Traffic-light driverless auxiliary device and method based on Faster RCNN

Abstract

The invention discloses a traffic-light driverless auxiliary device and method based on the Faster RCNN, and the device mainly comprises a main control Raspberry Pi 3B+, a wide angle camera, a buzzerprompt module, and a liquid crystal display screen module. The main control Raspberry Pi 3B+ is provided with a deep learning frame TensorFlow, and operates an RCNN (regional convolutional neural network) model. The wide angle camera collects a current road image in real time, determines the specific position of traffic lights through the deep learning model, and obtains a bounding rectangle. An ROI of the traffic lights is cut through OpenCV according to the bounding rectangle, so the calculation burden is smaller. After conventional filtering and other preprocessing operations, an image is converted into a Lab color space form a BGR color space, and channel a is independently extracted, and the traffic lights are recognized according to the ratio of the area of a connected domain. A final result will be prompted through the buzzer module and the display screen module. The device and method facilitate the reduction of traffic accidents, and improves the safety coefficient of driving.

Description

technical field [0001] The patent of the present invention relates to the field of unmanned driving and assisted driving, in particular to an RCNN-based traffic light recognition scheme design. Background technique [0002] In recent years, technological innovations in the direction of unmanned driving have continued to emerge, and many intelligent devices and systems have been widely practiced on actual roads, and can complete a certain degree of automatic or assisted driving. The effective recognition of traffic lights is one of the very important research topics. If the current traffic light information can be conveyed to the driver or the automatic driving system in a timely and accurate manner, it will be very beneficial to reduce traffic accidents and improve driving safety. [0003] The traffic lights and traffic signs in real life are complex and diverse. In addition to the circular shape of the common motor vehicle signal lights, there are also pedestrian signal lig...

AI Technical Summary

Problems solved by technology

Traditional BGR or HSV image processing methods are difficult to make a system with strong generalization ability, so it is imperative to use deep learning combined with traditional image processing methods

Images