Application (pre-grant publication)
TECHNIQUES FOR INFERRING THE CONFIGURATION OF A ROOM FROM SKELETON TRACKING
- Number
- 20200294247
- Published
- 2020-09-17
- Filed
- 2019-03-14
- Assignee
- DISNEY ENTERPRISES, INC.
- Inventors
- BAUMBACH; Elliott, GOSLIN; Michael
- CPC
- G06V20/10; G06T15/00; G06V40/168; G06N5/04; G06T7/246; G06T7/251
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Skeleton-tracking CV technique to infer room configuration for interactive experiences.
Abstract
In various embodiments, a map inference application automatically maps a user space. A camera is positioned within the user space. In operation, the map inference application determines a path of a first moving object within the user space based on a tracking dataset generated from images captured by the camera. Subsequently, the map inference application infers a walking space within the user space based on the path. The map inference application then generates a model of at least a portion of the user space based on the walking space. One or more movements of a second object within the user space are based on the model. Advantageously, unlike prior art solutions, the map inference application enables a model of a user space to be automatically and efficiently generated based on images from a single stationary camera.
Background
BACKGROUNDField of the Various Embodiments
Embodiments of the present invention relate generally to computer science and navigation technology and, more specifically, to techniques for inferring the configuration of a room from skeleton tracking.Description of the Related Art
In some advanced gaming applications, a user interacts with a transformed version of the room in which the user is located. For example, an adventure gaming application could provide a virtual reality (“VR”) forest in which the carpet of the room is replaced with a virtual forest floor and items in the room, such as a desk and a chair, are replaced with virtual trees in the virtual forest. The adventure gaming application could position some virtual objects in locations that are accessible to the user and other virtual objects in locations that are inaccessible to the user (e.g., above a 7 ft high floor lamp). To properly transform the room, the gaming application requires a model of the room.
In one approach to generating a model of a room, the user holds a camera and manually points the camera at different areas in the room while slowly rotating the camera horizontally and vertically and/or walking around the room. Subsequently, an image-based room modeling application creates a model of the room based on the images from the camera. The resulting model usually includes a set of surface areas representing the walls, floors, and different objects in the room. One drawback of generating