Moving-object-traceable anti-collision warning method and device thereof

Abstract

The invention provides a moving-object-traceable anti-collision warning method and a device thereof. The device is arranged on a vehicle, a plurality of continuous images in 180 degrees of a front area are captured, at least one kind of obstacles among the continuous images is recognized through the images, and dynamic obstacles are found out; continuous relative positions of the dynamic obstacles and the vehicle are detected, and a first collision area of the vehicle is estimated; a second collision area of the dynamic obstacles is estimated according to the continuous relative positions and an extended kalman filtering algorithm; finally, a first collision point is estimated according to the first collision area and the second collision area, when the first collision area and the second collision area are at least partially overlapped, collision time is estimated, and a warning signal is output to warn a driver so as to improve driving safety.

Description

technical field [0001] The invention relates to an anti-collision warning method and its device, in particular to an anti-collision warning method capable of tracking moving objects and its device. Background technique [0002] As a means of transportation and transportation, vehicles have already played an important and indispensable role in human life. However, traffic accidents frequently occur in the densely populated living environment, and there are many reasons for traffic accidents, which can be broadly divided into weather, natural environment factors and human factors. In order to effectively reduce the probability of traffic accidents, related prevention The driving safety warning technology that the vehicle in running collides with other vehicles or pedestrians etc. unexpectedly has been developed successively for the selection of car owners to improve driving safety. [0003] Continuing on the products of driving safety warning, the most common use of GPS posit...

AI Technical Summary

Problems solved by technology

[0003] Continuing on the products of driving safety warning, the most common use of GPS positioning system is to detect obstacles and the relative distance between them and current vehicles. However, GPS is limited to environmental factors, such as current vehicles driving into areas with shelters , the obstacle cannot be detected, and the practicability is limited for the driver; or the distance sensor, image sensor, etc. are used, the distance sensor mainly assists obstacles in one direction, and the image sensor Wide-area visual aids can effectively assist the driver to grasp the relative distance between the current vehicle dynamics and obstacles, so as to reduce the occurrence of collision accidents

[0004] Furthermore, in order to improve the accuracy of estimating the relative distance between the current vehicle dynamics and the obstacle, a Kalman filter algorithm has been proposed to estimate the relative distance between the current vehicle and the obstacle and the collision time prediction method, however, This algorithm is only suitable for the estimation of linearly moving objects, and cannot be applied to predict the possibility of collision coming from any direction towards the driver, so the practical benefit is limited

Images