Method for acquiring coordinate transformation matrix and positioning target in monitoring picture

Abstract

The invention discloses a method for acquiring a coordinate transformation matrix and positioning a target in a monitoring picture, and the method comprises the steps: controlling a camera to move toa preset PTZ position, and enabling the PTZ position to serve as a calibration scene; selecting at least one calibration point from the calibration scene; obtaining pixel coordinates of a calibrationpoint in a camera coordinate system corresponding to the camera in the calibration scene; acquiring GPS information of the calibration point and GPS information of the camera; establishing a world coordinate system by taking the projection point of the camera on the ground as an original point, and calculating the world coordinate of the calibration point by utilizing the GPS information of the calibration point and the GPS information of the camera; calculating to obtain an external parameter matrix of a world coordinate system and a camera coordinate system by utilizing the world coordinatesof the calibration points and the pixel coordinates of the calibration points. The PTZ position does not need to be adjusted for multiple times, the calibration workload is reduced, the world coordinate of the target point can be converted into the pixel coordinate by utilizing the external parameter matrix of the conversion relationship between the world coordinate system and the camera coordinate system, and the difficulty of positioning calculation is reduced.

Description

technical field [0001] The invention relates to the technical field of intelligent video monitoring, in particular to a method for acquiring a coordinate conversion matrix and locating a target in a monitoring screen. Background technique [0002] With the progress and development of society, the application of target recognition, tracking, scene recognition and indexing is becoming more and more extensive, and people's requirements for video surveillance are also getting higher and higher. In the field of intelligent video surveillance, functions such as displaying landmark buildings in the video frame, tracking moving vehicles, and associating other monitoring equipment have been valued by major security monitoring manufacturers. Through the rich media capabilities of augmented reality tags, various Spatial relationships of class structured and unstructured data. For example: [0003] The existing technology is to calibrate around the camera by using the calibration poin...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a method for acquiring a coordinate transformation matrix and locating a target in a monitoring screen, which solves the problem that in the prior art, multiple PTZ positions are required to perform calibration operations to predict the pixel coordinates of the target point, resulting in calibration The workload is heavy and inconvenient, and the process of predicting the pixel coordinates of the target point is complicated

Images