CN117474337B - Port hazard source detection method and system based on big data - Google Patents
Port hazard source detection method and system based on big data Download PDFInfo
- Publication number
- CN117474337B CN117474337B CN202311478212.6A CN202311478212A CN117474337B CN 117474337 B CN117474337 B CN 117474337B CN 202311478212 A CN202311478212 A CN 202311478212A CN 117474337 B CN117474337 B CN 117474337B
- Authority
- CN
- China
- Prior art keywords
- port
- data
- related data
- hazard
- video
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 230000003449 preventive effect Effects 0.000 claims abstract description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013480 data collection Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000007547 defect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000002329 infrared spectrum Methods 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009182 swimming Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a port hazard source detection method and system based on big data, belonging to the technical field of hazard source detection, wherein the method specifically comprises the following steps: the method comprises the steps of collecting port-related data, preprocessing the port-related data, detecting targets in the preprocessed port-related data, detecting port dangerous sources according to the preprocessed port-related data and the targets in the preprocessed port-related data, evaluating the dangerous degree of the detected port dangerous sources, formulating corresponding preventive and emergency measures, collecting and analyzing the port data in real time, monitoring in real time, detecting the dangerous sources in real time according to complex port environments, evaluating the dangerous degree of the subsequent dangerous sources, formulating corresponding preventive and emergency measures, improving the detection accuracy, and greatly improving the port safety.
Description
Technical Field
The invention belongs to the technical field of dangerous source detection, and particularly relates to a port dangerous source detection method and system based on big data.
Background
In recent years, the port industry in China develops rapidly, achieves a witnessed achievement, and in the future, the port industry still keeps a rapid growth trend. While port economies are growing, port security issues are becoming increasingly important, and in new situations, port security research is facing both greater development opportunities and more serious challenges. An important basic work for improving port safety production is to strengthen port safety research, provide theoretical and technical support for port safety production, and provide scientific decision basis for port safety supervision and management departments at all levels.
Because of the complexity of the port environment, manual inspection is adopted at present, time and labor are consumed, and no better method is available for detecting the dangerous source of the port.
For example, china patent with the publication number CN111028483B discloses an intelligent hazard source warning method and a related device. Be applied to intelligent dangerous source warning device, intelligent dangerous source warning device locates in the target area, intelligent dangerous source warning device and local server or cloud ware communication connection, include: detecting whether a dangerous source exists in a target area in real time; if the dangerous source exists in the target area, acquiring the attribute of the dangerous source; a dangerous source identification instruction is sent to a local server or a cloud server, the dangerous source identification instruction carries the attribute of a dangerous source, and the dangerous source identification instruction is used for indicating whether the local server or the cloud server identifies that the dangerous source needs to be warned; when a warning confirmation instruction from a local server or a cloud server is received, the intelligent dangerous source warning device is controlled to move to a preset position of a target area for warning. According to the technical scheme, the dangerous source of the indoor environment can be detected in time and warning can be made, and safety of indoor personnel is guaranteed.
The Chinese patent with the application publication number of CN108957573A discloses a dangerous source detection device and a dangerous source detection method. The dangerous source detection device comprises a reflection focusing device, an infrared sensor and a processor, wherein the reflection focusing device is used for reflecting and focusing light rays in a preset range to a sensing element of the infrared sensor; the light rays comprise infrared light rays; the infrared sensor is used for sensing the light received by the sensor element so as to acquire infrared spectrum information of a preset wave band; the processor is connected with the infrared sensor and is used for collecting the infrared spectrum information of the preset wave band, processing the infrared spectrum information of the preset wave band and judging whether a dangerous source exists in the preset range according to the processed infrared spectrum information of the preset wave band. The invention can remotely and widely detect the dangerous source in the protection area or space and acquire the coordinate position of the dangerous source, thereby realizing remote, wide-range, extremely early, high-sensitivity and reliable dangerous source detection alarm.
The above patents all suffer from the following drawbacks: the application scene range is smaller, and the method is not suitable for complex port environments.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a port hazard source detection method and system based on big data, which are used for collecting port related data, preprocessing the port related data, detecting targets in the preprocessed port related data, detecting port hazard sources according to the preprocessed port related data and targets in the preprocessed port related data, evaluating the hazard degree of the detected port hazard sources, formulating corresponding preventive and emergency measures, acquiring and analyzing the port data in real time, monitoring in real time, detecting the hazard sources in real time according to complex port environment, evaluating the hazard degree of subsequent hazard sources, formulating corresponding preventive and emergency measures, improving the detection accuracy and greatly improving the port safety.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the port hazard source detection method based on big data comprises the following specific steps:
Step S1: collecting port-related data and preprocessing the port-related data;
step S2: detecting targets in the preprocessed port-related data;
Step S3: detecting a port hazard source according to the preprocessed port related data and the targets in the preprocessed port related data;
step S4: carrying out risk degree assessment on the detected harbour risk sources, and formulating corresponding preventive and emergency measures;
step S5: and carrying out real-time acquisition and analysis and real-time monitoring on the port data.
Specifically, the port-related data in step S1 includes: port office video image data, port traffic video image data, port dock video image data, and port warehouse video image data.
Specifically, the preprocessing in step S1 includes: denoising and graying video images, and removing image defects caused by working temperature, climate environment change, light change, external environment change and interference factors of a camera photosensitive element, wherein the image defects comprise image blurring and gray dynamic range deviation.
Specifically, the specific method in step S2 is as follows:
step S201: setting a frame of image of video in the preprocessed port-related data as F (x, y), setting a window in the image F (x, y) as W (x, y), setting the central coordinate of the window W (x, y) as (x, y), and calculating gray values in the window, wherein the calculation formula is as follows:
Wherein c (Deltax, deltay) represents the gray value within the window W (x, y), deltax, deltay represents the displacement of the window W (x, y), A transpose of the displacement matrix representing the window W (x, y), M (x, y) representing the Harris matrix;
step S202: feature points in the window W (x, y) are selected, and constraint conditions are selected as follows:
TZ＝min(λ1,λ2)，
wherein TZ represents a constraint condition for selecting characteristic points of the window W (x, y), and lambda 1、λ2 represents characteristic values of the matrix c (deltax, deltay);
step S203: setting a characteristic value threshold value as R, and when TZ is larger than R, setting TZ as a characteristic point of a window W (x, y);
Step S204: repeating steps S201-S203 until all the characteristic points are selected, wherein the set of all the characteristic points is the target in the preprocessed port-related data.
Specifically, the specific method in step S3 is as follows:
step S301: the method comprises the steps of inputting a frame of image of a target in the data of the identified port into a trained convolutional neural network, wherein the frame of image is a previous frame of image F (x, y) and a next frame of image F (x, y);
Step S302: repeating the step S1, inputting the ith area video of the port related data into the trained convolutional neural network, wherein the final input formula is as follows:
Wherein S i represents the final input of the convolutional neural network, Z im represents the m-th frame image of the i-th region video, Z i(m+1) represents the m+1-th frame image of the i-th region video, Z i(m-1) represents the m-1-th frame image of the i-th region video, C i represents the convolution, and n represents the number of frames contained in the i-th region video;
Step S303: outputting the probability of containing a dangerous source at the moment t in the ith regional video of the port related data, wherein the specific formula is as follows:
Git＝ηtΔJ(Sit,Mit)，
Wherein, G it represents the probability that the t moment in the i-th region video of the port-related data contains a dangerous source, η t represents the learning rate of the convolutional neural network at the t moment, Δj represents the cost function of the convolutional neural network, S it represents the input image at the t moment in the i-th region video of the port-related data, and M it represents the target set at the t moment in the i-th region video of the port-related data;
Step S304: and (3) repeating the steps S301-S303, and calculating the probability that all dangerous sources are contained in the port related data.
Specifically, the convolutional neural network is ResNet + DenseNet network.
Port hazard source detecting system based on big data includes: the system comprises a port data collection module, a port data target detection module, a port hazard source hazard degree assessment module, a real-time monitoring module,
The port data collection module comprises a port data collection unit and a port data preprocessing unit, wherein the port data collection unit is used for collecting and collecting port-related data, and the port data preprocessing unit is used for preprocessing the port-related data;
The port data target detection module is used for detecting targets in the preprocessed port related data;
The port dangerous source detection module is used for detecting the port dangerous source according to the preprocessed port related data and the targets in the preprocessed port related data;
The port hazard source hazard degree evaluation module is used for evaluating the hazard degree of the detected port hazard source and making corresponding preventive and emergency measures;
the real-time monitoring module is used for collecting and analyzing the port data in real time and monitoring the port data in real time.
An electronic device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of a big data based harbour hazard detection method when executing the computer program.
A computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a big data based harbour risk source detection method.
Compared with the prior art, the invention has the beneficial effects that:
1. the port hazard source detection system based on big data is provided by the invention, and the system is optimized and improved in architecture, operation steps and flow, and has the advantages of simple flow, low investment and operation cost and low production and working costs.
2. The invention provides a port hazard source detection method based on big data, which is used for collecting port related data, preprocessing the port related data, detecting targets in the preprocessed port related data, detecting port hazard sources according to the preprocessed port related data and targets in the preprocessed port related data, evaluating the hazard degree of the detected port hazard sources, formulating corresponding preventive and emergency measures, collecting and analyzing the port data in real time, monitoring the port data in real time, detecting the hazard sources in real time according to complex port environments, evaluating the hazard degree of subsequent hazard sources and formulating corresponding preventive and emergency measures, improving the detection accuracy and greatly improving the port safety.
Drawings
FIG. 1 is a flow chart of a port hazard source detection method based on big data;
FIG. 2 is a diagram of a port hazard source detection system architecture based on big data according to the present invention;
fig. 3 is an electronic equipment diagram of the port hazard source detection method based on big data.
Detailed Description
In order that the technical means, the creation characteristics, the achievement of the objects and the effects of the present invention may be easily understood, it should be noted that in the description of the present invention, the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements to be referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "a", "an", "the" and "the" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The invention is further described below in conjunction with the detailed description.
Example 1
Referring to fig. 1, an embodiment of the present invention is provided: the port hazard source detection method based on big data comprises the following specific steps:
Step S1: collecting port-related data and preprocessing the port-related data;
step S2: detecting targets in the preprocessed port-related data;
Step S3: detecting a port hazard source according to the preprocessed port related data and the targets in the preprocessed port related data;
step S4: carrying out risk degree assessment on the detected harbour risk sources, and formulating corresponding preventive and emergency measures;
The harbour hazard source carries out the dangerous degree assessment and includes: an) office activity: 1. computer radiation, risk levels 3 and 2, leaving doors and windows forget to lock, risk levels 1 and 3, ageing of circuits, risk levels 1 and 4, poor contact of electrical equipment, risk levels 1 and 5, improper use of office supplies, risk levels 2 and 6, illegal use of heating equipment, risk levels 2 and 7, lack of ground protection and earth leakage protection of a used power supply, and risk level 2; two) traffic activity: 1. overspeed driving, risk levels 1 and 2, drunk driving, risk levels 1 and 3, fatigue driving, risk levels 1 and 4, driving with diseases and getting on the road, risk levels 2 and 5, driving without safety belts, risk levels 2 and 6, driving with slippers, risk levels 2 and 7, vehicle faults without warning, risk levels 2 and 8, overload of the vehicle, risk levels 2 and 9, illegal parking and overtaking, risk levels 3 and 10, no fire extinguishing device or failure of the vehicle, risk levels 3 and 11, oiling in the running process of the vehicle, and risk level 1; thirdly), wharf warehouse operation: 1. wearing safety shoes and caps according to the regulations, wherein the risk levels 2 and 2 are not suitable for gangways, the risk levels 2 and 3 are suitable for wharfs and yards, the risk levels 2 and 4 are suitable for loading and unloading objects in thunder days, the risk levels 2 and 5 are suitable for swimming and fishing in wharf areas, the risk levels 3 and 6 are suitable for swimming and fishing in water and oil on the ground, and the risk level 2 is suitable for wharfs; fourth), cargo temporary storage: 1. the forklift and the wagon balance are overloaded, the risk levels 3 and 2 and the cargoes fall from high positions, the risk levels 3 and the stacking gravity center of the cargoes are unstable, the risk levels 3 and 4 and the stacking quantity of the cargoes are excessive, the risk levels 2 and 5 and the climbing pile exceed the bearing capacity of a warehouse, the risk levels 2 and 6 and the safety channel are blocked, and the risk level 3; fifth) others, and so forth.
The precautions and emergency measures taken include: 1) Reinforcing safety production education and management; 2) Effective measures are taken to stabilize staff teams; 3) The method takes the people as the basis, and improves the working environment; 4) Experience is continuously summarized, and safety management work is perfected.
Step S5: and carrying out real-time acquisition and analysis and real-time monitoring on the port data.
The port-related data in step S1 includes: port office video image data, port traffic video image data, port dock video image data, and port warehouse video image data.
