An AR home experience method in a large scene

Through the offline feature extraction and natural feature identification technology of binocular cameras, combined with binocular tracking and positioning and local map construction, the problem of using AR home experience technology in a small space is solved, and stable three-dimensional virtual objects in large scenes are achieved. Registration and tracking expand the application scope of virtual and real integration experience.

CN109613974AActive Publication Date: 2019-04-12MAANSHAN JUMEI YOUPIN DECORATION ENGINEERING CO LTD
2 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
MAANSHAN JUMEI YOUPIN DECORATION ENGINEERING CO LTD
Filing Date
2018-10-18
Publication Date
2019-04-12

AI Technical Summary

⚠Technical Problem

Existing AR home experience technology can only be used in a small space and cannot meet the need to observe the placement of virtual home objects at long distances and in a wide field of view, affecting the application scope and stability of the AR home experience.

⚗Method used

Binocular cameras are used for offline feature extraction, and an offline feature library is generated. Through natural feature identification technology, binocular tracking and local map construction technology, three-dimensional virtual object registration and extended tracking and positioning in large environments are realized, solving the problem of camera positioning. The problem of recognition and positioning of attitude changes.

🎯Benefits of technology

It achieves a stable AR home experience in large scenes, expands the recognition and tracking range of virtual home objects, meets the needs for a more realistic and larger-scale virtual and real integration experience, and improves the application applicability and stability of the AR home experience.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an AR home experience method in a large scene. On the basis of combination of a natural feature identification-based three-dimensional registration method and a binocular tracking positioning and local mapping method, the camera attitude is estimated by using feature points of a real-time scene and corresponding three-dimensional points thereof under the binocular trackingpositioning and local map construction technology. According to the mode, on-site environment features shot in real time are used as recognition tracking objects, a virtual home model can still be normally positioned and tracked under the condition that no identification graph exists, the problems that an existing AR home experience application is small in use range and poor in stability are solved, and therefore the AR home experience of virtual and real fusion can be met in a wider range and more truly.
Need to check novelty before this filing date? Find Prior Art