CN114898181A - Hidden danger violation identification method and device for explosion-related video - Google Patents
Hidden danger violation identification method and device for explosion-related video Download PDFInfo
- Publication number
- CN114898181A CN114898181A CN202210552989.1A CN202210552989A CN114898181A CN 114898181 A CN114898181 A CN 114898181A CN 202210552989 A CN202210552989 A CN 202210552989A CN 114898181 A CN114898181 A CN 114898181A
- Authority
- CN
- China
- Prior art keywords
- video
- explosion
- model
- violation
- identification
- 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a hidden danger violation identification method and a hidden danger violation identification device for an explosion-related video, which relate to the field of explosion construction, and the method comprises the steps of S1 constructing a video authenticity detection model, a video target identification model and an identity identification model; s2, constructing an annotation database and a face information database; s3, training and optimizing a video target recognition model and an identity recognition model; s4, acquiring the explosion-related video; s5, carrying out authenticity analysis on the explosion-related video, and identifying related information of the blasting operation and information of blasting operators; s6, analyzing hidden dangers and violation conditions in the blasting video; the video true and false detection model, the optimized video target identification model and the optimized identity identification model are used for analyzing the explosion-related video, analyzing and judging the true and false of the explosion-related video, the related operation information in the explosion process and the information of operators operating the explosion, judging whether potential safety hazards exist in the process operation or not according to the analysis results, and standardizing the operation of the operators.
Description
Technical Field
The invention relates to the field of blasting construction, in particular to a hidden danger violation identification method and device for an explosion-related video.
Background
In the field of safety supervision of oil exploration technology, how to ensure the working quality, flow normalization and personal safety of blasting workers and constructors in the civil blasting operation process is a technical problem in the field.
Most of prior art take information acquisition terminal equipment for constructor, carry out normative operation and record the operation process completely, submit operation video data for the information acquisition center on the same day, carry out the manual work and judge whether construction flow is qualified, for example: the safety helmet is not worn, the anti-static clothes are not worn, the explosive is subjected to evidence-keeping comparison, and the like, in the judging process, a large number of videos need to be audited by workers every day, and visual fatigue can cause missed inspection and missed report. Human judgment is subjective, and data examination cannot strictly meet the established standard. Meanwhile, the conventional technology wastes a large amount of manpower, material resources and financial resources.
Disclosure of Invention
The invention aims to solve the problems and designs a hidden danger violation identification method and device for an implosion video.
The invention realizes the purpose through the following technical scheme:
the hidden danger violation identification method for the explosion-related video comprises the following steps:
s1, constructing a video authenticity detection model, a video target identification model and an identity identification model, wherein the video target identification model is a YOLOv5 detection model, and the identity identification model is a face identification model;
s2, constructing a label database and a face information database, labeling the training data set to export a label file to form a label database, wherein the face information database stores the relevant information of the certified civil explosion operating personnel;
s3, training and optimizing the video target recognition model by adopting the annotation database, and training and optimizing the identity recognition model by adopting the face information database;
s4, acquiring the explosion-related video to be analyzed;
s5, importing the explosion-related video to be analyzed into a video authenticity detection model, an optimized video target identification model and an optimized identity identification model, and carrying out authenticity analysis on the explosion-related video, identification of relevant information of explosion operation and identification of information of explosion operators;
and S6, carrying out authenticity analysis according to the blasting video, identifying relevant information of blasting operation and identifying information of blasting operators, and analyzing hidden dangers and violation conditions in the blasting video.
A hidden danger identification equipment that breaks rules and regulations for concerning with exploding video, including bottom layer server, bottom layer server includes:
a reservoir; the storage is used for storing a computer program;
a processor; the processor is used for executing the computer program, and when the processor executes the computer program, the steps of the hidden danger violation identification method for the explosion-related video are realized.
The invention has the beneficial effects that: the video explosion-related video is analyzed through the video true and false detection model, the optimized video target identification model and the optimized identity identification model, the true and false performance of the explosion-related video, the related operation information in the explosion process and the operator information of operation explosion are analyzed and judged, whether potential safety hazards exist in the process operation or not is judged through the analysis results, the operation of workers is standardized, efficient operation, accurate judgment and intelligent analysis are realized, the management and control of safety problems are more efficient, and a large amount of manpower, material resources and financial resources are saved.
