Driving blind spot monitoring method, apparatus and device, and readable storage medium
By determining the background area and obstacle monitoring area in the driving blind spot monitoring system, calculating the grayscale standard value and judging the obstacle, the problem of high missed detection rate in the prior art is solved, and higher obstacle identification accuracy and lower implementation cost are achieved.
WO2025060413A1 Publication Date: 2025-03-27DONGFENG COMML VEHICLE CO LTD
5 Cites 2 Cited by
Patent Information
- Application Number
- PCT/CN2024/088761
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-09-22
- Filing Date
- 2024-04-19
- Publication Date
- 2025-03-27
AI Technical Summary
Technical Problem
The existing driving blind spot monitoring methods are prone to missed detection. Due to the feature matching algorithm and feature database, the types of obstacles are limited.
Method used
By determining the background area and obstacle monitoring area from the video data collected from the target camera, the grayscale change reference value of the target image group is calculated, the grayscale standard value is calculated based on the target image group, and whether there are obstacles in the obstacle monitoring area is judged.
Benefits of technology
Reduces missed detection, does not rely on feature matching and feature databases, reduces implementation costs, and improves the accuracy of identification of obstacles.
✦ Generated by Eureka AI based on patent content.
Abstract
The present application provides a driving blind spot monitoring method, apparatus and device, and a readable storage medium. The method comprises: determining a background area and an obstacle monitoring area from areas photographed by a target camera; preprocessing video data collected by the target camera to obtain target video data; determining a target image group from the target video data; for each pixel point in the obstacle monitoring area, taking a grayscale average value of a same pixel point in the target image group as a grayscale standard value of the pixel point; and outputting an obstacle recognition result in the obstacle monitoring area on the basis of differences between the grayscale values of all the pixel points in the obstacle monitoring area in subsequent images of the target image group and the corresponding grayscale standard values. The present application does not depend on feature matching and is not limited by a feature database, thereby reducing missed detection.
Need to check novelty before this filing date? Find Prior Art