Remote Sensing Image Registration with Line Segments and Their Intersections
Image registration is a basic but essential step for remote sensing image processing, and finding stable features in multitemporal images is one of the most considerable challenges in the field. The main shape contours of artificial objects (e.g., roads, buildings, farmlands, and airports) can be ge...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/9/5/439 |
| _version_ | 1818974133621358592 |
|---|---|
| author | Chengjin Lyu Jie Jiang |
| author_facet | Chengjin Lyu Jie Jiang |
| author_sort | Chengjin Lyu |
| collection | DOAJ |
| description | Image registration is a basic but essential step for remote sensing image processing, and finding stable features in multitemporal images is one of the most considerable challenges in the field. The main shape contours of artificial objects (e.g., roads, buildings, farmlands, and airports) can be generally described as a group of line segments, which are stable features, even in images with evident background changes (e.g., images taken before and after a disaster). In this study, a registration method that uses line segments and their intersections is proposed for multitemporal remote sensing images. First, line segments are extracted in image pyramids to unify the scales of the reference image and the test image. Then, a line descriptor based on the gradient distribution of local areas is constructed, and the segments are matched in image pyramids. Lastly, triplets of intersections of matching lines are selected to estimate affine transformation between two images. Additional corresponding intersections are provided based on the estimated transformation, and an iterative process is adopted to remove outliers. The performance of the proposed method is tested on a variety of optical remote sensing image pairs, including synthetic and real data. Compared with existing methods, our method can provide more accurate registration results, even in images with significant background changes. |
| first_indexed | 2024-12-20T15:35:13Z |
| format | Article |
| id | doaj.art-0b5860ab66634a0b86c451cbd7efe08a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T15:35:13Z |
| publishDate | 2017-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0b5860ab66634a0b86c451cbd7efe08a2022-12-21T19:35:27ZengMDPI AGRemote Sensing2072-42922017-05-019543910.3390/rs9050439rs9050439Remote Sensing Image Registration with Line Segments and Their IntersectionsChengjin Lyu0Jie Jiang1School of Instrumentation Science and Optoelectronics Engineering, Beihang University, No. 37 Xueyuan Road, Beijing 100191, ChinaSchool of Instrumentation Science and Optoelectronics Engineering, Beihang University, No. 37 Xueyuan Road, Beijing 100191, ChinaImage registration is a basic but essential step for remote sensing image processing, and finding stable features in multitemporal images is one of the most considerable challenges in the field. The main shape contours of artificial objects (e.g., roads, buildings, farmlands, and airports) can be generally described as a group of line segments, which are stable features, even in images with evident background changes (e.g., images taken before and after a disaster). In this study, a registration method that uses line segments and their intersections is proposed for multitemporal remote sensing images. First, line segments are extracted in image pyramids to unify the scales of the reference image and the test image. Then, a line descriptor based on the gradient distribution of local areas is constructed, and the segments are matched in image pyramids. Lastly, triplets of intersections of matching lines are selected to estimate affine transformation between two images. Additional corresponding intersections are provided based on the estimated transformation, and an iterative process is adopted to remove outliers. The performance of the proposed method is tested on a variety of optical remote sensing image pairs, including synthetic and real data. Compared with existing methods, our method can provide more accurate registration results, even in images with significant background changes.http://www.mdpi.com/2072-4292/9/5/439image registrationremote sensingline segmentsintersection points |
| spellingShingle | Chengjin Lyu Jie Jiang Remote Sensing Image Registration with Line Segments and Their Intersections Remote Sensing image registration remote sensing line segments intersection points |
| title | Remote Sensing Image Registration with Line Segments and Their Intersections |
| title_full | Remote Sensing Image Registration with Line Segments and Their Intersections |
| title_fullStr | Remote Sensing Image Registration with Line Segments and Their Intersections |
| title_full_unstemmed | Remote Sensing Image Registration with Line Segments and Their Intersections |
| title_short | Remote Sensing Image Registration with Line Segments and Their Intersections |
| title_sort | remote sensing image registration with line segments and their intersections |
| topic | image registration remote sensing line segments intersection points |
| url | http://www.mdpi.com/2072-4292/9/5/439 |
| work_keys_str_mv | AT chengjinlyu remotesensingimageregistrationwithlinesegmentsandtheirintersections AT jiejiang remotesensingimageregistrationwithlinesegmentsandtheirintersections |