Blind area collision prediction method during self-vehicle turning, equipment and storage medium

A prediction method, self-vehicle technology, applied to vehicle components, transportation and packaging, external condition input parameters, etc., can solve problems such as unpredictable collision risk, increased driving risk, and lack of emergency braking function

CN113511197AInactive Publication Date: 2021-10-19TIANJIN SOTEREA AUTOMOTIVE TECH LMITED CO +1
5 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2021-10-19
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to the field of camera detection, and discloses a blind area collision prediction method during self-vehicle turning, equipment and a storage medium. The method comprises the steps: in the self-vehicle turning process, acquiring multiple images shot by a vehicle-mounted BSD camera; performing target identification and tracking on blind areas in the multiple images, and determining a dynamic target which is identified to be pre-collided; calculating the relative speed and the relative distance between the dynamic target and the self-vehicle in the predicted self-vehicle trajectory direction; dividing the relative distance by the relative speed to calculate a collision duration; and if the dynamic target is predicted to be within the predicted self-vehicle trajectory range after the collision duration, determining that the dynamic target collides with the self-vehicle after the collision duration. According to the embodiment, whether the vehicle collides with the dynamic target in the blind area or not is predicted when the vehicle turns.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of collision prediction, in particular to a blind spot collision prediction method, device and storage medium when an ego vehicle turns. Background technique

[0002] The vehicle-mounted BSD (Blind Spot Detection, blind spot monitoring) camera (hereinafter referred to as the camera) is installed on both sides of the rear of the vehicle, and is used to detect the blind spots on both sides of the rear of the vehicle when the vehicle is driving. When pedestrians or riders are detected approaching the vehicle, an early warning will be triggered, such as flashing lights or sounding the horn.

[0003] Current BSD products (including the above-mentioned cameras) only provide early warning functions, and do not have emergency braking functions, nor can they predict whether there is a risk of collision. Especially in the scene where the vehicle is turning, the probability of collision is higher and the risk of driving increas...

Examples

Embodiment Construction

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0027] The blind spot collision prediction method when the own vehicle is turning provided by the embodiment of the present invention is mainly applicable to predicting whether the own vehicle collides with a dynamic target in the blind zone when the own vehicle is turning. The blind spot collision prediction method when the ego vehicle is turning provided by the embodiment of the present invention can be executed by electronic equipment.

[0028] figur...