Traffic sign identification method, device and equipment
By preprocessing and feature extraction of driving images, integrating multi-scale features and performing bounding box regression and target classification processing, the problem of low accuracy in identifying traffic signs in the autonomous driving system is solved, and the recognition accuracy and reliability of safe driving of vehicles are improved.
CN119649334APending Publication Date: 2025-03-18HUNAN UNIV OF TECH
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202411496826.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-03-18
AI Technical Summary
Technical Problem
The autonomous driving system has low accuracy in identifying traffic signs, which affects the safe driving of the vehicle.
Method used
By acquiring driving images, preprocessing and feature extraction, multi-scale feature data are fused, bounding box regression and target classification are performed to improve the recognition accuracy of traffic signs.
Benefits of technology
It improves the accuracy and accuracy of the identification of traffic signs by the autonomous driving system, and improves the safe driving reliability of autonomous driving vehicles.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention provides a traffic sign recognition method, device and equipment, belongs to the technical field of computer information processing, and solves the problems that an automatic driving system is low in traffic sign recognition accuracy and poor in accuracy, and vehicle safety driving is affected. The method comprises the following steps: acquiring a driving image; preprocessing the driving image to obtain standard image data; performing feature extraction processing on the standard image data to obtain multi-scale feature data; performing fusion processing on the multi-scale feature data to obtain fused feature data; and performing bounding box regression and target classification processing on the fused feature data to obtain identification data. According to the scheme, the recognition accuracy and accuracy of the automatic driving system on the traffic sign board are improved, and the safe driving reliability of the automatic driving vehicle is improved.
Need to check novelty before this filing date? Find Prior Art