CN116546023A - Method and system for identifying violent behaviors of oil and gas operation area - Google Patents
Method and system for identifying violent behaviors of oil and gas operation area Download PDFInfo
- Publication number
- CN116546023A CN116546023A CN202310822127.0A CN202310822127A CN116546023A CN 116546023 A CN116546023 A CN 116546023A CN 202310822127 A CN202310822127 A CN 202310822127A CN 116546023 A CN116546023 A CN 116546023A
- Authority
- CN
- China
- Prior art keywords
- video data
- real
- time video
- time
- training
- 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.)
- Granted
Links
- 206010001488 Aggression Diseases 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 68
- 238000001514 detection method Methods 0.000 claims abstract description 57
- 230000006399 behavior Effects 0.000 claims abstract description 48
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims description 36
- 238000012360 testing method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 230000002123 temporal effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- 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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Social Psychology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for identifying violent behaviors of an oil and gas operation area, wherein the method comprises the following steps: s100: collecting real-time video data of operators in an oil and gas operation area; s200: preprocessing the acquired real-time video data through an edge end to obtain preprocessed real-time video data; s300: transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in an oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server; s400: identifying whether the worker has violent behaviors according to the detection result; s500: and if the violent behavior of the operator is identified, early warning is carried out.
Description
Technical Field
The disclosure belongs to the technical field of image processing, and particularly relates to a method and a system for identifying violent behaviors in an oil and gas operation area.
Background
The violent behavior identification of the oil and gas operation area is generally based on the traditional security cameras, and the operation area is monitored by means of manpower observation, so that the violent behavior is missed to be detected, and real-time alarm is difficult to realize; to solve the problem, although the intelligent video detection system based on the deep learning violence behavior can be adopted, the video is required to be transmitted into the cloud for calculation, so that time delay is caused in transmission, and the real-time performance is poor.
Disclosure of Invention
Aiming at the defects in the prior art, the purpose of the present disclosure is to provide a method for identifying violent behaviors of an oil and gas operation area, which can accurately identify the violent behaviors of the operation area and perform early warning in time.
In order to achieve the above object, the present disclosure provides the following technical solutions:
a violent behavior identification method for an oil and gas operation area comprises the following steps:
s100: collecting real-time video data of operators in an oil and gas operation area;
s200: preprocessing the acquired real-time video data through an edge end to obtain preprocessed real-time video data;
s300: transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in an oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
s400: and identifying whether the violent behavior exists in the operator according to the detection result.
Preferably, in step S200, the preprocessing the collected real-time video data includes the following steps: and performing sparse frame extraction processing on the acquired real-time video data.
Preferably, in step S300, the spatiotemporal double-scale violence detection model includes: convolution feature extraction block, double pool layer, short time extraction block, long time extraction block, trans module, full connection module and Softmax function.
Preferably, in step S300, the spatiotemporal double-scale violence detection model is trained by the following steps:
s301: constructing a data set, preprocessing the data set, and dividing the data set into a training set and a testing set;
s302: setting training parameters, training the model by using the preprocessed training set, wherein a training strategy is set as a linear prediction strategy, and after a certain training time is reached, the model training is completed;
s303: testing the trained model by using the preprocessed test set, and passing the test when the output confidence of the model reaches 0.95 or more; otherwise, resetting the training parameters to train the model.
Preferably, the method further comprises the steps of:
s500: and if the violent behavior of the operator is identified, early warning is carried out.
The present disclosure also provides an oil and gas operation area violence behavior recognition system, comprising:
the acquisition module is used for acquiring real-time video data of operators in the oil and gas operation area;
the preprocessing module is used for preprocessing the acquired real-time video data through the edge end so as to obtain preprocessed real-time video data;
the detection module is used for transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in the oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
and the identification module is used for identifying whether the violent behavior exists in the operator according to the detection result.
Preferably, the detection module includes:
the training module is used for training the space-time double-scale violence behavior detection model through the cloud server so as to obtain a trained space-time double-scale violence behavior detection model.
Preferably, the system further comprises:
and the early warning module is used for carrying out early warning when the violent behavior of the operator is identified.
The present disclosure also provides an oil and gas operation area violence behavior recognition system, comprising:
the monitoring camera is used for collecting real-time video data of operators in the oil and gas operation area;
the edge end is used for preprocessing the collected real-time video data to obtain preprocessed real-time video data; the time-space double-scale violence behavior detection model is used for transmitting the preprocessed real-time video data to the edge end so as to detect behaviors of operators in the oil-gas operation area and identify whether the operators have violence behaviors according to detection results; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
the early warning module is used for early warning when the edge end recognizes that the worker has violent behaviors;
the cloud server is used for training a space-time double-scale violence behavior detection model.
The present disclosure also proposes a computer storage medium comprising:
a memory for storing computer instructions,
a processor for executing the computer instructions to implement a method as claimed in any preceding claim.
Compared with the prior art, the beneficial effects that this disclosure brought are:
1. the method comprises the steps that training set samples sent by all edge ends are collected through a cloud server to construct and train a space-time double-scale violence behavior detection model, the training set samples are sent to the edge ends after training is completed, and then the edge ends can accurately identify violence behaviors in an oil-gas operation area;
2. the system and the method can be deployed on an intelligent gateway at the network edge side, and the collected data is processed nearby without uploading a large amount of data to a remote core management platform. Compared with cloud computing, the edge computing utilizes the existing data and computing capacity on the cloud server, the response time for obtaining the identification result is greatly shortened, and when the identification result is returned, the feature information of the video can be further sent to the cloud server to serve as a new training set to optimize the model and the optimized model is sent to the edge end again, so that self-optimization is achieved by the edge end and the cloud server.
Drawings
FIG. 1 is a flow chart of a method for identifying violent behaviors in an oil and gas operation area according to one embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of a spatiotemporal double-scale violence behavior detection model provided in another embodiment of the present disclosure;
FIG. 3 is a block diagram of a convolution extraction block in a model provided in accordance with another embodiment of the present disclosure;
FIG. 4 is a block diagram of a short extraction block and a long extraction block provided in another embodiment of the present disclosure;
FIG. 5 is a feature diagram of short term extraction block and long term extraction block extraction provided by another embodiment of the present disclosure;
FIG. 6 is a diagram of an edge cloud architecture provided by one embodiment of the present disclosure;
fig. 7 is an edge-side algorithm diagram according to another embodiment of the present disclosure.
Detailed Description
Specific embodiments of the present disclosure will be described in detail below with reference to fig. 1 to 7. While specific embodiments of the disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It should be noted that certain terms are used throughout the description and claims to refer to particular components. Those of skill in the art will understand that a person may refer to the same component by different names. The specification and claims do not identify differences in terms of components, but rather differences in terms of the functionality of the components. As used throughout the specification and claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description hereinafter sets forth the preferred embodiments for carrying out the present disclosure, but is not intended to limit the scope of the disclosure in general, as the description proceeds. The scope of the present disclosure is defined by the appended claims.
For the purposes of promoting an understanding of the embodiments of the disclosure, reference will now be made to the embodiments illustrated in the drawings and specific examples, without the intention of being limiting the embodiments of the disclosure.
In one embodiment, as shown in fig. 1, the disclosure proposes a method for identifying violent behaviors in an oil and gas operation area, including the following steps:
s100: collecting real-time video data of operators in an oil and gas operation area;
s200: preprocessing the acquired real-time video data through an edge end, namely properly cutting the size of the video data to obtain preprocessed real-time video data;
s300: transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in an oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
s400: and identifying whether the violent behavior exists in the operator according to the detection result.
In another embodiment, in step S200, the preprocessing the collected real-time video data includes the following steps: and performing sparse frame extraction processing on the acquired real-time video data.
In this embodiment, the sparse frame extraction process is performed on the collected real-time video data by:
wherein, the liquid crystal display device comprises a liquid crystal display device,for a sparse frame-extraction interval,for the total frame of the video,is the total set after sparse frame extraction.
The frame number of the video subjected to the sparse frame extraction process is adjusted to 32 frames, and the image input resolution is adjusted to 224 x 224.
In another embodiment, in step S300, as shown in fig. 2, the spatiotemporal double-scale violence detection model includes: convolution feature extraction block, double pool layer, short time extraction block, long time extraction block, trans module, full connection module and Softmax function.
In this embodiment, the pre-processed real-time video data is first coarsely extracted by using a 2d+1d convolution extraction block (STM) shown in fig. 3 to obtain key features (e.g. time sequence differences of limbs actions of operators) between the foreground and the background in the video data, where the convolution extraction block is composed of four space-time convolution blocks and two maximum spatial pooling.
Secondly, the key features extracted by the convolution extraction block are fed into a double pool layer comprising a time pool and a cross-channel pool for constructing different modality data having a short frame rate and a long frame rate, respectively. On the acquired different frame rate characteristics, the present embodiment pertinently extracts different temporal spatial scale features for two mode data by a short time extraction block (STB) and a long time extraction block (LTB) (the structure is shown in fig. 4), the STB focuses on extracting spatial features, and the LTB focuses on extracting temporal features, wherein the STB module performs feature extraction on short frame rate data with rich spatial features by using 1X3 spatial convolution of large channels, and the number of large channels is set to 128, 256, 512 and 2048. In contrast to STB, LTB applies more temporal convolution to accommodate long frame rate data with rich temporal features and, to reduce spatial extraction capability to 32, 64, 128 and 256 in the channel dimension, the dual branches respectively focus on different modality data extraction.
Through the extraction of the short-time extraction block and the long-time extraction block, two groups of feature images shown in fig. 5 can be obtained, channel normalization operation is carried out on the two groups of feature images to improve fusion efficiency, a Trans module is designed, the Trans module realizes matching on time dimension of double branches through 3D convolution and carries out transverse connection operation so as to promote feature interaction between STB and LTB, the fused features are 128-dimensional feature vectors, the 128-dimensional feature vectors are input into a full connection module, the full connection module outputs 2-dimensional vectors representing violent behaviors and non-violent behaviors, the vector is activated by utilizing a Softmax function, the confidence coefficient of the vector is obtained, and a confidence coefficient calculation formula is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,represent the firstThe number of vectors is the number of vectors,representing an exponential function.
Further, whether violent behaviors exist can be judged according to the confidence coefficient obtained through calculation in the above formula, and because the training data mainly define violent fight as violent behaviors (specifically including limb conflicts such as punch making or kicking), if the confidence coefficient is larger than a set threshold (the threshold is set to be 95% in the embodiment), the violent behaviors of operators in the oil and gas operation area are judged; otherwise, no violent behavior exists.
In another embodiment, the spatiotemporal double-scale violent behavior detection model is trained by:
s301: constructing a data set, preprocessing the data set, and dividing the data set into a training set and a testing set;
s302: setting an Adam optimizer, setting training parameters as lr=0.0001, beta1=0.9, beta2=0.99 and epsilon=1e-8, training a model by using a preprocessed training set, setting a training strategy as a linear prediction strategy, and finishing model training after a certain training times are reached;
s303: testing the trained model by using the preprocessed test set, and passing the test when the output confidence of the model reaches 0.95 or more; otherwise, the training parameters are reset (for example, the model learning rate is reduced) to train the model.
In another embodiment, the method further comprises the steps of:
s500: and if the violent behavior of the operator is identified, early warning is carried out.
In another embodiment, the present disclosure further provides a system for identifying violent behaviors in an oil and gas operation area, including:
the acquisition module is used for acquiring real-time video data of operators in the oil and gas operation area;
the preprocessing module is used for preprocessing the acquired real-time video data through the edge end so as to obtain preprocessed real-time video data;
the detection module is used for transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in the oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
and the identification module is used for identifying whether the violent behavior exists in the operator according to the detection result.
