نوع مقاله : علمی - پژوهشی
نویسندگان
1 کارشناس ارشد گروه مهندسی برق، واحد سیرجان، دانشگاه آزاد اسلامی، سیرجان
2 استادیار باشگاه پژوهشگران جوان و نخبگان، واحد خمینیشهر، دانشگاه آزاد اسلامی اصفهان
چکیده
فرایند انطباق تصویر یکی از شاخههای مهم در زمینة پردازش تصویر است که پیشپردازشی ضروری، جهت استفاده از اطلاعات تصاویر چندسنجندة سنجش از دوری محسوب میشود. الگوریتم تبدیل ویژگی مقیاس ثابت(SIFT) از رایجترین روشهای مبتنیبر ویژگی است که بهطور گسترده، برای انطباق این تصاویر استفاده میشود. یکی از مهمترین نقاط ضعف این الگوریتم ایجاد تناظرهای نادرست بسیار زیاد است. در این مقاله، بهمنظور افزایش دقت انطباق تصویر چندسنجندة سنجش از دوری، روش جدیدی براساس روابط فضایی نقاط متناظر SIFT پیشنهاد شده است که تناظرهای نادرست را به تناظرهای درست تبدیل میکند. در ابتدا، مشخصکردن نقاط کلیدی و تناظریابی اولیه، با استفاده از الگوریتم SIFT، انجام میشود. سپس، با استفاده از روش پیشنهادی مبتنیبر تبدیل افاین، تناظرهای نادرست اصلاح و فرایند انطباق صورت میگیرد. نوآوری دیگرِ مقاله پیشنهادِ دو معیار جدید برای ارزیابی کارآیی روشهای انطباق تصویر، علاوهبر معیارهای کلاسیک دقت تناظریابی، نرخ تکرارپذیری ویژگی و تعداد تناظرهای درست است که بیان میکند، بهدلیل ضعف معیارهای کلاسیک، تعداد کل تناظرها را در نظر نمیگیرند. نتایج شبیهسازی نشان میدهد روش پیشنهادی مقاله باعث بهبود میانگین 48/11 درصدی در نرخ تکرارپذیری و میانگین 20/14 درصدی ضریب همبستگی در مقایسه با روش رانساک شده و این روش پیشنهادی میتواند بهمنزلة روشی جدید و کارآ در بهبود تناظریابی این تصاویر بهکار رود.
کلیدواژهها
عنوان مقاله [English]
A New Method in Image Matching Based on Spatial Relationships in Multi-Sensor Remote Sensing Images
نویسندگان [English]
- Z Hossein-Nejad 1
- M Nasri 2
1 M.Sc. of Electrical Engineering department, Sirjan branch, Islamic Azad University, Sirjan
2 Assistant Prof. of Young Researchers and Elite Club, Khomeinishahr Branch, Islamic Azad University, Khomeinishahr, Isfahan
چکیده [English]
Image registration process is one of the most important branches in the field of image processing, which is an essential preprocessing for the use of remote sensing. Scale invariant feature transform (SIFT) is one of the most commonly used feature-based methods for registration of images. However, a main weakness of this algorithm is the creation of a large number of mismatches. Based on the spatial relationships of the corresponding points of SIFT, the proposed method in this paper increases the accuracy of image registration in multi-sensor remote sensing images, changing mismatches into correct matches. Initially, key points matching is performed using the SIFT algorithm. Then, using the proposed affine-transformation-based approach, the mismatches are corrected and matching is done. Another novelty of the paper is suggesting two new criteria for assessing the efficiency of image matching methods in addition to the classical criteria of matching precision. As a weakness of the classical criteria that do not consider the total number of matches, feature repeatability rate and the number of correct matches are not defined efficiently. Simulation results show that the proposed method improves the rate of repeatability by 11.41% and cross- correlation coefficient by 14.20% on the average compared to the RANSAC method. Therefore, the proposed method can be used as a new and effective way of improving image matching.
کلیدواژهها [English]
- Image registration
- Matching
- Affine Transform
- Multi-Sensor Remote-Sensing Image
- صداقت، ا.، عبادی، ح.، مختارزاده، م.، 1389، بهبود الگوریتم SIFT بهمنظور تناظریابی تصاویر ماهوارهای، سنجش از دور و GIS ایران، سال دوم، شمارة 4، صص. 100-83.
- فلاح یخدانی، م.، عزیزی، ع.، 1390، هممرجعنمودن تصاویر ماهوارهای IRS-P6 وIRS-P5 براساس الگوریتم SIFT، همایش ژئوماتیک 90، دورة اول, شمارة 2، صص. 78-67.
- Belongie, S., Malik, J. & Puzicha, J., 2002, Shape Matching and Object Recognition Using Shape Contexts, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, PP. 509-522.
- Fischler, M.A. & Bolles, R.C., 1981, Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Commu-nications of the ACM, 24, PP. 381-395.
- Hasan, M., Jia, X., Robles-Kelly, A., Zhou, J.R. & Pickering, M., 2010, Multi-Spectral Remote Sensing Image Registration via Spatial Relationship Analysis on Sift Keypoints, in Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International, PP. 1011-1014.
- Hossein-Nejad, Z. & Nasri, M., 2017, RKEM: Redundant Keypoint Elimination Method in Image Registration, IET Image Processing, 11, PP. 273-284.
- Hossein-Nejad ., Z. & Nasri, M., 2016, Image Registration Method Based on SIFT Features and Adaptive RANSAC Transform, Communication and Signal Processing (ICCSP), 2016 International Conference, PP.1087-1091.
- Hsu C.-T. & Beuker, R.A., 2000, Multiresolution Feature-Based Image Registration, in Visual Communications and Image Processing, PP. 1490-1498.
