Adaptive dual fractional‐order variational optical flow model for motion estimation
Insufficient illumination and illumination variation in image sequences make it challenging for algorithms to obtain clear outlines for objects in motion. This study proposes a high‐performance adaptive dual fractional‐order variational optical flow model which could be used to resolve these issues....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-04-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5285 |
| _version_ | 1797684218115915776 |
|---|---|
| author | Bin Zhu Lian‐Fang Tian Qi‐Liang Du Qiu‐Xia Wu Farisi Zeyad Sahl Yao Yeboah |
| author_facet | Bin Zhu Lian‐Fang Tian Qi‐Liang Du Qiu‐Xia Wu Farisi Zeyad Sahl Yao Yeboah |
| author_sort | Bin Zhu |
| collection | DOAJ |
| description | Insufficient illumination and illumination variation in image sequences make it challenging for algorithms to obtain clear outlines for objects in motion. This study proposes a high‐performance adaptive dual fractional‐order variational optical flow model which could be used to resolve these issues. The proposed method revitalises the original dual fractional‐order optical flow model and adopts a fractional differential mask in both the data and smoothness terms of the traditional Horn–Schunck model. The main innovation of this work is to fit a flow field regional to a variety of fractional‐order differential masks. The domain of each region is determined adaptively. The order and size of the fractional‐order differential masks for each region are adjusted by image signal to noise ratio while the shape of the fractional‐order differential mask is regulated to prevent interference from surrounding regions. Adjusting the fractional‐order differential mask adaptively enables the proposed method to accurately segment motion objects in poor and variable illumination regions as well. The experimental results show that our algorithm outperforms the current state‐of‐the‐art algorithms on low‐light real scene videos and also achieves competitive results on the Middlebury, KITTI and MPI Sintel public benchmarks. |
| first_indexed | 2024-03-12T00:26:29Z |
| format | Article |
| id | doaj.art-acbbf35bfc404bdea734fd87829983c5 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:26:29Z |
| publishDate | 2019-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-acbbf35bfc404bdea734fd87829983c52023-09-15T10:35:47ZengWileyIET Computer Vision1751-96321751-96402019-04-0113327728410.1049/iet-cvi.2018.5285Adaptive dual fractional‐order variational optical flow model for motion estimationBin Zhu0Lian‐Fang Tian1Qi‐Liang Du2Qiu‐Xia Wu3Farisi Zeyad Sahl4Yao Yeboah5School of Automation Science and Engineering, South China University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaSchool of Automation Science and Engineering, South China University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaSchool of Automation Science and Engineering, South China University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaSchool of Software Engineering, South China University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaSchool of Automation Science and Engineering, South China University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaSchool of Automation, Guangdong University of TechnologyGuangzhou CityGuangdong ProvincePeople's Republic of ChinaInsufficient illumination and illumination variation in image sequences make it challenging for algorithms to obtain clear outlines for objects in motion. This study proposes a high‐performance adaptive dual fractional‐order variational optical flow model which could be used to resolve these issues. The proposed method revitalises the original dual fractional‐order optical flow model and adopts a fractional differential mask in both the data and smoothness terms of the traditional Horn–Schunck model. The main innovation of this work is to fit a flow field regional to a variety of fractional‐order differential masks. The domain of each region is determined adaptively. The order and size of the fractional‐order differential masks for each region are adjusted by image signal to noise ratio while the shape of the fractional‐order differential mask is regulated to prevent interference from surrounding regions. Adjusting the fractional‐order differential mask adaptively enables the proposed method to accurately segment motion objects in poor and variable illumination regions as well. The experimental results show that our algorithm outperforms the current state‐of‐the‐art algorithms on low‐light real scene videos and also achieves competitive results on the Middlebury, KITTI and MPI Sintel public benchmarks.https://doi.org/10.1049/iet-cvi.2018.5285illumination variationhigh-performance adaptive dual fractional-order variational optical flow modelfractional differential maskfractional-order differential maskmotion estimationimage sequences |
| spellingShingle | Bin Zhu Lian‐Fang Tian Qi‐Liang Du Qiu‐Xia Wu Farisi Zeyad Sahl Yao Yeboah Adaptive dual fractional‐order variational optical flow model for motion estimation IET Computer Vision illumination variation high-performance adaptive dual fractional-order variational optical flow model fractional differential mask fractional-order differential mask motion estimation image sequences |
| title | Adaptive dual fractional‐order variational optical flow model for motion estimation |
| title_full | Adaptive dual fractional‐order variational optical flow model for motion estimation |
| title_fullStr | Adaptive dual fractional‐order variational optical flow model for motion estimation |
| title_full_unstemmed | Adaptive dual fractional‐order variational optical flow model for motion estimation |
| title_short | Adaptive dual fractional‐order variational optical flow model for motion estimation |
| title_sort | adaptive dual fractional order variational optical flow model for motion estimation |
| topic | illumination variation high-performance adaptive dual fractional-order variational optical flow model fractional differential mask fractional-order differential mask motion estimation image sequences |
| url | https://doi.org/10.1049/iet-cvi.2018.5285 |
| work_keys_str_mv | AT binzhu adaptivedualfractionalordervariationalopticalflowmodelformotionestimation AT lianfangtian adaptivedualfractionalordervariationalopticalflowmodelformotionestimation AT qiliangdu adaptivedualfractionalordervariationalopticalflowmodelformotionestimation AT qiuxiawu adaptivedualfractionalordervariationalopticalflowmodelformotionestimation AT farisizeyadsahl adaptivedualfractionalordervariationalopticalflowmodelformotionestimation AT yaoyeboah adaptivedualfractionalordervariationalopticalflowmodelformotionestimation |