Drawings
FIG. 1 is a schematic diagram of a video object recognition model in the present invention;
FIG. 2 is a flow chart of the present invention for analyzing the cleanliness of an implosion-related video;
FIG. 3 is a flow chart of the identification of the identity recognition model of the present invention;
FIG. 4 is a flow chart of the detection of the video authenticity detection model in the present invention;
FIG. 5 is an RNN text recognition framework of the present invention;
fig. 6 is a single-layer bidirectional RNN network of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
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 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 invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "inside", "outside", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, or the orientations or positional relationships that the products of the present invention are conventionally placed in use, or the orientations or positional relationships that are conventionally understood by those skilled in the art, and are used for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it is also to be noted that, unless otherwise explicitly stated or limited, the terms "disposed" and "connected" are to be interpreted broadly, and for example, "connected" may be a fixed connection, a detachable connection, or an integral connection; can be mechanically or electrically connected; the connection may be direct or indirect via an intermediate medium, and may be a communication between the two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The following detailed description of embodiments of the invention refers to the accompanying drawings.
The hidden danger violation identification method for the explosion-related video comprises the following steps:
s1, constructing a video authenticity detection model, a video target identification model and an identity identification model, wherein the video target identification model is a YOLOv5 detection model, and the identity identification model is a face identification model.
S2, constructing a label database and a face information database, labeling the training data set to export a label file, and forming a label database, wherein the face information database stores the relevant information of the certified civil explosion operating personnel.
And S3, training and optimizing the video target recognition model by adopting the annotation database, and training and optimizing the identity recognition model by adopting the face information database.
And S4, acquiring the explosion-related video to be analyzed.
S0, analyzing and evaluating the definition of the image in the explosion-related video to be analyzed, and screening and removing the image; as shown in fig. 2, the method specifically includes:
s01, carrying out Fourier transformation on the image of the explosion-related video to be analyzed to convert the image into a frequency domain,
n is a drawingLike the sequence length, F (i, j) represents a matrix of size N × N, where i ═ 0,1,2, ·, N-1, and j · 0,1,2, ·, N-1, and F (k, l) represent the fourier transform of F (i, j)
S02, removing low-frequency signals with the frequency lower than the preset frequency;
s03 transforming the image from the frequency domain to the spatial domain using a fast fourier transform,
S04, calculating an amplitude mean value in the spatial domain, wherein the image with the amplitude mean value larger than a preset threshold is a clear image, otherwise, the image is a fuzzy image, and the fuzzy image is removed.
And S5, importing the explosion-related video to be analyzed into a video authenticity detection model, an optimized video target identification model and an optimized identity identification model, and carrying out authenticity analysis on the explosion-related video, identification of relevant information of explosion operation and identification of explosion operators.
And S6, carrying out authenticity analysis according to the blasting video, identifying relevant information of blasting operation and identifying information of blasting operators, and analyzing hidden dangers and violation conditions in the blasting video.
The video true and false detection model, the optimized video target identification model and the optimized identity identification model are used for analyzing the explosion-related video, analyzing and judging the true and false of the explosion-related video, the related operation information in the explosion process and the operator information for operating the explosion, judging whether potential safety hazards exist in the process operation or not according to the analysis results, standardizing the operation of workers, realizing efficient operation, accurate judgment and intelligent analysis, ensuring that the management and control of safety problems are more efficient, and saving a large amount of manpower, material resources and financial resources;
the method has the advantages that the recording conditions of the field video are complex, so that the quality of the video is poor, the definition of an explosion-related video image is analyzed and evaluated before the explosion-related video is analyzed, a fuzzy video is rapidly screened from a large number of videos, and the rechecking efficiency is improved; the blurring reduces the definition of the image, seriously affects the image quality, and causes difficulty and even failure of image analysis, processing and receiving, so an effective blurring evaluation method must be used to control the use of the blurred image, thereby improving the overall performance of the system.
A hidden danger identification equipment that breaks rules and regulations for concerning with exploding video, including bottom layer server, bottom layer server includes:
a reservoir; the storage is used for storing a computer program;
a processor; the processor is used for executing the computer program, and when the processor executes the computer program, the steps of the hidden danger violation identification method for the explosion-related video are realized.
The hidden danger violation identification device further comprises acquisition equipment, the acquisition equipment is used for acquiring the relevant information of the blasting video and blasting personnel, and the acquisition equipment is in communication connection with the bottom layer server.
The hidden danger violation identification device further comprises a cloud server and a remote terminal, and a signal end of the cloud server is connected with a signal end of the remote terminal and a signal end of the bottom layer server respectively.
The video target recognition model is a YOLOv5 detection model, as shown in FIG. 1, a first-order target detection algorithm-YOLOv 5 is adopted for target detection, the method has a good Pytrch framework, a data set of the method can be conveniently trained, and the Pytroch framework is more easily put into production. Not only is the environment easily configured, but also the model training is very fast, and batch reasoning produces real-time results. The method can directly and effectively reason the input of the port of the network camera for single images, batch processing images, videos and even network cameras. Finally, the detection speed of the YOLOv5s is very high, and the judgment results of a large number of job videos can be obtained in a short time.
YOLOv5 is a single-stage target detection algorithm, and new improvement ideas are added to the algorithm, so that the speed and the precision of the algorithm are greatly improved. The main improvement idea is as follows:
input end: in a model training stage, some improvement ideas are provided, and mainly comprise Mosaic data enhancement, self-adaptive anchor frame calculation and self-adaptive picture scaling;
reference network: some new ideas in other detection algorithms are fused, and the method mainly comprises the following steps: focus structure and CSP structure;
the hack network: some layers are often inserted between a BackBone network (BackBone) and a final Head output layer of the target detection network, and an FPN + PAN structure is added in YOLOv 5;
head output layer: the output layer's anchor box mechanism is the same as YOLOv4, and the main improvements are the Loss function GIOU _ Loss during training and the DIOU _ nms of the prediction box filtering.
The identity recognition model is a face recognition model, the process of face recognition is shown in fig. 3, and the face detection: finding the positions of all human faces in the image (the result is a detection frame) by using a human face detection model (a target detection model or other detection models), and cutting out the image of the human face part;
aligning the human face: correcting the face by using a face alignment model, and performing correction based on key points of the face to align the key points of the standard face;
face coding: coding the face image by using a deep learning model, and extracting the face characteristics;
identity recognition: and comparing the face features with data in a face library to judge the identity of the face.
FaceNet is a general face recognition system: deep Convolutional Neural Network (CNN) learning is employed to map the image to euclidean space. The spatial distance is directly related to the picture similarity: the distance between different images of the same person in space is small, and the distance between the images of different persons in space is large, so that the method can be used for face verification, recognition and clustering.
FaceNet uses a deep neural network to extract features and uses triplet _ loss to measure the distance error between samples during training. The neural network is continuously made to be difficult before training or in online learning, namely the neural network is always searched for the self which is not similar to the sample, and is also searched for the other people which are similar to the self. Through a random gradient descent method, the differences of all samples of the system are continuously shortened, meanwhile, the differences with other people are enlarged as much as possible, and finally an optimal value is achieved.
For the whole FaceNet structure, a very deep network inclusion ResNet-v2 is adopted, and a model structure consisting of 3 inclusion modules with residual connection and 1 inclusion v4 module is used for feature extraction.
The overall framework of the model is basically consistent with other classical deep learning methods. The front feature extraction part is based on CNN, except a deep network inclusion-v 4, and a feature normalization layer is arranged behind the front feature extraction part, so that the two-normal form of features
The image features are mapped to a hypersphere, so that the difference caused by the imaging environment of the sample can be avoided. And finally, using triplet _ loss as loss, adding a Stochastic Gradient Descent (SDG) method for back propagation, connecting the model increment with a residual error, wherein the model increment is also one of the prominent points of the method, and improving the training convergence speed.
The video authenticity detection model is an OCR character recognition model, as shown in figure 4, the video authenticity detection model in the invention is mainly divided into two parts:
judging whether the video is true or false: and identifying whether the watermark time of the lower right corner of the video shooting area is consistent with the working time of the day by using an OCR character recognition technology, so as to prevent the occurrence of spliced video.
