CN109325520A - A kind of inspection method of Oil spills, apparatus and system - Google Patents
A kind of inspection method of Oil spills, apparatus and system Download PDFInfo
- Publication number
- CN109325520A CN109325520A CN201810970710.5A CN201810970710A CN109325520A CN 109325520 A CN109325520 A CN 109325520A CN 201810970710 A CN201810970710 A CN 201810970710A CN 109325520 A CN109325520 A CN 109325520A
- Authority
- CN
- China
- Prior art keywords
- image
- oil spills
- probability
- object image
- data
- 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
Classifications
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
This application provides a kind of inspection methods of Oil spills, device and system, wherein this method comprises: collected first object image is input to Oil spills detection model trained in advance in real time by unmanned plane, determines the first probability that Oil spills occurs；If first probability is more than preset threshold, anti-interference process is carried out to the first object image, to obtain the second target image；Second target image is inputted into the Oil spills detection model, determines the second probability that Oil spills occurs；After determining that second probability is more than the preset threshold, determines and Oil spills occurs.The embodiment of the present application precisely assesses Oil spills probability by unmanned plane automatic detecting and training Oil spills detection model, and automatic detection Oil spills situation can effectively reduce the labor intensity and security risk of patrol officer in traditional artificial routine inspection mode.
Description
Technical field
This application involves technical field of automatic control, more particularly, to a kind of inspection method of Oil spills, device and
System.
Background technique
With flourishing for petroleum industry, at 2016 beginning of the year of cut-off, the oil-gas pipeline total kilometrage in China is nearly 150,000 public
In, the oil storage tank quantity for oil movement and storage surpasses 900,000, these oil movement and storage pressure vessel facilities are national economy and resident
Daily life important energy safeguard is provided.Because petroleum itself is highly corrosive, although currently used for oil movement and storage
Pressure vessel used many technologies and carry out correlative protections, but not in time or external force is destroyed due to maintenance
Reason (steals oil, breakage in installation etc.), inevitably brings Oil spills risk and security risk.
The security risk of oil movement and storage pressure vessel facility is excluded presently mainly by way of inspection.The side of inspection
Formula is generally by manual inspection, and the artificial safe condition for judging oil movement and storage pressure vessel, efficiency are lower.
Summary of the invention
In view of this, the inspection method for being designed to provide a kind of Oil spills, the device and system of the application, to stone
Oily leakage probability is precisely assessed, automatic detection Oil spills situation, with effectively reduce patrol officer labor intensity and
Security risk.
In a first aspect, the embodiment of the present application provides a kind of inspection method of Oil spills, wherein include:
By unmanned plane, collected first object image is input to Oil spills detection model trained in advance in real time, determines
The first probability of Oil spills occurs；
If first probability is more than preset threshold, anti-interference process is carried out to the first object image, to obtain the
Two target images；
Second target image is inputted into the Oil spills detection model, determines that Oil spills occurs second is general
Rate；
After determining that second probability is more than the preset threshold, determines and Oil spills occurs.
With reference to first aspect, the embodiment of the present application provides the first possible embodiment of first aspect, wherein institute
If stating first probability more than preset threshold, anti-interference process is carried out to the first object image, to obtain the second target
Image, comprising:
According to the grey scale pixel value of the first object image, first object image is divided into the first foreground image section
With the first background image portion；
According to the maximum class variance between the first foreground image section and the first background image portion, segmentation prospect is determined
With the segmentation threshold of background；
Based on the determining segmentation threshold, image dividing processing is carried out to the first object image, obtains described the
Two target images.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide second of first aspect
Possible embodiment, wherein the Oil spills detection model is obtained according to following steps training:
Using depth convolutional neural networks model as basic training pattern；
Oil spills image pattern and petroleum are not leaked into image pattern as the training set of the grounding model, incited somebody to action
Known Oil spills result detects mould as a result, training obtains the Oil spills as the output of the grounding model
Type.
With reference to first aspect, the embodiment of the present application provides the third possible embodiment of first aspect, wherein really
Surely after generation Oil spills, further includes:
According to the location information of the corresponding target area of the first object image, the true geographic region of Oil spills is determined
Domain.
With reference to first aspect, the embodiment of the present application provides the 4th kind of possible embodiment of first aspect, wherein really
Surely after generation Oil spills, further includes:
Obtain the acquisition parameters information of the first object image of unmanned plane shooting；The acquisition parameters information includes nothing
Man-machine flying height, camera pixel number, camera horizon field angle and video camera vertical field of view angle；
According to the Pixel Information of the acquisition parameters information and second target image, Oil spills area is calculated.
Second aspect, the embodiment of the present application also provide a kind of check device of Oil spills, wherein include: the first data
Obtain module, the first data analysis module, the second data analysis module, data comparison module and the first data processing module；
The data acquisition module, for obtaining first object image in real time；
First data analysis module is examined for the first object image to be input to Oil spills trained in advance
Model is surveyed, to determine the first probability that Oil spills occurs；
The data comparison module, the size for first probability and preset threshold；
First data processing module, if being more than preset threshold for first probability, to the first object figure
As carrying out anti-interference process, to obtain the second target image；
Second data analysis module, for second target image to be inputted the Oil spills detection model,
Determine the second probability that Oil spills occurs.
In conjunction with second aspect, the embodiment of the present application provides the first possible embodiment of second aspect, wherein institute
Stating data processing module includes image segmentation unit, image determination unit and image generation unit；
Described image cutting unit, for the grey scale pixel value according to the first object image, by first object figure
As being divided into the first foreground image section and the first background image portion；
Described image determination unit, for according to the maximum between the first foreground image section and the first background image portion
Class variance, to determine the segmentation threshold of segmentation foreground and background；
Described image generation unit, for carrying out figure to the first object image based on the determining segmentation threshold
As dividing processing, to obtain second target image.
