Image stitching method by multi‐feature constrained alignment and colour adjustment
Abstract Image alignment and colour consistency are two challenging tasks for image stitching. Traditional point correspondence methods are difficult to achieve good alignments due to their insufficiency and unreliability. The results are prone to errors and distortions. On the other hand, the probl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12120 |
| _version_ | 1818022262417129472 |
|---|---|
| author | Xingsheng Yuan Yongbin Zheng Wei Zhao Jiongming Su Jianzhai Wu |
| author_facet | Xingsheng Yuan Yongbin Zheng Wei Zhao Jiongming Su Jianzhai Wu |
| author_sort | Xingsheng Yuan |
| collection | DOAJ |
| description | Abstract Image alignment and colour consistency are two challenging tasks for image stitching. Traditional point correspondence methods are difficult to achieve good alignments due to their insufficiency and unreliability. The results are prone to errors and distortions. On the other hand, the problem of colour inconsistency in overlapping area between image pairs is still difficult to solve, especially when the illumination difference between images is large. To solve these problems, the authors integrate point features and line features into a warping model through a designed energy function. Line features will provide geometric constraints for image stitching, and remedy the defect of point correspondences in low‐textured image stitching. A global colour consistency optimization method with colour mapping via a histogram extreme point‐matching algorithm is proposed. The colour characteristic of reference images will be transferred to the others to achieve a global colour consistency. The proposed method is evaluated on a series of images, and compared with other methods. The experiments demonstrate that the proposed method provides convincing stitching results and achieves satisfied colour consistency results. |
| first_indexed | 2024-04-14T08:29:53Z |
| format | Article |
| id | doaj.art-65b871f8cf0b43979b64ba6cc15e6cc3 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-14T08:29:53Z |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-65b871f8cf0b43979b64ba6cc15e6cc32022-12-22T02:03:57ZengWileyIET Image Processing1751-96591751-96672021-05-011571499150710.1049/ipr2.12120Image stitching method by multi‐feature constrained alignment and colour adjustmentXingsheng Yuan0Yongbin Zheng1Wei Zhao2Jiongming Su3Jianzhai Wu4School of Intelligence Science and Technology National University of Defense Technology Changsha ChinaSchool of Intelligence Science and Technology National University of Defense Technology Changsha ChinaDepartment of Information Technology of Hunan Police Academy Changsha ChinaSchool of Intelligence Science and Technology National University of Defense Technology Changsha ChinaSchool of Intelligence Science and Technology National University of Defense Technology Changsha ChinaAbstract Image alignment and colour consistency are two challenging tasks for image stitching. Traditional point correspondence methods are difficult to achieve good alignments due to their insufficiency and unreliability. The results are prone to errors and distortions. On the other hand, the problem of colour inconsistency in overlapping area between image pairs is still difficult to solve, especially when the illumination difference between images is large. To solve these problems, the authors integrate point features and line features into a warping model through a designed energy function. Line features will provide geometric constraints for image stitching, and remedy the defect of point correspondences in low‐textured image stitching. A global colour consistency optimization method with colour mapping via a histogram extreme point‐matching algorithm is proposed. The colour characteristic of reference images will be transferred to the others to achieve a global colour consistency. The proposed method is evaluated on a series of images, and compared with other methods. The experiments demonstrate that the proposed method provides convincing stitching results and achieves satisfied colour consistency results.https://doi.org/10.1049/ipr2.12120Image recognitionComputer vision and image processing techniques |
| spellingShingle | Xingsheng Yuan Yongbin Zheng Wei Zhao Jiongming Su Jianzhai Wu Image stitching method by multi‐feature constrained alignment and colour adjustment IET Image Processing Image recognition Computer vision and image processing techniques |
| title | Image stitching method by multi‐feature constrained alignment and colour adjustment |
| title_full | Image stitching method by multi‐feature constrained alignment and colour adjustment |
| title_fullStr | Image stitching method by multi‐feature constrained alignment and colour adjustment |
| title_full_unstemmed | Image stitching method by multi‐feature constrained alignment and colour adjustment |
| title_short | Image stitching method by multi‐feature constrained alignment and colour adjustment |
| title_sort | image stitching method by multi feature constrained alignment and colour adjustment |
| topic | Image recognition Computer vision and image processing techniques |
| url | https://doi.org/10.1049/ipr2.12120 |
| work_keys_str_mv | AT xingshengyuan imagestitchingmethodbymultifeatureconstrainedalignmentandcolouradjustment AT yongbinzheng imagestitchingmethodbymultifeatureconstrainedalignmentandcolouradjustment AT weizhao imagestitchingmethodbymultifeatureconstrainedalignmentandcolouradjustment AT jiongmingsu imagestitchingmethodbymultifeatureconstrainedalignmentandcolouradjustment AT jianzhaiwu imagestitchingmethodbymultifeatureconstrainedalignmentandcolouradjustment |