Research on traditional and deep learning strategies based on optical flow estimation - a review
Optical flow estimation captures the motion information of objects in a scene through analyzing the displacement of pixels in an image over time. This technology provides a powerful tool for vision systems, allowing them to understand and perceive changes in dynamic environments. Optical flow estima...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157824001186 |
| _version_ | 1831886581458272256 |
|---|---|
| author | Yifan Wang Wu Wang Yang Li Jinshi Guo Yu Xu Jiaqi Ma Yu Ling Yanan Fu Yaodong Jia |
| author_facet | Yifan Wang Wu Wang Yang Li Jinshi Guo Yu Xu Jiaqi Ma Yu Ling Yanan Fu Yaodong Jia |
| author_sort | Yifan Wang |
| collection | DOAJ |
| description | Optical flow estimation captures the motion information of objects in a scene through analyzing the displacement of pixels in an image over time. This technology provides a powerful tool for vision systems, allowing them to understand and perceive changes in dynamic environments. Optical flow estimation has a wide range of applications in fields such as military, medicine, traffic regulation, and intelligent robotics. This study systematically explores two key directions in the field of optical flow estimation—traditional methods and emerging strategies based on deep learning—aiming to provide a comprehensive and in-depth perspective to help scholars gain a deeper understanding of the development of the optical flow estimation field. First, the core principles and constraints of conventional optical flow estimation are briefly analyzed, focusing on reviewing the faced challenges and associated solutions based on differential, variational, and matching optical flow estimation principles. Then, we discuss the backbone networks and training strategies used in deep learning approaches in depth, with a particular focus on the current challenges faced under supervised and unsupervised conditions, as well as existing solutions. In addition, to evaluate the performance of these methods, existing datasets and evaluation indicators are analyzed and comprehensive comparisons on several publicly available datasets are conducted. Finally, we discuss prospects related to various application fields and future research directions in the field of optical flow estimation. |
| first_indexed | 2024-04-24T12:46:52Z |
| format | Article |
| id | doaj.art-7519f30e4668432eb97c6158d02d1c50 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2025-03-21T23:46:01Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-7519f30e4668432eb97c6158d02d1c502024-05-18T06:35:31ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782024-04-01364102029Research on traditional and deep learning strategies based on optical flow estimation - a reviewYifan Wang0Wu Wang1Yang Li2Jinshi Guo3Yu Xu4Jiaqi Ma5Yu Ling6Yanan Fu7Yaodong Jia8School of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaNorthern Navigation Control Technology Co., Ltd, Beijing 100000, China; School of Computing, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China; Corresponding author.School of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Electric and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaOptical flow estimation captures the motion information of objects in a scene through analyzing the displacement of pixels in an image over time. This technology provides a powerful tool for vision systems, allowing them to understand and perceive changes in dynamic environments. Optical flow estimation has a wide range of applications in fields such as military, medicine, traffic regulation, and intelligent robotics. This study systematically explores two key directions in the field of optical flow estimation—traditional methods and emerging strategies based on deep learning—aiming to provide a comprehensive and in-depth perspective to help scholars gain a deeper understanding of the development of the optical flow estimation field. First, the core principles and constraints of conventional optical flow estimation are briefly analyzed, focusing on reviewing the faced challenges and associated solutions based on differential, variational, and matching optical flow estimation principles. Then, we discuss the backbone networks and training strategies used in deep learning approaches in depth, with a particular focus on the current challenges faced under supervised and unsupervised conditions, as well as existing solutions. In addition, to evaluate the performance of these methods, existing datasets and evaluation indicators are analyzed and comprehensive comparisons on several publicly available datasets are conducted. Finally, we discuss prospects related to various application fields and future research directions in the field of optical flow estimation.http://www.sciencedirect.com/science/article/pii/S1319157824001186Optical flowDeep learningBackbone networksConstraintsTraining strategies |
| spellingShingle | Yifan Wang Wu Wang Yang Li Jinshi Guo Yu Xu Jiaqi Ma Yu Ling Yanan Fu Yaodong Jia Research on traditional and deep learning strategies based on optical flow estimation - a review Journal of King Saud University: Computer and Information Sciences Optical flow Deep learning Backbone networks Constraints Training strategies |
| title | Research on traditional and deep learning strategies based on optical flow estimation - a review |
| title_full | Research on traditional and deep learning strategies based on optical flow estimation - a review |
| title_fullStr | Research on traditional and deep learning strategies based on optical flow estimation - a review |
| title_full_unstemmed | Research on traditional and deep learning strategies based on optical flow estimation - a review |
| title_short | Research on traditional and deep learning strategies based on optical flow estimation - a review |
| title_sort | research on traditional and deep learning strategies based on optical flow estimation a review |
| topic | Optical flow Deep learning Backbone networks Constraints Training strategies |
| url | http://www.sciencedirect.com/science/article/pii/S1319157824001186 |
| work_keys_str_mv | AT yifanwang researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT wuwang researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT yangli researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT jinshiguo researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT yuxu researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT jiaqima researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT yuling researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT yananfu researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview AT yaodongjia researchontraditionalanddeeplearningstrategiesbasedonopticalflowestimationareview |