Method for identifying unsafe behaviors of power plant workers

A technology of safe behavior and staff, applied in the field of computer vision, can solve problems such as the powerlessness of deeper semantic target tasks, and achieve the effects of saving manpower, ensuring safe production, and low price
CN113111771AInactive Publication Date: 2021-07-13济南奔腾时代电力科技有限公司
0 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
济南奔腾时代电力科技有限公司
Publication Date
2021-07-13
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention belongs to the technical field of computer vision, and particularly relates to a method for identifying unsafe behaviors of power plant workers. The method specifically comprises the steps of presetting a plurality of working personnel unsafe behaviors, obtaining a field video image, analyzing the video image through a convolutional neural network of an improved YOLOv4 algorithm, and identifying the unsafe behaviors, including unsafe behavior analysis of a single-frame image, unsafe behavior analysis of a video sequence, and unsafe behavior analysis of a specific task and a scene. The method has the beneficial effects that the method is based on a computer vision technology, and unsafe behaviors are recognized in combination with unsafe behavior semantic information. Compared with an existing scheme, the method has the advantages of low price, high efficiency, real-time detection and no dead angle leakage, and a large amount of manpower, material resources and financial resources are saved. The method can be popularized and applied to unsafe behavior identification scenes in all industrial fields.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of computer vision, and in particular relates to a method for identifying unsafe behaviors of power plant staff. Background technique

[0002] The traditional identification of unsafe human behavior is carried out by manual on-site inspection or video viewing in the monitoring room. Although the accuracy of this method is very high, the efficiency is extremely low and the coverage is small. It is difficult to identify all unsafe behaviors comprehensively and in real time. Therefore, unsafe behaviors in power plants still occur from time to time.

[0003] In recent years, with the development of computer vision technology, intrusion detection technology has begun to be applied to unsafe behavior recognition. The characteristic of intrusion detection technology is to determine whether there is a target by calculating the frame difference of two consecutive video frames. This method is more effective for movi...

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