Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for automatically judging dress code through surveillance video

A technology for automatic judgment and monitoring of video, applied in closed-circuit television systems, instruments, biological neural network models, etc., can solve problems such as poor detection results, complex kitchen environment, and easy interference of light by smoke, etc., to improve detection results, Robustness, the effect of reducing the input of supervisory manpower

Inactive Publication Date: 2018-05-18
CHENGDU REMARK TECH CO LTD +1
View PDF8 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are also traditional image processing methods that use features such as color or shape for detection and judgment. However, the kitchen environment is very complicated, and the light is easily disturbed by smoke and other interferences, so the detection results are not good.

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
  • Method for automatically judging dress code through surveillance video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] A method for automatically judging the dress code through surveillance video, mainly used to judge whether the head dress of the operator is standard, mainly includes the following steps:

[0031] Step A1: The video captures the clothing characteristics of the workers and generates images;

[0032] Step A2: Use the deep learning method to process the marked image of the worker's attire; extract the feature of the worker's attire, select the last layer as the result of feature extraction, and use the softmax function to calculate the probability, and output the calculated maximum value to generate training Model;

[0033] Step A3: Input the image generated in step A1 into the training model generated in step A2, and output an alarm message if it is detected that the attire of the worker does not meet the set standard.

[0034] The present invention collects the information on the head dress of the operator in real time through the camera, converts the video information ...

Embodiment 2

[0036] This embodiment is further optimized on the basis of Embodiment 1, and the step A2 mainly includes the following steps:

[0037] Step A21: Collect images of workers with different types of clothing, and mark the images; divide the images of marked workers into 13×13 rectangular blocks, and use a clustering method to predict anchor points for each rectangular block Frame, the rectangular block takes 5 anchor frames, the size of the anchor frame matches the size of different detection objects;

[0038] Step A22: Input the divided rectangular block into a multi-layer convolutional neural network, use the convolutional neural network to extract image features, take out the features of the last layer, and input them into the softmax function, and select the maximum probability value as the output result , resulting in a training model.

[0039] The present invention collects the information on the head dress of the operator in real time through the camera, converts the vide...

Embodiment 3

[0042] This embodiment is further optimized on the basis of Embodiment 1 or 2. In the step A1, the collected video is converted into an image, the image is divided into several 13×13 rectangular blocks, and each rectangular block is aggregated. Class prediction anchor point frame, described rectangular block takes 5 anchor point frames, and the size of anchor point frame matches the size of different detected objects;

[0043] In the step A3, input the image generated in the step A1 to the training model, use the convolutional neural network to extract the features of the image, take out the features of the last layer and input the softmax function, and initially judge whether each rectangular block contains the worker's head Internal features, if the rectangular block contains the head features of the worker, then generate the corresponding bounding box, and give the probability values ​​of violation and non-violation respectively, and select the largest probability value as t...

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 automatically judging a dress code through a surveillance video, and is mainly used for judging whether the dressing of the head of an operator is normative or not. The method comprises the following steps that: through a camera, collecting the head characteristics of the operator on line, and generating an image; and through a deep learning training model, extracting image characteristics, judging whether the dressing of the head of the operator is normative or not, and if the dressing of the head of the operator is not normative, outputting alarm information. By use of a deep learning method, features are automatically extracted, the extracted features exhibit better robustness so as to greatly improve a detection result, working efficiency is improved, supervision cost is saved, a supervision dimension is expanded, and supervision accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of video monitoring and identification of dress, and in particular relates to a method for automatically judging a dress code through monitoring video. Background technique [0002] In large factories, it is often necessary to regulate the dress, and the head dress is very important to the production safety of the factory. Especially in the fields of chemical industry and food. In the chemical industry, wearing headgear can reduce the hazards of falling objects to workers; in the field of food safety, workers often need to wear masks and hats. Standardized and uniform clothing can isolate food contamination, which has a major impact on food hygiene and safety. It can be seen that the importance of standard dress to production safety, especially the standard dress of the head. However, at present, the monitoring of dress codes only relies on manpower, and the supervision has the largest controllable space. ...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46H04N7/18G06N3/04
CPCH04N7/18G06V40/10G06V10/267G06V10/40G06N3/045
Inventor 任帅
Owner CHENGDU REMARK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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