OS-PSO: A Modified Ratio of Exponentially Weighted Averages-Based Optical and SAR Image Registration
Abstract
:1. Introduction
- We propose a novel optical and SAR image registration approach based on the OS-SIFT. A modified ratio of exponentially weighted averages (MROEWA) operator is designed for the gradient computation of SAR images, aiming to eliminate the problem of the sharp increase in the gradient magnitude at edge points due to sudden dark patches, so that the gradient distributions of SAR images are more consistent with the gradient distributions of optical images computed using the multiscale Sobel operator.
- An enhanced matching method is introduced that defines a novel matching distance based on the scale, position, and main orientation of the key-points for more accurate correspondences.
- We construct an optical and SAR image dataset named BISTU-OPT-SAR and validate the different performances of the OS-PSO algorithm in Sentinel and Gaofen images in combination with the public WHU-OPT-SAR dataset [29]. Furthermore, the performance of the OS-PSO algorithm in different scenarios, such as urban, suburban, river, farmland, and lake, is thoroughly discussed and analyzed.
2. Related Works
2.1. Gradient Computation
2.2. Key-Point Detection
2.3. Descriptor Extraction
2.4. Key-Point Matching
3. The Proposed Registration Framework
3.1. MROEWA Operator
3.2. Enhanced Feature Matching
4. Experimental Results and Discussion
4.1. Description of the Datasets and Parameter Settings
4.2. Evaluation Criteria
4.3. Experiments on Key-Point Detection
4.4. Experiments on Enhanced Matching
4.5. Discussion on the Robustness of Geometric Differences
4.6. Comparative Experiments in Different Scenarios
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Wu, Y.; Hei, G.; Teng, D.; Wan, Q.; Zhao, Y.; Chen, M.; Xia, Y.; Jiang, M.; Li, S. Optical image and SAR image registration based on position constraint. In Proceedings of the Fourth International Conference on Geology, Mapping, and Remote Sensing (ICGMRS 2023), Wuhan, China, 14–16 April 2023; SPIE: Bellingham, WA, USA, 2024; pp. 347–352. [Google Scholar]
- Guillet, J.P.; Recur, B.; Frederique, L.; Bousquet, B.; Canioni, L.; Manek-Hönninger, I.; Desbarats, P.; Mounaix, P. Review of terahertz tomography techniques. J. Infrared Millim. Terahertz Waves 2014, 35, 382–411. [Google Scholar] [CrossRef]
- Baraha, S.; Sahoo, A.K. Synthetic aperture radar image and its despeckling using variational methods: A review of recent trends. Signal Process. 2023, 212, 109156. [Google Scholar] [CrossRef]
- Ye, Y.; Zhang, J.; Zhou, L.; Li, J.; Ren, X.; Fan, J. Optical and SAR image fusion based on complementary feature decomposition and visual saliency features. IEEE Trans. Geosci. Remote Sens. 2024, 62, 5205315. [Google Scholar] [CrossRef]
- Karim, S.; Tong, G.; Li, J.; Qadir, A.; Farooq, U.; Yu, Y. Current advances and future perspectives of image fusion: A comprehensive review. Inf. Fusion 2023, 90, 185–217. [Google Scholar] [CrossRef]
- Iqbal, M.Z.; Razzak, I.; Qayyum, A.; Nguyen, T.T.; Tanveer, M.; Sowmya, A. Hybrid unsupervised paradigm based deformable image fusion for 4D CT lung image modality. Inf. Fusion 2024, 102, 102061. [Google Scholar] [CrossRef]
- Li, J.; Bi, G.; Wang, X.; Nie, T.; Huang, L. Radiation-Variation Insensitive Coarse-to-Fine Image Registration for Infrared and Visible Remote Sensing Based on Zero-Shot Learning. Remote Sens. 2024, 16, 214. [Google Scholar] [CrossRef]
