In-vehicle passenger detection method and system

Abstract

The invention provides an in-vehicle passenger detection method and system, and relates to the technical field of in-vehicle passenger retention detection, and the method comprises the steps: continuously transmitting radar signals to a to-be-detected area in a vehicle, and receiving corresponding radar echo signals; distance information and angle information are extracted from the radar echo signals, and corresponding distance azimuth heat maps are obtained through processing according to the distance information and the angle information; performing feature extraction on each distance azimuth heat map to obtain corresponding passenger feature data; and inputting the passenger feature data into a classification model obtained by pre-training, and processing the passenger feature data to obtain passenger distribution data of the to-be-detected area. The system has the advantages that the millimeter-wave radar is used for detecting passengers in the vehicle, all-weather work can be achieved, the system is not sensitive to light in the vehicle, and privacy of the passengers in the vehicle can be effectively protected; the passenger distribution in the vehicle can be effectively detected, the detection accuracy is high, and accidents caused by the fact that children are left in the vehicle are reduced.

Description

technical field [0001] The invention relates to the technical field of occupant retention detection in a vehicle, in particular to a method and system for occupant detection in a vehicle. Background technique [0002] With the vigorous development of unmanned driving, various ADAS (Advanced Driving Assistant System), that is, advanced driver assistance systems have emerged as the times require. Among them, it includes not only the adaptive cruise system with the function of sensing the environment outside the vehicle, the lane departure warning system, the collision avoidance or pre-collision system, the automatic parking system, the blind spot detection system, etc., but also the driver who perceives the environment inside the vehicle. Fatigue detection and vehicle occupant detection, etc. All of these are of great significance to the development of unmanned driving to a higher level. [0003] Person detection plays an important role in a variety of applications. Most of...

AI Technical Summary

Problems solved by technology

However, since the method is primarily based on the weight on the seat, mechanical sensors may not be able to distinguish between a person and another object placed above the seat, prone to false alarms or false negatives for children who are not heavy enough

Ultrasonic sensors are mainly used in parking assistance systems, and it is difficult to classify detection targets, that is, it is difficult to distinguish whether the target is a human

The camera has blind spots, such as objects behind the front passenger seat are difficult to monitor; the performance in terms of privacy is not ideal; and it is difficult to identify occlusions such as children covered by blankets

Images