Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent identification method

An intelligent identification and sensor technology, applied in the field of intelligent identification, can solve the problems of increasing the difficulty of data processing and the large number of samples

Inactive Publication Date: 2018-11-23
陈啸
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that a high-resolution sensor needs to be used to obtain a large number of samples; it is necessary to robustly extract the moving target for the video sequence, and it is also necessary to model the movement mode and trajectory of the moving target; the motion characteristics are encoded into a time-domain High-dimensional spatial data increases the difficulty of data processing

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
  • Intelligent identification method
  • Intelligent identification method
  • Intelligent identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Pyroelectric infrared sensing model such as figure 1 As shown, the sensor used in each sensor module is a commercial D205B pyroelectric infrared sensor, which is sensitive to radiation in the wavelength range of 8-14μm, while the wavelength of human pyroelectric infrared radiation (at 37°C or 98°F) The typical value is 9.55μm, which is in its sensitive sensing range. Because of its bipolar setting, it is only excited by the changing heat radiation source, so it can be used to sense the movement changes of the human body. The system is processed by Fresnel lens mask, and the effect of region segmentation is as follows: figure 2 As shown, the determination of the Fresnel lens mask scheme is to divide its surface into 19 areas, that is, the field of view is divided into 19 sub-areas. Such as image 3 The black area shown is the occlusion part, the white cell part is the visible part, and the position of the visible area is generated by a pseudo-random sequence. This sys...

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 an intelligent identification method. A pyroelectric infrared sensor is used; an original signal can be guaranteed to be correctly restored according to the randomness and irrelevance of an observation matrix in a compressed sensing theory; a modulation mode of random coding is adopted for a Fresnel lens mounted in the front of the sensor; and a view field of a random arrayof the sensor is obtained.

Description

technical field [0001] This technical method is to use compressed infrared sensing technology to carry out semantic recognition of gestures, according to human motion characteristics, use a random array of pyroelectric infrared sensors to obtain human motion characteristic data, and obtain gesture semantic information through data compression extraction and machine learning. G01D in the analysis and measurement control technology is not specific to the measurement of specific equipment. Background technique [0002] The compressed sensing theory emerging in the past two years shows that , without losing the information needed to approximate the original signal , Sampling the signal with the fewest number of observations , Realize the dimensionality reduction processing of the signal , That is, directly sample the signal to obtain a compressed representation of the signal , Thus, in the case of saving sampling and transmission costs , The purpose of compressing whi...

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): G06K9/00
CPCG06V40/28
Inventor 陈啸
Owner 陈啸