Method and device for predicting collision between objects

Abstract

The invention discloses a method and a device for predicting the collision between objects. The method comprises the following steps: shooting two images of a second object at the position of a first object; determining an identical feature point pair on the second object in the two images; determining the distance between the two feature points of the feature point pair in each image; and determining the time of collision between the first object and the second object according to the distance between the two feature points of the feature point pair in each image and the shooting time interval of the two images. The predicted collision time can visually represent the collision risk at the current moment, and thus, drivers can be warned in a timely manner to perform a corresponding operation. Moreover, the method and the device have the advantages of high accuracy, good reliability, convenient use, low cost, low power consumption, and the like.

Description

technical field [0001] The invention relates to a collision prediction method and device between objects. Background technique [0002] With the rapid development of the automobile industry, the number of vehicles on the road has increased significantly, and automobile collision accidents have occurred frequently. Improper operation of the driver himself is one of the main causes of accidents. If it is possible to predict the occurrence of collision accidents and give appropriate warnings to drivers, it is of great significance for reducing traffic accidents and improving driving safety. In recent years, an image-based advanced driver assistance system (Advanced Driver Assistant System, referred to as ADAS) has received extensive attention. ADAS usually has a collision warning system, which collects video streams by means of a camera installed on the vehicle, and then estimates the possible collision time between the vehicle and the vehicle in front, thereby predicting pot...

AI Technical Summary

Problems solved by technology

Although judging according to the width of the vehicle can overcome the problem of limited installation position of the camera, in the actual driving process, the current vehicle is often not directly in front of the vehicle. Therefore, the camera can not only collect the image of the rear of the vehicle in front, but also The image of the side of the vehicle in front is collected, which makes it difficult for the system to clearly define the boundary of the rear of the vehicle in front, and cannot determine the actual width of the rear of the vehicle in front, resulting in inaccurate determination of the collision time

[0007] Prior art 4: The scheme disclosed in the invention with the authorized announcement number CN100386595C and the title "A vehicle collision avoidance warning method and its device" can only obtain the distance between the same feature points in two or more images. However, the speed of change of the distance between feature points cannot intuitively express the risk of collision during driving, so the solution of prior art 4 cannot predict the risk of collision, and needs to be supplemented by other calculation rules or model to achieve this

[0008] For the above problems, no effective solutions have been proposed so far

Images