And (3) identifying construction at night: the video shot on the day of the operation is utilized, the watermark date on the video is extracted, whether the worker is in construction at night or not is judged, the phenomenon is avoided, and safety control is enhanced.
The video authenticity detection model is a main framework based on the RNN character recognition algorithm, as shown in figure 5,
(1) the size of the window in the Max posing is 1 x 2, so that the proposed features have transverse length, and the recognition of a longer text is facilitated;
(2) the CNN + RNN is difficult to train, so that BatchNorm is added, and the model convergence is facilitated;
the advantages are that:
(1) end-to-end training is possible;
(2) the method does not need to perform character segmentation and horizontal scaling operation, only needs to scale to a fixed length in the vertical direction, and can identify sequences with any length;
(3) dictionary-based models and arbitrary models that are not dictionary-based can be trained;
(4) training speed is fast and the model is small.
The entire CRNN network may be divided into three parts: convolutional Layers, namely a common CNN network, is used for extracting Convolutional feature maps of an input image, namely converting the image into a Convolutional feature matrix;
the circulation network layer is a deep bidirectional LSTM network, character sequence features are continuously extracted on the basis of convolution features, the deep RNN network refers to an RNN network with more than two Layers, and the structure of a single-layer bidirectional RNN network is shown in FIG. 6,
in CRNN a second stack-shaped deep bidirectional structure is used.
Transmission Layers-outputs RNN as softmax, and then outputs characters.
The invention solves the problem of safety management and control in the geophysical prospecting process, such as: blasting personnel can not be on duty, wear safety helmet and antistatic clothes, and can discharge and blast at night. Judging whether potential safety hazards exist in the process operation or not through model detection, and standardizing the operation of workers;
through the integration of a bottom algorithm and a front end, efficient operation, accurate judgment and intelligent analysis are realized, the management and control of safety problems are more efficient, and a large amount of manpower, material resources and financial resources are saved.
The method integrates a target detection technology, an OCR character recognition technology, a face recognition technology, a video fuzzy judgment technology, a distributed information processing technology and the like, can judge the normalization of the operation of the explosion-related video, processes the video through a bottom layer algorithm, generates an analysis result through a front-end functional platform, stores the analysis result in a background, and transmits the analysis result to a supervision department or an acquisition center.
The technical solution of the present invention is not limited to the limitations of the above specific embodiments, and all technical modifications made according to the technical solution of the present invention fall within the protection scope of the present invention.
Claims (7)
1. A hidden danger violation identification method for an implosion video is characterized by comprising the following steps:
s1, constructing a video authenticity detection model, a video target identification model and an identity identification model, wherein the video target identification model is a YOLOv5 detection model, and the identity identification model is a face identification model;
s2, constructing a label database and a face information database, labeling the training data set to export a label file to form a label database, wherein the face information database stores the relevant information of the certified civil explosion operating personnel;
s3, training and optimizing the video target recognition model by adopting the annotation database, and training and optimizing the identity recognition model by adopting the face information database;
s4, acquiring the explosion-related video to be analyzed;
s5, importing the explosion-related video to be analyzed into a video authenticity detection model, an optimized video target identification model and an optimized identity identification model, and carrying out authenticity analysis on the explosion-related video, identification of relevant information of explosion operation and identification of information of explosion operators;
and S6, carrying out authenticity analysis according to the blasting video, identifying relevant information of blasting operation and identifying information of blasting operators, and analyzing hidden dangers and violation conditions in the blasting video.
2. The method for identifying the hidden danger violation for the explosion-related video as recited in claim 1, wherein a step S0 is further included between S4 and S5, and the definition of the image in the explosion-related video to be analyzed is analyzed, evaluated and screened out.
3. The method for identifying a hidden danger violation for an implosion-related video as recited in claim 1, wherein S0 comprises:
s01, carrying out Fourier transformation on the image of the explosion-related video to be analyzed, and converting the image into a frequency domain;
s02, removing low-frequency signals with the frequency lower than the preset frequency;
s03, converting the image from a frequency domain to a space domain by using fast Fourier transform;
and S04, calculating an amplitude mean value in the spatial domain, judging whether the image is a blurred image according to the amplitude mean value, and removing the blurred image.
