Method and system for calibrating multiple cameras

Abstract

The invention provides a method for calibrating multiple cameras, comprising the following steps: synchronizing the system time of the multiple cameras; establishing a field-of-view overlap area relationship diagram of the multiple cameras; calculating the average depth error estimated value of trajectory points of a tracked object extracted from each field-of-view overlap area, estimating the calibration error magnification factor of one jump of each field-of-view overlap area based on the average depth error estimated value, and giving the corresponding jump a weight based on the estimated calibration error magnification factor so as to convert the field-of-view overlap area relationship diagram into a weighted field-of-view overlap area relationship diagram; and acquiring a reference camera corresponding to the minimum calibration cumulative error by a minimum path algorithm based on the weighted field-of-view overlap area relationship diagram.

Description

technical field [0001] The invention relates to a method and system for calibrating multiple cameras, in particular to a method and system for improving the calibration accuracy of a camera network composed of multiple cameras by dynamically selecting one or more reference cameras as reference cameras. Background technique [0002] Recently, the research on human tracking and positioning system is no longer limited to the original positioning and tracking under constrained conditions, such as in the laboratory environment, the existing research scenarios have been expanded to complex real scenes such as subway stations and airports . In addition, for the existing video surveillance system, it is required not only to accurately provide the coordinates of the tracked person in the two-dimensional image, but also to provide the position of the tracked person in the real three-dimensional space. In order to meet the above needs, a tracking system based on multiple binocular ste...

AI Technical Summary

Problems solved by technology

Moreover, since this method adopts a sequential method to calibrate the deployed cameras, the calibration result of the binocular camera to be calibrated is related to the calibration result of the calibrated binocular camera that has an overlapping field of view with it, so there is a calibration Error Cumulative Propagation Problem

In this case, when an object to be tracked enters the field of view of the binocular camera with a large calibration error, but not in the field of view of the binocular camera with a small calibration error, it may be due to the large error of the binocular camera. Large and cause inaccurate positioning of objects

Images