Method for showing actual object in shared enhanced actual scene in multi-azimuth way

Abstract

The invention discloses a method for showing an actual object in a shared enhanced actual scene in a multi-azimuth way. The method for showing the actual object in the shared enhanced actual scene in the multi-azimuth way comprises the following steps of: according to characteristics of vertex distribution of a scene area, and according to the coverage area of video sequences to the scene and the number of required apparatuses, optimizing setting ways of multiple video sequences; determining an observation area of each video sequence; matching and determining a shared area between the video sequences according to a characteristic that a standard marker and the dimensions of the video sequences in different azimuths are unchanged; computing a spatial position relationship of all video sequences; finishing false or true registering of each video sequence by using the standard marker; integrating the local descriptions of the video sequences on the actual object, and estimating a three-dimensional convex hull of the actual object according to a computer vision principle; for an entering new cooperative user, giving a rapid registering method according to the spatial position relationship of all video sequences; and drawing a two-dimensional mapping effect of the actual object in the video sequence in each azimuth. The application cost of the method provided by the invention is low, and by the method, a rapid response can be made to the entering new cooperative user.

Description

technical field [0001] The invention relates to the fields of computational geometry, image processing and augmented reality, in particular to a representation method for real objects in multi-directional video sequences sharing augmented reality scenes. Background technique [0002] In collaborative augmented reality, when different collaborative users enter the augmented reality scene, they often have different viewpoints and different interactions in their respective perception and interaction areas. In order to enable these users to jointly complete the predetermined defense tasks, it is necessary Establishing a shared augmented reality scene requires a collaborative augmented reality system capable of depicting multiple orientations and constantly changing real environments, and establishing a 3D space model of the scene based on multiple video sequences. Among them, the multi-directional representation of real objects in the scene is an urgent problem to be solved, inc...

AI Technical Summary

Problems solved by technology

In order to track real objects in real time, the system uses a color calibration object to obtain the position of the real object, thereby calculating the position of the corresponding virtual model in the virtual coordinates, and drawing, the system can make the user in the virtual scene Experience events in the middle, but this method is relatively expensive to use instruments, and is limited to very few users

[0008] By analyzing the research status at home and abroad, it can be concluded that although many organizations or institutions are currently studying the multi-directional representation of real objects in collaborative augmented reality systems, there are still three problems: First: most of the current shared augmented reality Scenes seldom consider how to use fewer cameras to obtain a larger observation range. They all assume that the set video sequence has been able to fully obtain the required real environment information, and does not describe the setting method of multiple video sequences; secondly , after setting up multi-video sequences, existing institutions seldom conduct research on registration information complementation. Even if this issue is considered, they seldom consider the impact of errors on complementary results, and error analysis is not fed back into complementary calculations; finally , in the representation of real objects for collaborative work tasks, many methods model the entire environment, which is computationally intensive, and does not take into account the need for information sharing in shared augmented reality scenarios

Images