CN108318008A - A kind of detection method of geological disaster, device and system - Google Patents
A kind of detection method of geological disaster, device and system Download PDFInfo
- Publication number
- CN108318008A CN108318008A CN201711338254.4A CN201711338254A CN108318008A CN 108318008 A CN108318008 A CN 108318008A CN 201711338254 A CN201711338254 A CN 201711338254A CN 108318008 A CN108318008 A CN 108318008A
- Authority
- CN
- China
- Prior art keywords
- target location
- image
- unmanned plane
- plane device
- target
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 210000005036 nerve Anatomy 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000005540 biological transmission Effects 0.000 claims description 11
- 238000013441 quality evaluation Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000001303 quality assessment method Methods 0.000 claims description 3
- 239000011257 shell material Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000004913 activation Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000011435 rock Substances 0.000 description 3
- 238000011176 pooling Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- 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
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- 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
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Astronomy & Astrophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Radar, Positioning & Navigation (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the present invention provides a kind of detection method of geological disaster, device and system, is related to technical field of electronic equipment.Wherein, this method includes：It includes the coordinate of target location to send flight directive and give unmanned plane device, flight directive, when unmanned plane device flies to target location, receive the image for the target location that unmanned plane device is sent, according to preset artificial nerve network model, determine that the landform of target location is abnormal, and prompt user.By receiving the image of unmanned plane device shooting and determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement, improve accuracy rate, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve the accuracy and efficiency of judgement.
Description
Technical field
The invention belongs to technical field of electronic equipment more particularly to a kind of detection method of geological disaster, device and system.
Background technology
The generation of geological disaster causes prodigious harm to the lives and properties of people, for example, earthquake, mud-rock flow.
In practical applications, when there is geological disaster, the image data typically taken photo by plane using satellite or according to taking photo by plane
Content carry out three-dimensional modeling to expert judgments disaster the case where.But the usual clarity of image data that satellite is taken photo by plane is not high,
The scene that can not accurately see disaster is easy the case where existence information lacks furthermore with the model obtained after three-dimensional modeling,
Above two method can lead to the problem that the accuracy judged is poor, efficiency is low.
Invention content
The present invention provides a kind of detection method of geological disaster, device and system, it is intended to solve existing judgment method and lead
Cause judges that geological disaster accuracy is poor, the low problem of efficiency.
A kind of detection method for geological disaster that first aspect present invention provides, including：
It includes the coordinate of target location to send flight directive and give unmanned plane device, the flight directive；
When the unmanned plane device flies to the target location, the target location that the unmanned plane device is sent is received
Image；
According to preset artificial nerve network model, determine that the landform of the target location is abnormal, and prompt user.
A kind of detection device for geological disaster that the second fermentation of the present invention provides, including：
Sending module includes the coordinate of target location for sending flight directive to give unmanned plane device, the flight directive；
Receiving module, for when the unmanned plane device flies to the target location, receiving the unmanned plane device
The image information of the target location of transmission；
Determining module, for comparing described image information and the artificial nerve network model of preset target location
It is right, determine that the landform of the target location is abnormal, and prompt user.
A kind of detection system for geological disaster that third aspect present invention provides, including：Control terminal and unmanned plane device；
The control terminal is the detection device of the geological disaster described in second aspect；
The unmanned plane device, the flight directive sent for receiving the control terminal, and according to the flight directive
The coordinate of middle target location, flight to the target location, and the acquisition target location image information, and by the figure
As information is sent to the control terminal.
A kind of detection method of geological disaster provided by the invention, device and system, by receiving the shooting of unmanned plane device
Image and determine that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can
To reduce erroneous judgement, accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, with
And improve the accuracy and efficiency of judgement.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention.
Fig. 1 is a kind of implementation process schematic diagram of the detection method for geological disaster that first embodiment of the invention provides；
Fig. 2 is a kind of implementation process schematic diagram of the detection method for geological disaster that second embodiment of the invention provides；
Fig. 3 is a kind of structural schematic diagram of the detection device for geological disaster that third embodiment of the invention provides；
Fig. 4 is a kind of structural schematic diagram of the detection device for geological disaster that fourth embodiment of the invention provides；
Fig. 5 is a kind of structural schematic diagram of the detection system for geological disaster that fifth embodiment of the invention provides
Fig. 6 is the structural schematic diagram for the airplane parking area device that fifth embodiment of the invention provides.