In another embodiment, the detection module includes:
the training module is used for training the space-time double-scale violence behavior detection model through the cloud server so as to obtain a trained space-time double-scale violence behavior detection model.
In another embodiment, the system further comprises:
and the early warning module is used for carrying out early warning when the violent behavior of the operator is identified.
In another embodiment, as shown in fig. 6, the present disclosure further provides a system for identifying violence in an oil and gas operation area, including:
the monitoring camera is used for collecting real-time video data of operators in the oil and gas operation area;
the edge end is used for preprocessing the collected real-time video data to obtain preprocessed real-time video data; the time-space double-scale violence behavior detection model is used for transmitting the preprocessed real-time video data to the edge end so as to detect behaviors of operators in the oil-gas operation area and identify whether the operators have violence behaviors according to detection results; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
the early warning module is used for early warning when the edge end recognizes that the worker has violent behaviors;
the cloud server is used for training a space-time double-scale violence behavior detection model.
In this embodiment, as shown in fig. 7, the processing of video data based on the above system includes the following steps:
the monitoring camera transmits the acquired video data to edge computing equipment (such as Jetson Xavier NX), the edge computing equipment performs sparse frame extraction on the video data to obtain a sparse set of the video data and serve as input data of a detection model, and the frame extraction flow is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for a sparse frame-extraction interval,for the total frame of the video,is the total set after sparse frame extraction.
After the obtained sparse set passes through a violent behavior recognition detection model built in the edge computing equipment, corresponding confidence coefficient is obtained through double-scale fusion prediction, and whether an alarm needs to be sent out is judged through an edge server.
The edge server uploads the result video summarized by the edge computing equipment and the video sending the alarm information to the cloud server, and the cloud server uses the relevant video to further train the corresponding model, update the parameters of the model and improve the accuracy of the model.
In another embodiment, the present disclosure also provides a computer storage medium comprising:
a memory for storing computer instructions,
a processor for executing the computer instructions to implement a method as claimed in any preceding claim.
Although embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the specific embodiments and application fields described above, wherein the verification object is not limited to a specific sensor arrangement angle or a split leaf disk structure, and the specific embodiments described above are merely illustrative, instructive, and not restrictive. Those skilled in the art, having the benefit of this disclosure, may effect numerous forms of the invention without departing from the scope of the invention as claimed.
Claims (10)
1. A violent behavior identification method for an oil and gas operation area comprises the following steps:
s100: collecting real-time video data of operators in an oil and gas operation area;
s200: preprocessing the acquired real-time video data through an edge end to obtain preprocessed real-time video data;
s300: transmitting the preprocessed real-time video data to a space-time double-scale violent behavior detection model at the edge end to obtain a behavior detection result of operators in an oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
s400: and identifying whether the violent behaviors exist for the operators according to the behavior detection result.
2. The method according to claim 1, wherein in step S200, the preprocessing of the acquired real-time video data comprises the steps of: and performing sparse frame extraction processing on the acquired real-time video data.
3. The method of claim 1, wherein in step S300, the spatiotemporal double-scale violence detection model comprises: convolution feature extraction block, double pool layer, short time extraction block, long time extraction block, trans module, full connection module and Softmax function.
4. The method according to claim 1, wherein in step S300 the spatiotemporal double-scale violent behavior detection model is trained by:
s301: constructing a data set, preprocessing the data set, and dividing the data set into a training set and a testing set;
s302: setting training parameters, training the model by using the preprocessed training set, wherein a training strategy is set as a linear prediction strategy, and after a certain training time is reached, the model training is completed;
s303: testing the trained model by using the preprocessed test set, and passing the test when the output confidence of the model reaches 0.95 or more; otherwise, resetting the training parameters to train the model.
5. The method of claim 1, wherein the method further comprises the steps of:
s500: and if the violent behavior of the operator is identified, early warning is carried out.
