CN113095132B - Neural network based gas field identification method, system, terminal and storage medium - Google Patents
Neural network based gas field identification method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN113095132B CN113095132B CN202110240015.5A CN202110240015A CN113095132B CN 113095132 B CN113095132 B CN 113095132B CN 202110240015 A CN202110240015 A CN 202110240015A CN 113095132 B CN113095132 B CN 113095132B
- Authority
- CN
- China
- Prior art keywords
- target
- behavior
- target detection
- video
- detection result
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The application provides a method, a system, a terminal and a storage medium for detecting and identifying a target in a gas field based on a neural network, wherein the method comprises the following steps: determining a target to be detected of a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected; extracting key frames of the videos with the 2D rectangular frames and the joint points calibrated, and combining the extracted pictures into a target behavior video to be detected; respectively inputting the behavior videos of the target to be detected into a preset target detection network model and a behavior recognition network model for training; inputting a real-time monitoring video of a target area of a gas operation site into a trained target detection network model to obtain a target detection result; and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into the trained behavior recognition network model, and obtaining a behavior prediction result.
Description
Technical Field
The application relates to the field of monitoring safety of gas facilities, in particular to a neural network-based gas field identification method, system, terminal and storage medium.
Background
With the development of urban gas industry, urban gas pipelines are also increasing continuously, the urban gas pipelines are one of important infrastructure of urban construction, and the development of urban gas pipe network facilities becomes an important mark of urban modernization. The safety problem of the gas facility is a key link influencing public safety, and the basic conditions for ensuring safe operation and stable supply of gas are provided. For the management of the safe operation of the urban gas operation site, besides various methods and means of conventional law, administration, economy and the like, technical safety precaution means are also required to be introduced to ensure the safe operation of the urban gas operation. How to discover and accurately locate the destructive behavior in time, give an alarm in time and prevent the destruction of a gas operation field is a problem which needs to be solved urgently by urban gas companies.
Patent CN107147886A discloses a video optimized storage system, which stores videos returned from a scene into different storage devices according to the bitrate, and can optimize the storage in this way, but does not perform artificial intelligence processing prediction processing on the data, and the whole system has no other functions except for storing the videos. The patent CN109120896A discloses a system integrating monitoring and background management, which enables the staff to perform real-time monitoring and processing through the returned data in the background. Although this method is feasible, it still requires manpower and the system itself has no ability to make a judgment about the situation at the site.
In the methods disclosed in patent CN107147886A and patent CN109120896A, videos are optimally stored, wherein patent CN109120896A further establishes a background monitoring and supervising platform. They do not have artificial intelligence prejudgments on live video. This greatly increases labor costs and may not be able to immediately respond to an emergency due to the negligence of the monitoring staff.
Therefore, a method, a system, a terminal and a storage medium for identifying a gas field based on a neural network are needed to solve the problem that a monitoring video of a gas operation field cannot identify abnormal conditions for safety early warning.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a method, a system, a terminal and a storage medium for identifying a gas field based on a neural network, and solves the problems that in the prior art, a monitoring video of a gas operation field cannot identify abnormal conditions to perform safety early warning, and the like.
In order to solve the above technical problem, in a first aspect, the present application provides a method for detecting a target and identifying a behavior in a gas field based on a neural network, including:
acquiring a monitoring video of a target area of a gas operation site;
determining a target to be detected of a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected;
extracting key frames of the videos with the 2D rectangular frames and the joint points calibrated, and combining the extracted pictures into a target behavior video to be detected;
respectively inputting the target behavior video to be detected into a preset target detection network model and a preset behavior recognition network model for training;
inputting a real-time monitoring video of a target area of a gas operation site into a trained target detection network model to obtain a target detection result;
and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Optionally, the determining a target to be detected of a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected includes:
and calibrating the type of the target to be detected in the monitoring video of the target area of the gas operation site by using a 2D rectangular frame, and calibrating the position information and the category information of the joint point of the target to be detected.
Optionally, the extracting key frames of the videos with the 2D rectangular frame and the joint points calibrated and combining the extracted pictures into the target behavior video to be detected includes:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a target behavior video to be detected, and storing the target behavior video to a terminal database.
Optionally, the method of inputting the real-time monitoring video of the target area of the gas operation site into the trained target detection network model to obtain the target detection result further includes:
if the target detection result is a worker, the worker does not process the target detection result;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Optionally, if the target detection result is a non-worker and does not carry an illegal apparatus that damages a gas device, the real-time monitoring video is input to the trained behavior recognition network model to obtain a behavior prediction result, further including:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-illegal behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and illegal behavior information, and sequencing the monitoring video to a terminal database according to time information.