Specific implementation mode
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described reality
It is only a part of the embodiment of the present invention to apply example, and not all embodiments.Based on the embodiments of the present invention, people in the art
The every other embodiment that member is obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, Fig. 1 is a kind of implementation process of the detection method for geological disaster that first embodiment of the invention provides
The detection method of schematic diagram, geological disaster shown in FIG. 1 mainly includes the following steps that：
S101, transmission flight directive give unmanned plane device；
The flight directive is to fly to the instruction of target location for controlling unmanned plane device, wherein flight directive includes
The coordinate of target location.
S102, when the unmanned plane device flies to the target location, receive the unmanned plane device transmission target location
Image information；
S103, the image information is compared with the artificial nerve network model of preset target location, determines the mesh
The landform of cursor position is abnormal, and prompts user.
The detection method of a kind of geological disaster provided by the invention, by the image and root that receive the shooting of unmanned plane device
Determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement,
Accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve judgement
Accuracy and efficiency.
Referring to Fig. 2, Fig. 2 is a kind of implementation process of the detection method for geological disaster that second embodiment of the invention provides
The detection method of schematic diagram, geological disaster shown in Fig. 2 is applied to terminal, wherein this method mainly includes the following steps that：
S201, transmission flight directive give unmanned plane device；
The flight directive is to fly to the instruction of target location for controlling unmanned plane device, wherein flight directive includes
The coordinate of target location.
S202, when the unmanned plane device flies to the target location, receive the unmanned plane device transmission target location
Image information；
Image information is the information for indicating target location image, for example, photo or video.
In practical applications, flight directive is additionally operable to when unmanned plane device flies to the coordinate of target location, controls nothing
The image of human-machine device photographic subjects position, and it is sent to terminal.
S203, the first image that geological disaster occurs and the second image that geological disaster does not occur are obtained；
Occur geological disaster the first image can be occur mud-rock flow terrain graph, occur earthquake terrain graph,
The image of the other geological disasters of Freshets roar down from the mountains terrain graph etc. occurs.It is corresponding, the second image of geological disaster does not occur
For the terrain graph that mud-rock flow does not occur, the terrain graph that earthquake does not occur, the others such as terrain graph that do not occur that Freshets roar down from the mountains
The image of geological disaster.
Preferably, the environment in the first image and the second image is same or similar.
S204, first image and second image are learnt using AlexNet models, obtains the artificial neural network
Network model；
Specifically, the first image and the second image are input in AlexNet models, wherein preset artificial neural network
Network model is by being configured AlexNet models, i.e., the first layer of AlexNet models and the second layer are convolutional layer, first layer
Can Relu activation primitives be utilized to activate with the second layer, then carry out the ponds pooling again, finally carry out norm normalization.
Wherein, the filter of first layer is 96*11*11, and the filter of step-length 4, the second layer is 256*5*5.Third layer, the 4th layer and
Layer 5 is similarly convolutional layer, carries out Relu activation primitive activation, wherein the filter of third layer is 384*3*3, the 4th layer
Filter is 384*3*3, and the filter of layer 5 is 256*3*3.The ponds pooling, then full articulamentum are first carried out to layer 5
Then output 4096 carries out Relu activation primitive activation, reuses dropout layers, the output result that layer 5 is arranged is two,
Geological disaster occurs or geological disaster does not occur.
Specifically, being sent out to come down as a result, geological disaster such as occurs for output can be set according to actual conditions
Freshets roar down from the mountains for Radix Rehmanniae shake or generation.It can be not come down that geological disaster does not occur, and earthquake does not occur or mountain torrents do not occur
It breaks out.
