Virtual-real fusion rendering method and device based on monocular camera reconstruction

Abstract

The invention discloses a virtual-real fusion rendering method and device based on monocular camera reconstruction, and the method and device can solve the problem that display lacks depth perception when virtual and real are mutually shielded, improve the depth perception of a doctor in augmented reality display, can obtain the position relation between a virtual model and a real anatomical structure more accurately, and are conducive to the expansion of an operation field. The method comprises the following steps: (1) reconstructing a real scene in real time through a monocular camera to obtain three-dimensional point cloud information of a real target; (2) judging whether the virtual model is shielded or not by calculating the distance from the optical center of the monocular camera to the real target three-dimensional point cloud and the distance from the optical center to the virtual model; and (3) only rendering the edge contour of the sheltered part of the virtual model, and normally rendering and displaying the unsheltered part.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a virtual-real fusion rendering method based on monocular camera reconstruction and a virtual-real fusion rendering device based on monocular camera reconstruction, which are mainly used for target virtual-real occlusion processing in augmented reality display. Background technique [0002] At present, the medical-grade augmented reality display technology superimposes the virtual model on the real target, but the virtual-real superimposition does not deal with the depth problem, and only places the virtual model at a specific position in the space, which causes the virtual model to be blocked by the real target. , the virtual model is still floating in front of the target, lacking the sense of reality in the depth direction. [0003] In the medical field, when the 3D virtual model of important tissues is enhanced and fused with the real environment, if t...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the defects of the prior art, the technical problem to be solved in the present invention is to provide a virtual-real fusion rendering method based on monocular camera reconstruction, which can solve the problem of lack of depth sense when the virtual and real are mutually occluded, and improve the doctor's ability to enhance The depth perception in reality display can more accurately obtain the positional relationship between the virtual model and the real anatomical structure, which helps to expand the surgical field of view

Images