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

High-altitude safety belt detection method, device and equipment based on multiple modes and storage medium

A detection method and a technology for seat belts, applied in the computer field, can solve the problems of easy concealment of features, easy occurrence of false detection and missed detection, easy false detection, etc., to achieve excellent detection accuracy and robustness, and to improve detection accuracy. Effect

Inactive Publication Date: 2021-06-18
创新奇智(北京)科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if the seat belt is directly detected, because the outdoor environment is complex, especially in the construction site and electric power industry, it is easy to detect the seat belt directly, and in the high altitude, the posture of the person changes greatly, and the features are easy to be covered, which is prone to false detection. and missed

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
  • High-altitude safety belt detection method, device and equipment based on multiple modes and storage medium
  • High-altitude safety belt detection method, device and equipment based on multiple modes and storage medium
  • High-altitude safety belt detection method, device and equipment based on multiple modes and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] see figure 1 , figure 1 It is a schematic flowchart of a method for detecting high-altitude safety belts based on multimodality disclosed in the embodiment of the present application. Such as figure 1 As shown, the embodiment of the present application discloses a multimodal high-altitude safety belt detection method, including steps:

[0056] 101. Obtain the operation map of personnel at height collected by the first imaging device and the thermal imaging diagram of personnel at height collected by the second imaging device;

[0057] 102. Calibrate the thermal imaging map of high-altitude personnel according to the RGB image, and obtain the calibrated thermal imaging map;

[0058] 103. According to the preset image feature extraction network, extract the image features of the aerial work map and use it as the first image feature;

[0059] 104. Extract the image features of the calibrated thermal image and use them as the second image features;

[0060] 105. Determ...

Embodiment 2

[0085] see image 3 , image 3 It is a schematic structural diagram of a multi-modal high-altitude safety belt detection device disclosed in the embodiment of the application. Such as image 3 As shown, the device of the embodiment of the present application includes:

[0086] An acquisition module 201, configured to acquire the operation map of the high-altitude personnel collected by the first imaging device and the thermal imaging diagram of the high-altitude personnel collected by the second imaging device;

[0087] Calibration module 202, used for calibrating the thermal imaging map of high-altitude personnel according to the RGB image, and obtaining the calibrated thermal imaging map;

[0088] The first feature extraction module 203 is used to extract the image features of the high-altitude personnel operation map according to the preset image feature extraction network as the first image feature;

[0089] The second feature extraction module 204 is used to extract t...

Embodiment 3

[0095] see Figure 4 , Figure 4 It is a schematic structural diagram of a high-altitude safety belt detection device based on multi-modality disclosed in the embodiment of the application. Such as Figure 4 As shown, the equipment of the embodiment of the present application includes:

[0096] processor 301; and

[0097] The memory 302 is configured to store machine-readable instructions. When the instructions are executed by the processor 301, the processor 301 executes the multi-modal high-altitude safety belt detection method disclosed in Embodiment 1 of the present application.

[0098] Compared with the existing technology, the device in the embodiment of the present application can integrate RGB images and thermal imaging images through multi-modal input, and greatly improve the detection accuracy of people through their complementarity, while the existing technology only uses A certain mode is used for human detection, and under the premise that the outdoor high-al...

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 multi-mode-based high-altitude safety belt detection method, device and equipment and a storage medium. The method comprises the following steps: collecting a high-altitude personnel operation picture acquired by a first imaging device and a high-altitude personnel thermal imaging picture acquired by a second imaging device; calibrating the thermal image of the high-altitude personnel according to the RGB image to obtain a calibrated thermal image; according to a preset image feature extraction network, extracting an image feature of the high-altitude personnel operation image and taking the image feature as a first image feature; extracting an image feature of the calibrated thermal image and taking the image feature as a second image feature; determining a human shape image of the high-altitude personnel according to the first image feature and the second image feature; determining an image of a key part of the high-altitude personnel according to the human shape image of the high-altitude personnel; and detecting whether the high-altitude personnel wear safety belts according to the images of the key parts of the high-altitude personnel. According to the method, whether the safety belt of the high-altitude personnel is worn normatively or not can be quickly and accurately recognized, and the method has better robustness.

Description

technical field [0001] The present application relates to the field of computer technology, in particular, to a method, device, equipment and storage medium for detecting high-altitude safety belts based on multimodality. Background technique [0002] With the development of society, enterprises have more and more clear requirements for safe production and safe construction. According to the safety production regulations, safety helmets and safety belts must be worn when working at heights. Among them, the shape of the seat belt is changeable, and there are standard requirements when wearing it. If it is not worn properly, there will be life safety hazards when working at high altitudes. When working at high altitudes, due to the load-bearing problem of the seat belt, a certain belt of the seat belt breaks and the staff The unknown happens from time to time. Therefore, monitoring the safety belt wearing of high-altitude workers at all times is related to the safety of worke...

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): G06K9/00G06K9/46
CPCG06V40/10G06V10/44
Inventor 张发恩张沁薇
Owner 创新奇智(北京)科技有限公司
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