Fire-fighting point location automatic layout method applied to cloud platform

A cloud platform, firefighting technology, applied in instruments, character and pattern recognition, geometric CAD, etc., can solve the problems of high cost, long time, large error, etc., and achieve the effect of high accuracy, small error in detection results, and fast speed

Pending Publication Date: 2020-05-19
WUHAN WUTOS
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since there are many fire-fighting equipment points on the fire-fighting drawings, manual layout has the disadvantages of high cost, long time and large errors. Therefore, in order to solve the above problems, the present invention provides an automatic fire-fighting point layout applied to the cloud platform. The method of drawing can improve the efficiency and accuracy of the layout of firefighting points

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
  • Fire-fighting point location automatic layout method applied to cloud platform
  • Fire-fighting point location automatic layout method applied to cloud platform
  • Fire-fighting point location automatic layout method applied to cloud platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 and figure 2 As shown, a method for automatic layout of firefighting points applied to a cloud platform of the present invention comprises the following steps:

[0033] S1. Convert the fire-fighting drawings to be detected into two identical pictures respectively, and name the two pictures as a display picture and a recognition picture respectively;

[0034] In this embodiment, the fire-fighting drawings are in the DWG format, and the fire-fighting drawings in the DWG format need to be converted into images in the PNG format or JPG format, wherein the conversion process can be converted by existing software, and the present embodiment does not relate to format conversion Improve.

[0035] S2, building a training model;

[0036] Further preferably, the training model includes a multi-category firefighting point training model, and each type of firefighting point training model detects the position coordinates and category information of the same type...

Embodiment 2

[0042] On the basis of Embodiment 1, this embodiment provides a method for constructing a training model. In the present embodiment, the construction method of the fire-fighting point training model of each category is the same, therefore, only introduces the construction method of the fire-fighting point training model of a kind of category here, specifically comprises the following steps:

[0043] S101. Intercept an image of a fixed size in the region containing the target image in the picture to be detected, mark it as a positive sample, and store all the positive samples in the positive sample set; intercept an image of the same size in the region not including the target image and mark it as a negative sample, Store all negative samples in the negative sample set;

[0044] S102. Perform grayscale and normalization processing on the positive sample and the negative sample;

[0045] Among them, grayscale is to regard the image as a grayscale three-dimensional image. In th...

Embodiment 3

[0055] On the basis of Embodiment 2, the present embodiment provides a method for detecting and identifying firefighting point position coordinates and category information on the picture according to the training model, which specifically includes the following steps:

[0056] S201. Construct a positive feature vector and a negative feature vector with the same latitude as the training process, and use the trained SVM classification model to set the feature vector;

[0057] S202. Cut the recognition picture into small images of a fixed size, record the original coordinate position of each pixel in the small image, and arrange the small images into an image matrix in sequence according to the cutting order;

[0058] Since the resolution of the recognition image to be detected is large, most of which exceed 10000*10000 pixels, it is easy to cause computer memory overflow when calculating the overall HOG feature, so the recognition image needs to be cut into small images of a fix...

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 provides a firefighting point location automatic layout method applied to a cloud platform. A plurality of types of firefighting point location training models are constructed, the firefighting point location training model of each type detects the position coordinates and type information of the firefighting point locations of the same type on the image to be identified, through multiple types of firefighting point location training models, position coordinates and type information of all firefighting point locations on an image to be identified can be detected, and the multipletypes of firefighting point location training models are high in detection speed, high in efficiency and high in accuracy; and on the basis of construction of a traditional SVM classification model,a difficult case processing step is added, the target image which is not detected and the non-target image which is detected to be wrong are intercepted again and expanded into the positive and negative sample set, the SVM classification model is retrained, and parameters of the SVM classification model are increased, so that the detection result error of the SVM classification model is small, andthe detection result is accurate.

Description

technical field [0001] The invention relates to the field of point layout, in particular to a method for automatic fire point layout applied to a cloud platform. Background technique [0002] With the popularity of the Internet of Things, the cloud platform of intelligent fire protection based on the Internet of Things has been widely used. Since there are many connected units on the smart firefighting IoT cloud platform, a large number of firefighting drawings will be generated. The firefighting drawings are generally in DWG format, and the smart firefighting IoT cloud platform does not support viewing files in DWG format. Therefore, only DWG format fire drawings into images in PNG or JPG format, so that they can be displayed on the smart fire IoT cloud platform. The smart fire fighting IoT cloud platform needs to mark all the fire potentials on the fire drawing in PNG format or JPG format. Since there are many fire-fighting equipment points on the fire-fighting drawings,...

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): G06F30/12G06K9/62
CPCG06F18/214
Inventor 胡捷付苗董雷赵鹏陈双双王哲
Owner WUHAN WUTOS
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