Heterogeneous scene matching based on the gradient direction distribution field
Abstract Heterogeneous scene matching is a key technology in the field of computer vision. The image rotation problem is popular and difficult in the field of heterogeneous scene matching. In this paper, a heterogeneous scene matching method based on the gradient direction distribution field is prop...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-04-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13640-023-00608-x |
| _version_ | 1797836309038891008 |
|---|---|
| author | Qingge Li Ruitao Lu Xiaogang Yang Siyu Wang Tong Shen Wenxin Xia Zhaoying Wei |
| author_facet | Qingge Li Ruitao Lu Xiaogang Yang Siyu Wang Tong Shen Wenxin Xia Zhaoying Wei |
| author_sort | Qingge Li |
| collection | DOAJ |
| description | Abstract Heterogeneous scene matching is a key technology in the field of computer vision. The image rotation problem is popular and difficult in the field of heterogeneous scene matching. In this paper, a heterogeneous scene matching method based on the gradient direction distribution field is proposed, and distributed field theory is introduced into heterogeneous scene matching for the first time. First, the distribution field of the gradient direction is constructed and fuzzified, and then the effective regions are selected. Then, the distribution field of the main direction is defined to solve the matching errors due to the existence of rotational transformations between heterogeneous source images. Third, the chi-square distance is introduced as a similarity measure. Finally, the hill-climbing method search strategy, which greatly improves the efficiency of the algorithm, is adopted. Experimental results on 8 pairs of infrared and visible heterogeneous images demonstrate that the proposed method outperforms the other state-of-the-art region-based matching methods in terms of the robustness, accuracy, and real-time performance. |
| first_indexed | 2024-04-09T15:07:50Z |
| format | Article |
| id | doaj.art-c844b7b22fdb4731bc7a161b7329f72f |
| institution | Directory Open Access Journal |
| issn | 1687-5281 |
| language | English |
| last_indexed | 2024-04-09T15:07:50Z |
| publishDate | 2023-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-c844b7b22fdb4731bc7a161b7329f72f2023-04-30T11:24:14ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812023-04-012023111710.1186/s13640-023-00608-xHeterogeneous scene matching based on the gradient direction distribution fieldQingge Li0Ruitao Lu1Xiaogang Yang2Siyu Wang3Tong Shen4Wenxin Xia5Zhaoying Wei6Rocket Force University of EngineeringRocket Force University of EngineeringRocket Force University of EngineeringRocket Force University of EngineeringRocket Force University of EngineeringRocket Force University of EngineeringCollege of Science, Xi’an Shiyou UniversityAbstract Heterogeneous scene matching is a key technology in the field of computer vision. The image rotation problem is popular and difficult in the field of heterogeneous scene matching. In this paper, a heterogeneous scene matching method based on the gradient direction distribution field is proposed, and distributed field theory is introduced into heterogeneous scene matching for the first time. First, the distribution field of the gradient direction is constructed and fuzzified, and then the effective regions are selected. Then, the distribution field of the main direction is defined to solve the matching errors due to the existence of rotational transformations between heterogeneous source images. Third, the chi-square distance is introduced as a similarity measure. Finally, the hill-climbing method search strategy, which greatly improves the efficiency of the algorithm, is adopted. Experimental results on 8 pairs of infrared and visible heterogeneous images demonstrate that the proposed method outperforms the other state-of-the-art region-based matching methods in terms of the robustness, accuracy, and real-time performance.https://doi.org/10.1186/s13640-023-00608-xHeterogeneous imagesScene matchingDistribution fieldHill-climbing method |
| spellingShingle | Qingge Li Ruitao Lu Xiaogang Yang Siyu Wang Tong Shen Wenxin Xia Zhaoying Wei Heterogeneous scene matching based on the gradient direction distribution field EURASIP Journal on Image and Video Processing Heterogeneous images Scene matching Distribution field Hill-climbing method |
| title | Heterogeneous scene matching based on the gradient direction distribution field |
| title_full | Heterogeneous scene matching based on the gradient direction distribution field |
| title_fullStr | Heterogeneous scene matching based on the gradient direction distribution field |
| title_full_unstemmed | Heterogeneous scene matching based on the gradient direction distribution field |
| title_short | Heterogeneous scene matching based on the gradient direction distribution field |
| title_sort | heterogeneous scene matching based on the gradient direction distribution field |
| topic | Heterogeneous images Scene matching Distribution field Hill-climbing method |
| url | https://doi.org/10.1186/s13640-023-00608-x |
| work_keys_str_mv | AT qinggeli heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT ruitaolu heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT xiaogangyang heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT siyuwang heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT tongshen heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT wenxinxia heterogeneousscenematchingbasedonthegradientdirectiondistributionfield AT zhaoyingwei heterogeneousscenematchingbasedonthegradientdirectiondistributionfield |