Method for identifying road speed limit sign running on auxiliary driving edge equipment

Abstract

The invention discloses a method for identifying a road speed limit sign running on auxiliary driving edge equipment, and belongs to the technical field of image processing. The method comprises the following steps: acquiring an original image of a vehicle-mounted usb camera; performing color space conversion and equalization on the original image; carrying out median filtering, binaryzation and morphological transformation on the image; carrying out contour detection on the image, and preliminarily determining an area where a speed limit sign possibly exists in the original image; filtering the area in which the speed limit sign possibly exists in the original image, and determining a to-be-identified speed limit sign area which conforms to a specific shape in the original image; identifying the to-be-identified speed limit sign area by using a LeNet-5 algorithm; completing deployment on an embedded platform Nvidia Jetson Agx Xavier, and a reasoning and detecting video stream from a camera in real time. The method has very high accuracy, the LeNet-5 model training time is short, the speed limit sign can be recognized in a very short time, and deployment and implementation on auxiliary driving edge equipment are facilitated.

Description

technical field [0001] The invention relates to a road speed limit sign recognition method running on an auxiliary driving edge device, and belongs to the technical field of image processing. Background technique [0002] In today's society, the number of cars has increased sharply, and road traffic jams have become common, which has brought great trouble to people's life and travel; traffic signs contain a lot of road information, which can be used for drivers during driving. Provide timely road environment information to comply with traffic rules. However, in the case of complex road conditions, drivers usually ignore the traffic signs on the roadside, resulting in traffic accidents, resulting in huge economic losses and casualties. Therefore, in recent years, traffic sign recognition technology in assisted driving has gradually attracted extensive attention from researchers at home and abroad. [0003] The traffic sign recognition technology with high precision and fast...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is: due to the correlation of each color channel, the recognition result is easily affected by light, etc., resulting in the incompleteness of traffic sign recognition

[0005] The current speed limit sign recognition algorithm cannot meet the requirements of real-time performance and high precision at the same time. Therefore, how to deploy a speed limit sign recognition algorithm in the field of assisted driving with high accuracy and real-time performance on embedded devices is as follows: At the same time, it provides strong support for the development of related theories and applications of assisted driving vehicles, and has important theoretical significance and practical value.

Images