In conjunction with second aspect, the embodiment of the present application provides second of possible embodiment of second aspect, wherein also
It include: image determining module；
Described image determining module, for the location information according to the corresponding target area of the first object image, really
Determine the true geographic area of Oil spills.
In conjunction with second aspect, the embodiment of the present application provides the third possible embodiment of second aspect, wherein also
It include: the second data acquisition module and the second data processing module；
Second data acquisition module, the acquisition parameters letter of the first object image for obtaining unmanned plane shooting
Breath；
Second data processing module, for the pixel according to the acquisition parameters information and second target image
Information, to calculate Oil spills area.
The third aspect, the embodiment of the present application also provide a kind of inspection system of Oil spills, comprising: data processing service
Device, drone body, ground communications base station and enterprise intelligent control centre；
The data processing server, to execute method as claimed in claim 1 to 5, and by implementing result
It is transferred to the enterprise intelligent control centre；
The enterprise intelligent control centre, for the implementing result of the transmission of processing server based on the data, to described
Ground communications base station sends drone body operational order；
The ground communications base station, the drone body operation sent for responding the enterprise intelligent control centre
Instruction.
A kind of inspection method of Oil spills provided by the embodiments of the present application, apparatus and system, using unmanned plane is real-time
Collected first object image is input to Oil spills detection model trained in advance, determines that Oil spills occurs first is general
Rate；If first probability is more than preset threshold, anti-interference process is carried out to the first object image, to obtain the second target
Image；Second target image is inputted into the Oil spills detection model, determines the second probability that Oil spills occurs；?
Determine that second probability is more than determining generation Oil spills after the preset threshold.Mould is detected by trained Oil spills
Type determines whether to occur Oil spills, and the accuracy of identification is more than artificial judgment, it is visual to be no longer highly dependent on operator
It checks.Meanwhile relative to manual inspection or the method for manual control unmanned plane inspection, more efficient, cost is smaller, automation
Degree is higher, is influenced by manual operation smaller.In addition to this, using hierarchical detection mode, it is being based on collected first object
Image determine occur Oil spills the first probability be more than preset threshold after, based on to first object image carry out anti-interference process
Rear the second target image, which determines, occurs whether the second probability of Oil spills is more than preset threshold, only the second probability also above
After second threshold, just Oil spills occurs for confirmation, to reduce the probability of erroneous judgement.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of flow chart of the inspection method of Oil spills provided by the embodiment of the present application；
Fig. 2 shows a kind of optimized flow charts of the inspection method of Oil spills provided by the embodiment of the present application；
Fig. 3 shows the effect picture provided by the embodiment of the present application after anti-interference process；
Fig. 4 shows the optimized flow chart of the inspection method of another kind Oil spills provided by the embodiment of the present application；
Fig. 5 shows the optimized flow chart of the inspection method of another kind Oil spills provided by the embodiment of the present application；
Fig. 6 shows the effect picture crossed provided by the embodiment of the present application by maximum between-cluster variance algorithm process；
Fig. 7 shows and calculates Oil spills area using maximum extreme value stability region algorithm provided by the embodiment of the present application
Schematic illustration；
Fig. 8 shows a kind of structural schematic diagram of the check device of Oil spills provided by the embodiment of the present application；
Fig. 9 shows the schematic diagram of enterprise intelligent production center monitor front end provided by the embodiment of the present application.
Figure 10, which is shown, utilizes the effect picture after the inspection method of Oil spills provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
With flourishing for petroleum industry, at 2016 beginning of the year of cut-off, the oil-gas pipeline total kilometrage in China is nearly 150,000 public
In, the oil storage tank quantity for oil movement and storage surpasses 900,000, these oil movement and storage pressure vessel facilities are national economy and resident
Daily life important energy safeguard is provided.Since petroleum itself is highly corrosive, although currently used for oil movement and storage
Pressure vessel used many technologies and carry out correlative protections, but because maintenance not in time or external force is destroyed
Reason (steals oil, breakage in installation etc.), inevitably brings Oil spills risk and security risk.Petroleum once a leak occurs,
Irreversible damage can be caused to environment, while be easy burning, explosion under the conditions ofs open fire etc., make the personal safety as well as the property safety of the people
Receive threat.
In order to avoid oil movement and storage system leaks, oil play uses multiple technologies means at present to monitor pressure
The integrality of container, but due to the influence of the physical characteristics such as petroleum itself is sticky, complicated component, at present most it is effective still
Carry out inspection for pressure vessel.
Traditional oil movement and storage pressure vessel patrol worker is made mainly through the regular inspection of safety inspector and higher level's supervise and examine portion
The irregular selective examination two ways of door, and be using human contact's mode, large labor intensity, operation procedure complexity, resource
Configure it is too fat to move it is various, work efficiency is low, the period is longer, especially difficult location often can not guarantee both quality and quantity on time complete measurement appoint
Business.In recent years, start to apply unmanned plane in the scene of shooting Oil spills.But current inspection work still height relies on people
Work carries out flight control and the judgement for petroleum " evaporating, emitting, dripping or leaking of liquid or gas " situation, and the carry out correlation training of professional will increase
Enterprise operation cost.And the external environment (such as illumination, shooting angle) when due to the resolution ratio and shooting of picture of taking photo by plane influences,
Even by the personnel of professional training, for petroleum " evaporating, emitting, dripping or leaking of liquid or gas " situation detection effect all vulnerable to larger impact, in reality
There is significant limitation on border in.
Based on the above issues, the embodiment of the present application provides a kind of inspection method of Oil spills, device and system, below
It is described by embodiment.
For the inspection convenient for understanding the present embodiment, first to a kind of Oil spills disclosed in the embodiment of the present application
Method describes in detail.