S205, the image information is compared with the artificial nerve network model of preset target location, determines the mesh
The landform of cursor position is abnormal, and prompts user；
Further, step S205 includes the following steps：
Step 1: the image of the target location is clearly handled, and to treated, image carries out quality evaluation, obtains
To multiple images characteristic value；
Specifically, first, defogging is carried out to the image I (x) of target location to image using following formula, after obtaining defogging
Image J (x).
Wherein, A is global atmosphere light ingredient, and t (x) is transmissivity, t0=0.1.
In practical applications, when the value very little of projection figure t (x), the value of J (x) can be caused bigger than normal, to keep image whole
It is excessive to white field, therefore a threshold value t is set0, when t (x) is less than t0When, enable t (x)=t0。
Secondly, super-resolution rebuilding is carried out to the image after defogging using SRCNN algorithms, obtains clearly image；
Again, quality evaluation is carried out to clearly image using BRISQUE quality evaluations algorithm, obtains image feature value.
Specially：Specification operation is carried out to clearly image, obtains mean value comparison standardization coefficient (Mean Subtracted
Contrast Normalized, MSCN)
Wherein, w={ wk,l| k=-K ..., K, l=-L ... L }, i and the coordinate that j is image, C 1, K=L=3.
Using generalized Gaussian distribution formula, the characteristic value f1-f2 of image is calculated.
Since the product of adjacent pixel MSCN coefficients is distributed difference, to MSCN obtained above, i.e.,Four it is reversed
Product count, wherein level be H, leading diagonal D1, be vertically V, counter-diagonal D2, following formula calculates separately
Obtain 16 values.
Then 16 values are obtained using asymmetric generalized Gaussian distribution formula calculating aforementioned four formula to be calculated
Characteristic value f3~f18.Fuzzy Processing finally is carried out to artwork, carried out that other 18 are calculated in the past according to above-mentioned steps
Feature.
Step 2: image feature value is trained and is classified using SVM algorithm, target image is obtained；
Specifically, 36 features obtained above are trained and are classified using SVM algorithm, obtain target image.Its
In, target image is clearly image.
Step 3: the target image is input in the artificial nerve network model, the landform for obtaining the target location is different
Normal information.
S206, the image information by the target location, determine the coordinate of target group position；
Specifically, after the image information for receiving target location, human face analysis is carried out to target image, determines target group
The coordinate of the position at place.
S207, the flight directive for sending the coordinate comprising the target group position give the unmanned plane device；
S208, when the unmanned plane device flies to position where the target group, send voice messaging or launch and refer to
It enables to the unmanned plane device to play the voice messaging and launch article to the target group.
In practical applications, when unmanned plane device flies the position to where target group, terminal send voice messaging or
It launches instruction and gives unmanned plane device.Wherein, voice messaging is the voice for playing to target group, launches instruction as controlling
The instruction that delivery device in unmanned plane device processed unclamps, so that substance is delivered to target group.
The detection method of a kind of geological disaster provided by the invention, by the image and root that receive the shooting of unmanned plane device
Determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement,
Accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve judgement
Accuracy and efficiency.
Referring to Fig. 3, Fig. 3 is a kind of structural representation of the detection device for geological disaster that third embodiment of the invention provides
Figure, the detection device of geological disaster shown in Fig. 3 include mainly：Sending module 301, receiving module 302 and determining module 303.
The function of each module is described in detail below：
Sending module 301 gives unmanned plane device for sending flight directive.
Flight directive includes the coordinate of target location.
Receiving module 302, for when unmanned plane device flies to target location, receiving the target that unmanned plane device is sent
The image information of position.
Determining module 303, for image information to be compared with the artificial nerve network model of preset target location,
It determines that the landform of target location is abnormal, and prompts user.
Details is not use up in third embodiment of the invention, please refers to the first and second embodiments described in Fig. 1 and Fig. 2,
This is repeated no more.
The detection device of a kind of geological disaster provided by the invention, by the image and root that receive the shooting of unmanned plane device
Determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement,
Accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve judgement
Accuracy and efficiency.
Referring to Fig. 4, Fig. 4 is a kind of structural representation of the detection device for geological disaster that fourth embodiment of the invention provides
Figure, the detection device of geological disaster shown in Fig. 4 include mainly：Sending module 401, determining module 403, obtains receiving module 402
Modulus block 405 and study module 406, wherein determining module 403 includes：Processing module 413, evaluation module 423, sort module
433 and input module 443.The function of each module is described in detail below：
Sending module 401 gives unmanned plane device for sending flight directive.
Flight directive includes the coordinate of target location.
Receiving module 402, for when unmanned plane device flies to target location, receiving the target that unmanned plane device is sent
The image information of position.
Determining module 403, for image information to be compared with the artificial nerve network model of preset target location,
It determines that the landform of target location is abnormal, and prompts user.
Further, which further includes：
Acquisition module 405, for obtaining the first image that geological disaster occurs and the second image that geological disaster does not occur.
Study module 406 is obtained for being learnt to first image and second image using AlexNet models
The artificial nerve network model.
Further, it is determined that module 403 includes：Processing module 413, evaluation module 423, sort module 433 and input mould
Block 443.
Processing module 413, for clearly being handled the image of the target location；
Evaluation module 423 obtains multiple images characteristic value for carrying out quality evaluation to treated image；
Sort module 433 obtains target image for quality assessment value to be trained and classified using SVM algorithm；
Input module 443 obtains target location for target image to be input in the artificial nerve network model
The information of landform exception.
Further,
Determining module 403 is additionally operable to the image information by target location, determines the coordinate of target group position.
Sending module 401, the flight directive for being additionally operable to send the coordinate comprising target group position are filled to unmanned plane
It sets.
Sending module 401 is additionally operable to, when unmanned plane device flies position to where target group, send voice messaging
Or instruction is launched to unmanned plane device to play voice messaging and launch article to the target group.
Details is not use up in fourth embodiment of the invention, please refers to the first and second embodiments described in Fig. 1 and Fig. 2,
This is repeated no more.
The detection device of a kind of geological disaster provided by the invention, by the image and root that receive the shooting of unmanned plane device
Determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement,
Accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve judgement
Accuracy and efficiency.
Referring to Fig. 5, Fig. 5 is a kind of structural representation of the detection system for geological disaster that fifth embodiment of the invention provides
Figure, the detection system of geological disaster shown in fig. 5 include mainly：Control terminal 501, unmanned plane device 502 and with airplane parking area fill
Set 503.The function of each module is described in detail below：
Control terminal 501 is the detection device for the geological disaster that the third and fourth embodiment of the invention provides.
Control terminal 501 realizes the detail of its geological disaster detection method, please refers to Fig. 1 and shown in Fig. 2 first
And second embodiment, details are not described herein.
Unmanned plane device 502, the flight directive for receiving the transmission of control terminal 502, and according to target in flight directive
The image information of the coordinate of position, flight to target location, and acquisition target location, and image information is sent to control eventually
End 502.
Airplane parking area device 503, for receiving the flight directive, and the lid for controlling airplane parking area device 503 is opened, and control
The built-in lifter of system increases, so that unmanned plane device 501 flies out.
Further,
Unmanned plane device 502 is additionally operable to receive the coordinate comprising target group position of the transmission of control terminal 501
Flight directive, and flying the position to where target group according to coordinate, and receive voice messaging that control terminal is sent and
Instruction is launched, and plays phonetic order and launches the article carried according to instruction is launched.
Further, Fig. 6 is please referred to, Fig. 6 shows the structural schematic diagram of airplane parking area device 503, wherein airplane parking area device
503 include control chip, shell 613, lifter 623, support plate 633 and lid 643.
Shell 613 and lid 643 surround closed space, for placing unmanned plane device 502.
Specifically, shell 613 can be package assembly, or integrated formed structure.Shell 613 and lid 643 enclose
At space can be other space structures for placing object such as cube structure, cylindrical structure or rectangular configuration.Shell
Material selected by body can be plastics or metal.
Preferably, the space that shell 613 surrounds is rectangle, size 50cm*40cm*50cm.
Specifically, lid 643 covers the opening of shell 513.
One embodiment of the present of invention, the side of lid 643 and the opening of shell 613 are fixed from one side edge, and lid
The 643 opening one side edges that can surround shell 613 rotate.After receiving flight directive, lid 643 is along fixed side
Unscrew at edge, so that unmanned plane device 502 flies out.
An alternative embodiment of the invention, two edges that the opening of shell 513 is opposite are equipped with sliding rail.Lid 643 wraps
Include two parts, wherein slided respectively along the sliding rail at opening edge at two-part edge.After receiving flight directive, lid
Two parts of body 643 are slided along sliding rail, are opened among it, so that unmanned plane device 502 flies out.
The bottom of lifter 623 and the inside of shell 613 are fixed, the top support plate 533 of lifter 623, support plate 633
For placing unmanned plane device 502.
Specifically, lifter 623 can be telescopic rod, or fold the lifting gear formed by multiple bars.Wherein,
Lifter 623 can be multiple, or one.Preferably, lifter 623 is 2.
Specifically, support plate 533 is placed in the top of lifter, a platform is formed, for placing unmanned plane device 502.
Control chip is connect with lifter 623 and lid 643, the flight directive for receiving control terminal transmission, and is controlled
Lifter 623 processed increases and control lid 643 is opened.
Further, unmanned plane device, including：Control panel, loudspeaker and dispensing control machine.
Control panel is connect with loudspeaker and dispensing control machine respectively, the voice messaging for receiving control terminal transmission and throwing
Put instruction.
Loudspeaker, for playing voice messaging.
Control machine is launched, for being instructed according to dispensing, and launches article.
The detection system of a kind of geological disaster provided by the invention, by the image and root that receive the shooting of unmanned plane device
Determining that the landform of target location is abnormal according to preset artificial nerve network model, one side image clearly can reduce erroneous judgement,
Accuracy rate is improved, on the other hand, can be to avoid loss of learning using artificial nerve network model the problem of, and improve judgement
Accuracy and efficiency.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement etc., should all be included in the protection scope of the present invention made by within refreshing and principle.
Claims (11)
1. a kind of detection method of geological disaster, which is characterized in that the method includes：
It includes the coordinate of target location to send flight directive and give unmanned plane device, the flight directive；
When the unmanned plane device flies to the target location, the figure for the target location that the unmanned plane device is sent is received
Picture；
According to preset artificial nerve network model, determine that the landform of the target location is abnormal, and prompt user.
2. according to the method described in claim 1, it is characterized in that, the artificial neural network according to preset target location
Model before the landform exception for determining the target location, further includes：
Obtain the first image that geological disaster occurs and the second image that geological disaster does not occur；
Described first image and second image are learnt using AlexNet models, obtain the artificial neural network
Model.
3. method according to claim 1 or 2, which is characterized in that it is described according to preset artificial nerve network model, really
The landform of the fixed target location is abnormal, specifically includes：
The image of the target location is clearly handled, and to treated, image carries out quality evaluation, obtains multiple figures
As characteristic value；
Quality assessment value is trained and is classified using SVM algorithm, obtains target image；
The target image is input in the artificial nerve network model, the letter of the landform exception of the target location is obtained
Breath.
4. according to the method described in claim 1, it is characterized in that, described by described image information and preset target location
Artificial nerve network model is compared, and determines that the landform of the target location is abnormal, and after prompting user, further includes：
By the image information of the target location, the coordinate of target group position is determined；
The flight directive of the coordinate comprising the target group position is sent to the unmanned plane device；
When the unmanned plane device flies to position where the target group, sends voice messaging or launch instruction to institute
Unmanned plane device is stated to play the voice messaging and launch article to the target group.
5. a kind of detection device of geological disaster, which is characterized in that described device includes：
Sending module includes the coordinate of target location for sending flight directive to give unmanned plane device, the flight directive；
Receiving module is sent for when the unmanned plane device flies to the target location, receiving the unmanned plane device
Target location image information；
Determining module, for described image information to be compared with the artificial nerve network model of preset target location, really
The landform of the fixed target location is abnormal, and prompts user.
6. device according to claim 5, which is characterized in that described device further includes：
Acquisition module, for obtaining the first image that geological disaster occurs and the second image that geological disaster does not occur；
Study module is obtained described for being learnt to described first image and second image using AlexNet models
Artificial nerve network model.
