Skeletal Model Tracking via Depth Image Magnetization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing applications, such as games and multimedia, face challenges in user interaction due to complex and non-intuitive control systems that do not directly correspond to real-world actions, creating a barrier between users and the application.
Innovation Solution
A system and method for tracking a user in a scene using depth images to generate and adjust a skeletal model that mimics the user's movements, allowing natural gestures and movements to control in-game actions or application functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional controllers and controls are used, then application functionality can be controlled, but user interaction becomes difficult and creates a barrier between user and application
Solution Approach 1:
The patent uses motion capture technology to copy the user's physical movements directly onto the game character. The system tracks the user's skeletal movements and replicates them in the virtual environment, eliminating the need for abstract controllers and creating a direct mapping between physical and virtual actions.
Solution Approach 2:
The patent replaces traditional mechanical controllers (gamepads, keyboards, mice) with optical motion capture systems. Instead of using abstract button presses or joystick movements, the system uses cameras to detect and track physical body movements, substituting the mechanical control interface with an optical sensing and direct motion translation system.
2Ease of operation
If controls are simplified for easier learning, then user accessibility improves, but the ability to perform complex application actions may be limited
Solution Approach 1:
The patent employs dynamic skeletal models that can adapt to various user movements and poses. The skeletal structure allows for natural, fluid motion capture that can represent a wide range of actions from simple gestures to complex combat moves, providing both ease of use and high versatility through the same system.
Solution Approach 2:
The patent segments the human body into a skeletal structure with joints and bones, allowing independent tracking and control of different body parts. This segmentation enables complex movements to be broken down into manageable skeletal rotations and translations, making the control system both versatile for complex actions and intuitive for simple interactions.
Data Source
AI summary
An image such as a depth image of a scene may be received, observed, or captured by a device and a model of a user in the depth image may be generated. The background of a received depth image may be removed to isolate a human target in the received depth image. A model may then be adjusted to fit within the isolated human target in the received depth image. To adjust the model, a joint or a bone may be magnetized to the closest pixel of the isolated human target. The joint or the bone may then be refined such that the joint or the bone may be further adjusted to a pixel equidistant between two edges the body part of the isolated human target where the joint or bone may have been magnetized.