As shown in Figure 1, a kind of inspection method of Oil spills, comprising the following steps:
Real-time collected first object image is input to Oil spills detection model trained in advance, determined by S101
The first probability of Oil spills occurs；
S102 carries out anti-interference process to the first object image if first probability is more than preset threshold, with
To the second target image；
Second target image is inputted the Oil spills detection model by S103, is determined and is occurred the of Oil spills
Two probability；
S104 is determined and Oil spills is occurred after determining that second probability is more than the preset threshold.
Wherein, in step S101, real-time collected first object image is input to preparatory trained Oil spills
In detection model.First object image is the image for including Oil spills scene, is shot by unmanned plane real-time on-site.Training in advance
Oil spills detection model be to be shot on the spot using same model unmanned plane, obtain Oil spills image pattern, and will obtain
The Oil spills image pattern got does not leak the training set that model is used as together with image pattern with petroleum after being pre-processed, so
Training depth convolutional neural networks on the basis of grounding model afterwards, obtain Oil spills detection model, and petroleum is let out
Leak detection model is deployed on data processing server.It is pre- that grounding model can be Google Net Inception V3
Training pattern.By Oil spills model, finally determines the probability of generation Oil spills in region in the picture of input, determine this
Probability is the first probability.
In step S102, when the first probability is more than preset threshold, anti-interference process is carried out to first object image, with
To the second target image.Preset threshold is the value of an artificial settings, when the probability obtained after Oil spills detection model
It is greater than preset threshold, then passes through secondary judgement, determines and Oil spills occurs.
Step S103 is that the second target image Jing Guo anti-interference process is again inputted into petroleum on the basis of S102
Leak detection model, to obtain the second probability.This is the area shown to the first object image of input oil leak detection model
Whether domain occurs the secondary judgement of Oil spills, to reduce a possibility that judging by accident.
Step S104 is that the second probability for obtaining previous step is compared with preset threshold, it is determined whether is more than default
Threshold value when the second probability is still above preset threshold then determines that Oil spills occurs.
Further, such as Fig. 2, step S102 the following steps are included:
First object image is divided into the first foreground picture according to the grey scale pixel value of the first object image by S201
As part and the first background image portion；
S202 is determined and is divided according to the maximum class variance between the first foreground image section and the first background image portion
Cut the segmentation threshold of foreground and background；
S203 is carried out image dividing processing to the first object image, is obtained institute based on the determining segmentation threshold
State the second target image.
The step of step S201 to S203 entirety is by the grey scale pixel value of first object image, by first object image
It is divided into the first foreground image section and the first background image portion, when taking optimal threshold, the difference between two parts should
It is the largest, the standard of the measurement difference used here is exactly relatively conventional maximum between-cluster variance.First foreground image section
If the inter-class variance between the first background image portion is bigger, just illustrates to constitute the difference between two parts of image and get over
Greatly, target is divided by mistake when partial target is divided into background or part background by mistake, all two parts difference can be caused to become smaller, when being taken
The segmentation of threshold value makes to mean that misclassification probability minimum when inter-class variance maximum.When variance maximum, it is believed that prospect at this time
With background difference maximum, gray value at this time is optimal threshold.At this moment according to determining segmentation threshold, to first object image into
Row dividing processing shows the first foreground image section and the segmentation of the first background image portion.Meanwhile it as shown in figure 3, will
The region of foreground image section i.e. Oil spills is irised out on picture to be come, and will likely become the background white of chaff interferent
Substitution, is formed a sharp contrast with the black with Oil spills region.Or the background of chaff interferent is blocked, before protrusion
Scape image section, i.e. Oil spills region, to obtain the second target image after anti-interference process.
As shown in figure 4, the step of training Oil spills detection model, includes:
S401, using depth convolutional neural networks model as basic training pattern；
Oil spills image pattern and petroleum are not leaked image pattern as the training of the grounding model by S402
Collection, using known Oil spills result as the output of the grounding model as a result, training obtains the Oil spills inspection
Survey model.
In step S401, Google Net Inception V3 is participated in training by the application.Step
Rapid S402 specifically includes following treatment process.Unmanned plane is obtained first, and stone occurs from multiple angle shot oil movement and storage pressure vessels
The real-time video of oil leakage, and framing is intercepted according to certain time interval to these real-time videos, obtain Oil spills figure
Decent；Secondly, being pre-processed to Oil spills image pattern.Pretreated process includes: to adjust the comparison of original image
Degree is secondary by rotating one counterclockwise according to every 45 ° to original image to simulate the Oil spills scene under different illumination conditions
The image of Cheng Xin is to simulate the Oil spills situation under different shooting angles, by amplifying contracting according to a certain percentage to original image
It is small to simulate the Oil spills situation taken under different height；Finally, using pretreated picture to Google Net
The parameter of Inception V3 basic model is adjusted, and it is refreshing to train the new depth convolution for detecting Oil spills
It is deployed on data processing server through network model, and by the network.Specifically, being carried out using depth convolutional neural networks
The extraction of feature simultaneously designs the detection that detector completes Oil spills region；The Oil spills in Oil spills region will have been marked out
Training set of the image pattern as the grounding model supervises the training of pilot model with the Oil spills result of mark,
So that the output result of model constantly converges on annotation results, to complete the training of model.
After determining generation Oil spills, it can also be believed according to the position of the corresponding target area of the first object image
Breath, determines Oil spills region.Location information includes the longitude and latitude in captured region, can be accurately positioned Oil spills region
Position.
As shown in figure 5, further including following steps after Oil spills has been determined according to above-mentioned steps:
S501 obtains the acquisition parameters information of the first object image of unmanned plane shooting；The acquisition parameters information
Including drone flying height, camera pixel number, camera horizon field angle and video camera vertical field of view angle；
S502 calculates Oil spills face according to the Pixel Information of the acquisition parameters information and second target image
Product.
