Supercharge Your Innovation With Domain-Expert AI Agents!

Detection method of the number of people in the protective cabin

A detection method and technology of a protective cabin, applied in the field of image processing, can solve problems such as false detection, unclear focus, and unsatisfactory image quality, and achieve accurate detection and high accuracy

Active Publication Date: 2022-05-20
杭州智诺科技股份有限公司
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with the pattern recognition method is that the quality of the images captured by the actual protective cabin camera is often not ideal. Problems such as unclear focus, lens flare, and prism distortion often occur. Applying head detection to videos with poor image quality is prone to failure.
If the threshold of head detection is lowered for this purpose, a large number of false detections will be introduced, resulting in a misjudgment of the number of people in the cabin

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
  • Detection method of the number of people in the protective cabin
  • Detection method of the number of people in the protective cabin
  • Detection method of the number of people in the protective cabin

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0045] like figure 1 As shown, a detection method for the number of people in a protective cabin includes the following steps:

[0046] Step 100, obtaining monitoring video data, the monitoring video data includes several frames of pictures arranged in chronological order;

[0047] Step 200, background difference, obtain foreground mask image

[0048] like figure 2 As shown, a mixed Gaussian model is established for each pixel of each frame of picture;

[0049] Step 210, if the probability value calculated based on the established mixed Gaussian distribution of the pixel point is greater than the preset threshold, it is judged that the pixel point is a background point; otherwise, it is judged that the pixel point is a foreground point, and each frame of the picture is obtained The foreground mask image M(p);

[0050] Step 220, update the...

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 method for detecting the number of people in a protective cabin. The invention performs background difference and pattern recognition calculation on the input monitoring video data, obtains a foreground mask image through background difference, and obtains a head confidence image through pattern recognition. By fusing the two images, an image identifying the confidence of each image position is obtained. Perform raster maximization on this image to obtain the number of people. The invention has the characteristics of being able to accurately detect the number of people in the protective cabin, and the accuracy rate is higher than 98%.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting the number of people in a protective cabin capable of accurately judging the number of people in an image. Background technique [0002] In order to improve financial security and protect people who withdraw money, more and more ATMs have been equipped with protective cabins on the outside in recent years, and they have played a good role in practice. [0003] The premise that the protective cabin can play a protective role is that the suspect must be isolated from the cabin. When a criminal suspect commits a crime, he may use methods such as pulling the door to follow when the door is not closed, and holding the cashier to enter the cabin together. [0004] Once the criminal suspect enters the cabin, there is no guarantee for the safety of the cashier. For this reason, many banks have installed cameras on the top of the protective cabin to obser...

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): G06V20/52G06V10/764G06K9/62G06T7/00
CPCG06T7/0002G06T2207/30232G06T2207/30196G06T2207/20016G06V20/52G06F18/2431
Inventor 刘玉宇王增锹
Owner 杭州智诺科技股份有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More