Multi-Camera Touch Detection Using Triangulation and Ghost Target Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Camera-based systems for detecting touches on a surface are limited to detecting a single target using triangulation, as they cannot sense depth information, leading to undefined or undesirable effects when multiple targets are touched simultaneously.
Innovation Solution
A system that uses multiple cameras to detect and track multiple simultaneous targets by determining potential positions through triangulation, analyzing occlusions in the field of view to distinguish between real and ghost targets, and refining the positions based on previous target data and surface boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera-based triangulation is used to detect targets on a surface, then single target detection is achieved, but multiple simultaneous targets cannot be detected
Solution Approach 1:
The patent segments the detection process into multiple independent stages: (1) detecting occlusions in camera images, (2) generating potential target positions through triangulation for each occlusion pair, (3) filtering potential positions by analyzing surface boundaries and geometric constraints, and (4) matching occlusions to real targets. This segmentation allows the system to handle multiple targets by processing each occlusion pair independently while maintaining accurate position detection through triangulation.
2Measurement precision
If triangulation is used to determine target position, then position information is obtained, but depth information cannot be sensed
Solution Approach 1:
The patent addresses the depth information loss by transitioning from 2D camera images to 3D spatial reasoning through triangulation. By using multiple camera views and geometric intersection, the system recovers depth information implicitly through the triangulation process, effectively adding the depth dimension back to the measurement without requiring direct depth sensing hardware.
3Adaptability or versatility
If multiple cameras are used to detect targets, then triangulation capability is enabled, but system complexity increases
Solution Approach 1:
The patent implements self-service by having the system automatically generate and filter potential target positions without manual intervention. The algorithm autonomously processes occlusion data, performs triangulation, applies geometric constraints, and identifies real targets from potential positions, eliminating the need for complex manual configuration or post-processing intervention.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate detection and tracking of multiple targets on a surface, allowing multiple users to interact simultaneously without the need for sequential input, improving usability in multi-user applications.
Implementation Method 1
Another type of touchable display may use a camera, or other type of light sensor (e.g., visual and/or infrared light sensors), to detect a touch on the screen
Implementation Method 2
In order for the cameras to better sense the target, a contrasting material, such as black tape or other dark material, may be placed opposite the cameras. Thus, when a user touches the screen, the cameras sense the single target as a single bright spot within each camera's field of view. Each camera produces a two-dimensional output (i.e., a picture with no depth information) so that the target may be at any position along a ray from the focal point of the camera, through the target, and beyond. Because multiple cameras sense the target, it is possible to triangulate the position of the single target on the surface by: (1) determining the ray for each camera; and (2) determining the intersection of the two or more rays.
Data Source
AI summary
A system and method for determining positions of multiple targets on a planar surface is described. The targets subject to detection may include a touch from a body part (such as a finger), a pen, or other objects. The system and method may use light sensors, such as cameras, to generate information for the multiple simultaneous targets (such as finger, pens, etc.) that are proximate to or on the planar surface. The information from the cameras may be used to generate possible targets. The possible targets include both “real” targets (a target associated with an actual touch) and “ghost” targets (a target not associated with an actual touch). Using analysis, such as a history of previous targets, the list of potential targets may then be narrowed to the multiple targets by analyzing state information for targets from a previous cycle (such as the targets determined during a previous frame).