Unmanned plane inspection route is preset according to the GPS coordinate of oil movement and storage pressure vessel, allows unmanned plane according to particular flight
Parameter (speed, height etc.) flight.Unmanned plane inspection route is planned according to the GPS coordinate of oil movement and storage pressure vessel, by route
System for flight control computer is written.
In step S501, the acquisition parameters information of the first object image of unmanned plane shooting is obtained.Wherein, unmanned plane
Flying height can obtain in the flight parameter that unmanned plane is passed back, and camera pixel number is the video camera according to entrained by unmanned plane
Determined by model, the horizontal field of view angle and vertical field of view angle of video camera are also related to video camera model.In step S502
The Pixel Information of two target images refers to the second target image obtained after anti-interference process for first object image, number
According to processing server using maximum extreme value stability region algorithm, automatically extracts and be detected as in the second target image containing petroleum region
Connected component contained by pixel value P.As shown in fig. 6, for by the effect picture of maximum between-cluster variance algorithm.By pixel value P and step
The acquisition parameters information of obtained first object image substitutes into formula in rapid S401Its
P in middle formula0For camera pixel sum, only determined by video camera model；H is drone flying height in formula, can
It is obtained from the flight data that unmanned plane is passed back；α and β in formula are respectively the horizontal and vertical field angle of camera lens, only with take the photograph
Camera model is related.As shown in fig. 7, illustrating for the principle for calculating Oil spills area using maximum extreme value stability region algorithm
Figure.Meanwhile data packing is equally sent to by ground data processing server, data sampling by unmanned aerial vehicle onboard data radio station
Frequency is consistent with frame rate is cut, and guarantees that every picture and flight data correspond.
To sum up, in the above method, same model unmanned plane is used to be shot on the spot first, obtains Oil spills image sample
This, and Oil spills image pattern and petroleum are not leaked into image pattern as the training set of the grounding model, it will
Output result of the Oil spills result known as the grounding model；Then in Google Net Inception V3
According to the data set training depth convolutional neural networks manually marked on the basis of basic model, and model is deployed at data
It manages on server；Finally the image that unmanned plane in actual use takes is input in model and is judged, for more than one
The picture for determining threshold value eliminates chaff interferent using maximum between-cluster variance algorithm, uses if still having Oil spills situation by model judgement
Maximum extreme value stability region algorithm automatically extracts Oil spills region, calculates leakage area, assesses oil leak degree, and correlation is believed
Breath is presented on enterprise intelligent control centre and mobile terminal.
In addition, as shown in figure 8, present invention also provides a kind of check devices of Oil spills, comprising: the first data acquisition
Module 801, the first data analysis module 802, the second data analysis module 803, data comparison module 804 and the first data processing
Module 805；First data acquisition module 801, for obtaining first object image in real time；First data analysis module 802, is used for
First object image is input to Oil spills detection model trained in advance, to determine the first probability that Oil spills occurs；
Data comparison module 804, for comparing the size of the first probability and preset threshold；First data processing module 805, if for the
One probability is more than preset threshold, anti-interference process is carried out to first object image, to obtain the second target image；Second data point
Module 803 is analysed, for second target image to be inputted the Oil spills detection model, determines the of generation Oil spills
Two probability.
Further, the first data processing module 805 includes image segmentation unit 8051, image determination unit 8052 and figure
As generation unit 8053；
Image segmentation unit 8051 draws first object image for the grey scale pixel value according to first object image
It is divided into the first foreground image section and the first background image portion；
Image determination unit 8052, for according to the maximum between the first foreground image section and the first background image portion
Class variance, to determine the segmentation threshold of segmentation foreground and background；
Image generation unit 8053, for carrying out image point to first object image based on the determining segmentation threshold
Processing is cut, to obtain the second target image.
Further, device further include: image determining module 806；
Image determining module 806 is determined for the location information according to the corresponding target area of the first object image
The true geographic area of Oil spills.
In addition, returning apparatus further include: the second data acquisition module 807 and the second data processing module 808；
Second data acquisition module 807, the acquisition parameters letter of the first object image for obtaining unmanned plane shooting
Breath；
Second data processing module 808, for the pixel according to the acquisition parameters information and second target image
Information, to calculate Oil spills area.
The application also provides a kind of inspection system of Oil spills, which includes: data processing server, unmanned plane sheet
Body, ground communications base station and enterprise intelligent control centre；
Implementing result to execute such as above-mentioned method, and is transferred to enterprise's intelligence by the data processing server
It can control center；
The enterprise intelligent control centre, for the implementing result of the transmission of processing server based on the data, to described
Ground communications base station sends drone body operational order；
The ground communications base station, the drone body operation sent for responding the enterprise intelligent control centre
Instruction.
Flight control system, communication system, mission payload and dynamical system are equipped in drone body, wherein described
Flight control system includes being made of GPS module and inertial navigation module (Inertial measurement unit, IMU)
Integrated navigation system and acceptable ground control instruction and to dynamical system issue instruction flight control system.Wherein,
Control system includes that airborne microprocessor, laser ranging obstacle avoidance system, data radio station, figure conduct electricity platform, receiver, data storage mould
Block, binocular vision sensor, infrared distance sensor, gyroscope, IMU and GPS integrated navigation module, electron speed regulator and its attached
Belong to motor, the airborne microprocessor is connected with communication system, mission payload and dynamical system by bus.Communication system packet
Include the receiver for receiving ground control signal, transmitter and use for passing through wireless network communication with ground communications base station
In the transmitter with passing of satelline 4G network communication.Mission payload includes high-definition camera (using in the daytime), infrared camera
(night use), the holder for installing fixed video camera and its attached stepper motor.Mission payload system uses modularization
Design can switch disparate modules according to natural environments such as illumination by flight-line service personnel.Dynamical system include unmanned electromechanical source,
Power supply voltage-stabilizing system, electric motor and controller system.Ground communications base station includes base station power supply system, wireless signal sending and receiving stations, base
Station control, antenna.Power supply system provides power supply to base station controller and wireless signal sending and receiving stations, and sending and receiving stations include for nothing
The data radio station of man-machine transmission control instruction, the data radio station for receiving and transmitting unmanned plane during flying parameter and for receive simultaneously
The figure of transmission unmanned plane shooting picture conducts electricity platform.Base station controller is used for distribution, release and the management of unmanned plane wireless channel, day
Line is for receiving and emitting radio wave.
