Real-time measurement of fluorescent oil film motion path based on GPU
In the wind tunnel experiment, the existing CPU-based optical flow method takes too long to solve the velocity field of the fluorescent oil film, while the GPU-based optical flow method has the problem of insufficient utilization of GPU resources.To this end, a real-time measurement method of GPU fl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Advances in Aeronautical Science and Engineering
2023-02-01
|
| Series: | Hangkong gongcheng jinzhan |
| Subjects: | |
| Online Access: | http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2022048 |
| _version_ | 1797823300715413504 |
|---|---|
| author | WU Peiling ZHANG Zhengyu SUN Wei |
| author_facet | WU Peiling ZHANG Zhengyu SUN Wei |
| author_sort | WU Peiling |
| collection | DOAJ |
| description | In the wind tunnel experiment, the existing CPU-based optical flow method takes too long to solve the velocity field of the fluorescent oil film, while the GPU-based optical flow method has the problem of insufficient utilization of GPU resources.To this end, a real-time measurement method of GPU fluorescent oil film motion path based on fluorescent oil film image segmentation and critical constraints is proposed.The fluorescent oil film time-series image is divided into blocks and processed in parallel according to the resources of the GPU, and the corresponding optical flow parallel computing strategy is created, that is, the advantages of the parallel pipeline architecture of the GPU and the shared memory are fully utilized to realize the optical flow calculation of each parallel block.At the same time, combined with the critical constraints between blocks, the number of iterative calculations is controlled by the iterative difference of the speed matrix of each block as a symbol.The experimental results show that the method proposed in this paper is 2 789.5 times faster than the traditional CPU-based optical flow method under the condition of ensuring the calculation accuracy of the velocity field of the fluorescent oil film motion, and the average speed of the GPU optical flow method of the whole frame image is improved.10.09 times and the real-time solution speed can reach 90 frames per second. |
| first_indexed | 2024-03-13T10:22:03Z |
| format | Article |
| id | doaj.art-a5682c8a8fbe4c63b9d90208d77a67cf |
| institution | Directory Open Access Journal |
| issn | 1674-8190 |
| language | zho |
| last_indexed | 2024-03-13T10:22:03Z |
| publishDate | 2023-02-01 |
| publisher | Editorial Department of Advances in Aeronautical Science and Engineering |
| record_format | Article |
| series | Hangkong gongcheng jinzhan |
| spelling | doaj.art-a5682c8a8fbe4c63b9d90208d77a67cf2023-05-20T08:56:58ZzhoEditorial Department of Advances in Aeronautical Science and EngineeringHangkong gongcheng jinzhan1674-81902023-02-01141157164,17410.16615/j.cnki.1674-8190.2023.01.1920230119Real-time measurement of fluorescent oil film motion path based on GPUWU Peiling0ZHANG Zhengyu1SUN Wei2School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaIn the wind tunnel experiment, the existing CPU-based optical flow method takes too long to solve the velocity field of the fluorescent oil film, while the GPU-based optical flow method has the problem of insufficient utilization of GPU resources.To this end, a real-time measurement method of GPU fluorescent oil film motion path based on fluorescent oil film image segmentation and critical constraints is proposed.The fluorescent oil film time-series image is divided into blocks and processed in parallel according to the resources of the GPU, and the corresponding optical flow parallel computing strategy is created, that is, the advantages of the parallel pipeline architecture of the GPU and the shared memory are fully utilized to realize the optical flow calculation of each parallel block.At the same time, combined with the critical constraints between blocks, the number of iterative calculations is controlled by the iterative difference of the speed matrix of each block as a symbol.The experimental results show that the method proposed in this paper is 2 789.5 times faster than the traditional CPU-based optical flow method under the condition of ensuring the calculation accuracy of the velocity field of the fluorescent oil film motion, and the average speed of the GPU optical flow method of the whole frame image is improved.10.09 times and the real-time solution speed can reach 90 frames per second.http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2022048optical flow methodimage blockcritical constraintfluorescent oil filmshared memory |
| spellingShingle | WU Peiling ZHANG Zhengyu SUN Wei Real-time measurement of fluorescent oil film motion path based on GPU Hangkong gongcheng jinzhan optical flow method image block critical constraint fluorescent oil film shared memory |
| title | Real-time measurement of fluorescent oil film motion path based on GPU |
| title_full | Real-time measurement of fluorescent oil film motion path based on GPU |
| title_fullStr | Real-time measurement of fluorescent oil film motion path based on GPU |
| title_full_unstemmed | Real-time measurement of fluorescent oil film motion path based on GPU |
| title_short | Real-time measurement of fluorescent oil film motion path based on GPU |
| title_sort | real time measurement of fluorescent oil film motion path based on gpu |
| topic | optical flow method image block critical constraint fluorescent oil film shared memory |
| url | http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2022048 |
| work_keys_str_mv | AT wupeiling realtimemeasurementoffluorescentoilfilmmotionpathbasedongpu AT zhangzhengyu realtimemeasurementoffluorescentoilfilmmotionpathbasedongpu AT sunwei realtimemeasurementoffluorescentoilfilmmotionpathbasedongpu |