- Hou, X.; Gao, Q.; Wang, R.; Luo, X. Satellite-borne optical remote sensing image registration based on point features. Sensors 2021, 21, 2695. [Google Scholar] [CrossRef] [PubMed]
- Du, J.; Tang, S.; Jiang, T.; Lu, Z. Intensity-based robust similarity for multimodal image registration. Int. J. Comput. Math. 2006, 83, 49–57. [Google Scholar] [CrossRef]
- Gao, Z.; Gu, B.; Lin, J. Monomodal image registration using mutual information based methods. Image Vis. Comput. 2008, 26, 164–173. [Google Scholar] [CrossRef]
- Sarvaiya, J.N.; Patnaik, S.; Bombaywala, S. Image registration by template matching using normalized cross-correlation. In Proceedings of the 2009 International Conference on Advances in Computing, Control, and Telecommunication Technologies, Bangalore, India, 28–29 December 2009; pp. 819–822. [Google Scholar]
- Misra, I.; Rohil, M.K.; Manthira Moorthi, S.; Dhar, D. Feature based remote sensing image registration techniques: A comprehensive and comparative review. Int. J. Remote Sens. 2022, 43, 4477–4516. [Google Scholar] [CrossRef]
- Ma, J.; Jiang, X.; Fan, A.; Jiang, J.; Yan, J. Image matching from handcrafted to deep features: A survey. Int. J. Comput. Vis. 2021, 129, 23–79. [Google Scholar] [CrossRef]
- Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2004, 60, 91–110. [Google Scholar] [CrossRef]
- Dellinger, F.; Delon, J.; Gousseau, Y.; Michel, J.; Tupin, F. SAR-SIFT: A SIFT-like algorithm for SAR images. IEEE Trans. Geosci. Remote Sens. 2014, 53, 453–466. [Google Scholar] [CrossRef]
- Ma, W.; Wen, Z.; Wu, Y.; Jiao, L.; Gong, M.; Zheng, Y.; Liu, L. Remote sensing image registration with modified SIFT and enhanced feature matching. IEEE Geosci. Remote Sens. Lett. 2016, 14, 3–7. [Google Scholar] [CrossRef]
- Xiang, Y.; Wang, F.; You, H. OS-SIFT: A robust SIFT-like algorithm for high-resolution optical-to-SAR image registration in suburban areas. IEEE Trans. Geosci. Remote Sens. 2018, 56, 3078–3090. [Google Scholar] [CrossRef]
- Xiong, X.; Jin, G.; Xu, Q.; Zhang, H. Self-similarity features for multimodal remote sensing image matching. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 12440–12454. [Google Scholar] [CrossRef]
- Fan, J.; Wu, Y.; Li, M.; Liang, W.; Cao, Y. SAR and optical image registration using nonlinear diffusion and phase congruency structural descriptor. IEEE Trans. Geosci. Remote Sens. 2018, 56, 5368–5379. [Google Scholar] [CrossRef]
- Zhu, B.; Ye, Y.; Zhou, L.; Li, Z.; Yin, G. Robust registration of aerial images and LiDAR data using spatial constraints and Gabor structural features. ISPRS J. Photogramm. Remote Sens. 2021, 181, 129–147. [Google Scholar] [CrossRef]
- Li, J.; Hu, Q.; Ai, M. RIFT: Multi-modal image matching based on radiation-variation insensitive feature transform. IEEE Trans. Image Process. 2019, 29, 3296–3310. [Google Scholar] [CrossRef]
- Xiong, X.; Jin, G.; Xu, Q.; Zhang, H.; Wang, L.; Wu, K. Robust registration algorithm for optical and SAR images based on adjacent self-similarity feature. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5233117. [Google Scholar] [CrossRef]
- Zhang, Y.; Zhang, Z.; Ma, G.; Wu, J. Multi-source remote sensing image registration based on local deep learning feature. In Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 11–16 July 2021; pp. 3412–3415. [Google Scholar]