It is deployed on data processing server previously according to the trained Oil spills detection of Oil spills image pattern
Model is assessed for handling, judging, assess whether there is a situation where Oil spills and to leakage severity.Such as Fig. 9 institute
Show, include ground monitoring display, real-time remote monitoring platform and unmanned plane tele-control system in enterprise intelligent control centre,
Real-time monitoring platform can be shown on ground monitoring display enterprise's historical production data, unmanned plane real-time flight status data,
Section safe condition is produced, unmanned plane tele-control system is used to send flight attitude control instruction and control task to unmanned plane
Load completes required movement.As shown in Figure 10, the Oil spills regional effect figure to be handled using the above method and system.
In addition, the system further includes Cloud Server and mobile terminal.Cloud Server can be by network and ground data at
Reason server is connected, and the result after server process uploads to and cloud, through visualization technique in particular webpage
Show real-time inspection state, mobile terminal can check state by accessing webpage, but cannot repair in mobile terminal
Change web page contents and operation unmanned plane.
Meanwhile the flight data that processing result is transmitted back to unmanned plane data radio station by ground data processing server is together
Packing uploads to Cloud Server, and enterprise intelligent control centre and mobile terminal can be checked by way of accessing webpage visual
Change the unmanned plane inspection result of real-time exhibition in interface.According to visualization circle showed on enterprise intelligent control centre monitor
Face, operator remotely can assign instruction to unmanned plane, posture, speed, the height flown when adjusting unmanned plane automatic detecting
Etc. parameters, also can control unmanned plane spiral automatically about a certain point of interest it is circular.Meanwhile operator can also be by line walking system
System switches to manual operation mode, flexibly controls unmanned plane during flying.If unmanned plane does not detect Oil spills situation, according to default
Route continues line walking.
According to enterprise's production statistics data, some region of petroleum pipeline or Oil Tank Body occurred petroleum " race emit drop
The probability that oil leak occurs after leakage " accident again can be higher than other regions.When carrying out inspection using unmanned plane, when inspection to history is sent out
Gave birth to the region of Oil spills, unmanned plane can be kept to script setting speed 1/n (n is the positive number greater than 1, can by enterprise according to
Historical production data is freely set).
Oily event is stolen according to practical condition and generally betides night, is added in training depth convolutional neural networks
The portrait image that infrared camera takes.Using unmanned plane in night inspection, when cruising inspection system detects storage and transportation petroleum
There are when a suspect, can control unmanned plane to carry out surrounding flight and prompt around related personnel in pressure vessel a certain range
Enterprise intelligent control centre personnel on duty check.
In addition, can also be used other than daily line walking of the unmanned plane automatic tour inspection system in can be used for enterprise and normally produce
Repairerment situation after checking pressure vessel maintenance: unmanned plane carries out surrounding flight around the petroleum tank body after maintenance,
Petroleum is injected into the tank body by maintenance, oil spill situation such as occurs, unmanned plane cruising inspection system can issue oil leak automatically
Alarm.
Data processing server is made of a series of high-performance computers, wherein being deployed with based on obtaining in a large amount of actual productions
Mould made of Oil spills picture (including common camera shooting and infrared camera shooting) the data set training taken
Type, the image data collection are pre-processed by picture before training pattern to simulate the environment of different illumination and angle；The mould
Type is to be obtained based on Google Net Inception V3 pre-training model according to real data collection adjusting parameter re -training
, the model had also combined in addition to depth convolutional neural networks maximum between-cluster variance algorithm (also referred to as Da-Jin algorithm, OTSU) with
Influence of the background interference object for being similar to petroleum for depth convolutional neural networks model is eliminated, joined maximum in the model
Extreme value stability region algorithm (Maximally Stable Extremal Regions, MSER), which realizes automatically, lets out petroleum
The assessment of drain region area；Data processing server is connected with Cloud Server, and the picture that unmanned plane takes is handled
Afterwards, it is packaged jointly with the unmanned plane during flying parameter received and is uploaded to Cloud Server, in enterprise intelligent control centre front end and shifting
Dynamic terminal can visually show unmanned plane during flying position, flight status parameter, production history data and Oil spills general view
And severity.
Unmanned plane may be implemented to oil movement and storage pressure vessel automatic detecting in methods, devices and systems in the application, and
It detects whether that Oil spills accident occurs automatically using computer vision technique, is no longer highly dependent on operator and visually examines
It looks into.Based on high-performance pre-training network struction model, recognition accuracy is more than artificial judgment；Model just has been added in training
It is adjusted contrast, the authentic specimen that rotation, scaling processing are crossed, true environment can be simulated very well, for complex environment
There is higher robustness；Eliminating chaff interferent using maximum between-cluster variance algorithm influences；It is automatic using maximum extreme value stability region algorithm
Calculate Oil spills area；And it can control unmanned plane batch jobs；By the replacement modes such as battery can realize 24 hours not between
Disconnected inspection.Therefore relative to original manual inspection either manual control unmanned plane method for inspecting, more efficient, cost is more
Small, the degree of automation is higher, is influenced by manual operation smaller.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of inspection method of Oil spills characterized by comprising
By unmanned plane, collected first object image is input to Oil spills detection model trained in advance in real time, determines and occurs
First probability of Oil spills；
If first probability is more than preset threshold, anti-interference process is carried out to the first object image, to obtain the second mesh
Logo image；
Second target image is inputted into the Oil spills detection model, determines the second probability that Oil spills occurs；
After determining that second probability is more than the preset threshold, determines and Oil spills occurs.
