(01):248-254.
[7] Dellinger F,Delin J,Cousseau Y,et al.SAR-SIFT:a SIFT-like algorithm for SAR images[J] IEEE Transactions on Geoscience and Remote Densing.2015,53(1):453-466.
[8] Wang Wei,Wei Ming. Visible-infrared image registration for adaptive feature point detection[J].Journal of Image and Graphics,2017,22(2):179-187.(in Chinese)王晗,魏明.自适应特征点检测的可见—红外图像配准[J].中国图象图形学报,2017,22(2):179-187.
[9] Gao Jing,Wu Yufeng,Wu Kun,et al. Image Matching Algorithm Based on Corner Detection[J]. Chinese Journal of Scientific Instrument,2013,34(8):1717-1725.(in Chinese)高晶,吴育峰,吴昆,等.基于角点检测的图像匹配算法[J].仪器仪表学报,2013,34(8):1717-1725.
[10] LIU Chang,CUI Tong,HE Chenglong,et al.Infrared Visible Image Registration Based on Feature Matching with High Curvature[J].Command Information System and Technology,2016,7(1):13-17.(in Chinese)刘畅,崔桐,贺成龙,等.基于高曲率特征点匹配的红外可见光图像配准[J].指挥信息系统与技术,2016,7(1):13-17.
[11] Xu Jun,Fu Tianyu,Yang Jian,et al. Infrared and visible light image registration using salient analysis andimproved edge direction histogram features[J].Optics and Precision Engineering,2016,24(11):2830- 2840.(in Chinese)徐军,付天宇,杨健,等.采用显著性分析与改进边缘方向直方图特征的红外与可见光图像配准[J].光学精密工程,2016,24(11):2830-2840.
[12] Xiaodi Hou,Liqing Zhang.Saliency Detection:A Spectral Residual Approach[C].Computer Vision and Pattern Recognition,2007:1-8.
[13] ZHOU Wei,XIN Yun-hong. Infrared dim target detection based on saliency and scale space[J].Laser & Infrared,2015,45(4):452-456.(in Chinese)周姣,辛云宏.基于显著性与尺度空间的红外弱小目标检测[J].激光与红外,2015,45(4):452-456.
[14] Cheng,Ming Ming,et al.Global contrast based salient region detection[C].Computer Vision and Pattern Recognition IEEE,2011:409-416.
[15] ZHAO Wenda,ZHENG Zhijun,ZHAO Jian,et al.Enhanced details of infrared images basedon gradient histogram transformation[J].Optical Precision Engineering,2014,22(7):1962-1968.(in Chinese)赵文达,续志军,赵建,等.基于梯度直方图变换增强红外图像的细节[J].光学精密工程,2014,22(7):1962-1968.
[16] Rublee,E.,Rabaud,V.,Konolige,K et al.ORB:An effi-cient alternative to SIFT or SURF.Proceedings of 2011 IEEEInternational Conference on Computer Vision.2011.
[17] CHEN Liang,ZHOU Mengzhe,CHEN He. An Image Registration Method Combining Edge Region and Cross Correlation[J]. Journal of Beijing Institute of Technology,2016,36(3):320-325.(in Chinese)陈亮,周孟哲,陈禾.一种结合边缘区域和互相关的图像配准方法[J].北京理工大学学报,2016,36(3):320-325.
[2] Dong Xiaojie,Liu Erqi,Yang Jie,Wu Qiang.Visible and infrared automatic image registration based on SLER[J].Journal of Infrared and Millimeter Waves,2014,33(1):90-97.
[3] Shan-e-Ahmed Raze,Victor Sanchez,Gillian Prince.et al.Registration of thermal and visible light images if diseased plants using silhouette extraction in the wavelet domain[J].Pattern Registration,2015,48:2119-2129.
[4] Chaoqing Tang,GuiYun Tian,Xiaotian Chen,et al.Infrared and visible images registration with adaptable local-global feature integration for rail inspection[J].Infrared Physics & Technology,2017,(87):31-39.
