Tilt Angle Detection from Depth Images for Intuitive Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing applications face challenges in user interaction due to complex and non-intuitive controls, which can create a barrier between users and game or multimedia experiences, as controls often do not directly correspond to actual actions.
Innovation Solution
A system and method for detecting a tilt angle from a depth image, allowing a capture device to analyze human movements and adjust or interpret them as controls within applications, by calculating a tilt angle based on body part measurements and using it to rotate or transform images captured by the device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional controls (keyboards, mice, remotes) are used to manipulate game characters or application aspects, then control functionality is achieved, but the controls become difficult to learn and do not correspond to actual actions, creating a barrier between user and application
Solution Approach 1:
The system uses the user's own body movements as the control input mechanism. The capture device detects natural human movements and directly translates them into game character actions or application controls, allowing the user to control the application using their natural physical actions rather than learning arbitrary control schemes
Solution Approach 2:
The patent replaces traditional mechanical control interfaces (keyboards, mice, remotes) with an optical sensing system. A capture device uses depth imaging and skeletal tracking to detect body movements, substituting physical mechanical controls with optical field-based detection that naturally maps physical actions to digital controls
2Adaptability or versatility
If the capture device is tilted to capture depth images from different angles, then more comprehensive scene information is obtained, but the captured images become distorted or skewed
Solution Approach 1:
The system calculates the tilt angle of the capture device using the skeletal model and uses this information as feedback to correct the captured images. The tilt angle calculation provides quantitative feedback about device orientation, which is then used to transform and correct the depth images and RGB images to remove distortion and maintain accuracy regardless of capture angle
Solution Approach 2:
The patent dynamically adjusts image parameters based on the calculated tilt angle. By changing the transformation parameters applied to the captured images based on device orientation, the system maintains image accuracy across different capture angles, effectively compensating for the distortion caused by tilting
3Ease of operation
If natural body movements are used to control application actions, then user interaction becomes more intuitive, but the system requires complex depth imaging and movement analysis capabilities
Solution Approach 1:
The system segments the human body into a skeletal model with distinct joints and body parts. By dividing the complex task of full-body tracking into smaller components (detecting individual joints, then calculating relationships between them), the system makes movement detection more manageable and computationally efficient while maintaining natural interaction capabilities
Solution Approach 2:
The skeletal model serves as an intermediary between the raw depth image data and the final control commands. The capture device first extracts skeletal information from the depth images, then uses the skeletal model to interpret body movements and translate them into application controls, simplifying the overall processing pipeline
Data Source
AI summary
A depth image of a scene may be received, observed, or captured by a device. A human target in the depth image may then be scanned for one or more body parts such as shoulders, hips, knees, or the like. A tilt angle may then be calculated based on the body parts. For example, a first portion of pixels associated with an upper body part such as the shoulders and a second portion of pixels associated with a lower body part such as a midpoint between the hips and knees may be selected. The tilt angle may then be calculated using the first and second portions of pixels.