Front barrier detection system and method for unmanned driving automobile

Abstract

The invention discloses a front barrier detection system and method for an unmanned driving automobile. The system comprises a millimeter wave radar, a vision camera and an information processing system, wherein the millimeter wave radar is connected with an industrial control computer through a CAN bus, the vision camera is connected with the industrial control computer through a 1394 interface,the information processing system comprises functions as follows, space coordinate calibration and time synchronization for the millimeter wave radar and the vision camera are carried out, millimeterwave radar data is acquired and resolved, a data processing algorithm based on Kalman filtering is utilized to analyze the barrier information, false targets are eliminated to determine effective targets, the information of the vision camera is acquired, an image processing algorithm is utilized to detect barriers, the barrier information identified by the millimeter wave radar is compared with the barrier information identified by the vision camera, and the barriers detected by the two types of sensors are taken as the reference to establish an accurate grid map. The method is advantaged in that accuracy is high, cost is relatively low, and practicality of an unmanned automobile environment sensing system can be effectively improved.

Description

technical field [0001] The invention relates to a vehicle obstacle detection method, in particular to a front obstacle detection method for the fusion of millimeter wave radar and visual camera data of an unmanned vehicle. Background technique [0002] A driverless car is a kind of smart car, which mainly relies on the information processing system in the car to control the movement of the car. The information processing system in the car mainly includes the environment perception system, path planning system and decision-making control system. Among them, the environmental perception system is mainly responsible for sensing the environment around the vehicle, and generating an environmental map around the vehicle, providing an effective planning basis for the path planning system, thereby controlling the movement of the vehicle. In order to ensure the safety of the vehicle, the environmental perception system needs to have high accuracy, accurately describe the environment...

AI Technical Summary

Problems solved by technology

[0004] However, there are false detections and missed detections during the use of a single sensor. In order to ensure the accuracy of the environmental perception system, multiple sensors are usually used to detect surrounding obstacles and perform information fusion to obtain fused environmental information.

The application number is "201210309515.0" and the application publication number is "CN102837658A". The patent "Multi-Lidar Data Fusion System and Method in Intelligent Vehicles" discloses a multi-lidar data fusion system. The surrounding environment is detected, and the detection accuracy is high, but the structure is complex, the cost is high, and the practicability is poor

Images