Dynamic Gesture Recognition Using Depth and Grayscale Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gesture recognition technologies require high system computing power and suffer from significant delays, making real-time interaction difficult due to the reliance on deep learning methods and high resource consumption.
Innovation Solution
A gesture recognizing method that utilizes synchronously acquired depth maps and grayscale maps to extract spatial and posture information, reducing the need for complex deep learning algorithms and minimizing processing time, enabling quick gesture recognition and real-time interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep learning methods are used for gesture recognition, then recognition accuracy is improved, but processing time increases and system latency becomes high
Solution Approach 1:
The patent segments the gesture recognition process into distinct stages: depth map acquisition, grayscale map acquisition, gesture region detection using depth thresholding, and gesture type classification. By dividing the complex deep learning process into smaller, specialized steps with optimized algorithms for each stage, the system achieves both high accuracy and low processing time (5ms).
Solution Approach 2:
The patent changes the parameter space by using depth map data with adaptive depth thresholding instead of raw pixel data. This parameter transformation enables efficient gesture region segmentation and reduces computational complexity while maintaining recognition accuracy, allowing real-time processing at 200fps.
2Adaptability or versatility
If deep learning algorithms are employed, then gesture recognition capability is enhanced, but computing power requirements and system resource consumption increase
Solution Approach 1:
The patent replaces computationally intensive deep learning mechanical processes with more efficient algorithms. Specifically, it substitutes complex neural network inference with adaptive depth thresholding and convex hull-based gesture classification, dramatically reducing CPU/GPU resource consumption while maintaining versatile gesture recognition capability.
Solution Approach 2:
By transforming the input data into depth map representation and using adaptive thresholding parameters, the system changes the problem space to one that requires minimal computing power. This parameter-based approach enables resource-constrained devices to perform accurate gesture recognition without heavy deep learning model inference.
3Device complexity
If traditional gesture recognition methods are used, then system complexity is reduced, but interaction precision and depth information accuracy deteriorate
Solution Approach 1:
The patent adds the depth dimension by utilizing depth map data from time-of-flight or structured light sensors. This dimensional enhancement allows precise 3D gesture recognition and spatial positioning without significantly increasing system complexity, as the depth processing uses simple thresholding operations rather than complex algorithms.
Data Source
AI summary
A gesture recognizing method, an interactive method, a gesture interactive system, an electronic device, and a non-transitory computer-readable storage medium are disclosed. The gesture recognizing method includes: acquiring a plurality of groups of images taken respectively at different photographing moments for a gesture action object, wherein each group of images includes at least one pair of corresponding depth map and grayscale map; and according to the plurality of groups of images, obtaining spatial information by using the depth map in each group of images, and obtaining posture information for the gesture action object by using the grayscale map in each group of the images, to recognize a dynamic gesture change of the gesture action object. The gesture recognizing method reduces the processing time as a whole, can quickly obtain gesture recognition results, reduce the system resource occupation, and ensure the real-time gesture interaction.