The dangerous source sources of the port include: 1) A static hazard source, which refers to energy or substances present in the production system that may be accidentally released or leaked; 2) Situations where energy substance restraint measures may fail due to personnel errors, equipment obstructions, or environmental factors, etc.; 3) Unsafe factors 4) other factors such as production system distortion, breakage and disorder, operation disorder and the like caused by management defects, organization errors, management decision errors, system disturbance and the like.
The preprocessing in step S1 includes: denoising and graying video images, and removing image defects caused by working temperature, climate environment change, light change, external environment change and interference factors of a camera photosensitive element, wherein the image defects comprise image blurring and gray dynamic range deviation.
The specific method of the step S2 is as follows:
step S201: setting a frame of image of video in the preprocessed port-related data as F (x, y), setting a window in the image F (x, y) as W (x, y), setting the central coordinate of the window W (x, y) as (x, y), and calculating gray values in the window, wherein the calculation formula is as follows:
Wherein c (Deltax, deltay) represents the gray value within the window W (x, y), deltax, deltay represents the displacement of the window W (x, y), A transpose of the displacement matrix representing the window W (x, y), M (x, y) representing the Harris matrix;
step S202: feature points in the window W (x, y) are selected, and constraint conditions are selected as follows:
TZ＝min(λ1,λ2)，
wherein TZ represents a constraint condition for selecting characteristic points of the window W (x, y), and lambda 1、λ2 represents characteristic values of the matrix c (deltax, deltay);
step S203: setting a characteristic value threshold value as R, and when TZ is larger than R, setting TZ as a characteristic point of a window W (x, y);
Step S204: repeating steps S201-S203 until all the characteristic points are selected, wherein the set of all the characteristic points is the target in the preprocessed port-related data.
The specific method of the step S3 is as follows:
step S301: the method comprises the steps of inputting a frame of image of a target in the data of the identified port into a trained convolutional neural network, wherein the frame of image is a previous frame of image F (x, y) and a next frame of image F (x, y);
Step S302: repeating the step S1, inputting the ith area video of the port related data into the trained convolutional neural network, wherein the final input formula is as follows:
Wherein S i represents the final input of the convolutional neural network, Z im represents the m-th frame image of the i-th region video, Z i(m+1) represents the m+1-th frame image of the i-th region video, Z i(m-1) represents the m-1-th frame image of the i-th region video, C i represents the convolution, and n represents the number of frames contained in the i-th region video;
Step S303: outputting the probability of containing a dangerous source at the moment t in the ith regional video of the port related data, wherein the specific formula is as follows:
Git＝ηtΔJ(Sit,Mit)，
Wherein, G it represents the probability that the t moment in the i-th region video of the port-related data contains a dangerous source, η t represents the learning rate of the convolutional neural network at the t moment, Δj represents the cost function of the convolutional neural network, S it represents the input image at the t moment in the i-th region video of the port-related data, and M it represents the target set at the t moment in the i-th region video of the port-related data;
Step S304: and (3) repeating the steps S301-S303, and calculating the probability that all dangerous sources are contained in the port related data.
The convolutional neural network is ResNet + DenseNet network.
Example 2
Referring to fig. 2, the port hazard source detection system based on big data includes: the system comprises a port data collection module, a port data target detection module, a port hazard source hazard degree assessment module, a real-time monitoring module,
The port data collection module comprises a port data collection unit and a port data preprocessing unit, wherein the port data collection unit is used for collecting and collecting port-related data, and the port data preprocessing unit is used for preprocessing the port-related data;
The port data target detection module is used for detecting targets in the preprocessed port related data;
The port dangerous source detection module is used for detecting the port dangerous source according to the preprocessed port related data and the targets in the preprocessed port related data;
The port hazard source hazard degree evaluation module is used for evaluating the hazard degree of the detected port hazard source and making corresponding preventive and emergency measures;
the real-time monitoring module is used for collecting and analyzing the port data in real time and monitoring the port data in real time.
Example 3
Referring to fig. 3, an electronic device includes a memory and a processor, where the memory stores a computer program, and the processor implements steps of a port hazard source detection method based on big data when executing the computer program.
A computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a big data based harbour risk source detection method.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The port hazard source detection method based on big data is characterized by comprising the following specific steps:
Step S1: collecting port-related data and preprocessing the port-related data;
step S2: detecting targets in the preprocessed port-related data;
Step S3: detecting a port hazard source according to the preprocessed port related data and the targets in the preprocessed port related data;
step S4: carrying out risk degree assessment on the detected harbour risk sources, and formulating corresponding preventive and emergency measures;
step S5: carrying out real-time acquisition and analysis on port data and real-time monitoring;
the specific method of the step S3 is as follows:
Step S301: inputting a frame of images F (x, y) and a frame of images F (x, y) of a previous frame and a next frame of images F (x, y) of targets in the data related to the port into a trained convolutional neural network;
Step S302: repeating the step S1, inputting the ith area video of the port related data into the trained convolutional neural network, wherein the final input formula is as follows:
Wherein S i represents the final input of the convolutional neural network, Z im represents the m-th frame image of the i-th region video, Z i(m+1) represents the m+1-th frame image of the i-th region video, Z i(m-1) represents the m-1-th frame image of the i-th region video, C i represents the convolution, and n represents the number of frames contained in the i-th region video;
Step S303: outputting the probability of containing a dangerous source at the moment t in the ith regional video of the port related data, wherein the specific formula is as follows:
Git＝ηtΔJ(Sit,Mit)，
Wherein, G it represents the probability that the t moment in the i-th region video of the port-related data contains a dangerous source, η t represents the learning rate of the convolutional neural network at the t moment, Δj represents the cost function of the convolutional neural network, S it represents the input image at the t moment in the i-th region video of the port-related data, and M it represents the target set at the t moment in the i-th region video of the port-related data;
Step S304: and (3) repeating the steps S301-S303, and calculating the probability that all dangerous sources are contained in the port related data.
2. The big data based port hazard detection method according to claim 1, wherein the port-related data in step S1 comprises: port office video image data, port traffic video image data, port dock video image data, and port warehouse video image data.
3. The harbour risk source detection method based on big data as set forth in claim 2, wherein the preprocessing in step S1 includes: denoising and graying video images, and removing image defects caused by working temperature, climate environment change, light change, external environment change and interference factors of a camera photosensitive element, wherein the image defects comprise image blurring and gray dynamic range deviation.
4. The port hazard source detection method based on big data as claimed in claim 3, wherein the specific method of step S2 is as follows:
step S201: setting a frame of image of video in the preprocessed port-related data as F (x, y), setting a window in the image F (x, y) as W (x, y), setting the central coordinate of the window W (x, y) as (x, y), and calculating gray values in the window, wherein the calculation formula is as follows:
Wherein c (Deltax, deltay) represents the gray value within the window W (x, y), deltax, deltay represents the displacement of the window W (x, y), A transpose of the displacement matrix representing the window W (x, y), M (x, y) representing the Harris matrix;
step S202: feature points in the window W (x, y) are selected, and constraint conditions are selected as follows:
TZ＝min(λ1,λ2)，
wherein TZ represents a constraint condition for selecting characteristic points of the window W (x, y), and lambda 1、λ2 represents characteristic values of the matrix c (deltax, deltay);
step S203: setting a characteristic value threshold value as R, and when TZ is larger than R, setting TZ as a characteristic point of a window W (x, y);
Step S204: repeating steps S201-S203 until all the characteristic points are selected, wherein the set of all the characteristic points is the target in the preprocessed port-related data.
5. The harbour hazard source detection method based on big data as set forth in claim 1, wherein said convolutional neural network is ResNet + DenseNet network.
6. Big data based port hazard source detection system, which is realized based on the big data based port hazard source detection method according to any one of claims 1-5, and is characterized by comprising: the system comprises a port data collection module, a port data target detection module, a port hazard source hazard degree assessment module, a real-time monitoring module,
The port data collection module comprises a port data collection unit and a port data preprocessing unit, wherein the port data collection unit is used for collecting and collecting port-related data, and the port data preprocessing unit is used for preprocessing the port-related data;
The port data target detection module is used for detecting targets in the preprocessed port related data;
The port dangerous source detection module is used for detecting the port dangerous source according to the preprocessed port related data and the targets in the preprocessed port related data;
The port hazard source hazard degree evaluation module is used for evaluating the hazard degree of the detected port hazard source and making corresponding preventive and emergency measures;
the real-time monitoring module is used for collecting and analyzing the port data in real time and monitoring the port data in real time.
7. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the big data based harbour risk source detection method of any of claims 1-5.