- Quan, D.; Wei, H.; Wang, S.; Lei, R.; Duan, B.; Li, Y.; Hou, B.; Jiao, L. Self-distillation feature learning network for optical and SAR image registration. IEEE Trans. Geosci. Remote Sens. 2022, 60, 4706718. [Google Scholar] [CrossRef]
- Wu, W.; Xian, Y.; Su, J.; Ren, L. A Siamese template matching method for SAR and optical image. IEEE Geosci. Remote Sens. Lett. 2021, 19, 4017905. [Google Scholar] [CrossRef]
- Zhou, L.; Ye, Y.; Tang, T.; Nan, K.; Qin, Y. Robust matching for SAR and optical images using multiscale convolutional gradient features. IEEE Geosci. Remote Sens. Lett. 2021, 19, 4017605. [Google Scholar] [CrossRef]
- Xiang, D.; Xie, Y.; Cheng, J.; Xu, Y.; Zhang, H.; Zheng, Y. Optical and SAR image registration based on feature decoupling network. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5235913. [Google Scholar] [CrossRef]
- Li, Z.; Fu, Z.; Nie, H.; Chen, S. PM-Net: A Multi-Level Keypoints Detector and Patch Feature Learning Network for Optical and SAR Image Matching. Appl. Sci. 2022, 12, 5989. [Google Scholar] [CrossRef]
- Li, X.; Zhang, G.; Cui, H.; Hou, S.; Wang, S.; Li, X.; Chen, Y.; Li, Z.; Zhang, L. MCANet: A joint semantic segmentation framework of optical and SAR images for land use classification. Int. J. Appl. Earth Obs. Geoinf. 2022, 106, 102638. [Google Scholar] [CrossRef]
- Cheng-li, J.; Xiao-guang, Z.; Ling-jun, Z.; Gang-yao, K. A Modified ROEWA method for edge detection in SAR images. In Proceedings of the 2006 CIE International Conference on Radar, Shanghai, China, 16–19 October 2006; pp. 1–4. [Google Scholar]
- Harris, C.; Stephens, M. A combined corner and edge detector. In Proceedings of the Alvey Vision Conference, Manchester, UK, 31 August–2 September 1988; pp. 147–151. [Google Scholar]
- Mikolajczyk, K.; Schmid, C. A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 2005, 27, 1615–1630. [Google Scholar] [CrossRef] [PubMed]
- Hou, H.; Lan, C.; Xu, Q.; Lv, L.; Xiong, X.; Yao, F.; Wang, L. Attention-Based Matching Approach for Heterogeneous Remote Sensing Images. Remote Sens. 2022, 15, 163. [Google Scholar] [CrossRef]
- Zhang, X.; Wang, Y.; Liu, H. Robust optical and SAR image registration based on OS-SIFT and cascaded sample consensus. IEEE Geosci. Remote Sens. Lett. 2021, 19, 4011605. [Google Scholar] [CrossRef]
- Pepe, A.; Berardino, P.; Bonano, M.; Euillades, L.D.; Lanari, R.; Sansosti, E. SBAS-based satellite orbit correction for the generation of DInSAR time-series: Application to RADARSAT-1 data. IEEE Trans. Geosci. Remote Sens. 2011, 49, 5150–5165. [Google Scholar] [CrossRef]
- Mascolo, L.; Lopez-Sanchez, J.M.; Cloude, S.R. Thermal noise removal from polarimetric Sentinel-1 data. IEEE Geosci. Remote Sens. Lett. 2021, 19, 4009105. [Google Scholar] [CrossRef]
- Lee, J.-S.; Wen, J.-H.; Ainsworth, T.L.; Chen, K.-S.; Chen, A.J. Improved sigma filter for speckle filtering of SAR imagery. IEEE Trans. Geosci. Remote Sens. 2008, 47, 202–213. [Google Scholar]
- Shimada, M.; Isoguchi, O.; Tadono, T.; Isono, K. PALSAR radiometric and geometric calibration. IEEE Trans. Geosci. Remote Sens. 2009, 47, 3915–3932. [Google Scholar] [CrossRef]
- Werner, C.; Strozzi, T.; Wegmuller, U.; Wiesmann, A. SAR geocoding and multi-sensor image registration. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada, 24–28 June 2002; pp. 902–904. [Google Scholar]
- Mikolajczyk, K.; Schmid, C. An affine invariant interest point detector. In Proceedings of the Computer Vision—ECCV 2002: 7th European Conference on Computer Vision, Copenhagen, Denmark, 28–31 May 2002; Proceedings, Part I 7. pp. 128–142. [Google Scholar]
