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

Human Recognition Method Based on Stereo Vision and Infrared Imaging

A technology of infrared imaging and human recognition, which is applied in the field of sensor detection, can solve the problems of complex scene interference, static portrait misjudgment, etc., and achieve the effect of strong anti-interference ability, low false recognition rate and reliable detection

Active Publication Date: 2021-08-17
IBE ELECTRONICS CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, there are two main ways to detect human objects: the first is the human body infrared pyroelectric detection method, which can only detect dynamic human bodies, which has great limitations; the second is the machine vision method, which This method is easily disturbed by complex scenes, and static portraits in the environment will also be misjudged

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
  • Human Recognition Method Based on Stereo Vision and Infrared Imaging
  • Human Recognition Method Based on Stereo Vision and Infrared Imaging
  • Human Recognition Method Based on Stereo Vision and Infrared Imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with accompanying drawing:

[0020] refer to figure 1 -3. A human body recognition method based on stereo vision and infrared imaging, including a processor 1 for centralized processing, a first infrared imaging module 3 and a second infrared imaging module 2 connected to the processor 1, and the The data-storing RAM4 connected to the processor 1 also includes a power supply 5 that provides an operating voltage. The optical axes of the first infrared imaging module 3 and the second infrared imaging module 2 are parallel to each other, and the parameters are consistent, and the baseline The length is b, the focal length is f, and the pixel area is A.

[0021] Described processor 1 internal setting human body recognition method, described human body recognition method comprises the following steps:

[0022] (1) The processor 1 obtains the infrared image f of the scene through the first infrared imaging...

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

A human body recognition method based on stereo vision and infrared imaging is disclosed, including a processor, RAM, a first infrared imaging module and a second infrared imaging module, and the human body recognition method is set inside the processor, including the following steps: 1. Acquiring a scene Infrared image f 1 (x,y) and f 2 (x,y); 2. For f 1 (x, y) binarization processing to obtain a binary image I 0 (x,y); 3. to I 0 (x,y) corrosion operation to get the corrosion map I 1 (x,y); 4. to I 1 (x,y) expansion operation to get the expansion graph I 2 (x,y); 5. to I 2 (x,y) cyclic erosion until only the core point o is left j ; at I 1 In (x, y), use the image area pixel area calculation algorithm to get o j The pixel area of ​​the area s j ; 6. Calculate f 1 (x,y) and f 2 Parallax image d(x,y) of (x,y); 7. Core point o j The corresponding disparity d(x j ,y j ), and then calculate the distance D j ; 8. Calculate the imaging area S j 9. According to S j Size, to determine whether the imaging area may be a human body.

Description

technical field [0001] The invention relates to a human body recognition method based on stereo vision and infrared imaging, and belongs to the field of sensor detection. Background technique [0002] Human object detection has a very wide range of applications, such as intelligent monitoring, adjusting the angle of the camera according to the position of the human target to obtain the best monitoring effect, and smart home, adjusting the air outlet direction of the air conditioner or the heating device according to the position of the human target Heating direction to achieve the most comfortable effect. It can also control the start or stop of air conditioning equipment according to whether there are people in the environment to achieve the purpose of energy saving. However, at present, there are two main ways to detect human objects: the first is the human body infrared pyroelectric detection method, which can only detect dynamic human bodies, which has great limitations;...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/32
CPCG06V40/103G06V10/25
Inventor 何凌刚许尧军梁海刘瑜
Owner IBE ELECTRONICS CO LTD