Three-dimensional distance measurement method for adaptively adjusting baseline of binocular camera

Abstract

The invention discloses a three-dimensional distance measurement method for adaptively adjusting a baseline of a binocular camera, and aims to solve the problem that a calibration object is not easy to place when multi-view camera three-dimensional measurement is carried out in an outdoor scene, the size of a small marker is small, image pixels are few and blurred, the horizontal distance of pixels of matched feature points in binocular camera measurement is too small, the precision is low and use is not completed basically, a small marker is firstly used nearby to calibrate internal and external parameters of a binocular camera, then the baseline of the binocular camera is expanded, and after the baseline is expanded, the pixel distance on the same feature point image at a distance is increased, so that the measurement precision is improved; and after internal and external parameters obtained by original calibration are measured, and three-dimensional distance measurement is performedin a mode of quantifying a result in proportion. The binocular camera outdoor calibration becomes feasible, the precision of the obtained measurement result can reach within 0.5% under the conditionof accurately controlling the moving baseline distance of the camera, and the three-dimensional distance measurement method can also be applied to the application fields of target tracking monitoring,intelligent event analysis and the like.

Description

technical field [0001] The invention relates to the field of augmented reality in computer application technology and computer vision, in particular to a three-dimensional distance measurement method for adaptively adjusting the baseline of a binocular camera. This method is mainly applied to distance measurement in a large scene, where the large scene refers to a distance range of 10 meters to 100 meters. The specific subfields are 3D restoration of feature points in 3D scene restoration or reconstruction based on multiple images (pictures) from multiple perspectives, and distance measurement. The 3D restoration technology based on multi-view images is generally expressed in English as Structure from Motion (SfM), and it also has corresponding applications in photogrammetry. Background technique [0002] Augmented reality refers to a technology that extends and expands the human visual system by superimposing computer-generated virtual scenes, text annotations and other in...

AI Technical Summary

Problems solved by technology

[0026] The present invention aims to solve the technical problem of binocular cameras generating depth maps and 3D point clouds in stereo measurement: when performing 3D measurement with multi-view cameras in outdoor scenes, calibration objects are not easy to place, especially on the top of buildings, outdoors, etc. When installing on poles, etc.; due to its small size, there are few pixels in the image and the small markers are blurred. In the measurement of the binocular camera, the horizontal distance between the pixels of the matching feature points is too small, and the accuracy is not high, so it is basically unusable.

Images