Unmanned vehicle vision recognition system based on dual cameras

Abstract

The invention provides an unmanned vehicle vision recognition system based on dual cameras, which comprises a first image acquisition module, a second image acquisition module, a lane recognition module, a vehicle recognition module, a traffic sign recognition module, and a traffic signal lamp detection and recognition module. According to the unmanned vehicle vision recognition system based on dual cameras provided by the invention, the technical problems that a large amount of data needs to be processed due to a single camera in a vehicle vision processing system in the prior art, and the real-time performance is influenced can be solved.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a dual-camera-based visual recognition system for unmanned vehicles. Background technique [0002] Existing smart car vision processing systems generally use a single camera to collect data to identify road information such as lane lines, traffic signs, and traffic lights. However, in application, the lane line recognition hopes that the closest area captured by the camera is as close as possible to the car, while the recognition of traffic signs and traffic lights hopes that the area captured by the camera is wider and farther away, so as to facilitate real-time processing. At the same time, the use of a single camera needs to capture a large range, which requires a higher-pixel camera, which requires a large amount of data to process and affects real-time performance. Contents of the invention [0003] In order to solve the technical problem that a single camera processes a ...

AI Technical Summary

Problems solved by technology

At the same time, the use of a single camera needs to shoot a large range, which requires a camera with higher pixels, and the amount of data to be processed is large, which affects real-time performance.

Images