Device and method for identifying gestures through compressed infrared sensing

A gesture recognition, infrared technology, applied in the direction of character and pattern recognition, instruments, computer components, etc., can solve the problems that perception is difficult to overcome, distributed ubiquitous network implementation mode is difficult to carry, etc., achieve low power consumption characteristics, avoid Generation and processing of invalid or redundant information, low-cost effects

Inactive Publication Date: 2013-04-03
SUN YAT SEN UNIV
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These factors have placed excessive demands on network resources such as energy consumption, computing, and communication, which will be difficult for the distributed ubiquitous network implementation model
In other words, the excessive de

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Device and method for identifying gestures through compressed infrared sensing
  • Device and method for identifying gestures through compressed infrared sensing
  • Device and method for identifying gestures through compressed infrared sensing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] figure 1 The middle marks are: 1-pyroelectric infrared sensor, 2-Fresnel lens group.

[0032] Such as figure 1 The gesture recognition device implemented by compressed infrared sensing includes an array of pyroelectric infrared sensors 1 for acquiring gesture motion feature data and a Fresnel lens group 2 for modulating the field of view via a mask, and each pyroelectric infrared sensor 1 is installed at the front end A Fresnel lens set 2 .

[0033] In this embodiment, the pyroelectric infrared sensor 1 is a commercially available D205B pyroelectric infrared sensor, which is sensitive to thermal radiation in the wavelength range of 8-14 μm, and the pyroelectric infrared radiation wavelength of the human body (37°C or 98°F When) the typical value is 9.55μm, in its sensitive sensing range, with bipolar settings so that it can only be excited by changing thermal radiation, so it is suitable for the perception of human motion.

[0034] The Fresnel lens group used in the ...

Embodiment 2

[0040] A recognition method applied to a gesture recognition device implemented by compressed infrared sensing, comprising the following steps:

[0041] S1. Obtain the motion characteristic data of the gesture by measuring the output of the pyroelectric infrared sensor array;

[0042] S2. Using a vector quantization method to encode the acquired gesture motion feature data;

[0043] S3. Using the encoded motion feature training data to establish a classifier for gesture recognition;

[0044] S4. Use a classifier to make a decision on the coded motion feature test data to determine the semantics it represents.

[0045] The motion feature acquisition method in step S1 is as follows: when there is a thermal radiation change in the corresponding visible sampling cell of the pyroelectric infrared sensor, its measurement output is coded as 1, and when there is no thermal radiation change, its measurement output is coded as 0, by This is to obtain M-dimensional motion characteristi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a device and a method for identifying gestures through compressed infrared sensing. According to the device for identifying the gestures, a pyroelectricity infrared sensor array visibly modulates a sub field-of-view in a Fresnel lens installed in front of a pyroelectric sensor by means of a random coding mode to randomly compress and project high-dimensional infrared radiation states generated by gesture motions into low-dimensional pyroelectricity infrared sensing array measurement space, so that characteristics of the gesture motions are obtained. According to the method for identifying the gestures, each semantic motion characteristic sequence with special actions is subjected to characteristic parameter estimation by means of vector quantization, a codebook is distributed to each characteristic sequence through training data and used as a semantic expression template, and test data are subjected to decision making by means of a classifier to express semanteme, so that the gesture actions are distinguished. By means of compressed infrared sensing, the gesture motion characteristics are obtained, generation and processing progresses of redundant and invalid information are effectively avoided, complexity and hardware costs of a sensing system are obviously reduced, and a light weight gesture identification algorithm is supported.

Description

technical field [0001] The invention belongs to the measurement field of G01D in the analysis and measurement control technology that is not exclusive to specific equipment, and in particular relates to a gesture recognition device and a recognition method realized by compressed infrared sensing. Background technique [0002] The visual sensing technology governed by the Nyquist sampling rule has become the most widely used means of gesture behavior perception, including optical imaging technologies such as CCD and CMOS. Relying on visual sensing technology, the visual information processing process to realize gesture behavior recognition generally includes: first obtain the image data of the scene, then extract and track the area of ​​interest movement, and then encode the spatial information based on the motion characteristics. It also includes high-dimensional data in the time domain for classification processing to recognize the semantics of gestures. However, as the ph...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/66G01J5/10
Inventor 王国利刘佟郭雪梅
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap