Infrared Depth Sensing via Light Falloff for 3D Gesture Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional touch-sensitive display screens lack depth recognition and finger/hand disambiguation, limiting gesture recognition to two-dimensional interactions, and existing 3D depth recognition technologies are either too expensive or lack sufficient resolution for granular gesture detection.
Innovation Solution
A sensor unit employing an infrared light source and camera captures high-resolution infrared images to compute depth values based on the principle of light falloff, enabling the generation of high-resolution depth images that can recognize gestures made by a human hand or arm in three-dimensional space, even at distances from the display screen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional touch-sensitive display screens are used for gesture recognition, then the device can detect user input, but depth recognition and finger/hand disambiguation are not supported
Solution Approach 1:
The patent transitions from 2D touch-sensitive display interaction to 3D gesture recognition by incorporating depth information. An infrared camera captures images with depth data, enabling the system to recognize gestures in three-dimensional space rather than limited to the flat display surface. This dimensional expansion allows for disambiguation of finger movements and hand gestures that cannot be distinguished in 2D.
2Measurement precision
If binocular vision systems are used for depth recognition, then depth information can be obtained, but the system requires objects to have particular texture and resolution may be insufficient
Solution Approach 1:
The patent replaces binocular vision systems with an infrared camera-based depth sensing system. Instead of using stereoscopic RGB cameras that require texture for depth computation, the invention uses an infrared camera that captures depth information through infrared light reflection. This substitution eliminates the texture requirement and provides more reliable depth data for gesture recognition, particularly for human hands which may have varying textures.
3Measurement precision
If structured light systems are used for depth recognition, then depth computation is possible, but numerous pixels must be analyzed resulting in insufficient resolution
Solution Approach 1:
The patent extracts only the necessary depth information directly from infrared camera images without requiring complex pattern analysis of numerous pixels. The infrared camera captures images where depth can be computed directly from intensity variations, eliminating the need to analyze large numbers of pixels for pattern recognition. This extraction approach maintains high resolution while simplifying the depth computation process.
4Measurement precision
If time of flight systems are used for depth recognition, then depth measurement can be achieved, but the system is prohibitively expensive
Solution Approach 1:
The patent employs an infrared camera system that is significantly less expensive than time of flight systems while achieving comparable depth measurement capabilities. The infrared camera, combined with an infrared light source, provides a cost-effective alternative to expensive specialized depth sensors. This approach makes 3D gesture recognition accessible for consumer-level devices without requiring prohibitively expensive hardware.
5Measurement precision
If conventional depth recognition technologies are used, then depth information can be obtained, but the resolution lacks sufficiency for granular gesture detection
Solution Approach 1:
The infrared camera serves multiple functions: it captures visible light images for texture information and simultaneously captures infrared radiation for depth information. This multi-functionality allows the system to achieve high-resolution depth images that are sufficient for granular gesture detection, as the same sensor array is used for both imaging purposes, maximizing resolution without requiring separate specialized sensors.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Technologies pertaining to computing depth images of a scene that includes a mobile object based upon the principle of light falloff are described herein. An infrared image of a scene that includes a mobile object is captured, wherein the infrared image has a plurality of pixels having a respective plurality of intensity values. A depth image for the scene is computed based at least in part upon square roots of respective intensity values in the infrared image.