Three-dimensional reestablishing method for intelligent video monitoring

Abstract

The invention relates to a three-dimensional reestablishing method for intelligent video monitoring, which comprises the following steps: calibrating a camera and calibrating the camera deeply by adopting a direct linear method to obtain a transformation matrix M; calculating the position coordinates of a shooting point according to the perspective matrix M; and generating a three-dimensional outline altitude chart according to an isometric triangle theory in solid geometry and constructing a three-dimensional point set in a world coordinate system. According to the three-dimensional reestablishing method for intelligent video monitoring, the performance of an intelligent monitoring system is enhanced, and three-dimensional altitude information in a monitoring range can be accurately obtained; and moreover, the calculating speed is high.

Description

technical field [0001] The invention relates to a three-dimensional reconstruction method based on an intelligent video monitoring. Background technique [0002] The definition of 3D reconstruction uses computer to virtual represent 3D objects, and further analyzes the keys of various properties or characteristics. Roughly, it can be divided into two categories. The first category is to manually carry out three-dimensional geometric modeling through computer software, for example, by means of computer graphics software such as CAD and 3DMAX. The other is to use the obtained low-dimensional signal, process it into a graph or image with certain three-dimensional spatial position information, and reconstruct three-dimensional spatial information with the help of various depth recovery algorithms, such as binocular vision and multi-eye vision. The present invention is aimed at the second three-dimensional reconstruction method. [0003] In the traditional imaging process, the ...

AI Technical Summary

Problems solved by technology

Binocular stereo vision (binocular stereo vision) is currently the most widely used 3D reconstruction method, which mainly uses the parallax generated when the camera observes objects in the same scene at different positions to restore depth information, but binocular stereo vision There are still many problems. For example, the search and matching of points with the same name is the key and difficulty of the entire binocular vision. In addition, the binocular vision also faces the problem of calculation speed and accuracy, and special hardware is needed to accelerate the calculation.

Images