2. if the method according to claim 1, wherein first probability is more than preset threshold, to institute
It states first object image and carries out anti-interference process, to obtain the second target image, comprising:
According to the grey scale pixel value of the first object image, first object image is divided into the first foreground image section and
One background image portion；
According to the maximum class variance between the first foreground image section and the first background image portion, segmentation prospect and back are determined
The segmentation threshold of scape；
Based on the determining segmentation threshold, image dividing processing is carried out to the first object image, obtains second mesh
Logo image.
3. being detected the method according to claim 1, wherein obtaining the Oil spills according to following steps training
Model:
Using depth convolutional neural networks model as basic training pattern；
Oil spills image pattern and petroleum are not leaked into image pattern as the training set of the grounding model, it will be known
Oil spills result as the grounding model output as a result, training obtain the Oil spills detection model.
4. the method according to claim 1, wherein after determining generation Oil spills, further includes:
According to the location information of the corresponding target area of the first object image, the true geographic area of Oil spills is determined.
5. the method according to claim 1, wherein after determining generation Oil spills, further includes:
Obtain the acquisition parameters information of the first object image of unmanned plane shooting；The acquisition parameters information includes unmanned plane
Flying height, camera pixel number, camera horizon field angle and video camera vertical field of view angle；
According to the Pixel Information of the acquisition parameters information and second target image, Oil spills area is calculated.
6. a kind of check device of Oil spills characterized by comprising the first data acquisition module, the first data analyze mould
Block, the second data analysis module, data comparison module and the first data processing module；
First data acquisition module, for obtaining first object image in real time；
First data analysis module detects mould for the first object image to be input to Oil spills trained in advance
Type, to determine the first probability that Oil spills occurs；
The data comparison module, the size for first probability and preset threshold；
First data processing module, if for first probability be more than preset threshold, to the first object image into
Row anti-interference process, to obtain the second target image；
Second data analysis module is determined for second target image to be inputted the Oil spills detection model
The second probability of Oil spills occurs.
7. device according to claim 6 characterized by comprising first data processing module includes image point
Cut unit, image determination unit and image generation unit；
Described image cutting unit draws first object image for the grey scale pixel value according to the first object image
It is divided into the first foreground image section and the first background image portion；
Described image determination unit, for according to the maximum classification between the first foreground image section and the first background image portion
Variance, to determine the segmentation threshold of segmentation foreground and background；
Described image generation unit, for carrying out image point to the first object image based on the determining segmentation threshold
Processing is cut, to obtain second target image.
8. device according to claim 6, which is characterized in that further include: image determining module；
Described image determining module determines stone for the location information according to the corresponding target area of the first object image
The true geographic area of oil leakage.
9. device according to claim 6, which is characterized in that further include: at the second data acquisition module and the second data
Manage module；
Second data acquisition module, the acquisition parameters information of the first object image for obtaining unmanned plane shooting；
Second data processing module, for according to the acquisition parameters information and the pixel of second target image letter
Breath, to calculate Oil spills area.
10. a kind of inspection system of Oil spills characterized by comprising data processing server, drone body, ground
Communication base station and enterprise intelligent control centre；
The data processing server is transmitted to execute method as claimed in claim 1 to 5, and by implementing result
To the enterprise intelligent control centre；
The enterprise intelligent control centre, for the implementing result of the transmission of processing server based on the data, to the ground
Communication base station sends drone body operational order；
The ground communications base station refers to for responding the drone body operation that the enterprise intelligent control centre sends
It enables.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810970710.5A CN109325520B (en) | 2018-08-24 | 2018-08-24 | Method, device and system for checking petroleum leakage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810970710.5A CN109325520B (en) | 2018-08-24 | 2018-08-24 | Method, device and system for checking petroleum leakage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109325520A true CN109325520A (en) | 2019-02-12 |
| CN109325520B CN109325520B (en) | 2021-06-29 |
Family
ID=65263795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810970710.5A Active CN109325520B (en) | 2018-08-24 | 2018-08-24 | Method, device and system for checking petroleum leakage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325520B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363109A (en) * | 2019-06-26 | 2019-10-22 | 成都新舟锐视科技有限公司 | A kind of cover type Oil Leakage Detecting system and method based on computer vision |