In a second aspect, the present application further provides a gas field target detection and behavior recognition system based on a neural network, including:
the acquisition unit is configured for acquiring a monitoring video of a target area of a gas operation site;
the calibration unit is used for configuring a target to be detected for determining a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected;
the key frame extraction unit is configured for extracting key frames of videos for calibrating the 2D rectangular frame and the joint points, and combining the extracted pictures into a target behavior video to be detected;
the model training unit is configured to input the behavior video of the target to be detected into a preset target detection network model and a preset behavior recognition network model respectively for training;
the target detection unit is configured and used for inputting the real-time monitoring video of the target area of the gas operation site into the trained target detection network model and acquiring a target detection result;
and the behavior prediction unit is configured to input the real-time monitoring video into a trained behavior recognition network model to obtain a behavior prediction result if the target detection result is a non-worker and does not carry an illegal apparatus for destroying the gas equipment.
Optionally, the calibration unit is specifically configured to:
and calibrating the type of the target to be detected in the monitoring video of the target area of the gas operation site by using a 2D rectangular frame, and calibrating the position information and the category information of the joint point of the target to be detected.
Optionally, the key frame extracting unit is specifically configured to:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a target behavior video to be detected, and storing the target behavior video to a terminal database.
Optionally, the behavior prediction unit is specifically configured to:
if the target detection result is a worker, the worker does not process the target detection result;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Optionally, the behavior prediction unit is further specifically configured to:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
In a third aspect, the present application provides a terminal, comprising:
a processor, a memory, wherein,
the memory is used for storing a computer program which,
the processor is used for calling and running the computer program from the memory so as to make the terminal execute the method of the terminal.
In a fourth aspect, the present application provides a computer storage medium having instructions stored thereon, which when executed on a computer, cause the computer to perform the method of the above aspects.
Compared with the prior art, the method has the following beneficial effects:
according to the method and the device, the problems that in the prior art, the abnormal situation cannot be identified by the monitoring video of the gas operation site to carry out safety early warning are solved through target detection and behavior recognition module integrated monitoring based on the neural network, manpower is greatly reduced, and the processing speed of emergency events is increased. In addition, the application carries out video segmentation with the surveillance video according to the incident that detects out to optimize the storage, be convenient for the operation and maintenance personnel trace back the gas operation scene abnormal conditions and in time carry out the operation and maintenance and handle according to the surveillance video.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting and behavior recognizing a gas field target based on a neural network according to an embodiment of the present application;
FIG. 2 is a flow chart of another neural network-based gas field target detection and behavior recognition method provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a neural network-based gas field target detection and behavior recognition system according to another embodiment of the present application;
fig. 4 is a schematic structural diagram of a terminal system according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting and behavior recognizing a gas field target based on a neural network according to an embodiment of the present application, where the method 100 includes:
s101: acquiring a monitoring video of a target area of a gas operation site;
s102: determining a target to be detected of a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected;
s103: extracting key frames of the videos with the 2D rectangular frames and the joint points calibrated, and combining the extracted pictures into a target behavior video to be detected;
s104: respectively inputting the target behavior video to be detected into a preset target detection network model and a preset behavior recognition network model for training;
s105: inputting a real-time monitoring video of a target area of a gas operation site into a trained target detection network model to obtain a target detection result;
s106: and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Based on the above embodiment, as an optional embodiment, the S102 determines a target to be detected of a monitoring video of a target area of a gas operation site, and performs 2D rectangular frame calibration and joint point calibration on the target to be detected, including:
and calibrating the type of the target to be detected in the monitoring video of the target area of the gas operation site by using a 2D rectangular frame, and calibrating the position information and the category information of the joint point of the target to be detected.
Based on the above embodiment, as an optional embodiment, the S103 performs key frame extraction on the video with the 2D rectangular frame and the joint point calibrated, and combines the extracted pictures into the target behavior video to be detected, including:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a target behavior video to be detected, and storing the target behavior video to a terminal database.
