Traffic jam identification method, device, system and equipment and storage medium
A technology of traffic congestion and identification methods, applied in traffic control systems, traffic control systems of road vehicles, character and pattern recognition, etc. problems, to achieve the effect of improving judgment accuracy, improving accuracy, and improving accuracy
Inactive Publication Date: 2022-06-03
NAVINFO
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present application provides a traffic jam recognition method, device, system, equipment and storage medium, which are used to solve the problem that vehicles on the road are often dense, and multiple horizontal frames overlap, thereby affecting the judgment of the vehicle position and causing target detection The accuracy is low, which affects the accuracy of traffic jam recognition
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
In an optional implementation manner, step S303 includes:
Step b1, if the total number of target rectangles in the M images to be recognized is greater than a preset number threshold, it is determined that traffic congestion occurs in the target road area; the total number of target rectangles is that all vehicles in the M images to be recognized are converted to the target type The number of rectangles behind the vehicle.
[0047] Step b2: If the total number of target rectangular frames in the M images to be identified is less than or equal to a preset number threshold, it is determined that there is no traffic congestion in the target road area.
[0048] Wherein, before step b1, step b3 needs to be performed: determining the total number of target rectangular frames in the M images to be recognized. Specifically, determine the total number of target rectangular frames in the M images to be identified, including:
Step b31: Determine the number of vehicles of the target ca...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a traffic jam identification method, device and system, equipment and a storage medium. The method comprises the following steps: acquiring M to-be-recognized images; each to-be-recognized image comprises N vehicles in the target road area, and M and N are integers greater than or equal to 1; inputting each to-be-recognized image into a detection network to obtain a target image; the target image comprises N rectangular frames, and each rectangular frame comprises one of N vehicles; an included angle exists between one edge of each rectangular frame and the positive direction of the X axis of the image to be recognized, and the long edge of each rectangular frame faces the driving direction of the corresponding vehicle; and determining a traffic jam identification result of the target road area according to the number of the rectangular frames in the M to-be-identified images.
Description
technical field [0001] The present application relates to the technical field of intelligent transportation, and in particular, to a method, device, system, device and storage medium for identifying traffic congestion. Background technique [0002] Urban traffic congestion has gradually become a common phenomenon that affects the living comfort of urban populations. If traffic congestion can be predicted in advance, the phenomenon of urban traffic congestion can be alleviated. [0003] The premise of traffic congestion prediction is the identification of vehicles on the road, that is, the target detection algorithm is used to detect the vehicles in the road image, and then determine whether traffic congestion occurs. At present, the target detection algorithm is a target detection algorithm based on a convolutional neural network, which marks the detected vehicle through a horizontal frame. [0004] However, vehicles on the road are often denser, and there will be overlaps...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06V10/25G06V10/774G06V10/82G06K9/62G06N3/04G08G1/065
CPCG08G1/065G06N3/045G06F18/214
Inventor 葛文超霍敬宇
Owner NAVINFO