Multi-Camera Gesture Recognition Without Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition systems for computing devices face challenges in processing irrelevant information, requiring significant calibration, and struggling with ambient light conditions, especially outdoors, which slows down processing time and interferes with user experience.
Innovation Solution
A method using at least three cameras with fields of view adjacent to the display's surface, capturing images from the visual spectrum, allowing for efficient gesture recognition by comparing standard deviations and determining gesture dimensions based on images from multiple cameras, without the need for calibration, and functioning effectively indoors and outdoors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all captured information is processed, then gesture recognition accuracy is improved, but processing time increases
Solution Approach 1:
The patent extracts and processes only the relevant portion of captured information by identifying a region of interest (ROI) containing the gesture, rather than processing all captured data. This selective extraction maintains gesture recognition accuracy while significantly reducing processing time by eliminating irrelevant information from the processing pipeline.
Solution Approach 2:
The patent segments the captured image into a region of interest (ROI) that contains the gesture and processes only that segment. This segmentation approach divides the full image processing task into smaller, more manageable parts, allowing fast processing of only the necessary portion while maintaining recognition accuracy.
2Measurement precision
If calibration calculations are performed, then system accuracy is improved, but user experience is degraded due to setup time
Solution Approach 1:
The system performs self-calibration by automatically adapting to the user's environment and gesture characteristics during normal operation, eliminating the need for manual calibration steps. The system serves itself by learning from captured gesture data and adjusting its parameters automatically, maintaining accuracy without interfering with user experience.
Solution Approach 2:
The patent incorporates calibration actions into the normal operational flow, performing necessary adjustments preliminarily during initial use or transitions, rather than requiring a separate calibration phase. This allows the system to prepare and adapt in advance, maintaining accuracy while minimizing disruption to user experience.
3Difficulty of detecting and measuring
If infra-red camera is used, then gesture detection capability is improved, but adaptability to ambient light conditions deteriorates
Solution Approach 1:
The patent uses a standard camera capable of capturing images across different lighting conditions, making the system universal and adaptable to various environments including outdoor settings. The same camera hardware serves multiple functions by adjusting processing parameters based on ambient light conditions, eliminating the need for specialized infra-red equipment while maintaining gesture detection capability.
Solution Approach 2:
The system adapts to different ambient light conditions by dynamically changing processing parameters such as exposure time, gain, and threshold values based on the captured image characteristics. This parameter adjustment allows the same camera hardware to maintain gesture detection accuracy across varying lighting environments, from indoor to outdoor conditions.
Data Source
Figure 1~3
Figure 4~5
Figure 6~8
AI summary
A method and device for gesture recognition; the gesture being executed by a user in a gesture region which may be defined relative to a display surface. In an embodiment the gesture comprises a select and the device comprises at least three cameras operating in the visual range where a first camera is used to determine a horizontal location of the select gesture and the other cameras are used to determine a vertical location thereof.