Based on the foregoing embodiment, as an optional embodiment, if the target detection result is a non-worker and does not carry an illegal device that damages a gas appliance, the S106 inputs the real-time monitoring video to a trained behavior recognition network model to obtain a behavior prediction result, and further includes:
if the target detection result is a worker, the worker does not process the target detection result;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Based on the foregoing embodiment, as an optional embodiment, if the target detection result is a non-worker and does not carry an illegal device that damages a gas appliance, the S106 inputs the real-time monitoring video to a trained behavior recognition network model to obtain a behavior prediction result, and further includes:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
Specifically, as shown in fig. 2, fig. 2 is a flowchart of another gas field target detection and behavior recognition method based on a neural network according to an embodiment of the present application. Installing a monitoring camera in a target area of a gas operation site, acquiring a monitoring video of the target area of the gas operation site, performing real-time target detection on the monitoring video of the target area, determining a target to be detected (namely a person), and performing 2D rectangular frame and joint point calibration on the target to be detected; extracting key frames of the videos with the 2D rectangular frames and the joint points calibrated, and combining the extracted pictures into a target behavior video to be detected; and inputting the target behavior video to be detected into a preset target detection network model and a behavior recognition network model for training. Acquiring a real-time monitoring video, inputting the real-time monitoring video into a trained target detection network model, and acquiring whether a target detection result is a worker; if the target detection result is a worker, the worker does not process the target detection result; if the target detection result is that the target detection result is a non-worker and carries an illegal appliance which damages the gas equipment, starting early warning and informing field security personnel; if the target detection result is that the target detection result is a non-worker and does not carry an illegal appliance for destroying the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result; if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel; and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a gas field target detection and behavior recognition system based on a neural network according to an embodiment of the present application, where the system 300 includes:
the acquiring unit 301 is configured to acquire a monitoring video of a target area of a gas operation site;
the calibration unit 302 is configured to determine a target to be detected of a monitoring video of a target area of a gas operation site, and perform 2D rectangular frame calibration and joint point calibration on the target to be detected;
the key frame extraction unit 303 is configured to extract key frames of videos in which the 2D rectangular frame and the joint point are calibrated, and combine the extracted pictures into a target behavior video to be detected;
the model training unit 304 is configured to input the behavior video of the target to be detected into a preset target detection network model and a preset behavior recognition network model respectively for training;
the target detection unit 305 is configured to input a real-time monitoring video of a target area of a gas operation site into a trained target detection network model, and obtain a target detection result;
and the behavior prediction unit 306 is configured to input the real-time monitoring video to a trained behavior recognition network model to obtain a behavior prediction result if the target detection result is a non-worker and does not carry an illegal apparatus for destroying the gas equipment.
Based on the foregoing embodiment, as an optional embodiment, the calibration unit 302 is specifically configured to:
and calibrating the type of the target to be detected in the monitoring video of the target area of the gas operation site by using a 2D rectangular frame, and calibrating the position information and the category information of the joint point of the target to be detected.
Based on the foregoing embodiment, as an optional embodiment, the key frame extracting unit 303 is specifically configured to:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a behavior video of the target to be detected, and storing the behavior video to a terminal database.
Based on the foregoing embodiment, as an optional embodiment, the behavior prediction unit 306 is specifically configured to:
if the target detection result is a worker, the worker does not process the target detection result;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
and if the target detection result is that the target detection result is a non-worker and does not carry illegal equipment damaging the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result.
Based on the foregoing embodiment, as an optional embodiment, the behavior prediction unit 306 is further specifically configured to:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a terminal system 400 provided in the embodiment of the present application, where the terminal system 400 may be used to execute the method for detecting and behavior recognizing in a gas field based on a neural network according to the embodiment of the present invention.
The terminal system 400 may include: a processor 401, a memory 402, and a communication unit 403. The components communicate via one or more buses, and those skilled in the art will appreciate that the architecture of the servers shown in the figures is not intended to be limiting, and may be a bus architecture, a star architecture, a combination of more or less components than those shown, or a different arrangement of components.
The memory 402 may be used for storing instructions executed by the processor 401, and the memory 402 may be implemented by any type of volatile or non-volatile storage terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The execution instructions in the memory 402, when executed by the processor 401, enable the terminal system 400 to perform some or all of the steps in the method embodiments described below.
The processor 401 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by operating or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory. The processor may be composed of an Integrated Circuit (IC), for example, a single packaged IC, or a plurality of packaged ICs connected with the same or different functions. For example, the processor 401 may only include a Central Processing Unit (CPU). In the embodiment of the present invention, the CPU may be a single operation core, or may include multiple operation cores.
