Depth Image Segmentation for Natural Gesture Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing applications face challenges in user interaction due to complex and non-intuitive control systems that often disconnect users from the application experience, as controls do not directly correspond to real-world actions.
Innovation Solution
A system and method that processes depth information from a scene to isolate a human target, allowing for natural gestures and movements to control applications by analyzing depth images and removing non-human target pixels, enabling direct mapping of user actions to in-game or application controls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional controls (keyboards, mice, controllers) are used to manipulate game characters or application aspects, then the application can be controlled, but the controls become difficult to learn and create a barrier between the user and the application
Solution Approach 1:
The patent replaces traditional mechanical control systems (keyboards, mice, controllers) with a depth imaging system that captures spatial information and translates physical movements directly into application controls. The depth camera captures depth images, processes spatial coordinates of body parts, and maps these to game character movements, eliminating the need to learn complex control schemes while maintaining precise control capability
Solution Approach 2:
The patent creates a digital copy of the user's physical movements by capturing depth images and extracting spatial coordinates of body parts. This copy of the physical movement data is then used to control the game character or application, allowing direct translation of real-world actions into virtual actions without requiring intermediate control inputs
2Adaptability or versatility
If traditional controls are used, then application functionality is maintained, but the controls do not correspond to actual game actions or application actions
Solution Approach 1:
The patent segments the user's body into distinct parts (head, torso, arms, legs) by analyzing depth images and identifying spatial coordinates of each body part. This segmentation allows the system to track specific body parts independently and map them to corresponding game character actions, creating a direct and intuitive correspondence between physical movements and in-game actions
Solution Approach 2:
The patent changes the control parameter from discrete button presses to continuous spatial coordinates. By capturing the three-dimensional position of body parts and translating these coordinate changes directly into game character movements, the system creates a natural and intuitive control scheme where physical movement magnitude and direction directly correspond to in-game action magnitude and direction
3Loss of information
If depth images including environment are processed, then complete scene information is captured, but processing complexity increases and target isolation becomes difficult
Solution Approach 1:
The patent extracts the human target from the complete scene by analyzing depth images and identifying pixels that correspond to the human body based on spatial coordinates and depth values. The system separates target pixels from non-target pixels, allowing processing to focus only on relevant information while maintaining the ability to reconstruct the complete scene when needed
Data Source
AI summary
A depth image of a scene may be observed or captured by a capture device. The depth image may include a human target and an environment. One or more pixels of the depth image may be analyzed to determine whether the pixels in the depth image are associated with the environment of the depth image. The one or more pixels associated with the environment may then be discarded to isolate the human target and the depth image with the isolated human target may be processed.