Tangible Interface Detection Using Video Camera and Computer Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tangible user interfaces are expensive, difficult to set up, and have limited adoption due to the need for high-quality sensors, making them inaccessible to most consumers.
Innovation Solution
A platform that detects and enhances a physical activity surface by using existing hardware, such as a video camera, and novel computer vision algorithms to recognize and interact with tangible interface objects, providing a low-cost, intuitive, and real-time virtual experience without the need for specialized markers or symbols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-quality sensors are used to digitize user interactions, then measurement precision is improved, but device cost increases
Solution Approach 1:
The patent uses a video camera to capture optical images of tangible objects and creates digital copies through image processing. Instead of using expensive sensors to directly detect object properties, the system captures visual information and processes it computationally to achieve digitization, thereby reducing hardware costs while maintaining measurement capability
Solution Approach 2:
The patent replaces mechanical/optical sensor systems with a video-based computational approach. By substituting specialized sensors with a standard video camera and computer vision algorithms, the system achieves similar functional outcomes with lower-cost, more accessible hardware
2Measurement precision
If specialized hardware is used for tangible user interfaces, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent employs a video camera, which is a universal device already present in most computing devices, to perform multiple functions including object detection, tracking, and interaction recognition. This eliminates the need for specialized sensors and reduces system complexity while maintaining detection precision through software-based processing
Solution Approach 2:
The system uses the computing device's existing video camera and processing capabilities to detect and interpret tangible objects. The device leverages its own built-in resources rather than requiring external specialized hardware, simplifying the overall system architecture and reducing setup complexity
3Ease of manufacture
If existing video cameras are used instead of specialized sensors, then device cost is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent substitutes expensive specialized sensors with standard video camera hardware, compensating for the lower inherent precision of consumer-grade cameras through advanced computer vision algorithms and image processing techniques that extract meaningful information from video data
Solution Approach 2:
The system changes the processing parameters and computational approaches used to interpret video data, employing sophisticated algorithms that enhance the effective precision of the video camera output, allowing accurate object detection and recognition despite the use of lower-cost hardware
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Activity scene detection, display, and enhancement implementations are described. In an example implementation, a method includes displaying an animated character on a display of a computing device, detecting a tangible interface object on a physical activity scene proximate to the computing device, rendering a virtual interface object based on the tangible interface object, determining an interaction routine between the animated character and the virtual interface object, and executing the animation routine to animate on the display, an interaction between the animated character and the virtual interface object.