6. An oil and gas operation area violence identification system, comprising:
the acquisition module is used for acquiring real-time video data of operators in the oil and gas operation area;
the preprocessing module is used for preprocessing the acquired real-time video data through the edge end so as to obtain preprocessed real-time video data;
the detection module is used for transmitting the preprocessed real-time video data to a space-time double-scale violence behavior detection model at the edge end so as to detect the behaviors of operators in the oil-gas operation area; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
and the identification module is used for identifying whether the violent behavior exists in the operator according to the detection result.
7. The system of claim 6, wherein the detection module comprises:
the training module is used for training the space-time double-scale violence behavior detection model through the cloud server so as to obtain a trained space-time double-scale violence behavior detection model.
8. The system of claim 6, wherein the system further comprises:
and the early warning module is used for carrying out early warning when the violent behavior of the operator is identified.
9. An oil and gas operation area violence identification system, comprising:
the monitoring camera is used for collecting real-time video data of operators in the oil and gas operation area;
the edge end is used for preprocessing the collected real-time video data to obtain preprocessed real-time video data; the time-space double-scale violence behavior detection model is used for transmitting the preprocessed real-time video data to the edge end so as to detect behaviors of operators in the oil-gas operation area and identify whether the operators have violence behaviors according to detection results; the space-time double-scale violence behavior detection model collects real-time video data training set samples preprocessed by all edge ends through a cloud server in advance, and sends the real-time video data training set samples to the edge ends after training is completed by the cloud server;
the early warning module is used for early warning when the edge end recognizes that the worker has violent behaviors;
the cloud server is used for training a space-time double-scale violence behavior detection model.
10. A computer storage medium, comprising:
a memory for storing computer instructions,
a processor for executing the computer instructions to implement the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310822127.0A CN116546023B (en) | 2023-07-06 | 2023-07-06 | Method and system for identifying violent behaviors of oil and gas operation area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310822127.0A CN116546023B (en) | 2023-07-06 | 2023-07-06 | Method and system for identifying violent behaviors of oil and gas operation area |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116546023A true CN116546023A (en) | 2023-08-04 |
CN116546023B CN116546023B (en) | 2023-09-29 |
Family
ID=87447517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310822127.0A Active CN116546023B (en) | 2023-07-06 | 2023-07-06 | Method and system for identifying violent behaviors of oil and gas operation area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116546023B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117173690A (en) * | 2023-10-24 | 2023-12-05 | 四川泓宝润业工程技术有限公司 | Method and device for automatically positioning and reading natural gas meter, and electronic equipment |
CN117237994A (en) * | 2023-11-13 | 2023-12-15 | 四川泓宝润业工程技术有限公司 | Method, device and system for counting personnel and detecting behaviors in oil and gas operation area |
CN117830313A (en) * | 2024-03-05 | 2024-04-05 | 四川泓宝润业工程技术有限公司 | Method, device and system for detecting lower part of oilfield wellhead based on deep learning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190377953A1 (en) * | 2018-06-06 | 2019-12-12 | Seventh Sense Artificial Intelligence Pvt Ltd | Network switching appliance, process and system for performing visual analytics for a streaming video |
CN113469654A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Multi-level safety management and control system of transformer substation based on intelligent algorithm fusion |
CN113642403A (en) * | 2021-07-13 | 2021-11-12 | 重庆科技学院 | Crowd abnormal intelligent safety detection system based on edge calculation |
CN113887272A (en) * | 2021-07-13 | 2022-01-04 | 重庆科技学院 | Violent behavior intelligent safety detection system based on edge calculation |
CN114885119A (en) * | 2022-03-29 | 2022-08-09 | 西北大学 | Intelligent monitoring alarm system and method based on computer vision |
CN115346150A (en) * | 2022-07-19 | 2022-11-15 | 内蒙古工业大学 | Violent behavior detection method and system based on edge calculation |