| CN110553151A (en) * | 2019-07-17 | 2019-12-10 | 石化盈科信息技术有限责任公司 | pipeline leakage monitoring method and system |
| CN110705601A (en) * | 2019-09-09 | 2020-01-17 | 安徽继远软件有限公司 | Transformer substation equipment oil leakage image identification method based on single-stage target detection |
| CN111126196A (en) * | 2019-12-10 | 2020-05-08 | 安徽银河物联通信技术有限公司 | Equipment oil leakage detection method |
| CN111414955A (en) * | 2020-03-17 | 2020-07-14 | 北京中油瑞飞信息技术有限责任公司 | Intelligent detection method and device for leakage and overflow of petroleum drilling well and electronic equipment |
| CN111445462A (en) * | 2020-03-30 | 2020-07-24 | 国家计算机网络与信息安全管理中心 | Storage battery leakage detection method based on neural network and thermography |
| CN113255737A (en) * | 2021-04-30 | 2021-08-13 | 超节点创新科技(深圳)有限公司 | Method for sorting stacked luggage on civil aviation sorting line, electronic equipment and storage medium |
| CN113514193A (en) * | 2021-07-13 | 2021-10-19 | 江铃汽车股份有限公司 | Automobile collision fuel leakage detection method based on image recognition |
| CN113542595A (en) * | 2021-06-28 | 2021-10-22 | 北京沧沐科技有限公司 | Capturing and monitoring method and system based on day and night images |
| CN113670524A (en) * | 2021-07-13 | 2021-11-19 | 江铃汽车股份有限公司 | Detection method and detection system for fuel leakage in automobile collision |
| CN114992813A (en) * | 2022-06-17 | 2022-09-02 | 珠海格力电器股份有限公司 | Method and device for detecting substance leakage, air conditioning equipment and storage medium |
| CN115457297A (en) * | 2022-08-23 | 2022-12-09 | 中国航空油料集团有限公司 | Method and device for detecting oil leakage of aviation oil depot and aviation oil safety operation and maintenance system |
| CN116052061A (en) * | 2023-02-21 | 2023-05-02 | 嘉洋智慧安全科技(北京)股份有限公司 | Event monitoring method, event monitoring device, electronic equipment and storage medium |
| CN116259012A (en) * | 2023-05-16 | 2023-06-13 | 新疆克拉玛依市荣昌有限责任公司 | Monitoring system and method for embedded supercharged diesel tank |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170641A (en) * | 2007-12-05 | 2008-04-30 | 北京航空航天大学 | A method for image edge detection based on threshold sectioning |
| CN101571915A (en) * | 2009-06-16 | 2009-11-04 | 大连海事大学 | Method for identifying oil spill of SAR image based on characteristic value |
| CN107194368A (en) * | 2017-06-08 | 2017-09-22 | 广东容祺智能科技有限公司 | A kind of unmanned plane Crude Oil at Sea leakage is searched and emergency processing method |
| CN107871119A (en) * | 2017-11-01 | 2018-04-03 | 西安电子科技大学 | A kind of object detection method learnt based on object space knowledge and two-stage forecasting |
| CN108010156A (en) * | 2017-11-01 | 2018-05-08 | 北京航天福道高技术股份有限公司 | A kind of round-the-clock autonomous oil field cruising inspection system |
| CN108027884A (en) * | 2015-09-25 | 2018-05-11 | 高通股份有限公司 | Optimization object detects |
| CN108073933A (en) * | 2016-11-08 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of object detection method and device |
| US20180158189A1 (en) * | 2016-12-07 | 2018-06-07 | Samsung Electronics Co., Ltd. | System and method for a deep learning machine for object detection |
| US20180157899A1 (en) * | 2016-12-07 | 2018-06-07 | Samsung Electronics Co., Ltd. | Method and apparatus detecting a target |
| CN108154159A (en) * | 2017-12-25 | 2018-06-12 | 北京航空航天大学 | A kind of method for tracking target with automatic recovery ability based on Multistage Detector |
| CN108363998A (en) * | 2018-03-21 | 2018-08-03 | 北京迈格威科技有限公司 | A kind of detection method of object, device, system and electronic equipment |
-
2018
- 2018-08-24 CN CN201810970710.5A patent/CN109325520B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170641A (en) * | 2007-12-05 | 2008-04-30 | 北京航空航天大学 | A method for image edge detection based on threshold sectioning |
| CN101571915A (en) * | 2009-06-16 | 2009-11-04 | 大连海事大学 | Method for identifying oil spill of SAR image based on characteristic value |
| CN108027884A (en) * | 2015-09-25 | 2018-05-11 | 高通股份有限公司 | Optimization object detects |
| CN108073933A (en) * | 2016-11-08 | 2018-05-25 | 杭州海康威视数字技术股份有限公司 | A kind of object detection method and device |
| US20180158189A1 (en) * | 2016-12-07 | 2018-06-07 | Samsung Electronics Co., Ltd. | System and method for a deep learning machine for object detection |
| US20180157899A1 (en) * | 2016-12-07 | 2018-06-07 | Samsung Electronics Co., Ltd. | Method and apparatus detecting a target |
| CN107194368A (en) * | 2017-06-08 | 2017-09-22 | 广东容祺智能科技有限公司 | A kind of unmanned plane Crude Oil at Sea leakage is searched and emergency processing method |
| CN107871119A (en) * | 2017-11-01 | 2018-04-03 | 西安电子科技大学 | A kind of object detection method learnt based on object space knowledge and two-stage forecasting |
| CN108010156A (en) * | 2017-11-01 | 2018-05-08 | 北京航天福道高技术股份有限公司 | A kind of round-the-clock autonomous oil field cruising inspection system |
| CN108154159A (en) * | 2017-12-25 | 2018-06-12 | 北京航空航天大学 | A kind of method for tracking target with automatic recovery ability based on Multistage Detector |
| CN108363998A (en) * | 2018-03-21 | 2018-08-03 | 北京迈格威科技有限公司 | A kind of detection method of object, device, system and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| LEIMING LIU等: "Image segmentation based on gray stretch and threshold algorithm", 《OPTIK》 * |
| YUFENG SHEN等: "Detection of stored-grain insects using deep learning", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| 杨娟等: "区域建议网络的细粒度车型识别", 《中国图象图形学报》 * |
| 郝亚冰: "SAR图像去噪、分割及目标检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363109B (en) * | 2019-06-26 | 2023-03-24 | 成都新舟锐视科技有限公司 | Computer vision-based coverage type oil leakage detection system and method |
| CN110363109A (en) * | 2019-06-26 | 2019-10-22 | 成都新舟锐视科技有限公司 | A kind of cover type Oil Leakage Detecting system and method based on computer vision |