- Jagadish, H. & Prakash, J., 2017, Adaptive Markov Random Field Model for Area Based Image Registration and Change Detection, International Journal of Application or Innovation in Engineering & Management (IJAIEM), 6, PP. 50-58.
- Kupfer, B., Netanyahu, N.S. & Shimshoni, I., 2015, An Efficient SIFT-Based Mode-Seeking Algorithm for Sub-Pixel Registration of Remotely Sensed Images, Geoscience and Remote Sensing Letters, IEEE, 12, PP. 379-383.
- Kim, Y.S., Lee. J. H., & Ra, J. B., 2008, Multi-sensor image registration based on intensity and edge orientation information, Pattern recognition, Vol. 41, No.11, PP. 3356-3365.
- Liu, Z., An, J. & Jing, Y., 2012, A Simple and Robust Feature Point Matching Algorithm Based on Restricted Spatial Order Constraints for Aerial Image Registration, Geoscience and Remote Sensing, IEEE Transactions on, 50, PP. 514-527.
- Li, Q., Zhang, H. & Wang, T., 2011, Multispectral Image Matching Using Rotation-Invariant Distance, Geoscience and Remote Sensing Letters, IEEE, 8, PP. 406-410.
- Li, D. & Zhang, Y., 2012, A Novel Approach for the Registration of Weak Affine Images, Pattern Recognition Letters, 33, PP. 1647-1655.
- Lingua, A., Marenchino, D. & Nex, F., 2009, Performance Analysis of the SIFT Operator for Automatic Feature Extraction and Matching in Photogrammetric Applications, Sensors, 9, PP. 3745-3766.
- Lowe, D.G., 1999, Object Recognition from Local Scale-Invariant Features, in Computer Vision, 1999, The Proceedings of the Seventh IEEE International Conference on, PP. 1150-1157.
- Lowe, D.G., 2004, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, 60, PP. 91-110.
- Ma, K., Wen, Z., Wu, Y., Jiao, L., Gong, M. & Zheng, Y., 2017, Remote Sensing Image Registration With Modified SIFT and Enhanced Feature Matching, IEEE Geoscience and Remote Sensing Letters, 14, PP. 3-7.
- Mikolajczyk, K. & Schmid, C., 2002, An Affine Invariant Interest Point Detector, in Computer Vision—ECCV 2002, ed: Springer, PP. 128-142.
- Mikolajczyk, K., & Schmid, C., 2004, Scale & Affine Invariant Interest Point Detectors, International Journal of Computer Vision, Vol. 60, PP. 63-86.
- Mikolajczyk, K. & Schmid, C., 2005, A Performance Evaluation of Local Descriptors, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 27, no. 10, PP. 1615–1630.
- Moigne, J.Le., Netanyahu, N.S. & Eastman, R.D., 2011, Image Registration for Remote Sensing, Cambridge University Press.
- Moreno, P., Bernardino, A. & Santos-Victor, J., 2009, Improving the SIFT Descriptor with Smooth Derivative Filters, Pattern Recognition Letters, 30, PP. 18-26.
- Murphy, J.M., Moigne, J.Le. & Harding, D.J., 2016, Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features, IEEE Transactions on Geoscience and Remote Sensing, 54, PP. 1685-1704.
- Sedaghat, A., Mokhtarzade, M. & Ebadi, H., 2011, Uniform Robust Scale-Invariant Feature Matching for Optical Remote Sensing Images, Geoscience and Remote Sensing, IEEE Transactions, 49, PP. 4516-4527.
- Sedaghat, A. & Ebadi, H., 2015, Remote Sensing Image Matching Based on Adaptive Binning SIFT Descriptor, Geoscience and Remote Sensing, IEEE Transactions, 53, PP. 5283-5293.
- Song, Z., Zhou, S. & Guan, J., 2014, A Novel Image Registration Algorithm for Remote Sensing under Affine Transformation, Geoscience and Remote Sensing, IEEE Transactions, 52, PP. 4895-4912.
- Yang, X., Pei, J. & Sun, W., 2013, Elastic Image Registration Using Hierarchical Spatially Based Mean Shift, Computers in Biology and Medicine, 43, PP. 1086-1097.
- Wang, X. & Fu, W., 2008, Optimized SIFT Image Matching Algorithm, in Automation and Logistics, ICAL 2008, IEEE International Conference, PP. 843-847.
- Xu, P., Zhang, L., Yang, K. & Yao, H., 2013, Nested-SIFT for Efficient Image Matching and Retrieval, IEEE MultiMedia, 20, PP. 34-46.
- Ye, Y. & Shan, J., 2014, A Local Descriptor Based Registration Method for Multispectral Remote Sensing Images with Non-linear Intensity Differences, ISPRS Journal of Photogrammetry and Remote Sensing, 90, PP. 83-95,.
- Yi, Z., Zhiguo, C. & Yang, X., 2008, Multi-Spectral Remote Image Registration Based on SIFT, Electronics Letters, 44, PP. 1-2.
- Zhang, Q., Wang, L., Li, H. & Ma, Z., 2011, Similarity-Based Multimodality Image Fusion with Shiftable Complex Directional Pyramid, Pattern Recognition Letters, 32, PP. 1544-1553.
- Zitova, B. & Flusser, J., 2003, Image Registration Methods: A Survey, Image and Vision Computing, 21, PP. 977-1000.
- Zhang, R., Zhou, W., Li, Y., Yu, S. & Xie, Y., 2013, Nonrigid Registration of Lung CT Images Based on Tissue Features, Computational and Mathematical Methods in Medicine.
- Zhang, Q., Wang, Y. & Wang, L., 2015, Registration of Images with Affine Geometric Distortion Based on Maximally Stable External Regions and Phase Congruency, Image and Vision Computing, 36, PP. 23-39.