An affine invariant approach for dense wide baseline image matching
Visual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, where image matching is one of the key technologies. This article presents an affine invariant method to produce dense correspondences between uncalibrated wide baseline images. Under affine tr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-12-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147716680826 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547890819497984 |
|---|---|
| author | Fanhuai Shi Jian Gao Xixia Huang |
| author_facet | Fanhuai Shi Jian Gao Xixia Huang |
| author_sort | Fanhuai Shi |
| collection | DOAJ |
| description | Visual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, where image matching is one of the key technologies. This article presents an affine invariant method to produce dense correspondences between uncalibrated wide baseline images. Under affine transformations, both point location and its neighborhood texture are changed between views, so dense matching becomes a tough task. The proposed approach tends to solve this problem within a sparse-to-dense framework. The contribution of this article is in threefolds. First, a strategy of reliable sparse matching is proposed, which starts from affine invariant features extraction and matching and then these initial matches are utilized as spatial prior to produce more sparse matches. Second, match propagation from sparse feature points to its neighboring pixels is conducted in the way of region growing in an affine invariant framework. Third, the unmatched points are handled by low-rank matrix recovery technique. Comparison experiments of the proposed method versus existing ones show a significant improvement in the presence of large affine deformations. |
| format | Article |
| id | doaj-art-ff70ce17b94d4c3c92fdd626ae20e144 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2016-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-ff70ce17b94d4c3c92fdd626ae20e1442025-02-03T06:43:00ZengWileyInternational Journal of Distributed Sensor Networks1550-14772016-12-011210.1177/1550147716680826An affine invariant approach for dense wide baseline image matchingFanhuai Shi0Jian Gao1Xixia Huang2Department of Control Science and Engineering, College of Electronics and Information Engineering, Tongji University, Shanghai, ChinaDepartment of Computer Science and Engineering, New York University, New York, NY, USAKey Laboratory of Marine Technology and Control Engineering, Shanghai Maritime University, Shanghai, ChinaVisual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, where image matching is one of the key technologies. This article presents an affine invariant method to produce dense correspondences between uncalibrated wide baseline images. Under affine transformations, both point location and its neighborhood texture are changed between views, so dense matching becomes a tough task. The proposed approach tends to solve this problem within a sparse-to-dense framework. The contribution of this article is in threefolds. First, a strategy of reliable sparse matching is proposed, which starts from affine invariant features extraction and matching and then these initial matches are utilized as spatial prior to produce more sparse matches. Second, match propagation from sparse feature points to its neighboring pixels is conducted in the way of region growing in an affine invariant framework. Third, the unmatched points are handled by low-rank matrix recovery technique. Comparison experiments of the proposed method versus existing ones show a significant improvement in the presence of large affine deformations.https://doi.org/10.1177/1550147716680826 |
| spellingShingle | Fanhuai Shi Jian Gao Xixia Huang An affine invariant approach for dense wide baseline image matching International Journal of Distributed Sensor Networks |
| title | An affine invariant approach for dense wide baseline image matching |
| title_full | An affine invariant approach for dense wide baseline image matching |
| title_fullStr | An affine invariant approach for dense wide baseline image matching |
| title_full_unstemmed | An affine invariant approach for dense wide baseline image matching |
| title_short | An affine invariant approach for dense wide baseline image matching |
| title_sort | affine invariant approach for dense wide baseline image matching |
| url | https://doi.org/10.1177/1550147716680826 |
| work_keys_str_mv | AT fanhuaishi anaffineinvariantapproachfordensewidebaselineimagematching AT jiangao anaffineinvariantapproachfordensewidebaselineimagematching AT xixiahuang anaffineinvariantapproachfordensewidebaselineimagematching AT fanhuaishi affineinvariantapproachfordensewidebaselineimagematching AT jiangao affineinvariantapproachfordensewidebaselineimagematching AT xixiahuang affineinvariantapproachfordensewidebaselineimagematching |