A Vehicle Dimensions Dynamic Detection Method Based on Image Recognition
- Delivery
- Provide download link
- Format
- Price
- Non-members (tax incl.)：￥6,600 Members (tax incl.)：￥5,280
- Paper/Info type
- SAE Paper
No.2021-01-0167
- Pages
- 1-10(Total 10 p)
- Date of publication
- Apr 2021
- Publisher
- SAE International
- Language
- English
- Event
- SAE WCX Digital Summit 2021
Detailed Information
| Author(E) | 1) Feng’an Zhao, 2) Gangfeng Tan, 3) Bin Luo, 4) Wenchao Sun, 5) Jiaming Feng, 6) Kailang Chen |
|---|---|
| Affiliation(E) | 1) Wuhan University of Technology, 2) Wuhan University of Technology, 3) Hubei Public Security Department, 4) Wuhan University of Technology, 5) Wuhan University of Technology, 6) Wuhan University of Technology |
| Abstract(E) | The acquisition of vehicle dimensions in a vehicle’s moving process has a wide application in road monitoring, transportation, vehicle model recognition and non-contact overload recognition. At present, the detection of the vehicle dimensions mostly adopts the methods of human visual inspection and tool detection, which has a low detection efficiency and difficult to replicate on a large scale. Based on the image background subtraction method, this paper proposes a vehicle dimensions detection method, which can realize real-time detection of road vehicle dimensions. This method uses an adaptive Gaussian Mixture Model (GMM) to establish a background model based on the video stream. Initially, the moving target image is obtained by the background subtraction method, and then the edge detection under the Canny operator and Hough transform circle detection are performed on the image to obtain the pixel dimension of the vehicle's outline. Finally, the actual dimension is obtained by converting the image coordinate system to the actual coordinate system through dimension calibration. In this paper, nine types of vehicles were selected as experimental vehicles, and video data was captured with a digital camera and processed by image processing. Comparing the recognition result with actual dimensions, the recognition accuracy can be detected. Experimental results show that the vehicle dimensions recognition method proposed in this paper has good robustness, the relative error of identification can be controlled within 10%, and the minimum error can reach 4mm. The vehicle dimensions recognition method proposed in this paper can dynamically detect the dimensions of passing vehicles, which can significantly improve the identification efficiency of the vehicle dimensions, and is of great significance to road monitoring. |
