Target area detection method and device, storage medium and electronic device

Abstract

The embodiment of the invention provides a target area detection method and device, a storage medium and an electronic device, and the method comprises the steps: receiving original traffic data, obtaining a first area of a moving object in the original traffic data, carrying out the filtering of the first area based on a target threshold value, and obtaining a second area, target communication processing is carried out on the second area to obtain a target area detection frame, the target area detection frame is used for forming the target area in the traffic image data, the labor cost and the time cost in the process of determining the target area are saved, and the algorithm process is optimized.

Description

technical field [0001] Embodiments of the present invention relate to the field of data processing, and in particular, relate to a target area detection method, device, storage medium, and electronic device. Background technique [0002] With the advent of the information age, the field of artificial intelligence has also developed rapidly, and intelligent transportation has become an indispensable part of urban intelligent construction. [0003] Among them, in the monitoring of traffic events, relevant staff need to arrange different event monitoring tasks for cameras in different areas, such as illegal U-turns, vehicle congestion, abnormal parking, or detection of spilled objects, etc. How to determine the relevant target areas and arrange them The corresponding monitoring task becomes one of the important links. [0004] In the existing traffic incident deployment and control process, part of it is to manually frame the target area in the relevant video frame through the...

AI Technical Summary

Problems solved by technology

[0004] In the existing traffic incident deployment and control process, part of it is to manually frame the target area in the relevant video frame through the relevant algorithm staff, and then perform subsequent processing such as event detection on the target area, and manually framing the target area requires a lot of time. A lot of labor cost and time cost, and the frame line drawn manually is relatively rough, which is easy to cause data errors and missed detection;

[0005] The other part is to identify the lane line of the traffic road in the video frame through the background algorithm, and determine the target area through the lane line, but the visual error of the picture formed by the camera will make the lane line deviation and affect the accuracy of the target area determination; and some roads The lane lines in will be covered by passing vehicles, making it difficult to identify lane lines; and the process of determining the main lane line for detection and selecting the corresponding main lane line to form the target area is difficult to implement the algorithm

Images