Vehicle speed measurement method using monocular cameras
Abstract This paper proposes a method for fast and accurate vehicle speed measurement based on a monocular camera. Firstly, by establishing a new camera imaging model, the calibration method for variable focal lengths is optimized, simplifying the transformation process between the four coordinate s...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87077-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585876232732672 |
|---|---|
| author | Hao Lian Meian Li Ting Li Yongan Zhang Yanyu Shi Yikun Fan Wenqian Yang Huilin Jiang Peng Zhou Haibo Wu |
| author_facet | Hao Lian Meian Li Ting Li Yongan Zhang Yanyu Shi Yikun Fan Wenqian Yang Huilin Jiang Peng Zhou Haibo Wu |
| author_sort | Hao Lian |
| collection | DOAJ |
| description | Abstract This paper proposes a method for fast and accurate vehicle speed measurement based on a monocular camera. Firstly, by establishing a new camera imaging model, the calibration method for variable focal lengths is optimized, simplifying the transformation process between the four coordinate systems in traditional camera imaging models, and the method does not need to restore the pixel coordinates to dedistortion. Secondly, based on the camera imaging model, a two-dimensional positioning algorithm is proposed. By leveraging the characteristics of the speed measurement problem, the complex three-dimensional positioning problem is simplified into a two-dimensional model, reducing the overall computational complexity of the positioning problem. Finally, the algorithm is combined with You Only Look Once version 7 (YOLOv7) and Deep Simple Online and Realtime Tracking (DeepSORT) algorithms, integrating multiple model structures to optimize the network, achieving precise multi-target speed measurement. Experiments show that under frame-by-frame measurement conditions, the minimum and average accuracies of this method reach 95.1% and 97.6%, respectively. Compared with other methods, it has significant advantages in speed measurement accuracy and computational efficiency. Therefore, this research outcome is expected to play an important role in intelligent transportation systems and road safety management. |
| format | Article |
| id | doaj-art-cece4ad2ecb54c1bbae40a02e8ffb145 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cece4ad2ecb54c1bbae40a02e8ffb1452025-01-26T12:27:12ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-025-87077-6Vehicle speed measurement method using monocular camerasHao Lian0Meian Li1Ting Li2Yongan Zhang3Yanyu Shi4Yikun Fan5Wenqian Yang6Huilin Jiang7Peng Zhou8Haibo Wu9Computer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityComputer and Information Engineering College, Inner Mongolia Agricultural UniversityAbstract This paper proposes a method for fast and accurate vehicle speed measurement based on a monocular camera. Firstly, by establishing a new camera imaging model, the calibration method for variable focal lengths is optimized, simplifying the transformation process between the four coordinate systems in traditional camera imaging models, and the method does not need to restore the pixel coordinates to dedistortion. Secondly, based on the camera imaging model, a two-dimensional positioning algorithm is proposed. By leveraging the characteristics of the speed measurement problem, the complex three-dimensional positioning problem is simplified into a two-dimensional model, reducing the overall computational complexity of the positioning problem. Finally, the algorithm is combined with You Only Look Once version 7 (YOLOv7) and Deep Simple Online and Realtime Tracking (DeepSORT) algorithms, integrating multiple model structures to optimize the network, achieving precise multi-target speed measurement. Experiments show that under frame-by-frame measurement conditions, the minimum and average accuracies of this method reach 95.1% and 97.6%, respectively. Compared with other methods, it has significant advantages in speed measurement accuracy and computational efficiency. Therefore, this research outcome is expected to play an important role in intelligent transportation systems and road safety management.https://doi.org/10.1038/s41598-025-87077-6Monocular visionTwo-dimensional positioningCamera calibrationYOLOv7DeepSORT |
| spellingShingle | Hao Lian Meian Li Ting Li Yongan Zhang Yanyu Shi Yikun Fan Wenqian Yang Huilin Jiang Peng Zhou Haibo Wu Vehicle speed measurement method using monocular cameras Scientific Reports Monocular vision Two-dimensional positioning Camera calibration YOLOv7 DeepSORT |
| title | Vehicle speed measurement method using monocular cameras |
| title_full | Vehicle speed measurement method using monocular cameras |
| title_fullStr | Vehicle speed measurement method using monocular cameras |
| title_full_unstemmed | Vehicle speed measurement method using monocular cameras |
| title_short | Vehicle speed measurement method using monocular cameras |
| title_sort | vehicle speed measurement method using monocular cameras |
| topic | Monocular vision Two-dimensional positioning Camera calibration YOLOv7 DeepSORT |
| url | https://doi.org/10.1038/s41598-025-87077-6 |
| work_keys_str_mv | AT haolian vehiclespeedmeasurementmethodusingmonocularcameras AT meianli vehiclespeedmeasurementmethodusingmonocularcameras AT tingli vehiclespeedmeasurementmethodusingmonocularcameras AT yonganzhang vehiclespeedmeasurementmethodusingmonocularcameras AT yanyushi vehiclespeedmeasurementmethodusingmonocularcameras AT yikunfan vehiclespeedmeasurementmethodusingmonocularcameras AT wenqianyang vehiclespeedmeasurementmethodusingmonocularcameras AT huilinjiang vehiclespeedmeasurementmethodusingmonocularcameras AT pengzhou vehiclespeedmeasurementmethodusingmonocularcameras AT haibowu vehiclespeedmeasurementmethodusingmonocularcameras |