Construction violation behavior detection model construction method and application thereof

A technology for detecting models and building methods, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problem of inability to accurately detect the category and location of violations

Active Publication Date: 2020-10-27
HUAZHONG UNIV OF SCI & TECH
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a method for constructing a construction violation detection model and its application, which is used to solve the...

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
  • Construction violation behavior detection model construction method and application thereof
  • Construction violation behavior detection model construction method and application thereof
  • Construction violation behavior detection model construction method and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A construction method 100 of a construction violation detection model, such as figure 1 shown, including:

[0049] Step 110, obtaining the original image sample set of construction violations;

[0050] Step 120: Perform similarity pairing on the images in the original image sample set to obtain multiple sets of image pairs, perform foreground exchange on each set of image pairs, and perform style rendering on all the exchanged images to eliminate the effect caused by the exchange. Edge effect, get extended image sample set;

[0051] Step 130, based on the original image sample set and the extended image sample set, train a single-stage target detection network to obtain a violation detection model, wherein during training, the prediction of the branch and position prediction branch is based on the image context information and the detection network. As a result, network parameters are tuned.

[0052] It should be noted that in step 110, the monitoring video of the co...

Embodiment 2

[0094] A method for detecting construction violations, comprising:

[0095]Collect the construction image to be detected and input it into the construction violation detection model constructed by the construction method of the construction violation detection model described in the first embodiment. Based on the output results of the category prediction branch and the location prediction branch, it is obtained whether there is Construction violations and the type and location of the construction violation. The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

[0096] In the existing single-frame-based image processing methods, pure image classification can only give single-frame prediction results, but cannot give the location of violations. In this embodiment, the behavior detection method based on a single frame image will be adopted, and the model construction method in the above-mentioned embodiment 1 will be used to defi...

Embodiment 3

[0098] A computer-readable storage medium, the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the above A method for constructing a construction violation detection model described in Embodiment 1 and / or a construction violation detection method as described in Embodiment 2 above. The relevant technical solutions are the same as those in Embodiment 1 and Embodiment 2, and will not be repeated here.

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 relates to the field of violation behavior detection, and specifically discloses a construction violation behavior detection model construction method and application thereof. The methodcomprises the steps: carrying out the similarity pairing of images in an original image sample set, carrying out the foreground exchange of each group of image pairs, carrying out the style renderingof all exchanged images, and obtaining an extended image sample set; training a single-stage target detection network based on an original image sample set and an extended image sample set, adjustingand optimizing network parameters according to the text information of the images and prediction results of the category prediction branches and the position prediction branches in the detection network during training, and finally detecting violation behaviors based on the constructed violation behavior detection model. According to the method, pairing similarity enhancement is carried out on original samples, and the scale of training samples and the model training precision are greatly improved; in addition, context information is considered during training, regularization is carried out by adding the context information to the network, and the accuracy of target detection is greatly improved.

Description

technical field [0001] The invention belongs to the field of violation detection, and more specifically relates to a method for constructing a construction violation detection model and its application. Background technique [0002] During the construction process, ensuring construction safety is an important link to improve production efficiency, enhance enterprise benefits, and ensure employee safety. It is of great significance to design and produce an intelligent monitoring system so that it can automatically and accurately identify, judge, and locate workers in a complex and changeable industrial environment. Specifically, this system requires that the workers within the scope of the lens can be detected in real time through the camera to determine whether there is any behavior of not wearing a helmet or not wearing a seat belt. Alerts provide reliable information for background monitoring personnel. In this way, the safety of workers in the production environment can...

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): G06K9/00G06K9/46G06K9/62G06N3/08
CPCG06N3/08G06V20/40G06V10/40G06F18/22G06F18/214
Inventor 韩守东陈国荣马迪刘巾英陈阳
Owner HUAZHONG UNIV OF SCI & TECH
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