Target tracking method

Abstract

The invention discloses a target tracking method. The method comprises the steps that the high-precision three-dimensional space coordinate of a target is acquired; a high-precision positioning and attitude determination system is used to acquire the high-precision three-dimensional space coordinate and the attitude of a load in real time; according to the moving speed of the load and the geometric position relationship between a GNSS antenna and a camera in the high-precision positioning and attitude determination system, the three-dimensional space coordinate of a camera projection center is calculated; according to the three-dimensional space coordinate of the camera projection center and the three-dimensional space coordinate of the target, the target azimuth angle and the target attitude angle of the target are calculated; according to the target azimuth angle and the target attitude angle, the prediction attitude of a camera is calculated; the attitude of the camera is adjusted to the prediction attitude; and at an exposure position, the target is shot. The prediction attitude of the camera is adjusted in advance, which ensures that the attitude of the camera maintains stable in an exposure process, and a shot image is clear. The azimuth angle and the attitude angle of the camera are corresponding to the azimuth angle and the attitude angle of the target, which ensures that the target is at the middle position of the image shot by the camera.

Description

technical field [0001] The invention relates to the technical field of navigation positioning and target tracking, in particular to a target tracking method. Background technique [0002] Target tracking is a comprehensive application technology that integrates advanced achievements in various fields such as image processing, pattern recognition, artificial intelligence, automatic control, sensors, navigation and positioning, and is a widely used technology in military and civilian fields. [0003] At present, the tracking of the target is mainly based on vision-based target recognition and tracking and GNSS (Global Navigation Satellite System, Global Navigation Satellite System) tracking. [0004] Usually vision-based target tracking refers to the detection, recognition and tracking of moving targets or single-characteristic objects in image sequences, by obtaining parameters such as the position and speed of the target or features such as the shape and color of the target,...

AI Technical Summary

Problems solved by technology

[0006] The above methods can basically identify and automatically track targets to varying degrees, but there are problems such as low reliability, poor static target tracking effect, and difficulty in ensuring that the target is in the center of the captured picture under a narrow field of view.

Images