4. The method for identifying the hidden danger violation for the implosion-related video as recited in claim 1, wherein in S04, the graph with the amplitude mean value larger than the preset threshold is a clear image, otherwise, the graph is a blurred image.
5. A hidden danger identification device violating regulations for concerning with exploding video, its characterized in that includes bottom server, and bottom server includes:
a reservoir; the storage is used for storing a computer program;
a processor; the processor is adapted to execute a computer program, which when executed performs the steps of the method for identification of a hidden violation for an implosion video according to any of claims 1-4.
6. The hidden danger violation identification device for the implosion video as recited in claim 5, further comprising a collection device for collecting the information related to the blasting video and the blasting personnel, wherein the collection device is in communication connection with the underlying server.
7. The hidden danger violation identification device for the implosion-related video according to claim 5, further comprising a cloud server and a remote terminal, wherein a signal end of the cloud server is connected with a signal end of the remote terminal and a signal end of the bottom server respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210552989.1A CN114898181A (en) | 2022-05-19 | 2022-05-19 | Hidden danger violation identification method and device for explosion-related video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210552989.1A CN114898181A (en) | 2022-05-19 | 2022-05-19 | Hidden danger violation identification method and device for explosion-related video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114898181A true CN114898181A (en) | 2022-08-12 |
Family
ID=82724552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210552989.1A Pending CN114898181A (en) | 2022-05-19 | 2022-05-19 | Hidden danger violation identification method and device for explosion-related video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114898181A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797336A (en) * | 2023-02-01 | 2023-03-14 | 尚特杰电力科技有限公司 | Fault detection method and device of photovoltaic module, electronic equipment and storage medium |
-
2022
- 2022-05-19 CN CN202210552989.1A patent/CN114898181A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797336A (en) * | 2023-02-01 | 2023-03-14 | 尚特杰电力科技有限公司 | Fault detection method and device of photovoltaic module, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| EP3899508A1 (en) | Automated inspection system and associated method for assessing the condition of shipping containers | |
| CN111339883A (en) | Method for identifying and detecting abnormal behaviors in transformer substation based on artificial intelligence in complex scene | |
| CN111222478A (en) | Construction site safety protection detection method and system | |
| CN110390308B (en) | Video behavior identification method based on space-time confrontation generation network | |
| CN111582129A (en) | Real-time monitoring and alarming method and device for working state of shield machine driver | |
| CN112396635B (en) | Multi-target detection method based on multiple devices in complex environment | |
| CN111292321A (en) | Method for identifying defect image of insulator of power transmission line | |
| CN111667655A (en) | Infrared image-based high-speed railway safety area intrusion alarm device and method | |
| CN113569981A (en) | Power inspection bird nest detection method based on single-stage target detection network | |
| CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
| CN114898181A (en) | Hidden danger violation identification method and device for explosion-related video | |
| CN111126112B (en) | Candidate region determination method and device | |
| CN109359530B (en) | Intelligent video monitoring method and device | |
| CN110163081A (en) | SSD-based real-time regional intrusion detection method, system and storage medium | |
| CN117496570A (en) | Face recognition method and system based on multi-scale convolution | |
| CN117079026A (en) | Unmanned aerial vehicle power inspection hidden danger identification method based on improved YOLOv3 network | |
| CN116682057A (en) | Substation potential safety hazard detection method based on window self-attention mechanism | |
| CN115601674A (en) | Power transmission project smoke hidden danger identification method and device and storage medium | |
| CN115830701A (en) | Human violation behavior prediction method based on small sample learning | |
| CN115100546A (en) | Mobile-based small target defect identification method and system for power equipment | |
| CN115410035A (en) | Air traffic controller unsafe behavior classification method based on monitoring video | |
| CN114627540A (en) | Face information identification and comparison system for meeting reconnaissance application platform | |
| CN114694090A (en) | Campus abnormal behavior detection method based on improved PBAS algorithm and YOLOv5 | |
| CN114373116A (en) | Method, device, equipment and product for screening operation and maintenance site images |
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 |