| CN110553151A (en) * | 2019-07-17 | 2019-12-10 | 石化盈科信息技术有限责任公司 | pipeline leakage monitoring method and system |
| CN110553151B (en) * | 2019-07-17 | 2021-05-07 | 石化盈科信息技术有限责任公司 | Pipeline leakage monitoring method and system |
| CN110705601A (en) * | 2019-09-09 | 2020-01-17 | 安徽继远软件有限公司 | Transformer substation equipment oil leakage image identification method based on single-stage target detection |
| CN111126196A (en) * | 2019-12-10 | 2020-05-08 | 安徽银河物联通信技术有限公司 | Equipment oil leakage detection method |
| CN111414955A (en) * | 2020-03-17 | 2020-07-14 | 北京中油瑞飞信息技术有限责任公司 | Intelligent detection method and device for leakage and overflow of petroleum drilling well and electronic equipment |
| CN111414955B (en) * | 2020-03-17 | 2023-08-25 | 昆仑数智科技有限责任公司 | Intelligent detection method and device for petroleum drilling lost circulation overflow and electronic equipment |
| CN111445462A (en) * | 2020-03-30 | 2020-07-24 | 国家计算机网络与信息安全管理中心 | Storage battery leakage detection method based on neural network and thermography |
| CN113255737A (en) * | 2021-04-30 | 2021-08-13 | 超节点创新科技(深圳)有限公司 | Method for sorting stacked luggage on civil aviation sorting line, electronic equipment and storage medium |
| CN113255737B (en) * | 2021-04-30 | 2023-08-08 | 超节点创新科技(深圳)有限公司 | Method for sorting baggage in folded package on civil aviation sorting line, electronic equipment and storage medium |
| CN113542595A (en) * | 2021-06-28 | 2021-10-22 | 北京沧沐科技有限公司 | Capturing and monitoring method and system based on day and night images |
| CN113670524A (en) * | 2021-07-13 | 2021-11-19 | 江铃汽车股份有限公司 | Detection method and detection system for fuel leakage in automobile collision |
| CN113514193B (en) * | 2021-07-13 | 2022-12-02 | 江铃汽车股份有限公司 | Automobile collision fuel leakage detection method based on image recognition |
| CN113514193A (en) * | 2021-07-13 | 2021-10-19 | 江铃汽车股份有限公司 | Automobile collision fuel leakage detection method based on image recognition |
| CN114992813B (en) * | 2022-06-17 | 2023-05-12 | 珠海格力电器股份有限公司 | Method and device for detecting substance leakage, air conditioning equipment and storage medium |
| CN114992813A (en) * | 2022-06-17 | 2022-09-02 | 珠海格力电器股份有限公司 | Method and device for detecting substance leakage, air conditioning equipment and storage medium |
| CN115457297A (en) * | 2022-08-23 | 2022-12-09 | 中国航空油料集团有限公司 | Method and device for detecting oil leakage of aviation oil depot and aviation oil safety operation and maintenance system |
| CN115457297B (en) * | 2022-08-23 | 2023-09-26 | 中国航空油料集团有限公司 | Oil leakage detection method and device for aviation oil depot and aviation oil safety operation and maintenance system |
| CN116052061A (en) * | 2023-02-21 | 2023-05-02 | 嘉洋智慧安全科技(北京)股份有限公司 | Event monitoring method, event monitoring device, electronic equipment and storage medium |
| CN116052061B (en) * | 2023-02-21 | 2024-02-27 | 嘉洋智慧安全科技(北京)股份有限公司 | Event monitoring method, event monitoring device, electronic equipment and storage medium |
| CN116259012A (en) * | 2023-05-16 | 2023-06-13 | 新疆克拉玛依市荣昌有限责任公司 | Monitoring system and method for embedded supercharged diesel tank |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109325520B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325520A (en) | A kind of inspection method of Oil spills, apparatus and system | |
| CN107316012B (en) | Fire detection and tracking method of small unmanned helicopter | |
| US11620891B2 (en) | Method and system for determining area of fire and estimating progression of fire | |
| US20160214715A1 (en) | Systems, Methods and Devices for Collecting Data at Remote Oil and Natural Gas Sites | |
| CN107808425A (en) | Oil-gas pipeline cruising inspection system and its method for inspecting based on unmanned plane image | |
| KR20140029394A (en) | A surveillance system and a method for detecting a foreign object, debris, or damage in an airfield | |
| CN110673628B (en) | Inspection method for oil-gas pipeline of composite wing unmanned aerial vehicle | |
| CN106710128A (en) | Fire alarm early-warning unmanned aerial vehicle | |
| CN108257119B (en) | Near-shore sea area floating hazardous chemical detection early warning method based on near-ultraviolet image processing | |
| CN202094531U (en) | Power transmission line inspection device suitable for unmanned aerial vehicle | |
| CN102255259A (en) | Transmission line tour inspection device suitable for unmanned aerial vehicle | |
| CN105511491B (en) | A kind of unmanned plane device for driving away and method | |
| CA2902040C (en) | Reduction of sensor captured data streamed to an operator | |
| KR20140127574A (en) | Fire detecting system using unmanned aerial vehicle for reducing of fire misinformation | |
| US20220171068A1 (en) | Damage detection and analysis using three-dimensional surface scans | |
| US20190361466A1 (en) | Real-time system and method for asset management using unmanned aerial systems and edge computing | |
| CN108225111B (en) | Distributed anti-unmanned aerial vehicle system and method for intercepting unmanned aerial vehicle by interference | |
| CN110647170A (en) | Navigation mark inspection device and method based on unmanned aerial vehicle | |
| De Sousa et al. | Aerial forest fire detection and monitoring using a small uav | |
| CN110274160A (en) | A kind of pipeline cruising inspection system based on infrared visible light blending image | |
| CN210835732U (en) | Beacon inspection device based on unmanned aerial vehicle | |
| US11595634B2 (en) | Detection and ranging based on a single monoscopic frame | |
| CN117314157A (en) | Safety evaluation method, device, medium and equipment for mine slope stability | |
| CN114037910A (en) | Unmanned aerial vehicle forest fire detecting system | |
| CN210511074U (en) | Full-intelligent oil-gas pipeline inspection system based on unmanned aerial vehicle remote sensing and deep learning |
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 |