[5] Hu Yongli,Wang Liang,Liu Rong,et al.A Method of Infrared and Visible Satellite Image Registration from Rough to Fine[J].Spectroscopy and Spectral Analysis,2013,33(11):2968.(in Chinese)胡永利,王亮,刘蓉,等.一种从粗到精的红外和可见光卫星图像配准方法[J].光谱学与光谱分析,2013,33(11):2968-2972.
[6] Bai Lianfa,Han Jing,Zhang Yi,et al. Infrared and visible light image registration algorithm using improved gradient mutual information and particle swarm optimization algorithm[J].Infrared and Laser Engineering,2012,41(01):248-254.(in Chinese)柏连发,韩静,张毅,等.采用改进梯度互信息和粒子群优化算法的红外与可见光图像配准算法[J].红外与激光工程,2012,41(01):248-254.
[7] Dellinger F,Delin J,Cousseau Y,et al.SAR-SIFT:a SIFT-like algorithm for SAR images[J] IEEE Transactions on Geoscience and Remote Densing.2015,53(1):453-466.
[8] Wang Wei,Wei Ming. Visible-infrared image registration for adaptive feature point detection[J].Journal of Image and Graphics,2017,22(2):179-187.(in Chinese)王晗,魏明.自适应特征点检测的可见—红外图像配准[J].中国图象图形学报,2017,22(2):179-187.
[9] Gao Jing,Wu Yufeng,Wu Kun,et al. Image Matching Algorithm Based on Corner Detection[J]. Chinese Journal of Scientific Instrument,2013,34(8):1717-1725.(in Chinese)高晶,吴育峰,吴昆,等.基于角点检测的图像匹配算法[J].仪器仪表学报,2013,34(8):1717-1725.
[10] LIU Chang,CUI Tong,HE Chenglong,et al.Infrared Visible Image Registration Based on Feature Matching with High Curvature[J].Command Information System and Technology,2016,7(1):13-17.(in Chinese)刘畅,崔桐,贺成龙,等.基于高曲率特征点匹配的红外可见光图像配准[J].指挥信息系统与技术,2016,7(1):13-17.
[11] Xu Jun,Fu Tianyu,Yang Jian,et al. Infrared and visible light image registration using salient analysis andimproved edge direction histogram features[J].Optics and Precision Engineering,2016,24(11):2830- 2840.(in Chinese)徐军,付天宇,杨健,等.采用显著性分析与改进边缘方向直方图特征的红外与可见光图像配准[J].光学精密工程,2016,24(11):2830-2840.
[12] Xiaodi Hou,Liqing Zhang.Saliency Detection:A Spectral Residual Approach[C].Computer Vision and Pattern Recognition,2007:1-8.
[13] ZHOU Wei,XIN Yun-hong. Infrared dim target detection based on saliency and scale space[J].Laser & Infrared,2015,45(4):452-456.(in Chinese)周姣,辛云宏.基于显著性与尺度空间的红外弱小目标检测[J].激光与红外,2015,45(4):452-456.
[14] Cheng,Ming Ming,et al.Global contrast based salient region detection[C].Computer Vision and Pattern Recognition IEEE,2011:409-416.
[15] ZHAO Wenda,ZHENG Zhijun,ZHAO Jian,et al.Enhanced details of infrared images basedon gradient histogram transformation[J].Optical Precision Engineering,2014,22(7):1962-1968.(in Chinese)赵文达,续志军,赵建,等.基于梯度直方图变换增强红外图像的细节[J].光学精密工程,2014,22(7):1962-1968.
[16] Rublee,E.,Rabaud,V.,Konolige,K et al.ORB:An effi-cient alternative to SIFT or SURF.Proceedings of 2011 IEEEInternational Conference on Computer Vision.2011.
[17] CHEN Liang,ZHOU Mengzhe,CHEN He. An Image Registration Method Combining Edge Region and Cross Correlation[J]. Journal of Beijing Institute of Technology,2016,36(3):320-325.(in Chinese)陈亮,周孟哲,陈禾.一种结合边缘区域和互相关的图像配准方法[J].北京理工大学学报,2016,36(3):320-325.