- Zhou, Y.; Han, Z.; Dou, Z.; Huang, C.; Cong, L.; Lv, N.; Chen, C. Edge Consistency Feature Extraction Method for Multi-Source Image Registration. Remote Sens. 2023, 15, 5051. [Google Scholar] [CrossRef]
- Ye, Y.; Shan, J.; Bruzzone, L.; Shen, L. Robust registration of multimodal remote sensing images based on structural similarity. IEEE Trans. Geosci. Remote Sens. 2017, 55, 2941–2958. [Google Scholar] [CrossRef]
Datasets | Sensor | Resolution (m) | Size (Pixel) | Geographic Location |
---|---|---|---|---|
BISTU-OPT-SAR | Sentinel-2 | 10 | 1024 × 1024 | Tianjin, China |
Sentinel-1 | 10 | 1024 × 1024 | ||
Sentinel-2 | 10 | 850 × 850 | Anhui, China | |
Sentinel-1 | 10 | 850 × 850 | ||
WHU-OPT-SAR | GF-1 | 5 | 800 × 800 | Hubei, China |
GF-3 | 5 | 800 × 800 |
Pairs | Image Source | Size (pixel) | GSD (m) | Date | Description | Reference |
---|---|---|---|---|---|---|
P1 | Google Map | 520 × 520 | 0.95 | N/A | Image pairs with significant rotation differences and slight scale differences | [22] |
GF-3 | 500 × 500 | 1 | 02/2018 | |||
P2 | Google Earth | 406 × 406 | 1.80 | 11/2016 | Image pairs with significant scale differences | [22] |
GF-3 | 750 × 750 | 1 | 11/2016 | |||
P3 | Google Earth | 528 × 524 | 3 | 11/2007 | Image pairs with slight scale and rotation differences | [42] |
TerraSAR-X | 534 × 524 | 3 | 12/2007 | |||
P4 | Google Earth | 774 × 692 | 1 | 10/2012 | Image pairs with significant translation and rotation differences | [17] |
TerraSAR-X | 900 × 795 | 1 | 12/2010 |
Methods | Evaluation Index | 1 | 2 | 3 | 4 | 5 | 6 |
---|---|---|---|---|---|---|---|
PSO-SIFT | CMN | - | - | 43 | 40 | 34 | - |
RMSE | - | - | 1.261 | 1.400 | 1.152 | - | |
SAR-SIFT | CMN | 12 | - | 50 | - | 38 | 11 |
RMSE | 1.019 | - | 1.351 | - | 1.376 | 1.137 | |
OS-SIFT | CMN | 11 | 5 | - | - | 14 | 7 |
RMSE | 1.039 | 1.288 | - | - | 1.313 | 1.048 | |
RIFT | CMN | 59 | 37 | 30 | 83 | 106 | 56 |
RMSE | 0.849 | 0.829 | 0.712 | 0.920 | 0.908 | 0.857 | |
OSS | CMN | 32 | 15 | 25 | 28 | 90 | 63 |
RMSE | 1.231 | 1.211 | 1.334 | 1.198 | 1.149 | 1.106 | |
OS-SIFT+PSO | CMN | 50 | 80 | - | - | 65 | 64 |
RMSE | 0.662 | 0.735 | - | - | 0.672 | 0.634 | |
MROEWA+FSC | CMN | 15 | 12 | 22 | 33 | 32 | 37 |
RMSE | 1.084 | 1.145 | 1.096 | 1.330 | 1.198 | 1.345 | |
OS-PSO | CMN | 110 | 83 | 140 | 86 | 170 | 73 |
RMSE | 0.693 | 0.689 | 0.712 | 0.705 | 0.670 | 0.632 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, H.; Song, Y.; Hu, J.; Li, Y.; Li, Y.; Gao, G. OS-PSO: A Modified Ratio of Exponentially Weighted Averages-Based Optical and SAR Image Registration. Sensors 2024, 24, 5959. https://doi.org/10.3390/s24185959
Zhang H, Song Y, Hu J, Li Y, Li Y, Gao G. OS-PSO: A Modified Ratio of Exponentially Weighted Averages-Based Optical and SAR Image Registration. Sensors. 2024; 24(18):5959. https://doi.org/10.3390/s24185959
Chicago/Turabian StyleZhang, Hui, Yu Song, Jingfang Hu, Yansheng Li, Yang Li, and Guowei Gao. 2024. "OS-PSO: A Modified Ratio of Exponentially Weighted Averages-Based Optical and SAR Image Registration" Sensors 24, no. 18: 5959. https://doi.org/10.3390/s24185959
APA StyleZhang, H., Song, Y., Hu, J., Li, Y., Li, Y., & Gao, G. (2024). OS-PSO: A Modified Ratio of Exponentially Weighted Averages-Based Optical and SAR Image Registration. Sensors, 24(18), 5959. https://doi.org/10.3390/s24185959