Précédent|Prochain

Multisensor remote sensing registration method and system based on dense feature of orientated phase

  • role： First author第一作者
  • Affiliation：

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China

  • Email：yeyuanxin110@163.com
  • Introduction：叶沅鑫，研究方向为遥感图像处理与分析。E-mail： yeyuanxin110@163.com
YE Yuanxin,  
  • Affiliation：

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China

WANG Mengmeng,  
  • Affiliation：

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China

YANG Chao,  
  • Affiliation：

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China

YU Zhirui,  
  • Affiliation：

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, China

GE Xuming

résumé

To solve the problem of registration difficulty caused by considerable geometric distortion and gray differences between multisensor remote sensing images, this study proposes a fast and accurate registration method based on structural similarity between images. In this method, the phase congruency model with illumination and contrast invariances is introduced to construct robust structural feature descriptors of images. First, the intensity and orientation of phase congruency are used to build a pixel-wise three-dimensional structural feature representation named Dense Feature of Orientated Phase (DFOP), which can effectively resist the grayscale difference between multisensor images by capturing geometric structures of images. Next, the DFOP feature descriptor is transformed into the frequency domain, and the single-step DFT approach is used to achieve fast matching with subpixel accuracy by employing a template matching scheme. In addition, a fast and robust automatic multisensor remote sensing image registration system is developed on the basis of the proposed DFOP. Finally, the proposed method and registration system is validated using multiple pairs of multisensor remote sensing images (including optical, LIDAR, and SAR) covering different scenes. Results show that the proposed DFOP achieves higher correct matching rate, and the developed registration system outperforms the registration module of ENVI and ERDAS in registration accuracy. Our system is available at https://github.com/yeyuanxin110/Remote-Sensing-Image-Registration-system.git

mots-clés

multi-sensor remote sensing images;image registration;phase congruency;dense feature of orientated phase;images registration system

References

  1. 1.
    Bruzzone L and Bovolo F. 2013. A novel framework for the design of change-detection systems for very-high-resolution remote sensing images. Proceedings of the IEEE, 101(3): 609-630
  2. 2.
    Dellinger F, Delon J, Gousseau Y, Michel J and Tupin F. 2015. SAR-SIFT: a SIFT-like algorithm for SAR images. IEEE Transactions on Geoscience and Remote Sensing, 53(1): 453-466
  3. 3.
    Feng R T, Shen H F, Bai J J and Li X H. 2021. Advances and opportunities in remote sensing image geometric registration: a systematic review of state-of-the-art approaches and future research directions. IEEE Geoscience and Remote Sensing Magazine, 9(4): 120-142
  4. 4.
    Fischler M A and Bolles R C. 1987. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography//Fischler M A and Firschein O, eds. Readings in Computer Vision. San Francisco: Morgan Kaufmann: 726-740
  5. 5.
    Foroosh H, Zerubia J B and Berthod M. 2002. Extension of phase correlation to subpixel registration. IEEE Transactions on Image Processing, 11(3): 188-200
  6. 6.
    Goncalves H, Corte-Real L and Goncalves J A. 2011. Automatic image registration through image segmentation and SIFT. IEEE Transactions on Geoscience and Remote Sensing, 49(7): 2589-2600
  7. 7.
    Grodecki J and Dial G. 2003. Block adjustment of high-resolution satellite images described by rational polynomials. Photogrammetric Engineering and Remote Sensing, 69(1): 59-68
  8. 8.
    Guizar-Sicairos M, Thurman S T and Fienup J R. 2008. Efficient subpixel image registration algorithms. Optics Letters, 33(2): 156-158
  9. 9.
    Hisham M B, Yaakob S N, Raof R A A, Nazren A B A and Wafi N M. 2015. Template matching using sum of squared difference and normalized cross correlation//2015 IEEE Student Conference on Research and Development (SCOReD). Kuala Lumpur: IEEE: 100-104
  10. 10.
    Huo C L, Pan C H, Huo L G and Zhou Z X. 2012. Multilevel SIFT matching for large-size VHR image registration. IEEE Geoscience and Remote Sensing Letters, 9(2): 171-175
  11. 11.
    Kovesi P. 1999. Image features from phase congruency. Journal of Computer Vision Research, 1(3): 1-26
  12. 12.
    Lan C Z, Lu W J, Yu J M and Xu Q. 2021. Deep learning algorithm for feature matching of cross modality remote sensing images. Acta Geodaetica et Cartographica Sinica, 50(2): 189-202
  13. 13.
    Li X H, Hui N, Shen H F, Fu Y J and Zhang L P. 2015. A robust mosaicking procedure for high spatial resolution remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 109: 108-125
  14. 14.
    Li Z H and Leung H. 2007. Contour-based multisensor image registration with rigid transformation//2007 10th International Conference on Information Fusion. Quebec: IEEE: 1-7
  15. 15.
    Lowe D G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2): 91-110
  16. 16.
    Lu J Z, Hu M Q, Dong J, Han S L and Su A. 2020. A novel dense descriptor based on structure tensor voting for multi-modal image matching. Chinese Journal of Aeronautics, 33(9): 2408-2419
  17. 17.
    Martinez A, Garcia-Consuegra J and Abad F. 1999. A correlation-symbolic approach to automatic remotely sensed image rectification//IEEE 1999 International Geoscience and Remote Sensing Symposium. Hamburg: IEEE: 336-338
  18. 18.
    Nan K, Qi H and Ye Y X. 2019. A template matching method of multimodal remote sensing images based on deep convolutional feature representation. Acta Geodaetica et Cartographica Sinica, 48(6): 727-736
  19. 19.
    Rosten E and Drummond T. 2006. Machine learning for high-speed corner detection//9th European Conference on Computer Vision. Graz: Springer: 430-443
  20. 20.
    Schmitt M, Tupin F and Zhu X X. 2017. Fusion of SAR and optical remote sensing data — challenges and recent trends//2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth: IEEE: 5458-5461
  21. 21.
    Suri S and Reinartz P. 2010. Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas. IEEE Transactions on Geoscience and Remote Sensing, 48(2): 939-949
  22. 22.
    Wang M M, Ye Y X, Zhu B and Zhang G. 2022. An automatic registration method for optical and SAR images based on spatial constraint and structure features. Geomatics and Information Science of Wuhan University, 47(1): 141-148
  23. 23.
    Xiang Y M, Wang F and You H J. 2018. OS-SIFT: a robust SIFT-like algorithm for high-resolution optical-to-SAR image registration in suburban areas. IEEE Transactions on Geoscience and Remote Sensing, 56(6): 3078-3090
  24. 24.
    Ye Y X, Bruzzone L, Shan J, Bovolo F and Zhu Q. 2019. Fast and robust matching for multimodal remote sensing image registration. IEEE Transactions on Geoscience and Remote Sensing, 57(11): 9059-9070
  25. 25.
    Ye Y X, Shan J, Bruzzone L and Shen L. 2017. Robust registration of multimodal remote sensing images based on structural similarity. IEEE Transactions on Geoscience and Remote Sensing, 55(5): 2941-2958
  26. 26.
    Zheng Y, Cao Z G and Xiao Y. 2008. Multi-spectral remote image registration based on SIFT. Electronics Letters, 44(2): 107-108
  27. 27.
    Zhu H, Jiao L C, Ma W P, Liu F and Zhao W. 2019. A novel neural network for remote sensing image matching. IEEE Transactions on Neural Networks and Learning Systems, 30(9): 2853-2865
  28. 28.
    Zitová B and Flusser J. 2003. Image registration methods: a survey. Image and Vision Computing, 21(11): 977-1000

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website