YOLO-based vehicle information detection and tracking method and device, and computer storage medium

Abstract

The embodiment of the invention provides a YOLO-based vehicle information detection and tracking method and device, and a computer storage medium, wherein the method comprises the steps of: obtainingvideo data to be detected; detecting an image to be detected through a pre-set YOLO-based vehicle object detection model, so that an object vehicle in the image to be detected is determined; detectingthe image to be detected through a pre-set YOLO-based vehicle logo detection model and a pre-set YOLO-based vehicle colour detection model, so that a logo detection result and a colour detection result of the object vehicle are obtained; and locking the object vehicle according to the logo detection result of the object vehicle and / or the colour detection result of the object vehicle, and tracking the object vehicle through data association. According to the scheme, the image to be detected is directly detected by utilization of the YOLO-based detection model; the object vehicle and the logoand the colour of the object vehicle are identified; therefore, the object vehicle is accurately locked and correspondingly tracked; and thus, the technical problems of being complex in implementationprocess and low in processing efficiency in the existing method can be solved.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a method, device and computer storage medium for vehicle information detection and tracking based on YOLO. Background technique [0002] With the development and popularization of technology, the use of computer vision technology to automatically detect and identify vehicles in the area has gradually received more and more attention and attention in the fields of urban monitoring, traffic guidance, and intelligent driving. [0003] At present, most of the existing vehicle tracking methods first divide the image into multiple image blocks based on corresponding feature extraction schemes (such as HOG, SURF, etc.), and then separately analyze the vehicle features in multiple image blocks (such as license plate and other features) to identify and detect separately, and then integrate the vehicle features identified from multiple image blocks to determine the basic ...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a YOLO-based vehicle information detection and tracking method and device to solve the technical problems of low vehicle identification and tracking speed and poor accuracy in the existing methods, so as to efficiently and accurately identify the target vehicle , and the technical effect of real-time tracking of the target vehicle in the acquired video data

Images