7. device according to claim 5 or 6, which is characterized in that the determining module includes：
Processing module, for clearly being handled the image of the target location；
Evaluation module obtains multiple images characteristic value for carrying out quality evaluation to treated image；
Sort module obtains target image for quality assessment value to be trained and classified using SVM algorithm；
Input module obtains the target location for the target image to be input in the artificial nerve network model
Landform exception information.
8. device according to claim 5, which is characterized in that
The determining module is additionally operable to the image information by the target location, determines the coordinate of target group position；
The sending module, be additionally operable to send comprising the target group position coordinate flight directive to it is described nobody
Machine device；
The sending module is additionally operable to, when the unmanned plane device flies to position where the target group, send language
Message ceases or launches instruction to the unmanned plane device to play the voice messaging and launch article to the target group.
9. a kind of detection system of geological disaster, which is characterized in that the system comprises：Control terminal, unmanned plane device and stop
Machine level ground device；
The control terminal is the detection device of claim 5~8 any one of them geological disaster；
The unmanned plane device is positioned in the airplane parking area device, the flight directive sent for receiving the control terminal,
And according to the coordinate of target location in the flight directive, flight to the target location, and the acquisition target location
Image information, and described image information is sent to the control terminal；
The airplane parking area device, for receiving the flight directive, and the lid for controlling the airplane parking area device is opened, and control
The built-in lifter of system increases, so that the unmanned plane device flies out.
10. system according to claim 1, which is characterized in that
The unmanned plane device is additionally operable to receive flying for the coordinate comprising target group position of the control terminal transmission
Row instruction, and fly to the position where the target group according to the coordinate, and receive what the control terminal was sent
Voice messaging and dispensing instruct, and play the phonetic order and instruct the article for launching carrying according to described launch.
11. system according to claim 1, which is characterized in that the airplane parking area device includes：Control chip, shell, liter
Device, support plate and lid drop；
The shell and the lid surround closed space, for placing the unmanned plane device；
The bottom of the lifter and the inside of the shell are fixed, and support plate described in the top braces of the lifter is described
Support plate is for placing the unmanned plane device；
The control chip is connect with the lifter and the lid, the flight directive for receiving control terminal transmission, and
It controls the lifter and increases and control lid opening.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711338254.4A CN108318008B (en) | 2017-12-14 | 2017-12-14 | Geological disaster detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711338254.4A CN108318008B (en) | 2017-12-14 | 2017-12-14 | Geological disaster detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108318008A true CN108318008A (en) | 2018-07-24 |
| CN108318008B CN108318008B (en) | 2024-09-20 |
Family
ID=62892657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711338254.4A Active CN108318008B (en) | 2017-12-14 | 2017-12-14 | Geological disaster detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108318008B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824142A (en) * | 2019-11-13 | 2020-02-21 | 杭州鲁尔物联科技有限公司 | Geological disaster prediction method, device and equipment |
| CN111339826A (en) * | 2020-05-06 | 2020-06-26 | 山西大学 | Landslide unmanned aerial vehicle linear sensor network frame detection system |
| CN111964649A (en) * | 2020-08-21 | 2020-11-20 | 武汉原点勘测设计工程有限公司 | Terrain information acquisition method based on unmanned aerial vehicle remote sensing |
| CN112013820A (en) * | 2020-09-04 | 2020-12-01 | 中山大学 | Real-time target detection method and device for deployment of airborne platform of unmanned aerial vehicle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299365A (en) * | 2014-08-06 | 2015-01-21 | 江苏恒创软件有限公司 | Method for monitoring mountain landslide and debris flow in mountainous areas based on unmanned aerial vehicle |
