Alarm method and device for recognizing obstacle, electronic equipment and storage medium

Abstract

The embodiment of the application discloses an alarm method and device for recognizing an obstacle, electronic equipment and a storage medium. The method comprises the steps: determining a first distance between an obstacle and a vehicle at a first moment; acquiring wheel speed pulse signal data of the vehicle in a time interval from the first moment to a second moment; determining a second distance between the obstacle and the vehicle at the second moment according to the first distance and the wheel speed pulse signal data, and sending an alarm signal if the second distance is smaller than apreset alarm distance threshold. According to the application, when the sensing device cannot sense the distance between the obstacle and the vehicle, the driving distance of the vehicle and the second distance between the obstacle and the vehicle at the second moment are determined according to the first distance memorized by the alarm device and the wheel speed pulse data signal of the vehicleacquired in real time; if the second distance is smaller than the preset alarm distance threshold, an alarm signal is sent out. Therefore, the limitation that the sensing device has a sensing blind area can be made up; and the vehicle can be prevented from colliding with obstacles, so that vehicle driving safety is improved.

Description

technical field [0001] The invention relates to the field of intelligent driving, in particular to an alarm method, device, electronic device and storage medium for identifying obstacles. Background technique [0002] With the increasing application of intelligent driving technology in automobiles, the safety performance of vehicles has also attracted more and more attention. As an important part of intelligent driving technology, fully automatic parking has an irreplaceable role especially in low-speed intelligent driving, such as valet parking. However, fully automatic parking has certain limitations. Fully automatic parking vehicles that rely on ultrasonic radar to perceive the environment are limited by the relative distance between the vehicle and the obstacle. Once the obstacle enters the blind spot of the vehicle, the ultrasonic radar will not be able to perceive it. The existence of obstacles, especially some small and low obstacles; fully automatic parking vehicles...

AI Technical Summary

Problems solved by technology

However, fully automatic parking has certain limitations. Fully automatic parking vehicles that rely on ultrasonic radar to perceive the environment are limited by the relative distance between the vehicle and obstacles. Once an obstacle enters the blind spot of the vehicle, ultrasonic radar will not be able to perceive it. The existence of obstacles, especially some small and low obstacles; fully automatic parking vehicles that rely on camera deep learning to perceive the environment are not only limited by illumination, but also by the color difference between obstacles and the surrounding environment, and In the early stage of design, it is necessary to collect a large amount of feature information of various objects and the dimension data of objects for storage for subsequent feature matching

[0003] Although the above two methods can assist in the realization of fully automatic parking, the ability to identify obstacles during parking is poor, especially for some small and low obstacles.

Images