Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images
Ground-to-aerial feature matching bridges information from cross-view images, which enables optimized urban applications, e.g., pixel-level geolocating and complete urban 3-D reconstruction. However, urban ground and aerial images typically suffer from drastic changes in viewpoint, scale, and illumi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9387538/ |
| _version_ | 1818620540448931840 |
|---|---|
| author | Xianwei Zheng Hongjie Li Hanjiang Xiong Xiao Xie |
| author_facet | Xianwei Zheng Hongjie Li Hanjiang Xiong Xiao Xie |
| author_sort | Xianwei Zheng |
| collection | DOAJ |
| description | Ground-to-aerial feature matching bridges information from cross-view images, which enables optimized urban applications, e.g., pixel-level geolocating and complete urban 3-D reconstruction. However, urban ground and aerial images typically suffer from drastic changes in viewpoint, scale, and illumination, together with repetitive patterns. Thus, direct matching of local features between ground and aerial images is particularly difficult because of the low similarity of local descriptors and high ambiguity in true–false match discrimination. For this challenging task, we propose a novel lattice-point mutually guided matching (LPMG) method in this article. We specifically address two key issues: 1) reducing descriptor variance and 2) enhancing true–false match discriminability. The former is solved by recovering the geometry and appearance of the underlying image region in 3-D through automatic view rectification on ground and aerial images. The latter is circumvented by replacing the conventional mismatch removal with an LPMG strategy. In this strategy, the topology structure of repeated façade elements (i.e., lattice), and the high reliable point matching seeds, are first extracted from the rectified ground and aerial images. Then, the point matching seeds guide the self-similar lattice tiles from two views to be precisely aligned, thereby estimating an accurate transformation model from lattice tile correspondences. Finally, the estimated model powerfully supervises the differentiation of true and false matches from the entire putative match set. Extensive experiments conducted on several datasets show that our method can obtain a considerable number of nearly pure correct matches from urban ground and aerial images, significantly outperforming those existing methods. |
| first_indexed | 2024-12-16T17:55:00Z |
| format | Article |
| id | doaj.art-57836b6831b6414ba53f976b3b567b73 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-16T17:55:00Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-57836b6831b6414ba53f976b3b567b732022-12-21T22:22:12ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01144737475210.1109/JSTARS.2021.30692229387538Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene ImagesXianwei Zheng0https://orcid.org/0000-0001-9783-3030Hongjie Li1Hanjiang Xiong2Xiao Xie3State Key Lab. LIESMARS, Wuhan University, Wuhan, ChinaState Key Lab. LIESMARS, Wuhan University, Wuhan, ChinaState Key Lab. LIESMARS, Wuhan University, Wuhan, ChinaSchool of Geodesy, and Geomatics, Wuhan University, Wuhan, ChinaGround-to-aerial feature matching bridges information from cross-view images, which enables optimized urban applications, e.g., pixel-level geolocating and complete urban 3-D reconstruction. However, urban ground and aerial images typically suffer from drastic changes in viewpoint, scale, and illumination, together with repetitive patterns. Thus, direct matching of local features between ground and aerial images is particularly difficult because of the low similarity of local descriptors and high ambiguity in true–false match discrimination. For this challenging task, we propose a novel lattice-point mutually guided matching (LPMG) method in this article. We specifically address two key issues: 1) reducing descriptor variance and 2) enhancing true–false match discriminability. The former is solved by recovering the geometry and appearance of the underlying image region in 3-D through automatic view rectification on ground and aerial images. The latter is circumvented by replacing the conventional mismatch removal with an LPMG strategy. In this strategy, the topology structure of repeated façade elements (i.e., lattice), and the high reliable point matching seeds, are first extracted from the rectified ground and aerial images. Then, the point matching seeds guide the self-similar lattice tiles from two views to be precisely aligned, thereby estimating an accurate transformation model from lattice tile correspondences. Finally, the estimated model powerfully supervises the differentiation of true and false matches from the entire putative match set. Extensive experiments conducted on several datasets show that our method can obtain a considerable number of nearly pure correct matches from urban ground and aerial images, significantly outperforming those existing methods.https://ieeexplore.ieee.org/document/9387538/Aerial oblique imageryfeature matchingground imageryground-to-aerial image matchingrepetitive pattern |
| spellingShingle | Xianwei Zheng Hongjie Li Hanjiang Xiong Xiao Xie Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aerial oblique imagery feature matching ground imagery ground-to-aerial image matching repetitive pattern |
| title | Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images |
| title_full | Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images |
| title_fullStr | Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images |
| title_full_unstemmed | Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images |
| title_short | Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images |
| title_sort | lattice point mutually guided ground to aerial feature matching for urban scene images |
| topic | Aerial oblique imagery feature matching ground imagery ground-to-aerial image matching repetitive pattern |
| url | https://ieeexplore.ieee.org/document/9387538/ |
| work_keys_str_mv | AT xianweizheng latticepointmutuallyguidedgroundtoaerialfeaturematchingforurbansceneimages AT hongjieli latticepointmutuallyguidedgroundtoaerialfeaturematchingforurbansceneimages AT hanjiangxiong latticepointmutuallyguidedgroundtoaerialfeaturematchingforurbansceneimages AT xiaoxie latticepointmutuallyguidedgroundtoaerialfeaturematchingforurbansceneimages |