Automatic braking method and system based on image recognition and millimeter-wave radar fusion

Abstract

The invention relates to an automatic braking method and system based on image recognition and millimeter-wave radar fusion. The method comprises the following steps: millimeter-wave radar is adopted to acquire a radar image of a target in front of a vehicle and the distance between the target and the vehicle; a vehicle-mounted camera is adopted to acquire an image of the environment in front of the vehicle and a target image; the radar image of the target, the image of the environment and the target image are processed through deep learning based semantic segmentation; weighting fusion is performed on the processed images, and the distance between the vehicle and the target, the speed and acceleration are calculated according to the image information subjected to weighting fusion; estimated time for collision of the vehicle with the target is calculated according to the distance between the vehicle and the target, the speed and the acceleration; the vehicle is controlled to brake automatically when the estimated time for collision reaches collision braking critical time point. Braking control is performed after weighting fusion of the radar image of the target, the image of the environment and the target image, so that the automatic braking accuracy is higher, and the driving safety is improved.

Description

technical field [0001] The invention relates to automatic braking control technology, in particular to an automatic braking method and system based on image recognition and millimeter wave radar fusion. Background technique [0002] The automatic braking system is mainly composed of three modules: the information collection system, the data analysis system and the actuator. The automatic braking system collects the external environment data of the vehicle through the information collection system, and then uses the data analysis system to further process the collected data to obtain The distance between the vehicle and the target in front, and the expected collision time with the target in front. The actuator system compares the output results of the data analysis system with the warning distance and safety distance, and gives an alarm prompt when the distance is less than the warning distance; when the distance is less than the safety distance, even if the driver does not h...

AI Technical Summary

Problems solved by technology

Image-based ranging systems are easily affected by light, weather, etc., especially at night and in extreme weather (such as fog, snow) conditions, the detection performance is greatly reduced

Images