CN116189286A (en) * | 2022-12-26 | 2023-05-30 | 西安工业大学 | Video image violence behavior detection model and detection method |
-
2023
- 2023-07-06 CN CN202310822127.0A patent/CN116546023B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190377953A1 (en) * | 2018-06-06 | 2019-12-12 | Seventh Sense Artificial Intelligence Pvt Ltd | Network switching appliance, process and system for performing visual analytics for a streaming video |
CN113469654A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Multi-level safety management and control system of transformer substation based on intelligent algorithm fusion |
CN113642403A (en) * | 2021-07-13 | 2021-11-12 | 重庆科技学院 | Crowd abnormal intelligent safety detection system based on edge calculation |
CN113887272A (en) * | 2021-07-13 | 2022-01-04 | 重庆科技学院 | Violent behavior intelligent safety detection system based on edge calculation |
CN114885119A (en) * | 2022-03-29 | 2022-08-09 | 西北大学 | Intelligent monitoring alarm system and method based on computer vision |
CN115346150A (en) * | 2022-07-19 | 2022-11-15 | 内蒙古工业大学 | Violent behavior detection method and system based on edge calculation |
CN116189286A (en) * | 2022-12-26 | 2023-05-30 | 西安工业大学 | Video image violence behavior detection model and detection method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117173690A (en) * | 2023-10-24 | 2023-12-05 | 四川泓宝润业工程技术有限公司 | Method and device for automatically positioning and reading natural gas meter, and electronic equipment |
CN117173690B (en) * | 2023-10-24 | 2024-01-26 | 四川泓宝润业工程技术有限公司 | Method and device for automatically positioning and reading natural gas meter, and electronic equipment |
CN117237994A (en) * | 2023-11-13 | 2023-12-15 | 四川泓宝润业工程技术有限公司 | Method, device and system for counting personnel and detecting behaviors in oil and gas operation area |
CN117237994B (en) * | 2023-11-13 | 2024-02-13 | 四川泓宝润业工程技术有限公司 | Method, device and system for counting personnel and detecting behaviors in oil and gas operation area |
CN117830313A (en) * | 2024-03-05 | 2024-04-05 | 四川泓宝润业工程技术有限公司 | Method, device and system for detecting lower part of oilfield wellhead based on deep learning |
CN117830313B (en) * | 2024-03-05 | 2024-05-28 | 四川泓宝润业工程技术有限公司 | Method, device and system for detecting lower part of oilfield wellhead based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN116546023B (en) | 2023-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116546023B (en) | Method and system for identifying violent behaviors of oil and gas operation area | |
CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
CN113052029A (en) | Abnormal behavior supervision method and device based on action recognition and storage medium | |
CN111860318A (en) | Construction site pedestrian loitering detection method, device, equipment and storage medium | |
CN103810717B (en) | A kind of human body behavioral value method and device | |
CN102915432B (en) | A kind of vehicle-mounted microcomputer image/video data extraction method and device | |
CN111222500A (en) | Label extraction method and device | |
CN107977656A (en) | A kind of pedestrian recognition methods and system again | |
CN111738218B (en) | Human body abnormal behavior recognition system and method | |
CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
CN110675395A (en) | Intelligent on-line monitoring method for power transmission line | |
CN115620212B (en) | Behavior identification method and system based on monitoring video | |
CN106851229B (en) | Security and protection intelligent decision method and system based on image recognition | |
CN105335726A (en) | Face recognition confidence coefficient acquisition method and system | |
US20240135710A1 (en) | Systems and methods for video analysis | |
CN115249331B (en) | Mine ecological safety identification method based on convolutional neural network model | |
CN112349057A (en) | Deep learning-based indoor smoke and fire detection method | |
CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
CN111126411B (en) | Abnormal behavior identification method and device | |
CN115861210A (en) | Transformer substation equipment abnormity detection method and system based on twin network | |
CN116092119A (en) | Human behavior recognition system based on multidimensional feature fusion and working method thereof | |
CN111476102A (en) | Safety protection method, central control equipment and computer storage medium | |
CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
CN112232236B (en) | Pedestrian flow monitoring method, system, computer equipment and storage medium | |
CN117669838A (en) | Optimized control system and method for production of neodymium-iron-boron magnet |
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 |