| KR20160072425A (en) * | 2014-12-15 | 2016-06-23 | 주식회사 펀진 | Drone monitoring and control system |
| CN105809679A (en) * | 2016-03-04 | 2016-07-27 | 李云栋 | Mountain railway side slope rockfall detection method based on visual analysis |
-
2017
- 2017-12-14 CN CN201711338254.4A patent/CN108318008B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299365A (en) * | 2014-08-06 | 2015-01-21 | 江苏恒创软件有限公司 | Method for monitoring mountain landslide and debris flow in mountainous areas based on unmanned aerial vehicle |
| KR20160072425A (en) * | 2014-12-15 | 2016-06-23 | 주식회사 펀진 | Drone monitoring and control system |
| CN105809679A (en) * | 2016-03-04 | 2016-07-27 | 李云栋 | Mountain railway side slope rockfall detection method based on visual analysis |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824142A (en) * | 2019-11-13 | 2020-02-21 | 杭州鲁尔物联科技有限公司 | Geological disaster prediction method, device and equipment |
| CN110824142B (en) * | 2019-11-13 | 2022-06-24 | 杭州鲁尔物联科技有限公司 | Geological disaster prediction method, device and equipment |
| CN111339826A (en) * | 2020-05-06 | 2020-06-26 | 山西大学 | Landslide unmanned aerial vehicle linear sensor network frame detection system |
| CN111339826B (en) * | 2020-05-06 | 2023-05-02 | 山西大学 | Landslide unmanned aerial vehicle linear sensor network frame detecting system |
| CN111964649A (en) * | 2020-08-21 | 2020-11-20 | 武汉原点勘测设计工程有限公司 | Terrain information acquisition method based on unmanned aerial vehicle remote sensing |
| CN112013820A (en) * | 2020-09-04 | 2020-12-01 | 中山大学 | Real-time target detection method and device for deployment of airborne platform of unmanned aerial vehicle |
| CN112013820B (en) * | 2020-09-04 | 2022-03-08 | 中山大学 | Real-time target detection method and device for deployment of airborne platform of unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108318008B (en) | 2024-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108318008A (en) | A kind of detection method of geological disaster, device and system | |
| CN104504748B (en) | A kind of infrared 3-D imaging system of unmanned plane oblique photograph and modeling method | |
| CN110097519B (en) | Dual-monitoring image defogging method, system, medium and device based on deep learning | |
| US10210905B2 (en) | Remote controlled object macro and autopilot system | |
| US11125561B2 (en) | Steering assist | |
| US10679511B2 (en) | Collision detection and avoidance | |
| US20190294742A1 (en) | Method and system for simulating visual data | |
| CN205263655U (en) | A system, Unmanned vehicles and ground satellite station for automatic generation panoramic photograph | |
| CN107479368A (en) | A kind of method and system of the training unmanned aerial vehicle (UAV) control model based on artificial intelligence | |
| CN109493300B (en) | Aerial image real-time defogging method based on FPGA (field programmable Gate array) convolutional neural network and unmanned aerial vehicle | |
| US20210009270A1 (en) | Methods and system for composing and capturing images | |
| CN104991562B (en) | The control method and aircraft of a kind of aircraft operating system, aircraft | |
| US11961407B2 (en) | Methods and associated systems for managing 3D flight paths | |
| CN107074347A (en) | Flight control method, system and unmanned vehicle | |
| CN107767443A (en) | A kind of three-dimensional visualization outdoor scene methods of exhibiting based on Unity3D | |
| US20220342428A1 (en) | Unmanned aerial vehicles | |
| CN116597155B (en) | Forest fire spreading prediction method and system based on multi-platform collaborative computing mode | |
| CN113807435A (en) | Remote sensing image characteristic point elevation acquisition method based on multiple sensors | |
| CN205787918U (en) | A kind of detection system of the automatic decision unmanned plane direction of motion | |
| CN114647255A (en) | Unmanned aerial vehicle sphere sensing and capturing device and method | |
| CN107458619A (en) | A kind of rotor Autonomous landing of full-automatic microminiature four and the method and system of charging | |
| CN104133874A (en) | Streetscape image generating method based on true color point cloud | |
| US20230377279A1 (en) | Space and content matching for augmented and mixed reality | |
| Atashgah et al. | Prediction of aerial-image motion blurs due to the flying vehicle dynamics and camera characteristics in a virtual environment | |
| CN112950715B (en) | Visual positioning method and device of unmanned aerial vehicle, computer equipment and storage medium |
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 |