Infrared and Visible Image Registration Algorithm Based on Edge Structure Features
-
摘要: 针对红外与可见光图像难以提取特征点实现配准的问题，提出一种基于边缘结构特征的红外与可见光图像配准算法。首先通过优化的显著性算法增强红外图像的结构特征；其次利用相位一致性提取红外和可见光图像的稳定边缘结构；然后提取边缘结构的ORB（oriented FAST and rotated BRIEF）特征点；最后结合KNN（K-nearest neighbor）算法和余弦相似度对匹配特征点进行筛选，并应用RANSAC（random sample consensus）算法进行提纯。实验表明，该算法能够克服灰度差异的影响，具有较高的配准精度和效率，有助于实现红外与可见光图像的配准。Abstract: Here, a registration algorithm based on edge structure features is proposed to solve the difficulty of extracting feature points from infrared and visible images. First, the structural features of infrared images are enhanced using an optimized saliency algorithm. Second, we extract the stable edge structures of the infrared and visible images using a phase consistency algorithm. Further, the ORB feature points are extracted from the edge structures. Finally, the KNN algorithm and cosine similarity are combined to filter the matching feature points, and the random sample consensus (RANSAC) algorithm is used for purification. Experimental results show that the algorithm overcomes the influence of grayscale differences between infrared and visible images. In addition, it achieves a high registration accuracy and efficiency, which is conducive to the registration of infrared and visible images.
-
Keywords:
- saliency detection /
- phase consistency /
- feature extraction /
- image registration
-
-
表 1 不同算法效果对比
Table 1 Comparison of effects of different algorithms
Scene Algorithm Registration/(%) Time/s 1 MI 53.1 7.73 ORB 25.8 1.43 This paper 92.5 1.68 2 MI 42.2 17.04 ORB 16.7 1.25 This paper 90.1 1.92 
下载: 导出CSV
-
[1] CHEN Yanjia. Visible and infrared image registration based on region features and edginess[J]. Machine Vision and Applications, 2018, 29(1): 113-123. DOI: 10.1007/s00138-017-0879-6
[2] ZENG Qiang. Real-time adaptive visible and infrared image registration based on morphological gradient and C_SIFT[J]. Journal of Real-Time Image Processing, 2019: 1-13.
[3] CHEN S, LI X, ZHAO L, et al. Medium-low resolution multisource remote sensing image registration based on SIFT and robust regional mutual information[J]. International Journal of Remote Sensing, 2018, 39(10): 3215-3242. DOI: 10.1080/01431161.2018.1437295
[4] XU W, ZHONG S, YAN L, et al. Moving object detection in aerial infrared images with registration accuracy prediction and feature points selection[J]. Infrared Physics & Technology, 2018, 92: 318-26.
[5] 张莉, 李彬, 田联房, 等. 基于局部结构张量-互信息的多模态图像配准[J]. 华南理工大学学报: 自然科学版, 2017, 45(7): 98-106. https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG201707014.htm ZHANG Li, LI Bin, TIAN Lianfang, et al. Multi-modal image registration on the basis of local structure tensor-mutual information[J]. Journal of South China University of Technology: Natural Science Edition, 2017, 45(7): 98-106. https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG201707014.htm
[6] 吴延海, 张程, 张烨. 基于梯度信息和区域互信息的图像配准[J]. 广西大学学报: 自然科学版, 2017, 42(2): 720-727. https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ201702040.htm WU Yanhai, ZHANG Cheng, ZHANG Ye. Image registration based on gradient and regional mutual information[J]. Journal of Guangxi University: Natural Science Edition, 2017, 42(2): 720-727. https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ201702040.htm
[7] XIANG Y, WANG F, YOU H. OS-SIFT: a robust SIFT-like algorithm for high-resolution optical-to-SAR image registration in suburban areas[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(6): 3078-3090. DOI: 10.1109/TGRS.2018.2790483
[8] 张晨光, 周诠, 回征. 基于SIFT特征点检测的低复杂度图像配准算法[J]. 扬州大学学报: 自然科学版, 2018, 21(4): 52-56. https://www.cnki.com.cn/Article/CJFDTOTAL-YZDZ201804012.htm ZHANG Chenguang, ZHOU Quan, HUI Zheng. A low-complexity image registration approach based on SIFT[J]. Journal of Yangzhou University: Nature Science Edition, 2018, 21(4): 52-56. https://www.cnki.com.cn/Article/CJFDTOTAL-YZDZ201804012.htm
[9] SHENG H. Medical image registration method based on tensor voting and Harris corner point detection[J]. Journal of Medical Imaging and Health Informatics, 2018, 8(3): 583-589. DOI: 10.1166/jmihi.2018.2322
[10] MENG Z. Image registration method based on optimized SURF algorithm[J]. American Journal of Optics and Photonics, 2019, 7(4): 63-69. DOI: 10.11648/j.ajop.20190704.11
[11] Morrone M Concetta, Ross John, Burr David C, et al. Mach bands are phase dependent[J]. Nature, 1986, 324: 250-253. DOI: 10.1038/324250a0
[12] LV L T, YUAN Q Q, LI Z X. An algorithm of iris feature-extracting based on 2D log-gabor[J]. Multi-media Tools and Applications, 2019, 78(16): 22643-22666. DOI: 10.1007/s11042-019-7551-2
[13] Ethan Rublee, Vincent Rabaud, Kurt Konolige, et al. ORB: an efficient alternative to SIFT or SURF[C]//Proceedings of IEEE International Conference on Computer Vision, 2011: 2564-2571.
计量
- 文章访问数: 167
- HTML全文浏览量: 48
- PDF下载量: 52
