The invention provides a vehicle speed detection method and device and a storage medium, and the method comprises the steps: employing an improved YOLOX target detection network to recognize a vehicle for collected continuous video frames; a DeepSort target tracking algorithm is used for matching identification results output by the target detection network before and after the frame, and the same target is found in different frames; and converting the position distance of the target in different frames of images into an actual ground plane distance by using a coordinate system transformation algorithm, and dividing the actual ground plane distance by the detection interval time to obtain the vehicle speed. According to the invention, based on the improved YOLOX target detection network and the DeepSort target tracking algorithm, in combination with the coordinate system conversion algorithm, the vehicle speed in the shooting area is detected economically and efficiently.
本发明提供了一种车辆速度检测方法、装置及存储介质,所述方法包括:对于收集的连续视频帧,使用改进的YOLOX目标检测网络来识别车辆;利用DeepSort目标跟踪算法对帧前后目标检测网络输出的识别结果进行匹配,在不同帧中找到相同的目标;利用坐标系变换算法将目标在不同帧图像中的位置距离转换为实际的地平面距离,并将其除以检测间隔时间,得到车速。本发明基于改进的YOLOX目标检测网络和DeepSort目标跟踪算法,结合坐标系换算算法,实现了经济、高效地检测拍摄区域内车辆速度。
Vehicle speed detection method and device and storage medium
一种车辆速度检测方法、装置及存储介质
2024-03-12
Patent
Elektronische Ressource
Chinesisch
IPC: | G06V / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Vehicle speed limit detection method and device, detection equipment and storage medium
Europäisches Patentamt | 2024
|Europäisches Patentamt | 2020
|Vehicle speed anomaly detection method, device and equipment and storage medium
Europäisches Patentamt | 2020
|VEHICLE SPEED GUIDING METHOD, DEVICE, VEHICLE, AND STORAGE MEDIUM
Europäisches Patentamt | 2022
|Europäisches Patentamt | 2020
|