Gesture detection method based on multi-feature fusion
A technology of multi-feature fusion and gesture detection, applied in instruments, character and pattern recognition, computer parts, etc., can solve the problems of high hardware cost, poor real-time performance, and poor human-computer interaction ability.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0027] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.
[0028] The present invention includes gesture classifier training and gesture detection two parts, as Figure 4 It is a schematic diagram of the training process of the gesture classifier (namely Adaboost).
[0029] First, common gestures under different lighting and distance conditions are used as positive samples, and a large number of indoor and outdoor pictures with low repeatability are selected as negative samples to establish a gesture set;
[0030] The present invention establishes a gesture sample set suitable for daily life, including 3000 positive sample pictures, 45000 negative sample pictures and 10000 test set pictures. The positive sample image is formed by superimposing the gesture image and the background image. Gesture pictures include three basic gestures of daily fingers close together, fingers spread apart, and ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com