Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning
The vast digital archives collected by optical remote sensing observations over a long period of time can be used to determine changes in the land surface and this information can be very useful in a variety of applications. However, accurate change extraction requires highly accurate image-to-image...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5360 |
| _version_ | 1797466622535925760 |
|---|---|
| author | Shuhei Hikosaka Hideyuki Tonooka |
| author_facet | Shuhei Hikosaka Hideyuki Tonooka |
| author_sort | Shuhei Hikosaka |
| collection | DOAJ |
| description | The vast digital archives collected by optical remote sensing observations over a long period of time can be used to determine changes in the land surface and this information can be very useful in a variety of applications. However, accurate change extraction requires highly accurate image-to-image registration, which is especially true when the target is urban areas in high-resolution remote sensing images. In this paper, we propose a new method for automatic registration between images that can be applied to noisy images such as old aerial photographs taken with analog film, in the case where changes in man-made objects such as buildings in urban areas are extracted from multitemporal high-resolution remote sensing images. The proposed method performs image-to-image registration by applying template matching to road masks extracted from images using a two-step deep learning model. We applied the proposed method to multitemporal images, including images taken more than 36 years before the reference image. As a result, the proposed method achieved registration accuracy at the subpixel level, which was more accurate than the conventional area-based and feature-based methods, even for image pairs with the most distant acquisition times. The proposed method is expected to provide more robust image-to-image registration for differences in sensor characteristics, acquisition time, resolution and color tone of two remote sensing images, as well as to temporal variations in vegetation and the effects of building shadows. These results were obtained with a road extraction model trained on images from a single area, single time period and single platform, demonstrating the high versatility of the model. Furthermore, the performance is expected to be improved and stabilized by using images from different areas, time periods and platforms for training. |
| first_indexed | 2024-03-09T18:42:17Z |
| format | Article |
| id | doaj.art-a6b1e98ae2ae4dffb523dfc8e0cf4522 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:42:17Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a6b1e98ae2ae4dffb523dfc8e0cf45222023-11-24T06:37:47ZengMDPI AGRemote Sensing2072-42922022-10-011421536010.3390/rs14215360Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep LearningShuhei Hikosaka0Hideyuki Tonooka1Graduate School of Science and Engineering, Ibaraki University, Hitachi 3168511, JapanGraduate School of Science and Engineering, Ibaraki University, Hitachi 3168511, JapanThe vast digital archives collected by optical remote sensing observations over a long period of time can be used to determine changes in the land surface and this information can be very useful in a variety of applications. However, accurate change extraction requires highly accurate image-to-image registration, which is especially true when the target is urban areas in high-resolution remote sensing images. In this paper, we propose a new method for automatic registration between images that can be applied to noisy images such as old aerial photographs taken with analog film, in the case where changes in man-made objects such as buildings in urban areas are extracted from multitemporal high-resolution remote sensing images. The proposed method performs image-to-image registration by applying template matching to road masks extracted from images using a two-step deep learning model. We applied the proposed method to multitemporal images, including images taken more than 36 years before the reference image. As a result, the proposed method achieved registration accuracy at the subpixel level, which was more accurate than the conventional area-based and feature-based methods, even for image pairs with the most distant acquisition times. The proposed method is expected to provide more robust image-to-image registration for differences in sensor characteristics, acquisition time, resolution and color tone of two remote sensing images, as well as to temporal variations in vegetation and the effects of building shadows. These results were obtained with a road extraction model trained on images from a single area, single time period and single platform, demonstrating the high versatility of the model. Furthermore, the performance is expected to be improved and stabilized by using images from different areas, time periods and platforms for training.https://www.mdpi.com/2072-4292/14/21/5360image-to-image registrationdeep learningtemplate matchinghigh-resolution remote sensingaerial photograph |
| spellingShingle | Shuhei Hikosaka Hideyuki Tonooka Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning Remote Sensing image-to-image registration deep learning template matching high-resolution remote sensing aerial photograph |
| title | Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning |
| title_full | Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning |
| title_fullStr | Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning |
| title_full_unstemmed | Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning |
| title_short | Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning |
| title_sort | image to image subpixel registration based on template matching of road network extracted by deep learning |
| topic | image-to-image registration deep learning template matching high-resolution remote sensing aerial photograph |
| url | https://www.mdpi.com/2072-4292/14/21/5360 |
| work_keys_str_mv | AT shuheihikosaka imagetoimagesubpixelregistrationbasedontemplatematchingofroadnetworkextractedbydeeplearning AT hideyukitonooka imagetoimagesubpixelregistrationbasedontemplatematchingofroadnetworkextractedbydeeplearning |