8. A computer readable storage medium having stored thereon computer instructions which when executed perform the steps of the big data based port hazard detection method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311478212.6A CN117474337B (en) | 2023-11-08 | 2023-11-08 | Port hazard source detection method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311478212.6A CN117474337B (en) | 2023-11-08 | 2023-11-08 | Port hazard source detection method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474337A CN117474337A (en) | 2024-01-30 |
| CN117474337B true CN117474337B (en) | 2024-06-18 |
Family
ID=89636069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311478212.6A Active CN117474337B (en) | 2023-11-08 | 2023-11-08 | Port hazard source detection method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474337B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113378648A (en) * | 2021-05-19 | 2021-09-10 | 上海可深信息科技有限公司 | Artificial intelligence port and wharf monitoring method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9811989B2 (en) * | 2014-09-30 | 2017-11-07 | The Boeing Company | Event detection system |
| CN108090599A (en) * | 2016-11-21 | 2018-05-29 | 上海海勃物流软件有限公司 | Container terminal operation cost control and customer value analysis method |
| CN107896253A (en) * | 2017-11-24 | 2018-04-10 | 上海璞玫信息科技有限公司 | A kind of dangerous material port area storing and transporting security supervisory systems |
| CN111754075A (en) * | 2020-05-25 | 2020-10-09 | 山东浪潮质量链科技有限公司 | Block chain-based multi-berth port ship scheduling method, equipment and medium |
| CN113065804B (en) * | 2021-04-27 | 2023-03-24 | 山东交通学院 | Hazardous chemical substance road transportation risk assessment method and system |
| CN114997773A (en) * | 2022-05-09 | 2022-09-02 | 江苏智赢信息科技有限公司 | Harbor dangerous cargo safety dynamic refined supervision system |
-
2023
- 2023-11-08 CN CN202311478212.6A patent/CN117474337B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113378648A (en) * | 2021-05-19 | 2021-09-10 | 上海可深信息科技有限公司 | Artificial intelligence port and wharf monitoring method |
Non-Patent Citations (2)
| Title |
|---|
| 吴心筱 等著.一种视频中人的动作分析与识别.北京理工大学出版社,2019,(第1版),第28-29页. * |
| 基于改进的Harris 角点的机载红外图像电子稳像;王施鳗 等;《红外技术》;20200630;第42卷(第6期);第573-579页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474337A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102206662B1 (en) | Vision camera system to manage an entrance and exit management of vehicles and to recognize objects of camera video data in a port container terminal and method thereof | |
| CN111144263B (en) | Construction worker high-falling accident early warning method and device | |
| KR102206658B1 (en) | Vision camera system to be communicated with Terminal Operating System through middleware in a port container terminal and method thereof | |
| CN111241959B (en) | Method for detecting personnel not wearing safety helmet through construction site video stream | |
| CN114612866B (en) | Intelligent identification method, device and equipment for safety in building site | |
| CN111401685B (en) | Limited space operation safety risk monitoring method | |
| CN111163290B (en) | Method for detecting and tracking night navigation ship | |
| CN116704411A (en) | Security control method, system and storage medium based on Internet of things | |
| CN118097916A (en) | Video monitoring intelligent analysis early warning system | |
| CN109492548B (en) | Method for obtaining region mask picture based on video analysis | |
| CN110703760A (en) | Newly-increased suspicious object detection method for security inspection robot | |
| CN117789403A (en) | Real-time detection method and system for personnel invasion in dangerous area of driving operation | |
| CN117474337B (en) | Port hazard source detection method and system based on big data | |
| CN115841730A (en) | Video monitoring system and abnormal event detection method | |
| CN114155470A (en) | River channel area intrusion detection method, system and storage medium | |
| CN110120142B (en) | Fire smoke video intelligent monitoring early warning system and early warning method | |
| CN118505165A (en) | Engineering project management system and method based on cloud computing | |
| CN117944837A (en) | Unmanned ship oil spill monitoring system and method | |
| CN115063427B (en) | Pollutant discharge monitoring image processing method for novel ship | |
| CN116228097A (en) | Dangerous goods storage emergency management system | |
| CN117292111A (en) | Offshore target detection and positioning system and method combining Beidou communication | |
| CN118654734B (en) | Building construction safety monitoring method | |
| JP2005353016A (en) | Evaluation and method for action pattern identification of moving image | |
| CN114399883A (en) | Blasting equipment transportation monitoring and early warning system and method | |
| CN117975642B (en) | Intelligent management system for fire-fighting facilities |
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 |