An ASIFT-Based Local Registration Method for Satellite Imagery
Imagery registration is a fundamental step, which greatly affects later processes in image mosaic, multi-spectral image fusion, digital surface modelling, etc., where the final solution needs blending of pixel information from more than one images. It is highly desired to find a way to identify regi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/7/6/7044 |
| _version_ | 1818262556128575488 |
|---|---|
| author | Xiangjun Wang Yang Li Hong Wei Feng Liu |
| author_facet | Xiangjun Wang Yang Li Hong Wei Feng Liu |
| author_sort | Xiangjun Wang |
| collection | DOAJ |
| description | Imagery registration is a fundamental step, which greatly affects later processes in image mosaic, multi-spectral image fusion, digital surface modelling, etc., where the final solution needs blending of pixel information from more than one images. It is highly desired to find a way to identify registration regions among input stereo image pairs with high accuracy, particularly in remote sensing applications in which ground control points (GCPs) are not always available, such as in selecting a landing zone on an outer space planet. In this paper, a framework for localization in image registration is developed. It strengthened the local registration accuracy from two aspects: less reprojection error and better feature point distribution. Affine scale-invariant feature transform (ASIFT) was used for acquiring feature points and correspondences on the input images. Then, a homography matrix was estimated as the transformation model by an improved random sample consensus (IM-RANSAC) algorithm. In order to identify a registration region with a better spatial distribution of feature points, the Euclidean distance between the feature points is applied (named the S criterion). Finally, the parameters of the homography matrix were optimized by the Levenberg–Marquardt (LM) algorithm with selective feature points from the chosen registration region. In the experiment section, the Chang’E-2 satellite remote sensing imagery was used for evaluating the performance of the proposed method. The experiment result demonstrates that the proposed method can automatically locate a specific region with high registration accuracy between input images by achieving lower root mean square error (RMSE) and better distribution of feature points. |
| first_indexed | 2024-12-12T19:05:00Z |
| format | Article |
| id | doaj.art-5a8524423b844083ac84de1794f00db6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-12T19:05:00Z |
| publishDate | 2015-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5a8524423b844083ac84de1794f00db62022-12-22T00:14:58ZengMDPI AGRemote Sensing2072-42922015-05-01767044706110.3390/rs70607044rs70607044An ASIFT-Based Local Registration Method for Satellite ImageryXiangjun Wang0Yang Li1Hong Wei2Feng Liu3State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, 92 Weijin Road, Tianjin 300072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, 92 Weijin Road, Tianjin 300072, ChinaComputer Vision Group, School of Systems Engineering, University of Reading, Berkshire RG6 6AY, UKState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, 92 Weijin Road, Tianjin 300072, ChinaImagery registration is a fundamental step, which greatly affects later processes in image mosaic, multi-spectral image fusion, digital surface modelling, etc., where the final solution needs blending of pixel information from more than one images. It is highly desired to find a way to identify registration regions among input stereo image pairs with high accuracy, particularly in remote sensing applications in which ground control points (GCPs) are not always available, such as in selecting a landing zone on an outer space planet. In this paper, a framework for localization in image registration is developed. It strengthened the local registration accuracy from two aspects: less reprojection error and better feature point distribution. Affine scale-invariant feature transform (ASIFT) was used for acquiring feature points and correspondences on the input images. Then, a homography matrix was estimated as the transformation model by an improved random sample consensus (IM-RANSAC) algorithm. In order to identify a registration region with a better spatial distribution of feature points, the Euclidean distance between the feature points is applied (named the S criterion). Finally, the parameters of the homography matrix were optimized by the Levenberg–Marquardt (LM) algorithm with selective feature points from the chosen registration region. In the experiment section, the Chang’E-2 satellite remote sensing imagery was used for evaluating the performance of the proposed method. The experiment result demonstrates that the proposed method can automatically locate a specific region with high registration accuracy between input images by achieving lower root mean square error (RMSE) and better distribution of feature points.http://www.mdpi.com/2072-4292/7/6/7044satellite remote sensinglocal image registrationimage mosaicASIFTRANSAC |
| spellingShingle | Xiangjun Wang Yang Li Hong Wei Feng Liu An ASIFT-Based Local Registration Method for Satellite Imagery Remote Sensing satellite remote sensing local image registration image mosaic ASIFT RANSAC |
| title | An ASIFT-Based Local Registration Method for Satellite Imagery |
| title_full | An ASIFT-Based Local Registration Method for Satellite Imagery |
| title_fullStr | An ASIFT-Based Local Registration Method for Satellite Imagery |
| title_full_unstemmed | An ASIFT-Based Local Registration Method for Satellite Imagery |
| title_short | An ASIFT-Based Local Registration Method for Satellite Imagery |
| title_sort | asift based local registration method for satellite imagery |
| topic | satellite remote sensing local image registration image mosaic ASIFT RANSAC |
| url | http://www.mdpi.com/2072-4292/7/6/7044 |
| work_keys_str_mv | AT xiangjunwang anasiftbasedlocalregistrationmethodforsatelliteimagery AT yangli anasiftbasedlocalregistrationmethodforsatelliteimagery AT hongwei anasiftbasedlocalregistrationmethodforsatelliteimagery AT fengliu anasiftbasedlocalregistrationmethodforsatelliteimagery AT xiangjunwang asiftbasedlocalregistrationmethodforsatelliteimagery AT yangli asiftbasedlocalregistrationmethodforsatelliteimagery AT hongwei asiftbasedlocalregistrationmethodforsatelliteimagery AT fengliu asiftbasedlocalregistrationmethodforsatelliteimagery |