CN112633238A - Electric welding construction detection method based on deep learning image processing - Google Patents
Electric welding construction detection method based on deep learning image processing Download PDFInfo
- Publication number
- CN112633238A CN112633238A CN202011636904.5A CN202011636904A CN112633238A CN 112633238 A CN112633238 A CN 112633238A CN 202011636904 A CN202011636904 A CN 202011636904A CN 112633238 A CN112633238 A CN 112633238A
- Authority
- CN
- China
- Prior art keywords
- electric welding
- welding construction
- deep learning
- method based
- detection method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an electric welding construction detection method based on deep learning image processing, which comprises the following steps: s1: collecting samples: collecting video information of a factory construction area; s2: carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene; s3: marking the collected video information to mark whether electric welding construction operation is in progress or not; s4: carrying out retrieval training on the marked data by using a deep learning algorithm; s5: carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model; s6: and acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using the model. According to the invention, the electric welding construction operation is judged by adopting a deep learning mode, so that whether the electric welding operation is carried out is determined, manual checking and monitoring are not needed, the manual work is saved, and the condition that the manual work cannot see is avoided.
Description
Technical Field
The invention relates to the technical field of electric welding construction analysis, in particular to an electric welding construction detection method based on deep learning image processing.
Background
With the rapid development of manufacturing industry, electric welding construction work is increasingly frequent in industrial production work. As a fire operation, electric welding has the danger of high temperature, high pressure, flammability and explosiveness, and molten metal sparks generated in electric welding on an operation site can splash everywhere or fall welding slag from high altitude, so that combustibles are easily ignited to cause fire accidents. The electric welding construction work must be approved by safety management personnel. After the approval procedure is processed, the party can carry out operation in the application time period. However, some enterprise workers have weak safety consciousness and good luck psychology, and can work against regulations, thereby bringing serious safety hazards.
In order to ensure that the electric welding operation is operated according to the regulations, the emergency management department carries out remote monitoring through a camera installed in a factory, and irregularly inspects and spot checks enterprises in the district, so that the electric welding operation is ensured to be carried out in a specified time period and accords with the operation specifications. Like production enterprises are often converged in the same area or the same industrial park, so that more enterprises exist in the district, and the hands of managers are limited, so that the enterprises cannot cover all areas. In addition, the monitoring is carried out by depending on manual and visual inspection, the efficiency is low, and the security holes can be caused by long-time fatigue operation.
Disclosure of Invention
The invention aims to provide an electric welding construction detection method based on deep learning image processing, and aims to solve the problems that in the prior art, the efficiency is low and long-time fatigue operation can bring about security holes by means of manual visual supervision.
In order to achieve the purpose, the invention provides the following technical scheme: an electric welding construction detection method based on deep learning image processing comprises the following steps:
s1: collecting samples: collecting video information of a factory construction area;
s2: carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene;
s3: marking the collected video information to mark whether electric welding construction operation is in progress or not;
s4: carrying out retrieval training on the marked data by using a deep learning algorithm;
s5: carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model;
s6: and acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using the model.
Preferably, in step S1, the sample collection is performed by a monitoring camera, and the shooting requirement is multi-angle and no dead angle, and the interval between the shooting and sampling of each time is less than 1 hour.
Preferably, the intelligent structuring process performed on the image or video in step S2 is to extract the actions and gestures of the person in the image or video.
Preferably, the person's actions include walking, squatting, standing, bending over.
Preferably, in step S3, the video information is marked by using a manual marker, and the tool used for manual marking is a labelImg tool.
Preferably, in the step S4, the search training is to build a neural network model according to the Faster R-CNN framework, search out a marked picture of the electric welding construction work, and determine an operation area of the electric welding construction work.
Preferably, in step S5, a ResNet-152-CNN convolutional neural network model is used as a classification model of the person, and classification training is performed to determine whether electric welding work is in progress or not.
Preferably, the detection of the live video data in step S6 is to extract any image in the video, and compare the extracted image with the target data in the CNN model to determine whether the electric welding construction work is being performed.
Preferably, the intelligent structuring of the image or video in step S2 further includes processing of electric welding colors near the person, and determining whether the color of the person region meets the color condition according to the color characteristics during electric welding operation; if the color condition is not met, the subsequent identification step is carried out.
Compared with the prior art, the invention has the beneficial effects that: whether the color of the personnel area meets the color condition can be judged according to the color characteristics during electric welding operation; if the color condition is not met, the subsequent identification step is carried out; marking the collected video information to mark whether electric welding construction operation is in progress or not; carrying out retrieval training on the marked data by using a deep learning algorithm; carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model; adopt the mode of degree of depth study to judge the electric welding construction operation to whether confirm to be welding the operation, need not the manual work and carry out the control and inspect, saved the manual work, and avoid the condition that artifical flesh and eyes can not see to take place.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Example one
Referring to fig. 1, in an embodiment of the present invention, a method for detecting electric welding construction based on deep learning image processing includes the following steps:
s1: collecting samples: collecting video information of a factory construction area;
s2: carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene;
s3: marking the collected video information to mark whether electric welding construction operation is in progress or not;
s4: carrying out retrieval training on the marked data by using a deep learning algorithm;
s5: carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model;
s6: and acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using the model.
