Deep learning-based detection method and system for petroleum well site personnel to pass through hoisting object
A deep learning and detection method technology, applied in the field of artificial intelligence video analysis, can solve problems such as difficult operations and difficult detection of hoisting objects, and achieve the effect of reducing the false alarm rate
Pending Publication Date: 2022-04-08
成都迈塔能卫科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the variety of hoisting objects on the oil well site, it is difficult to list them all, so it is difficult to detect the hoisting objects, and it is difficult to further analyze whether the corresponding operation violates regulations
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and / or steps.
[0048] Any feature disclosed in this application (including any appended claims, abstract and drawings), unless expressly stated otherwise, may be replaced by alternative features which are equivalent or serve a similar purpose. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features. This application is to solve the problem of how to detect people passing through hoisting objects, so it can be widely used in the analysis of hoisting operations.
[0049] Below, the technical solution of the present invention will be described in detail in conjunction with the accompanying drawings. Such as figure 1 Shown is a flow chart of a deep learning-based detection method for oil well site personnel passing through hoisting objects in 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
Login to View More Abstract
The invention discloses a deep learning-based detection method and system for a person in a petroleum well site to pass through a hoisting object, and belongs to the field of artificial intelligence video analysis. The method comprises the following steps: reading a camera video stream; extracting a current frame foreground target, and updating the background model image; detecting a target of a current frame of the video stream by a deep learning target detection technology, and adding the target to a target set of the current frame; for the foreground target of the image, removing the foreground target of the current frame by adopting an area proportion and a deep learning target detection result; inputting the remaining foreground targets and the personnel targets in the deep learning target detection result into a personnel crossing detection model for analysis, and judging whether there is a person crossing the foreground target; and if the output of the personnel crossing detection model is true, performing real-time screen capture and video recording, and outputting an alarm. The system comprises a camera video stream acquisition module, an image foreground extraction module, a deep learning target detection module, an image foreground target rejection module, a hoisting object personnel crossing detection module and an output alarm module. The method can solve the problem that the hoisted objects are various and cannot be effectively identified, and has the characteristics of high detection rate and low false alarm rate.
Description
technical field [0001] The invention relates to the field of artificial intelligence video analysis, in particular to a deep learning-based detection method and system for oil well site personnel passing through hoisting objects. Background technique [0002] It is of great significance to ensure the production safety of oil well sites. The traditional production safety inspection method mostly uses special production safety personnel to supervise production safety on site. However, there are many production oil well sites and it is difficult for safety professionals to cover them all. With the development of IT information technology and the popularization of video cameras, the oil operation site has realized the full coverage of video surveillance in the production process. The way of production safety inspection has also gradually changed from the inspection by on-site production safety officers to the manual inspection of production safety videos by production safety off...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/40G06V40/20G06V10/82G06N3/04G06N3/08
Inventor 曾金全谢瑜
Owner 成都迈塔能卫科技有限公司