A communication unit 403, configured to establish a communication channel so that the storage terminal can communicate with other terminals. And receiving user data sent by other terminals or sending the user data to other terminals.
The present application also provides a computer storage medium, wherein the computer storage medium may store a program, and the program may include some or all of the steps in the embodiments provided by the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
According to the method and the device, the problems that in the prior art, the abnormal situation cannot be identified by the monitoring video of the gas operation site to carry out safety early warning are solved through target detection and behavior recognition module integrated monitoring based on the neural network, manpower is greatly reduced, and the processing speed of emergency events is increased. In addition, the application carries out video segmentation with the surveillance video according to the incident that detects out to optimize the storage, be convenient for the operation and maintenance personnel trace back the gas operation scene abnormal conditions and in time carry out the operation and maintenance and handle according to the surveillance video.
The embodiments are described in a progressive mode in the specification, the emphasis of each embodiment is on the difference from the other embodiments, and the same and similar parts among the embodiments can be referred to each other. For the system provided by the embodiment, the description is relatively simple because the system corresponds to the method provided by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (6)
1. A fuel gas field target detection and behavior recognition method based on a neural network is characterized by comprising the following steps:
acquiring a monitoring video of a target area of a gas operation site;
determining a target to be detected of a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected;
extracting key frames of the videos with the 2D rectangular frames and the joint points calibrated, and combining the extracted pictures into a target behavior video to be detected;
respectively inputting the target behavior video to be detected into a preset target detection network model and a preset behavior recognition network model for training;
inputting a real-time monitoring video of a target area of a gas operation site into a trained target detection network model to obtain a target detection result;
if the target detection result is a worker, the worker does not process the target detection result;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
if the target detection result is that the target detection result is a non-worker and does not carry an illegal appliance for destroying the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result;
if the target detection result is a non-worker and does not carry an illegal appliance for destroying the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model to obtain a behavior prediction result, and further comprising:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
2. The method for detecting the target and identifying the behavior in the gas field based on the neural network as claimed in claim 1, wherein the method comprises the steps of extracting key frames from videos for calibrating 2D rectangular frames and joint points, and combining the extracted pictures into the behavior video of the target to be detected, and comprises the following steps:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a target behavior video to be detected, and storing the target behavior video to a terminal database.
3. A gas field target detection and behavior recognition system based on a neural network is characterized by comprising:
the acquisition unit is configured for acquiring a monitoring video of a target area of a gas operation site;
the calibration unit is used for configuring a target to be detected for determining a monitoring video of a target area of a gas operation site, and performing 2D rectangular frame calibration and joint point calibration on the target to be detected;
the key frame extraction unit is configured for extracting key frames of videos for calibrating the 2D rectangular frame and the joint points, and combining the extracted pictures into a target behavior video to be detected;
the model training unit is configured to input the behavior video of the target to be detected into a preset target detection network model and a preset behavior recognition network model respectively for training;
the target detection unit is configured and used for inputting the real-time monitoring video of the target area of the gas operation site into the trained target detection network model and acquiring a target detection result;
the behavior prediction unit is configured to not process the target detection result if the target detection result is a worker;
if the target detection result is that the target detection result is a non-worker and carries illegal equipment damaging the gas equipment, starting early warning and informing field security personnel;
if the target detection result is that the target detection result is a non-worker and does not carry an illegal appliance for destroying the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model, and obtaining a behavior prediction result;
if the target detection result is a non-worker and does not carry an illegal appliance for destroying the gas equipment, inputting the real-time monitoring video into a trained behavior recognition network model to obtain a behavior prediction result, and further comprising:
if the behavior prediction result is an illegal behavior, starting early warning and informing field security personnel;
and if the behavior prediction result is non-violation behavior, splitting the monitoring video according to the existence of personnel in a time axis, respectively annotating events, periods, personnel types, personnel numbers, place information and violation behavior information, and sequencing the events, the periods, the personnel types, the personnel numbers, the place information and the violation behavior information to a terminal database according to time information.
4. The system of claim 3, wherein the keyframe extraction unit is specifically configured to:
comparing each frame of the video with the previous frame, wherein the 2D rectangular frame and the joint points are calibrated;
if the difference between the current frame and the previous frame is greater than a preset threshold, the current frame is retained, and if the difference between the current frame and the previous frame is less than the preset threshold, the current frame is deleted;
and combining all the reserved frames into a target behavior video to be detected, and storing the target behavior video to a terminal database.
5. A terminal, comprising:
a processor;
a memory for storing instructions for execution by the processor;
wherein the processor is configured to perform the method of any of claims 1-2.
6. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110240015.5A CN113095132B (en) | 2021-03-04 | 2021-03-04 | Neural network based gas field identification method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110240015.5A CN113095132B (en) | 2021-03-04 | 2021-03-04 | Neural network based gas field identification method, system, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113095132A CN113095132A (en) | 2021-07-09 |
| CN113095132B true CN113095132B (en) | 2022-08-02 |
Family
ID=76666381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110240015.5A Active CN113095132B (en) | 2021-03-04 | 2021-03-04 | Neural network based gas field identification method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095132B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780077A (en) * | 2021-08-05 | 2021-12-10 | 深圳市燃气集团股份有限公司 | Target detection-based operation behavior specification detection method and device and terminal equipment |
| CN115346170B (en) * | 2022-08-11 | 2023-05-30 | 北京市燃气集团有限责任公司 | Intelligent monitoring method and device for gas facility area |
| CN115527158B (en) * | 2022-08-11 | 2023-04-25 | 北京市燃气集团有限责任公司 | Method and device for detecting abnormal behaviors of personnel based on video monitoring |
| CN116168313A (en) * | 2022-12-05 | 2023-05-26 | 广州视声智能股份有限公司 | Control method and device of intelligent device, storage medium and electronic device |
| CN117197728B (en) * | 2023-11-07 | 2024-01-23 | 成都千嘉科技股份有限公司 | Method for identifying real-time gas diffusing operation through wearable camera equipment |
| CN117611928B (en) * | 2024-01-23 | 2024-04-09 | 青岛国实科技集团有限公司 | Illegal electric welding identification method, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705389A (en) * | 2019-09-16 | 2020-01-17 | 全球能源互联网研究院有限公司 | Power grid operation behavior identification method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993031B (en) * | 2017-12-29 | 2021-07-20 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting target illegal driving behaviors of livestock-powered vehicle and camera |
| CN110740298A (en) * | 2019-10-28 | 2020-01-31 | 上海交通大学 | Distributed classroom discipline behavior detection system, method and medium |
| CN111144263B (en) * | 2019-12-20 | 2023-10-13 | 山东大学 | Construction worker high-falling accident early warning method and device |
| CN111783744A (en) * | 2020-07-31 | 2020-10-16 | 上海仁童电子科技有限公司 | Operation site safety protection detection method and device |
-
2021
- 2021-03-04 CN CN202110240015.5A patent/CN113095132B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705389A (en) * | 2019-09-16 | 2020-01-17 | 全球能源互联网研究院有限公司 | Power grid operation behavior identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113095132A (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113095132B (en) | Neural network based gas field identification method, system, terminal and storage medium | |
| CN112004067A (en) | Video monitoring method, device and storage medium | |
| CN108537243B (en) | Violation warning method and device | |
| CN112181786B (en) | Configuration method, device and equipment for inspection application | |
| CN112464030B (en) | Suspicious person determination method and suspicious person determination device | |
| CN108629310B (en) | Engineering management supervision method and device | |
| CN113888024A (en) | Operation monitoring method and device, electronic equipment and storage medium | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium | |
| CN115410112A (en) | Elevator abnormal stay recognition method and device and storage medium | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN114500574A (en) | Monitoring method, device and medium for improving grain depot safety based on block chain | |
| CN112911219A (en) | Method, system and equipment for identifying routing inspection route of power equipment | |
| CN116596510A (en) | Operation and maintenance fault management method, system, terminal equipment and storage medium | |
| CN112153341B (en) | Task supervision method, device and system, electronic equipment and storage medium | |
| CN114299476A (en) | Multi-channel monitoring video processing method, system, terminal and storage medium | |
| WO2022198507A1 (en) | Obstacle detection method, apparatus, and device, and computer storage medium | |
| CN113420631A (en) | Safety alarm method and device based on image recognition | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
| CN115394025A (en) | Monitoring method, monitoring device, electronic equipment and storage medium | |
| CN110909798A (en) | Multi-algorithm intelligent studying and judging method, system and server | |
| CN112883879B (en) | False position identification method, system, electronic equipment and medium | |
| CN116311080B (en) | Monitoring image detection method and device | |
| CN115376275B (en) | Construction safety warning method and system based on image processing | |
| CN114943884B (en) | Equipment protection method based on deep learning | |
| CN114708557B (en) | Electric power construction monitoring method and system based on air-ground communication |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |