Method and device for calculating position of target object based on monocular camera

Abstract

The invention provides a method and device for calculating the position of a target object based on a monocular camera, and relates to the technical field of road traffic. The method includes calibrating internal and external parameters of the monocular camera offline; collecting a single-frame image of the monocular camera, the positioning information of the vehicle in the map and the local map information around the vehicle in real time, and calculating the real position of the target object based on the fact that the real position of the target object is certainly on the connection ray of the central point of the monocular camera and the projection point of the target object in the same coordinate system. The method disclosed by the invention completely does not depend on horizon hypothesis, accurately calculates the real position of the target object, and is beneficial to road driving safety of the vehicle.

Description

technical field [0001] The invention relates to the technical field of road traffic, in particular to a method and device for calculating the position of an object based on a monocular camera. Background technique [0002] The current target depth estimation method based on the monocular camera restores the scale information of the monocular camera through the pre-calibrated camera height, and this method relies on the assumption of the ground plane, that is, the target object and the plane where the vehicle is located are on the same horizontal plane . The problem with this method is that in the actual application scenario, if the target object and the plane where the vehicle is located do not meet the assumption of the same horizontal plane, for example, the up and down slopes in the actual application scenario, the vehicle passing the speed bump or the uneven road surface cause If the self-vehicle bumps and the plane where the target object is located is not at the same ...

AI Technical Summary

Problems solved by technology

The problem with this method is that in the actual application scenario, if the target object and the plane where the vehicle is located do not meet the assumption of the same horizontal plane, for example, the up and down slopes in the actual application scenario, the vehicle passing the speed bump or the uneven road surface cause If the self-vehicle bumps and the plane where the target object is located is not at the same level as the self-vehicle, the projected position of the target object will be estimated too close or too far away, and the error is related to the camera installation height, angle, and the position of the target object on other planes Correlation, it is not easy to model the error, and the wrong position estimation will seriously affect the decision-making in the planning and control of the downstream modules

Images