Visualization method of multi-camera calibration results and system thereof

Abstract

The invention relates to the field of video monitoring and discloses a visualization method of multi-camera calibration results and a system thereof. According to the invention, the method comprises following steps of acquiring a plane mapping relation between a first camera image and a second camera image; receiving input information from an input device; according to the input information, generating and displaying a first auxiliary line on the first camera image; acquiring at least two points on the first auxiliary line, using the at least two points as a first point set and mapping all points in the first point set to the second camera image according to the plane mapping relation to serve as a second point set; and according to all points in the second point set, displaying a second auxiliary line on the second camera image. According to the invention, results of the multi-camera calibration are described through the auxiliary lines, thereby facilitating rapid and direct verification and observation of calibration conditions and confirmation of calibration precision.

Description

technical field [0001] The invention relates to the field of video monitoring, in particular to a visualization method and system for multi-camera calibration results. Background technique [0002] In the monitoring system, people may use the camera calibration technology to calibrate and correlate the images of multiple cameras, and make full use of the characteristics of multiple cameras for monitoring applications. Take the gun-ball linkage as an example, such as figure 1 Shown is the schematic diagram of the gun-ball linkage system. The gun-ball linkage system can make full use of the advantages of the wide monitoring scene of the gun machine and the ability of the ball machine to see the details of the target, and perform their duties. The bolt camera is used to overall control each moving target in the large scene, and the dome camera zooms in on the key targets to see the features clearly. The premise of the gun-ball linkage is to associate the two devices through c...

AI Technical Summary

Problems solved by technology

Although we have used some methods to filter out some inaccurate matching points, there are still some non-ground matching points that will be used in the calculation of plane matching, which will introduce errors in plane calibration

At the same time, even if our automatic point selection is relatively accurate, it is often near the calibration point. The calibration result is relatively accurate, but there may be large errors in other positions on the screen.

[0004] At present, the images of two cameras are usually displayed, and the staff directly compares whether there is a large error in the two images without the assistance of tools, and the accuracy of judgment is poor and the speed is slow.

Images