Preferably, in step S1, the sample collection is performed by a monitoring camera, and the shooting requirement is multi-angle and no dead angle, and the interval between the shooting and sampling of each time is less than 1 hour.
Preferably, the intelligent structuring process performed on the image or video in step S2 is to extract the actions and gestures of the person in the image or video.
Preferably, the person's actions include walking, squatting, standing, bending over.
Preferably, in step S3, the video information is marked by using a manual marker, and the tool used for manual marking is a labelImg tool.
Preferably, in the step S4, the search training is to build a neural network model according to the Faster R-CNN framework, search out a marked picture of the electric welding construction work, and determine an operation area of the electric welding construction work.
Preferably, in step S5, a ResNet-152-CNN convolutional neural network model is used as a classification model of the person, and classification training is performed to determine whether electric welding work is in progress or not.
Preferably, the detection of the live video data in step S6 is to extract any image in the video, and compare the extracted image with the target data in the CNN model to determine whether the electric welding construction work is being performed.
Preferably, the intelligent structuring of the image or video in step S2 further includes processing of electric welding colors near the person, and determining whether the color of the person region meets the color condition according to the color characteristics during electric welding operation; if the color condition is not met, the subsequent identification step is carried out.
The working principle of the invention is as follows: collecting video information of a factory construction area; carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene; judging whether the color of the personnel area meets the color condition or not according to the color characteristics during electric welding operation; if the color condition is not met, the subsequent identification step is carried out; marking the collected video information to mark whether electric welding construction operation is in progress or not; carrying out retrieval training on the marked data by using a deep learning algorithm; carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model; acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using a model; adopt the mode of degree of depth study to judge the electric welding construction operation to whether confirm to be welding the operation, need not the manual work and carry out the control and inspect, saved the manual work, and avoid the condition that artifical flesh and eyes can not see to take place.
Example two
Referring to fig. 1, in an embodiment of the present invention, a method for detecting electric welding construction based on deep learning image processing includes the following steps:
s1: collecting samples: collecting video information of a factory construction area;
s2: carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene;
s3: marking the collected video information to mark whether electric welding construction operation is in progress or not;
s4: carrying out retrieval training on the marked data by using a deep learning algorithm;
s5: carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model;
s6: and acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using the model.
Preferably, in step S1, the sample collection is performed by a monitoring camera, and the shooting requirement is multi-angle and no dead angle, and the interval between the shooting and sampling of each time is less than 1 hour.
Preferably, the intelligent structuring process performed on the image or video in step S2 is to extract the actions and gestures of the person in the image or video.
Preferably, the person's actions include walking, squatting, standing, bending over.
Preferably, in step S3, the video information is marked by using a manual marker, and the tool used for manual marking is a labelImg tool.
Preferably, in the step S4, the search training is to build a neural network model according to the Faster R-CNN framework, search out a marked picture of the electric welding construction work, and determine an operation area of the electric welding construction work.
Preferably, in step S5, a ResNet-152-CNN convolutional neural network model is used as a classification model of the person, and classification training is performed to determine whether electric welding work is in progress or not.
Preferably, the detection of the live video data in step S6 is to extract any image in the video, and compare the extracted image with the target data in the CNN model to determine whether the electric welding construction work is being performed.
The working principle of the invention is as follows: collecting video information of a factory construction area; carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene; marking the collected video information to mark whether electric welding construction operation is in progress or not; carrying out retrieval training on the marked data by using a deep learning algorithm; carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model; acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using a model; adopt the mode of degree of depth study to judge the electric welding construction operation to whether confirm to be welding the operation, need not the manual work and carry out the control and inspect, saved the manual work, and avoid the condition that artifical flesh and eyes can not see to take place.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. An electric welding construction detection method based on deep learning image processing is characterized in that: the method comprises the following steps:
s1: collecting samples: collecting video information of a factory construction area;
s2: carrying out intelligent structural processing on the image or the video, and identifying the human body attribute in the scene;
s3: marking the collected video information to mark whether electric welding construction operation is in progress or not;
s4: carrying out retrieval training on the marked data by using a deep learning algorithm;
s5: carrying out classification training on data of electric welding construction operation and data without electric welding construction operation to generate a CNN model;
s6: and acquiring video data of a construction site in real time, and detecting whether electric welding construction operation is carried out or not by using the model.
2. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: in the step S1, the sample collection is performed by a monitoring camera, and the shooting requirements are that there is no dead angle at multiple angles and the interval between shooting and sampling is less than 1 hour.
3. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: the intelligent structuring processing of the image or video in the step S2 is to extract the actions and gestures of the person in the image or video.
4. The electric welding construction detection method based on deep learning image processing as claimed in claim 3, characterized in that: the behaviors of the personnel comprise walking, squatting, standing and bending over.
5. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: in step S3, the video information is marked manually, and the tool used for manual marking is a labelImg tool.
6. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: in the step S4, the search training is to build a neural network model according to the Faster R-CNN framework, search out the marked picture of the electric welding construction work, and determine the operation area of the electric welding construction work.
7. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: in step S5, a ResNet-152-CNN convolutional neural network model is used as a classification model of the person, and classification training is performed to determine whether electric welding construction work is in progress or not.
8. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: in the step S6, the detection of the live video data is to extract any image in the video, and compare the extracted image with the target data in the CNN model, so as to determine whether the electric welding construction work is being performed.
9. The electric welding construction detection method based on deep learning image processing as claimed in claim 1, characterized in that: the intelligent structural processing of the image or video in the step S2 further includes processing of electric welding colors near the person, and determining whether the color of the person region meets the color condition according to the color characteristics during electric welding operation; if the color condition is not met, the subsequent identification step is carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636904.5A CN112633238A (en) | 2020-12-31 | 2020-12-31 | Electric welding construction detection method based on deep learning image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636904.5A CN112633238A (en) | 2020-12-31 | 2020-12-31 | Electric welding construction detection method based on deep learning image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112633238A true CN112633238A (en) | 2021-04-09 |
Family
ID=75290114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011636904.5A Pending CN112633238A (en) | 2020-12-31 | 2020-12-31 | Electric welding construction detection method based on deep learning image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633238A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954280A (en) * | 2021-04-21 | 2021-06-11 | 国网瑞嘉(天津)智能机器人有限公司 | Intelligent wearable device-based manual live working system and method |
| CN115052092A (en) * | 2022-06-17 | 2022-09-13 | 北京小明智铁科技有限公司 | Welding operation monitoring method and device and welding monitoring equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491830A (en) * | 2018-04-23 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning |
| CN110188709A (en) * | 2019-06-03 | 2019-08-30 | 济南浪潮高新科技投资发展有限公司 | The detection method and detection system of oil drum in remote sensing image based on deep learning |
| CN110826439A (en) * | 2019-10-25 | 2020-02-21 | 杭州叙简科技股份有限公司 | Electric welding construction detection method based on deep learning image processing |
-
2020
- 2020-12-31 CN CN202011636904.5A patent/CN112633238A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491830A (en) * | 2018-04-23 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning |
| CN110188709A (en) * | 2019-06-03 | 2019-08-30 | 济南浪潮高新科技投资发展有限公司 | The detection method and detection system of oil drum in remote sensing image based on deep learning |
| CN110826439A (en) * | 2019-10-25 | 2020-02-21 | 杭州叙简科技股份有限公司 | Electric welding construction detection method based on deep learning image processing |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954280A (en) * | 2021-04-21 | 2021-06-11 | 国网瑞嘉(天津)智能机器人有限公司 | Intelligent wearable device-based manual live working system and method |
| CN112954280B (en) * | 2021-04-21 | 2023-08-04 | 国网瑞嘉(天津)智能机器人有限公司 | Artificial live working system and method based on intelligent wearable equipment |
| CN115052092A (en) * | 2022-06-17 | 2022-09-13 | 北京小明智铁科技有限公司 | Welding operation monitoring method and device and welding monitoring equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113344326B (en) | System and method for identifying dynamic hidden danger and evaluating risk of special operation site | |
| Albert et al. | Empirical measurement and improvement of hazard recognition skill | |
| KR102369229B1 (en) | Risk prediction system and risk prediction method based on a rail robot specialized in an underground tunnel | |
| CN107862331A (en) | It is a kind of based on time series and CNN unsafe acts recognition methods and system | |
| CN112633238A (en) | Electric welding construction detection method based on deep learning image processing | |
| CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
| CN111814601A (en) | Video analysis method combining target detection and human body posture estimation | |
| CN114155601A (en) | Vision-based method and system for detecting dangerous behaviors of operating personnel | |
| CN111126293A (en) | Flame and smoke abnormal condition detection method and system | |
| CN111277748A (en) | Construction site fire management system based on video intelligent analysis and implementation method thereof | |
| CN118091054B (en) | Dangerous gas on-line monitoring system and method | |
| CN111259855A (en) | Mobile safety helmet wearing detection method based on deep learning | |
| CN110543866A (en) | Safety management system and method for capital construction engineering constructors | |
| CN115330129A (en) | Enterprise safety risk early warning analysis method and system | |
| CN118095835A (en) | Method and device for monitoring construction site, electronic equipment and storage medium | |
| CN113713292A (en) | Method and device for carrying out accurate flame discrimination, fire extinguishing point positioning and rapid fire extinguishing based on YOLOv5 model | |
| CN113361420A (en) | Mine fire monitoring method, device and equipment based on robot and storage medium | |
| CN115393789A (en) | Crowd gathering early warning method, system, equipment and storage medium for dangerous area of building site | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN117392591A (en) | Site security AI detection method and device | |
| CN115880722A (en) | Intelligent identification method, system and medium worn by power distribution operating personnel | |
| CN112949536B (en) | Fire alarm method based on cloud platform | |
| Reyes et al. | Safety gear compliance detection using data augmentation-assisted transfer learning in construction work environment | |
| CN111353465A (en) | Transformer substation personnel behavior analysis method and system based on deep learning technology | |
| CN113657165A (en) | Dangerous climbing behavior recognition algorithm in electric power field operation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |