[go: up one dir, main page]

CN114357227B - Onboard flood data processing method, device and system based on aviation emergency mode - Google Patents

Onboard flood data processing method, device and system based on aviation emergency mode Download PDF

Info

Publication number
CN114357227B
CN114357227B CN202111520821.4A CN202111520821A CN114357227B CN 114357227 B CN114357227 B CN 114357227B CN 202111520821 A CN202111520821 A CN 202111520821A CN 114357227 B CN114357227 B CN 114357227B
Authority
CN
China
Prior art keywords
target
image
information
flood
water body
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111520821.4A
Other languages
Chinese (zh)
Other versions
CN114357227A (en
Inventor
李儒�
潘洁
杨宏
胡晶晶
邓飚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aerospace Information Research Institute of CAS
Original Assignee
Aerospace Information Research Institute of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aerospace Information Research Institute of CAS filed Critical Aerospace Information Research Institute of CAS
Priority to CN202111520821.4A priority Critical patent/CN114357227B/en
Publication of CN114357227A publication Critical patent/CN114357227A/en
Application granted granted Critical
Publication of CN114357227B publication Critical patent/CN114357227B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Image Processing (AREA)

Abstract

The invention provides an on-board flood data processing method, device and system based on an aviation emergency mode, wherein the method comprises the steps of performing image mosaic based on an earth observation image to obtain a target image; the method comprises the steps of inputting a target image into a water body recognition model to obtain a water body recognition result, carrying out space analysis based on the water body recognition result and geographic information data to obtain comprehensive flood analysis information, and sending the comprehensive flood analysis information to a remote terminal when an aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, carries out preliminary study and judgment on disaster conditions and guides generation of rescue command decisions. The on-board flood data processing method, device and system based on the aviation emergency mode can achieve on-board real-time and quasi-real-time completion of flood data splicing, correction, information extraction and the like during flight, and after an airplane lands, information is transmitted to a ground command system, so that information processing efficiency and behavior are improved, and corresponding first-aid assistance significance is obvious.

Description

On-board flood data processing method, device and system based on aviation emergency mode
Technical Field
The invention relates to the technical field of aerial remote sensing, in particular to an on-board flood data processing method, device and system based on an aerial emergency mode.
Background
At present, flood disasters are one of main natural disasters, and huge casualties and economic losses are caused each year. For flood emergency rescue work, basic disaster information of a disaster area is mastered firstly, general evaluation of disaster is completed, and necessary guiding information is provided for rescue.
However, during flood, heavy rain or cloudy weather is often accompanied, the optical satellite remote sensing weather limit cannot continuously collect ground image data during rescue, and the microwave remote sensing satellite has certain cloud penetrating and rain penetrating capabilities, but the difficulty of the data processing technology is high. Therefore, aerial remote sensing is carried with various earth observation devices through a flight platform to carry out disaster area information acquisition, and cloud and rain limitation is less or less received, so that the method is certainly one of the optimal information acquisition means under the condition.
In the prior art, an aerial remote sensing flight platform is an unmanned aerial vehicle or an unmanned aerial vehicle, and is used for acquiring disaster area ground image data through flight, and after the aircraft lands, the disaster area image graph is spliced through a traditional photogrammetry method. On the basis, disaster information extraction is carried out. The process from the landing of the aircraft to the splicing of the image map and the extraction of the flood range usually requires more than several hours (influenced by factors such as the flying area, the flying relative height and the like), so that the processing time of remote sensing data is relatively delayed, and in the emergency rescue of large-scale flood disasters, the processing efficiency of the remote sensing data about flood inundation is lower, and the emergency rescue decision cannot be quickly assisted.
Disclosure of Invention
The invention provides an on-board flood data processing method, device and system based on an aviation emergency mode, which are used for solving the defects that in the prior art, the processing efficiency of remote sensing data submerged by flood is low and the situation is not present, realizing the on-board processing of comprehensive flood analysis information, reducing the time difference from data acquisition to data use and ensuring the high efficiency and the high situation of data.
The invention provides an on-board flood data processing method based on an aviation emergency mode, which comprises the following steps:
Based on the earth observation image, performing image mosaic to obtain a target image;
Inputting the target image into a water body recognition model to obtain a water body recognition result;
Based on the water body identification result and the geographic information data, performing spatial analysis to obtain comprehensive flood analysis information;
When an aircraft lands, the comprehensive flood analysis information is sent to a remote terminal, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary judgment on the disaster condition and guides the generation of rescue command decisions;
the ground observation image comprises an observation image shot by the aerial camera carried by the aircraft and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training sample and a predetermined water body label.
According to the on-board flood data processing method based on the aviation emergency mode, after spatial analysis is performed based on the water body identification result and the target thematic geographic data and comprehensive flood analysis information is obtained, the method further comprises the step of sending the comprehensive flood analysis information to a remote terminal in the flight process of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary research and judgment on disaster conditions, and guides generation of rescue command decisions.
According to the on-board flood data processing method based on the aviation emergency mode, the on-board flood data processing method based on the earth observation image is used for performing image mosaic to obtain a target image, and the on-board flood data processing method comprises the following steps:
Extracting a target observation image from the earth observation image based on a target parameter;
And performing image mosaic based on the target observation image to acquire a target image.
According to the on-board flood data processing method based on the aviation emergency mode provided by the invention, the target observation image is extracted from the earth observation image based on target parameters, and the method comprises the following steps:
acquiring the target observation image based on the target parameters, and recording target exposure time;
matching target GPS position information with the target observation image based on the target exposure time;
Wherein the target exposure time is an exposure time of the target observation image.
According to the on-board flood data processing method based on the aviation emergency mode provided by the invention, the image mosaic is carried out based on the target observation image, and the target image is obtained, and the method comprises the following steps:
performing image registration based on the target observation image, and extracting homonymous point pairs;
Based on the homonymy point pairs, carrying out affine transformation by adopting a least square method principle to obtain a spliced image;
And based on the spliced image, adopting a least square method principle to correlate the space geographic information, and generating the target image.
According to the on-board flood data processing method based on the aviation emergency mode provided by the invention, the space analysis is carried out based on the water body identification result and the geographic information data, and the comprehensive flood analysis information is obtained, and the method comprises the following steps:
based on the water body identification result and the target geographic information data, performing spatial analysis to obtain thematic information;
and based on the thematic information, carrying out statistics to obtain comprehensive flood analysis information.
According to the on-board flood data processing method based on the aviation emergency mode provided by the invention, the target image is input into the water body recognition model to obtain the water body recognition result, and the method comprises the following steps:
Acquiring water feature information based on the target image;
based on the water feature information, a water body identification result corresponding to the target image is obtained and output in a vector format.
The invention also provides an on-board data processing device of the aviation remote sensing emergency mode, which comprises:
the image acquisition module is used for performing image mosaic based on the earth observation image to acquire a target image;
the water body identification module is used for inputting the target image into a water body identification model to obtain a water body identification result;
The on-board data generation module is used for carrying out space analysis based on the water body identification result and the geographic information data to obtain comprehensive flood analysis information;
The landing data sending module is used for sending the comprehensive flood analysis information to a remote terminal when the aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study and judgment on the disaster condition and guides the generation of rescue command decisions;
the ground observation image comprises an observation image shot by the aerial camera carried by the aircraft and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training sample and a predetermined water body label.
According to the invention, the on-board flood data processing device based on the aviation emergency mode further comprises:
And the on-board data transmitting module is used for transmitting the comprehensive flood analysis information to a remote terminal in the flight process of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary research and judgment on the disaster condition and guides the generation of rescue command decisions.
The invention also provides an on-board flood data processing system based on the aviation emergency mode, which comprises one or more on-board flood data processing devices based on the aviation emergency mode, a remote terminal and a data processing system, wherein the on-board flood data processing device based on the aviation emergency mode further comprises the remote terminal;
The remote terminal is in communication connection with the floor data transmission module or the on-board data transmission module;
the remote terminal is used for receiving the comprehensive flood analysis information, performing preliminary research and judgment on the disaster condition and guiding generation of rescue command decisions.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the on-board flood data processing method based on the aviation emergency mode when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of an on-board flood data processing method based on aeronautical emergency mode as described in any one of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements the steps of an on-board flood data processing method based on aeronautical emergency mode as described in any one of the above.
According to the on-board flood data processing method, device and system based on the aviation emergency mode, on the basis of collecting ground observation images on a large scale in the air, image mosaic is carried out through a simplified method, a full-frame target image is obtained, a water body recognition result is obtained through recognizing the target image through a simplified water body recognition model, and the comprehensive flood analysis information is obtained through spatial analysis by combining geographic information data, and is sent to a remote terminal when an aircraft lands. The method can realize on-board real-time and quasi-real-time completion of flood data splicing, correction, information extraction and the like during the flight, and after the aircraft lands, the data is transmitted to a ground command system and a first-line rescue unit, so that the information processing efficiency and the situation are improved, and the corresponding emergency rescue significance is obvious.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an on-board flood data processing method based on an aviation emergency mode;
FIG. 2 is one of the sub-flow schematic diagrams of the on-board flood data processing method based on the aviation emergency mode provided by the invention;
FIG. 3 is a second schematic flow chart of an on-board flood data processing method based on an aviation emergency mode according to the present invention;
FIG. 4 is a third schematic sub-flow diagram of the on-board flood data processing method based on the aeronautical emergency mode provided by the invention;
FIG. 5 is a fourth sub-flow diagram of an on-board flood data processing method based on an aeronautical emergency mode provided by the invention;
FIG. 6 is a schematic structural diagram of an on-board flood data processing device based on an aviation emergency mode provided by the invention;
FIG. 7 is a schematic diagram of an on-board flood data processing system based on an aeronautical emergency mode;
Fig. 8 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Fig. 1 is a schematic flow chart of an on-board flood data processing method based on an aviation emergency mode. As shown in FIG. 1, the method for processing the on-board flood data based on the aviation emergency mode provided by the embodiment of the invention comprises the following steps of 101, performing image mosaic based on an earth observation image to obtain a target image.
The ground observation image comprises an observation image shot by a aerial camera mounted on the aircraft and GPS position information corresponding to the observation image.
It should be noted that, the execution main body of the on-board flood data processing method based on the aviation emergency mode provided by the embodiment of the invention is an on-board flood data processing device based on the aviation emergency mode.
The on-board flood data processing device based on the aviation emergency mode is a device arranged on an aircraft. The application scene of the on-board flood data processing device based on the aviation emergency mode is that in disaster relief, certain precision is sacrificed for a certain processing time in order to obtain high-performance information results by completing real-time or quasi-real-time processing of data on-board.
The application scene of the on-board flood data processing device based on the aviation emergency mode in the embodiment of the invention does not influence the work of carrying out aviation remote sensing data production and information extraction according to a normal program.
The type and layout positions of the aerial camera are not particularly limited in the embodiment of the invention, and the aerial camera can be an area array optical instrument, a linear array optical instrument, a spectrum instrument or a radar instrument by way of example.
Preferably, the aerial camera is mounted on a stable aircraft, ensuring that the camera lens is vertically downward, and the geometric correction of the image is achieved in a small amount of time by giving up the correction of the pose of the image, so that the on-board flood data processing device based on the aerial emergency mode only processes deformations caused by differences in resolution (ground object scaling), rotation and translation due to the flight altitude conversion.
Before step 101, an earth observation image acquired by a aerial camera mounted on an aircraft needs to be received.
The ground observation image is an image acquired by monitoring ground conditions by a aerial camera carried by the aerial vehicle after the aerial vehicle takes off, and the position information of a global positioning system (Global Positioning System, GPS) is recorded at the moment of acquiring the image. The earth observation images are used to reflect the ground conditions at various geographic locations of the pathway during the flight of the aircraft.
The number of earth observation images is not particularly limited in the embodiment of the present invention.
The earth-looking image may be all images acquired by the aircraft during flight.
Preferably, the earth observation image may be an image extracted from all the acquired images in accordance with a specified rule.
Specifically, in step 101, the on-board flood data processing device based on the aviation emergency mode composes a data pair from an earth observation image and corresponding GPS position information, and selects an image with uniform brightness and color as a reference image for mosaic, and other images are based on the reference image, so as to perform geometric registration, and all the images to be mosaic are mosaic from near to far under the same space coordinate system, thereby forming a target image.
The target image is a plurality of earth observation images acquired in the advancing process of the aircraft, and the images with larger frames are generated by embedding the images in the overlapped area. The target image comprises earth observation images and corresponding GPS position information, and the target image is used for representing the ground condition of the aircraft path and summary information of the corresponding geographic position.
Step 102, inputting the target image into a water body recognition model to obtain a water body recognition result.
The water body recognition model is obtained after training based on a training sample and a predetermined water body label.
It should be noted that the water body recognition model may be an artificial intelligence model, and the model type is not particularly limited in the embodiment of the present invention.
Preferably, the water body recognition model is a model based on supervised learning, and the model is trained from a training data set, and then test data is predicted.
Wherein, training data is various water sample data, and corresponding water label. Through training, the machine can find the relation between the sample and the label, and the label can be judged when the machine faces the test data.
The supervision algorithms used in embodiments of the present invention include, but are not limited to, linear regression, neural networks, decision trees, support vector machines, k nearest neighbor classification algorithms (k-NearestNeighbo, kNN), and the like.
And the finer the feature division in the supervision algorithm is, the longer the processing time is, and the better the classification effect is.
Preferably, in order to acquire high-performance data, the supervision algorithm is used for completing classification extraction according to huge differences of spectra (spectral reflectance values and curve forms) of the ground object water body and the ground object, and the differences of spatial distribution and textures of the flood water body and other ground objects are combined.
Specifically, in step 102, the on-board flood data processing device based on the aviation emergency mode performs rapid water body recognition on the target image in step 101 through the simplified water body recognition model trained in advance, so that a water body recognition result corresponding to the target image can be obtained.
The water body recognition result may be a probability value or a label result, and the form of the water body recognition result is not particularly limited in the embodiment of the invention.
Optionally, the water body recognition result may be a probability value, and the probability that any pixel point in the target image is a water body or a non-water body is described by the probability value.
Optionally, the water body identification result may be a label result, an intermediate numerical result is obtained through the model, the numerical result meets a preset target condition, and a corresponding label result is allocated to a target user corresponding to the numerical result.
For example, an intermediate numerical result is obtained through a water body recognition model, and is used for representing the probability that a certain pixel point in the target image is a water body. And according to a preset target condition, when the probability is larger than a preset threshold value, producing a label for expressing the pixel point as a water body, and giving the label to the user.
And 103, carrying out space analysis based on the water body identification result and the geographic information data to obtain comprehensive flood analysis information.
Before step 103, the on-board flood data processing device based on the aviation emergency mode needs to obtain the geographic information data of the corresponding location according to the GPS location information included in the target image obtained in step 101.
The geographic information data refers to basic geographic information of a region involved in a target image before the flood disaster is not suffered, and the information can be provided by various information acquisition and monitoring devices distributed densely or by each administrative unit.
The embodiment of the invention does not particularly limit the geographic information data. For example, the geographic information data may be information about roads, residential areas, reservoirs, river channels, mining areas, tailings ponds, factories, mines, or ecological protection areas, etc.
Specifically, in step 103, during the flight process of the aircraft, the on-board flood data processing device based on the aviation emergency mode registers the water body identification result obtained in step 102 with the existing geographic information data, so that the water body identification result is incorporated into a unified space geographic frame, and comprehensive flood analysis information is obtained.
The comprehensive flood analysis information refers to data which correlates a pixel coordinate system where a water body identification result is located with an actual space geographic coordinate system. The comprehensive flood analysis information is used for representing whether a water body exists in a specific actual geographic position, namely whether the water body is submerged by flood.
The embodiment of the present invention is not particularly limited to this process.
Illustratively, during the flight of an aircraft, a target image generated in conjunction with a concatenation of several earth-looking images has only a geographic location corresponding to each earth-looking image, but also spatial geographic information in the conventional sense. Thus, after the water body identification in step 102, only the approximate geographical location of the water body area can be determined, and the location of the flooding occurrence in the target image cannot be specifically located.
Therefore, in step 103, the water body recognition result and the geographic information data of the foundation such as the road, the building or the area are overlapped in the actual geographic coordinate space, and the tiger dune synthesizes flood analysis information, and the comprehensive flood analysis information can represent whether a certain road, a certain building or a certain area is submerged by flood.
The embodiment of the invention does not specifically describe the expression form of the comprehensive flood analysis information.
Alternatively, the integrated flood analysis information may include whether a certain road, a certain building, or a certain area is submerged by a flood, and be stored in a data raw format.
Alternatively, the comprehensive flood analysis information may further extract the area under flood flooding, the partition area, the buffer zone analysis result, and the like according to whether the actual geographic space is flooded or not.
Alternatively, the integrated flood analysis information may be statistical information generated according to whether or not the actual geospatial space is flooded.
For example, the statistical information can be automatically inserted into comprehensive flood analysis information by using a GIS software (geographic information software such as Arcgis) drawing template to complete a view, and the view is automatically inserted into a designed formatted disaster thematic report document (word document template), and the statistical analysis information is also automatically inserted into the report at the same time for quantitative decision.
And 104, when the aircraft lands, sending the comprehensive flood analysis information to the remote terminal, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary judgment on the disaster condition, and guides the generation of rescue command decisions.
Specifically, in step 104, after the processing of the integrated flood analysis information is completed on-board in step 103, when the aircraft lands, the on-board flood data processing apparatus based on the aviation emergency mode transmits the integrated flood analysis information to the remote terminal through the wireless communication technology.
Among other wireless communication technologies, but not limited to, WIFI wireless cellular signals (2G, 3G, 4G, 5G).
In the prior art, an aerial remote sensing is utilized to observe the disaster condition of a flood disaster in a certain area, an aerial camera is generally carried by an aircraft, the aircraft drives from a starting point to an end point, image data is collected, and after returning to the ground, the collected image data is transmitted to a remote terminal, so that the remote terminal can further process and analyze the original image data. Because the aircraft is required to travel and consume time, the data processed by the remote terminal only retain disaster information at the moment of image acquisition, but because the disaster is changeable instantaneously, the time interval between the moment of image acquisition and the moment of data landing processing is larger, the guiding effect of the disaster information at the moment of image acquisition on the disaster information at the current moment is probably not real-time and reliable, and the situation of the information is lower.
In the embodiment of the invention, in the process of turning back the aircraft, the on-board flood data processing device based on the aviation emergency mode processes and analyzes the original image data on the aircraft and uploads the processed image data to the remote terminal after landing, the time interval between the image acquisition time and the data processing time is smaller, and the remote terminal can directly conduct disaster rescue guidance according to the processed data after landing, so that the information has higher situation.
The embodiment of the invention acquires the ground observation image on the ground in a large scale on the basis of the air, performs image mosaic through a simplified method, acquires a full-frame target image, acquires a water body identification result through identifying the target image through a simplified water body identification model, performs spatial analysis by combining geographic information data to acquire comprehensive flood analysis information, and transmits the comprehensive flood analysis information to a remote terminal when an aircraft lands. The method can realize on-board real-time and quasi-real-time completion of flood data splicing, correction, information extraction and the like during the flight, and after the aircraft lands, the data is transmitted to a ground command system and a first-line rescue unit, so that the information processing efficiency and the situation are improved, and the corresponding emergency rescue significance is obvious.
On the basis of any embodiment, after the space analysis is performed based on the water body identification result and the target thematic geographic data to obtain the comprehensive flood analysis information, the method further comprises the step of sending the comprehensive flood analysis information to a remote terminal in the flight process of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary research and judgment on the disaster condition, and guides the generation of rescue command decisions.
Specifically, after step 103, when the aircraft is in flight, the on-board flood data processing device based on the aviation emergency mode transmits the integrated flood analysis information to the remote terminal through the wireless communication technology.
Among other wireless communication technologies, but not limited to, WIFI wireless cellular signals (2G, 3G, 4G, 5G), or instant messaging applications (e.g., mailboxes).
The embodiment of the invention acquires the ground observation image on the ground in a large scale on the air, performs image mosaic through a simplified method, acquires a full-frame target image, acquires a water body identification result through identifying the target image through a simplified water body identification model, performs spatial analysis by combining geographic information data to acquire comprehensive flood analysis information, and transmits the comprehensive flood analysis information to a remote terminal in the flight process of an aircraft. After the splicing, correction and information extraction of the data can be completed in real time and quasi-real time on the aircraft during the flight, the data is directly transmitted to a ground command system and a first-line rescue unit, the information processing efficiency and the behavior are improved, and the corresponding first-aid rescue significance is obvious.
On the basis of any embodiment, the image mosaic is performed based on the earth observation image, and the target image is acquired, wherein the target observation image is extracted from the earth observation image based on the target parameter.
The earth observation image is usually exposed and recorded according to time timing, or exposed and recorded according to distance fixed point, and finally the image position (usually the image center point position) is obtained by matching the exposure time with the on-board GPS data.
In normal production, a large proportion of overlapping degree (heading and sideways) is required to be set in order to ensure mapping accuracy of the image products, which leads to large overlapping of images, but correspondingly leads to large improvement of data volume. In the embodiment of the invention, the data volume needs to be reduced to sacrifice a certain observation precision and exchange the time of data processing
The target parameter is a parameter corresponding to a boundary condition of the extraction rule formed by taking the degree of overlap between the images as a guide.
The embodiment of the invention does not specifically limit the overlapping degree between the images.
Preferably, the degree of overlap between images is set to 5%. The target parameters corresponding thereto include, but are not limited to, one or more of exposure mode, flight speed, overlap, and weather conditions.
Specifically, in step 101, the on-board flood data processing device based on the aviation emergency mode extracts a plurality of target observation images from the earth observation images according to setting different target parameters, so that the overlap graph between the target observation images is 5%.
The acquisition of the target observation image is not particularly limited in the embodiment of the present invention.
Optionally, by programming, accessing a aerial camera storage unit, and extracting the obtained original earth observation image from the storage at intervals according to the designed exposure mode, the flying speed, the overlapping degree and the meteorological condition.
At this time, the image is the original spatial resolution data, the splicing effect is best, but the corresponding data size is larger, and the processing speed is slower.
Optionally, by programming, accessing a aerial camera operation management system or a memory, and extracting thumbnail images of the ground observation images from the memory at intervals according to the design exposure mode, the flying speed, the overlapping degree and the meteorological conditions.
The image thumbnail is a reduced resolution version of the original image, which is the same as the coverage area of the original image, but has low image spatial resolution and small data volume. The use of both methods depends on the level of on-board computer capability and the urgency of the disaster.
And performing image mosaic based on the target observation image to acquire a target image.
Specifically, the on-board flood data processing device based on the aviation emergency mode selects an image with relatively uniform brightness and color from the target observation images as a reference image, and registers and geometrically corrects the rest of the target observation images so as to inlay the overlapping part of the rest of the target observation images. A target image is acquired.
The embodiment of the invention extracts the target observation image from the earth observation image based on the target parameters, and performs image mosaic by a simplified method to obtain the full-frame target image. The method can realize on-board real-time and quasi-real-time data splicing, correction and information extraction during flight. And after the aircraft lands, data are transmitted to a ground command system and a first-line rescue unit, so that the information processing efficiency and the situation are improved, and the corresponding first-aid rescue significance is obvious.
On the basis of any of the above embodiments, extracting the target observation image from the earth observation image based on the target parameter includes acquiring the target observation image based on the target parameter, and recording a target exposure time.
Wherein the target exposure time is the exposure time of the target observation image.
Specifically, the comprehensive flood analysis information processing device based on the aerial remote sensing sets target parameters such as an exposure mode, a flight speed, overlapping degree, meteorological conditions and the like, and records target exposure time while extracting a target observation image.
The target exposure time refers to exposure time corresponding to the target observation image. The number of data of the target exposure time is equal to the number of target observation images.
And matching the target GPS position information with the target observation image based on the target exposure time.
Specifically, the on-board flood data processing device based on the aviation emergency mode calls GPS records of the aircraft according to the target exposure time to obtain target GPS position information, and takes the target GPS position information as position information corresponding to an exposure center point of a target observation image through the target exposure time, namely, each target observation image and the target GPS position information form a data pair.
The embodiment of the invention does not specifically limit the target GPS position information.
Alternatively, the target GPS location information may be a rough coordinate location obtained directly from an aircraft-onboard GPS device based on an airborne flood data processing device in an aeronautical emergency mode.
Alternatively, the target GPS location information may be a differential calculated fine coordinate location of the coarse coordinate location with ground base station observations or fine ephemeris.
The embodiment of the present invention is not particularly limited to this process.
Fig. 2 is an illustration of a sub-flow diagram of an on-board flood data processing method based on an aviation emergency mode according to the present invention. As shown in fig. 2, a specific embodiment of acquiring the observation image of the target is given below:
step 201, extracting a target observation image or a thumbnail of the target observation image according to the capability level and the disaster urgency of the onboard computer.
Step 202, extracting and matching target GPS position information.
And 203, forming a data pair by the target observation image and the target GPS position through the target exposure time, and completing the extraction of the optical aerial camera image.
The embodiment of the invention records the target exposure time while extracting the target observation image based on the target parameters, and correlates the target GPS position information with the target observation image through the target exposure time. The method can reduce the overlapping area between the images and improve the image processing efficiency under the condition of meeting certain precision. Furthermore, the information processing efficiency and the behavior are improved, and the significance of corresponding emergency assistance is obvious.
On the basis of any embodiment, the image mosaic is performed based on the target observation image, and the target image is acquired, wherein the image registration is performed based on the target observation image, and homonymous point pairs are extracted.
Specifically, the on-board flood data processing device based on the aviation emergency mode extracts homonymous feature points in an overlapping area of a target observation image serving as a reference image and each target observation image to be inlaid.
The method for extracting the homonymous feature points is not particularly limited in the embodiment of the invention.
Preferably, a splicing method based on a Harris angle point detector is adopted to extract homonymous point pairs, and the basic principle is as follows:
a local window is provided in the image to be detected, the intensity being changed by changing a small amount in the different directional windows.
E(u,v)=∑iw(xi,yi)[I(xi+u,yi+v)-I(xi,yi)]
Where w (x i,yi) is the window function of the detection window (x i,yi). I (x i,yi) is the image intensity value at position (x i,yi), and I (x i+u,yi +v) is the displacement intensity to (u, v). Local texture surrounding pixels (local texture around pixel), (x i,yi) can be represented as the following autocorrelation matrix:
wherein, AndThe gradient of I (x i,yi) in the x direction and the gradient of I (x i,yi) in the y direction are respectively, and the maximum eigenvalue corresponding to the two matrices C corresponds to one corner point. To make the algorithm stronger, the edge points can be eliminated with an R value of "cornerness":
R=Det(C)-αTr2(C)
Wherein Tr (C) is a tracking function of C, and alpha is in the range of 0.04-0.06. If the local maximum of R is higher than the threshold T, then this point is the corner point. After all the corner points of the two pictures are detected, the corresponding relation can be determined by a normalized cross Correlation (Normalization Cross-Correlation, NCC) method or an error square sum algorithm (Sum of Squared Differences, SSD) method.
Based on the homonymy point pair, affine transformation is carried out by adopting a least square method principle, and a spliced image is obtained.
Specifically, the on-board flood data processing device based on the aviation emergency mode solves affine transformation parameters through homonymous point pairs, and unifies target observation images to be inlaid into a global reference system by utilizing geometrical correspondence corresponding to the affine transformation parameters to obtain spliced images.
The spliced image refers to an image spliced by means of the characteristics of the image, and does not have space geographic information in the conventional sense.
The method for acquiring the spliced image is not particularly limited in the embodiment of the invention.
Preferably, affine transformation is performed by using a least square method principle, and a spliced image is obtained. The specific process is as follows:
affine transformation (Affine Transformation) refers to the process of transforming into another vector space by performing a linear transformation (multiplying by a matrix) and a translation (adding a vector) in the vector space.
Affine transformations represent the mapping relationship between two graphs, and can be expressed as:
The affine transformation matrix M is a 2*3 matrix, the matrix B plays a role of translation, and the diagonal line in the matrix A determines scaling, and the opposite diagonal line determines rotation or miscut.
The original pixel point coordinates (x, y), the coordinates of the point after affine transformation are T, so affine transformation is a linear transformation from two-dimensional coordinates (x, y) to two-dimensional coordinates (u, v), and the mathematical expression is as follows:
A and B in the equation are needed to be solved through the point pair with the same name, and the basic flow is as follows:
(1) Taking the input first image as a reference as an example, the selection of the same-name characteristic point pair with the adjacent image is completed.
(2) And solving affine transformation parameters A and B by using a least square method through a large number of homonymy feature point pairs.
(3) Affine transformation of the images to be spliced is carried out through the solved parameters.
(4) And splicing the converted image with the reference image.
Based on the spliced image, the space geographic information is related by adopting a least square method principle, and a target image is generated.
Specifically, the on-board flood data processing device based on the aviation emergency mode correlates the spliced image with the existing space geographic information, and outputs the spliced image which is incorporated into the unified space geographic frame as a target image.
The method for acquiring the target image according to the embodiment of the invention is not particularly limited.
Preferably, the central point of each target observation image participating in stitching is used as a ground control point (Ground Control Point, GCP), correction equation parameter calculation is completed through the associated target GPS position information by using a least square method, and then stitching image correction is completed, and the target images are acquired by incorporating the unified space geographic frame.
The embodiment of the present invention is not particularly limited to this process.
Fig. 3 is a schematic diagram illustrating a second sub-flow of the on-board flood data processing method based on the aviation emergency mode according to the present invention. As shown in fig. 3, a specific embodiment of acquiring the observation image of the target is given below:
and 301, performing image registration on the target observation image, and extracting homonymous point pairs.
Step 302, calculating affine transformation parameters.
Step 303, affine transformation is carried out on the image to be registered.
And 304, acquiring a spliced image.
Step 305, adding geospatial information encoding to the stitched image.
And 306, completing image mosaic.
According to the embodiment of the invention, the homonymy point pairs are extracted based on the target observation image with the fixed gesture, the spliced image is obtained by utilizing the homonymy point pairs through the least square method, and the target image is obtained by correlating the space geographic information through the least square method. The method can sacrifice a certain geometric precision, reduces the matching operation of the homonymous feature point pairs, saves the matching time of the homonymous feature point pairs on one hand, and avoids the difficult matching of the homonymous feature point pairs on the other hand, thereby being an effective compromise of precision and efficiency. Furthermore, the information processing efficiency and the behavior are improved, and the significance of corresponding emergency assistance is obvious.
Based on any one of the embodiments, spatial analysis is performed based on the water body identification result and the geographic information data to obtain comprehensive flood analysis information, including spatial analysis is performed based on the water body identification result and the target geographic information data to obtain thematic information.
The target geographic information data refers to data having directivity obtained by classifying the geographic information data according to the rescue task requirements.
The target geographic information data may be, for example, geographic data related to one or more of a roadway, a residential site, a reservoir, a river channel, a mine site, a tailings pond, a plant mine, and an ecologically protected area.
Specifically, in step 103, during the flight of the aircraft, the on-board flood data processing device based on the aviation emergency mode determines the water body identification result obtained in step 102 according to the current situation and the attention of the regional key target space distribution, registers the water body identification result with the existing target geographic information data, brings the water body identification result into a unified space geographic frame, and obtains thematic information corresponding to the target geographic information data.
The thematic information refers to data which correlates a pixel coordinate system where a water body identification result is located with an actual target geographic coordinate system. The thematic information is used for representing whether a water body exists in an actual geographic position corresponding to the thematic information, namely whether the water body is submerged by flood. The embodiment of the invention does not limit the thematic information in detail.
Optionally, if the target geographic information data is the geographic data related to the road, the corresponding thematic information is the road damage condition or availability information, so that whether the road is submerged by flood can be known, and the rescue road planning, the rescue repair and the like can be guided.
Optionally, if the target geographic information data is the relevant geographic data of the residential area, the corresponding thematic information is the disaster information of the residential area, so that the configuration of rescue force can be guided, and the like.
Optionally, if the target geographic information data is the reservoir and the river channel related geographic data, the corresponding thematic information is river channel and surrounding disaster information, so that hidden danger river levee investigation, disaster development simulation and disaster rescue scheduling can be guided.
Optionally, if the target geographic information data is related geographic data of a mining area, a tailing pond and factories and mines, the corresponding thematic information is the current situation of flooding of the tailing pond of the mining area, so that current situation investigation and secondary disaster occurrence development trend simulation can be guided.
And based on the thematic information, carrying out statistics to obtain comprehensive flood analysis information.
Specifically, the on-board flood data processing device based on the aviation emergency mode performs basic operations such as merging (Union), crossing (intersectional), identifying (Identity), deleting (Erase), updating (Update), clipping (Clip) and the like on the thematic information so as to complete spatial position, spatial distribution, spatial form, spatial distance, topological relation analysis and count comprehensive flood analysis information.
It can be understood that the comprehensive flood analysis information comprises the emphasis points of different topics, the corresponding area under flood inundation, subarea area, buffer area analysis results and the like.
The embodiment of the present invention is not particularly limited to this process.
Fig. 4 is a third schematic drawing of a sub-flow of the on-board flood data processing method based on the aviation emergency mode according to the present invention. As shown in fig. 3, a specific embodiment for acquiring the integrated flood analysis information is given below:
And 401, performing GIS (geographic information) space analysis according to the water body identification result and the target geographic information data to acquire thematic information.
And step 402, counting the analyzed thematic information to obtain comprehensive flood analysis information.
Step 403, according to the comprehensive flood analysis information, a regional disaster distribution and degree thematic map is produced, and necessary guiding information (such as road access information, disaster light and heavy degree grading information and the like) is provided for rescue.
The embodiment of the invention performs space analysis based on the water body identification result and the target geographic information data, extracts various thematic information quantitatively, and completes the establishment of comprehensive flood analysis information through statistics. Under the condition of ensuring certain precision, the deep processing capability expansion of the data can be completed in real time and quasi-real time on the machine, the data is directly transmitted to a ground command system and a first-line rescue unit, the high-performance data is rapidly converted into high-performance information, the information processing efficiency and the performance are improved, and the corresponding first-aid rescue significance is obvious.
On the basis of any embodiment, inputting the target image into the water body recognition model to acquire a water body recognition result comprises acquiring water body characteristic information based on the target image.
Specifically, in step 102, the on-board flood data processing device based on the aviation emergency mode inputs the target image generated in step 101 to a water body recognition model, performs feature extraction, and acquires water body feature information.
The process of feature extraction in the embodiment of the invention is not particularly limited.
Preferably, the spectral angle may be extracted as the water body characteristic information in consideration of the distinguishing and identifying efficiency of the characteristics.
Based on the water feature information, a water body identification result corresponding to the target image is obtained and output in a vector format.
Specifically, the on-board flood data processing device based on the aviation emergency mode performs target recognition and classification on the extracted features, completes extraction of a water body recognition result, and outputs a water body and non-water body bisection result.
For example, in identifying (classifying) a body of water, the simplest spectral angle or cross-correlation coefficient may be used to quickly determine if the pixel to be classified is consistent with or close to the body of water (sample) by comparison to a threshold below which it is determined to be a body of water, otherwise it is not.
The embodiment of the invention does not limit the output format of the water body identification result in particular.
Preferably, the on-board flood data processing device based on the aviation emergency mode converts the two-differentiated raster data (only two values are selectable for each pixel, such as non-0 or 1) into vector data through a vectorization method.
In step 103, the water body recognition result vector file containing the dotted line and the plane marks is superimposed with the real space geographic information for analysis, so that the water body recognition result vector file is used for positioning and navigation during ground rescue.
The embodiment of the present invention is not particularly limited to this process.
Fig. 5 is a schematic diagram showing a sub-flow of an on-board flood data processing method based on an aviation emergency mode according to the present invention. As shown in fig. 5, a specific embodiment for obtaining the water body identification result is given below:
Step 501, acquiring a target image to be subjected to water body identification.
Step 502, extracting spectral features of a target image.
Step 503, based on the spectral features of the target image, performing rapid identification and classification
Step 504, generating a grid-format classification result.
Step 505, format conversion is performed on the result of step 504, and a vector format classification result is generated.
According to the embodiment of the invention, the water body characteristic information of the target image is extracted according to the ground characteristics after the flood disaster occurs, and the water body identification result is quickly obtained by combining classification with target identification and is output in a vector format. Under the condition of ensuring certain precision, the algorithm complexity is reduced to reduce the processing time consumption, the data volume of the vectorized water body identification result is smaller, the information processing efficiency is improved to a certain extent, the situation is high, and the corresponding emergency rescue significance is obvious.
Fig. 6 is a schematic structural diagram of an on-board flood data processing device based on an aviation emergency mode. On the basis of any of the above embodiments, as shown in fig. 6, the apparatus includes an image acquisition module 610, a water body identification module 620, an on-board data generation module 630, and a floor data transmission module 640, wherein:
The image acquisition module 610 is configured to perform image mosaicing based on the earth observation image to acquire a target image.
The water body recognition module 620 is configured to input the target image into the water body recognition model, and obtain a water body recognition result.
The on-board data generating module 630 is configured to perform spatial analysis based on the water body identification result and the geographic information data, and obtain comprehensive flood analysis information.
And the landing data sending module 640 is used for sending the comprehensive flood analysis information to the remote terminal when the aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study and judgment on the disaster condition, and guides the generation of rescue command decisions.
The ground observation image comprises an observation image shot by an aerial camera carried by the aircraft and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training sample and a predetermined water body label.
Specifically, the image acquisition module 610, the water body identification module 620, the on-board data generation module 630, and the floor data transmission module 640 are electrically connected in sequence.
The image acquisition module 610 composes the earth observation image and the corresponding GPS position information into a data pair, and selects an image with uniform brightness and color as a reference image for mosaic, and the other images are based on the reference image, so as to perform geometric registration, and mosaic all the images to be mosaic from near to far under the same space coordinate system to form a target image.
The water body recognition module 620 performs rapid water body recognition on the target image in the image acquisition module 610 through the simplified water body recognition model trained in advance, and can obtain a water body recognition result corresponding to the target image.
The water body recognition result may be a probability value or a label result, and the form of the water body recognition result is not particularly limited in the embodiment of the invention.
The onboard data generating module 630 registers the water body recognition result obtained in the water body recognition module 620 with the existing geographic information data in the flight process of the aircraft, so that the water body recognition result is incorporated into a unified space geographic frame, and comprehensive flood analysis information is obtained.
The comprehensive flood analysis information refers to data which correlates a pixel coordinate system where a water body identification result is located with an actual space geographic coordinate system. The comprehensive flood analysis information is used for representing whether a water body exists in a specific actual geographic position, namely whether the water body is submerged by flood.
The landing data transmission module 640 transmits the integrated flood analysis information to the remote terminal through a wireless communication technology when the aircraft lands.
Among other wireless communication technologies, but not limited to, WIFI wireless cellular signals (2G, 3G, 4G, 5G).
Optionally, the device further comprises an on-board data transmission module, wherein:
And the on-board data transmitting module is used for transmitting the comprehensive flood analysis information to the remote terminal in the flight process of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study and judgment on the disaster condition and guides the generation of rescue command decisions.
Optionally, the image acquisition module 610 includes a decimation unit and a mosaic unit, wherein:
and an extraction unit for extracting a target observation image from the earth observation image based on the target parameter.
And the mosaic unit is used for performing image mosaic based on the target observation image to acquire a target image.
Optionally, the extracting unit includes a recording time subunit and a matching subunit, wherein:
and the recording time subunit is used for acquiring a target observation image based on the target parameter and recording the target exposure time.
And the matching subunit is used for matching the target GPS position information with the target observation image based on the target exposure time.
Wherein the target exposure time is the exposure time of the target observation image.
Optionally, the mosaic unit comprises a registration subunit, an affine subunit, and an association subunit, wherein:
and the registration subunit is used for carrying out image registration based on the target observation image and extracting homonymy point pairs.
And the affine subunit is used for carrying out affine transformation by adopting a least square method based on the homonymy point pairs to obtain a spliced image.
And the association subunit is used for generating a target image by associating the space geographic information based on the spliced image and adopting a least square method principle.
Optionally, the on-board data generating module 630 includes a thematic information acquiring unit and a statistics unit, where:
The thematic information acquisition unit is used for carrying out spatial analysis based on the water body identification result and the target geographic information data to acquire thematic information.
And the statistics unit is used for carrying out statistics based on the thematic information to obtain comprehensive flood analysis information.
Optionally, the water body recognition module 620 includes a feature extraction unit and a recognition unit, wherein:
and the feature extraction unit is used for acquiring the water feature information based on the target image.
And the recognition unit is used for obtaining a water body recognition result corresponding to the target image based on the water body characteristic information and outputting the water body recognition result in a vector format.
The on-board flood data processing device based on the aviation emergency mode provided by the embodiment of the invention is used for executing the on-board flood data processing method based on the aviation emergency mode, the implementation mode of the on-board flood data processing device based on the aviation emergency mode is consistent with the implementation mode of the on-board flood data processing method based on the aviation emergency mode provided by the invention, the same beneficial effects can be achieved, and the detailed description is omitted.
The embodiment of the invention acquires the ground observation image on the ground in a large scale on the basis of the air, performs image mosaic through a simplified method, acquires a full-frame target image, acquires a water body identification result through identifying the target image through a simplified water body identification model, performs spatial analysis by combining geographic information data to acquire comprehensive flood analysis information, and transmits the comprehensive flood analysis information to a remote terminal when an aircraft lands. The method can realize on-board real-time and quasi-real-time completion of flood data splicing, correction, information extraction and the like during the flight, and after the aircraft lands, the data is transmitted to a ground command system and a first-line rescue unit, so that the information processing efficiency and the situation are improved, and the corresponding emergency rescue significance is obvious.
On the basis of any embodiment, the device further comprises an on-board data sending module, wherein:
And the on-board data transmitting module is used for transmitting the comprehensive flood analysis information to the remote terminal in the flight process of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study and judgment on the disaster condition and guides the generation of rescue command decisions.
Specifically, the on-board data transmitting module transmits the comprehensive flood analysis information to the remote terminal through a wireless communication technology in the flight process of the aircraft.
Among other wireless communication technologies, but not limited to, WIFI wireless cellular signals (2G, 3G, 4G, 5G), or instant messaging applications (e.g., mailboxes).
The embodiment of the invention acquires the ground observation image on the ground in a large scale on the air, performs image mosaic through a simplified method, acquires a full-frame target image, acquires a water body identification result through identifying the target image through a simplified water body identification model, performs spatial analysis by combining geographic information data to acquire comprehensive flood analysis information, and transmits the comprehensive flood analysis information to a remote terminal in the flight process of an aircraft. After the splicing, correction and information extraction of the data can be completed in real time and quasi-real time on the aircraft during the flight, the data is directly transmitted to a ground command system and a first-line rescue unit, the information processing efficiency and the behavior are improved, and the corresponding first-aid rescue significance is obvious.
Fig. 7 is a schematic structural diagram of an on-board flood data processing system based on an aviation emergency mode. On the basis of any of the above embodiments, as shown in fig. 7, the system comprises one or more on-board flood data processing devices 710 based on aviation emergency mode, and further comprises a remote terminal 720.
The remote terminal is in communication connection with the floor data transmission module or the on-board data transmission module.
It should be noted that, the ground command system may be generated around the remote terminal 720, so that the ground command system may manage and collect the data of the on-board flood data processing device 710 based on the aviation emergency mode, and may command the disaster rescue in all directions.
Specifically, each of the on-board flood data processing devices 710 based on the aeronautical emergency mode establishes a corresponding wireless communication connection with the remote terminal 720 according to the settings of the transceiver devices on the aircraft.
Alternatively, when no satellite communication system is provided on the aircraft, communication may be directly with the remote terminal 720 via the floor data transmission module. The communication manner may be wireless communication technology (Wi-Fi), bluetooth, serial port, etc., which is not particularly limited in the embodiments of the present invention.
Alternatively, when a satellite communication system is provided on the aircraft, communication may be directly with the remote terminal 720 via an onboard data transmission module. The communication mode may be wireless communication technology (Wi-Fi), instant messaging software, etc., which is not particularly limited in the embodiments of the present invention.
The remote terminal 720 is used for receiving the comprehensive flood analysis information, performing preliminary study and judgment on the disaster condition, and guiding the generation of rescue command decisions.
Specifically, the remote terminal 720 receives the comprehensive flood analysis information sent by each on-board flood data processing device 710 based on the aviation emergency mode, and performs a first-stage study and judgment on the flood disaster situation at the corresponding moment according to the comprehensive flood analysis information, and gives a rescue command scheme for coping with the disaster.
The processing procedure of the remote terminal 720 is not particularly limited in the embodiment of the present invention.
Optionally, after receiving the comprehensive flood analysis information, the remote terminal 720 displays the comprehensive flood analysis information, and the user of the remote terminal 720 performs subjective analysis on the disaster situation and formulates a corresponding rescue scheme.
Optionally, after receiving the comprehensive flood analysis information, the remote terminal 720 executes a corresponding processing algorithm to objectively analyze the disaster situation and formulates a corresponding rescue scheme, so that a user of the remote terminal 720 can select or optimize the scheme. It can be appreciated that the time of generation of the integrated flood analysis information can be adjusted based on the amount of data and the information acquisition urgency conditions. The sequence of data processing and flight data acquisition can be adjusted through program control, and the comprehensive flood analysis information can be adjusted to be in a dynamic update state as well, but the dynamic update interval can be slightly larger, such as an hour interval, in consideration of actual use.
The embodiment of the invention acquires the ground observation image on the ground in a large scale on the basis of the air, performs image mosaic through a simplified method, acquires a full-frame target image, acquires a water body identification result through identifying the target image through a simplified water body identification model, performs spatial analysis by combining geographic information data to acquire comprehensive flood analysis information, and transmits the comprehensive flood analysis information to a remote terminal when an aircraft lands. The method can realize on-board real-time and quasi-real-time completion of flood data splicing, correction, information extraction and the like during the flight, and after the aircraft lands, the data is transmitted to a ground command system and a first-line rescue unit, so that the information processing efficiency and the situation are improved, and the corresponding emergency rescue significance is obvious.
Fig. 8 illustrates a physical schematic diagram of an electronic device, which may include a processor 810, a communication interface (Communications Interface) 820, a memory 830, and a communication bus 840, as shown in fig. 8, where the processor 810, the communication interface 820, and the memory 830 perform communication with each other via the communication bus 840. The processor 810 may invoke logic instructions in the memory 830 to perform an on-board flood data processing method based on an aviation emergency mode, the method comprising performing image mosaicing based on an earth observation image, acquiring a target image, inputting the target image into a water body recognition model, acquiring a water body recognition result, performing spatial analysis based on the water body recognition result and geographic information data, acquiring comprehensive flood analysis information, and transmitting the comprehensive flood analysis information to a remote terminal when an aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary research and judgment on a disaster condition, and guides generation of rescue command decisions, wherein the earth observation image comprises an observation image shot by an aerial camera carried by the aircraft, and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training sample and a predetermined water body label.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In another aspect, the invention further provides a computer program product, the computer program product comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer program can execute the on-board flood data processing method based on the aviation emergency mode, which is provided by the method, the method comprises the steps of performing image mosaic based on an earth observation image, obtaining a target image, inputting the target image into a water body recognition model, obtaining a water body recognition result, performing space analysis based on the water body recognition result and geographic information data, obtaining comprehensive flood analysis information, and when an aircraft lands on the ground, sending the comprehensive flood analysis information to a remote terminal, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study on the disaster condition, and guides to generate rescue command decisions, wherein the earth observation image comprises an observation image shot by an aerial camera carried by the aircraft, and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training and a pre-determined water body sample.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program being implemented when executed by a processor to perform the method for processing on-board flood data based on an aeronautical emergency mode provided by the above methods, the method comprising performing image mosaicing based on an earth observation image, acquiring a target image, inputting the target image into a water body recognition model, acquiring a water body recognition result, performing spatial analysis based on the water body recognition result and geographic information data, acquiring comprehensive flood analysis information, and transmitting the comprehensive flood analysis information to a remote terminal when an aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, performs preliminary study on a disaster condition, and guides generation of a rescue command decision, wherein the earth observation image includes an observation image captured by an aerial camera carried by the aircraft, and GPS position information corresponding to the observation image, and the water body recognition model is obtained after training based on a training sample and a predetermined water body tag.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.

Claims (9)

1.一种基于航空应急模式的机上洪水数据处理方法,其特征在于,包括:1. A method for processing flood data on board an aircraft based on an aviation emergency mode, characterized by comprising: 基于目标参数,从对地观测图像中抽取目标观测图像,并记录目标曝光时间;基于所述目标曝光时间,将目标GPS位置信息与所述目标观测图像进行匹配;其中,所述目标曝光时间是所述目标观测图像的曝光时间;基于所述目标观测图像,进行图像配准,提取同名点对;基于所述同名点对,采用最小二乘法原理进行仿射变换,获取拼接图像;基于所述拼接图像,采用最小二乘法原理关联空间地理信息,生成目标图像;Based on the target parameters, extract the target observation image from the ground observation image and record the target exposure time; based on the target exposure time, match the target GPS location information with the target observation image; wherein the target exposure time is the exposure time of the target observation image; based on the target observation image, perform image registration and extract the same-name point pairs; based on the same-name point pairs, use the least squares principle to perform affine transformation to obtain a spliced image; based on the spliced image, use the least squares principle to associate spatial geographic information to generate a target image; 将所述目标图像输入至水体识别模型中,获取水体识别结果;Inputting the target image into a water body recognition model to obtain a water body recognition result; 基于所述水体识别结果和目标地理信息数据,进行空间分析,获取专题信息;基于所述专题信息,进行统计,获取综合洪水分析信息;Based on the water body identification results and the target geographic information data, spatial analysis is performed to obtain thematic information; based on the thematic information, statistics are performed to obtain comprehensive flood analysis information; 在飞行器落地时,将所述综合洪水分析信息发送至远程终端,以使得所述远程终端接收所述综合洪水分析信息,对灾情进行初步研判,并指导生成救援指挥决策;When the aircraft lands, the comprehensive flood analysis information is sent to a remote terminal, so that the remote terminal receives the comprehensive flood analysis information, makes a preliminary assessment of the disaster situation, and guides the generation of rescue command decisions; 其中,所述对地观测图像包括所述飞行器搭载的航摄仪拍摄的观测图像,以及与所述观测图像对应的GPS位置信息,所述水体识别模型是基于训练样本以及预先确定的水体标签进行训练后得到。The ground observation image includes an observation image taken by an aerial camera carried by the aircraft and GPS location information corresponding to the observation image, and the water body recognition model is obtained after training based on training samples and predetermined water body labels. 2.根据权利要求1所述的基于航空应急模式的机上洪水数据处理方法,其特征在于,在所述基于所述水体识别结果和目标专题地理数据,进行空间分析,获取综合洪水分析信息之后,还包括:在所述飞行器的飞行过程中,将所述综合洪水分析信息发送至远程终端,以使得所述远程终端接收所述综合洪水分析信息,对灾情进行初步研判,并指导生成救援指挥决策。2. According to claim 1, the onboard flood data processing method based on the aviation emergency mode is characterized in that, after performing spatial analysis based on the water body identification results and target thematic geographic data to obtain comprehensive flood analysis information, it also includes: during the flight of the aircraft, sending the comprehensive flood analysis information to a remote terminal, so that the remote terminal receives the comprehensive flood analysis information, conducts a preliminary assessment of the disaster situation, and guides the generation of rescue command decisions. 3.根据权利要求1或2所述的基于航空应急模式的机上洪水数据处理方法,其特征在于,所述将所述目标图像输入至水体识别模型中,获取水体识别结果,包括:3. The method for processing flood data on board based on aviation emergency mode according to claim 1 or 2, characterized in that the step of inputting the target image into a water body recognition model to obtain a water body recognition result comprises: 基于所述目标图像,获取水体特征信息;Based on the target image, acquiring water body characteristic information; 基于所述水体特征信息,获得与所述目标图像对应的水体识别结果并以矢量格式输出。Based on the water body feature information, a water body recognition result corresponding to the target image is obtained and output in a vector format. 4.一种基于航空应急模式的机上洪水数据处理装置,其特征在于,包括:4. An onboard flood data processing device based on aviation emergency mode, characterized by comprising: 图像获取模块,用于基于目标参数,从对地观测图像中抽取目标观测图像,并记录目标曝光时间;基于所述目标曝光时间,将目标GPS位置信息与所述目标观测图像进行匹配;其中,所述目标曝光时间是所述目标观测图像的曝光时间;基于所述目标观测图像,进行图像配准,提取同名点对;基于所述同名点对,采用最小二乘法原理进行仿射变换,获取拼接图像;基于所述拼接图像,采用最小二乘法原理关联空间地理信息,生成目标图像;An image acquisition module is used to extract a target observation image from a ground observation image based on target parameters and record the target exposure time; based on the target exposure time, match the target GPS location information with the target observation image; wherein the target exposure time is the exposure time of the target observation image; based on the target observation image, perform image registration and extract same-name point pairs; based on the same-name point pairs, perform affine transformation using the least squares principle to obtain a spliced image; based on the spliced image, associate spatial geographic information using the least squares principle to generate a target image; 水体识别模块,用于将所述目标图像输入至水体识别模型中,获取水体识别结果;A water body recognition module, used for inputting the target image into a water body recognition model to obtain a water body recognition result; 机上数据生成模块,用于基于所述水体识别结果和目标地理信息数据,进行空间分析,获取专题信息;基于所述专题信息,进行统计,获取综合洪水分析信息;An onboard data generation module is used to perform spatial analysis based on the water body identification results and target geographic information data to obtain thematic information; based on the thematic information, perform statistics to obtain comprehensive flood analysis information; 落地数据发送模块,用于在飞行器落地时,将所述综合洪水分析信息发送至远程终端,以使得所述远程终端接收所述综合洪水分析信息,对灾情进行初步研判,并指导生成救援指挥决策;A landing data sending module is used to send the comprehensive flood analysis information to a remote terminal when the aircraft lands, so that the remote terminal receives the comprehensive flood analysis information, makes a preliminary assessment of the disaster situation, and guides the generation of rescue command decisions; 其中,所述对地观测图像包括所述飞行器搭载的航摄仪拍摄的观测图像,以及与所述观测图像对应的GPS位置信息,所述水体识别模型是基于训练样本以及预先确定的水体标签进行训练后得到。The ground observation image includes an observation image taken by an aerial camera carried by the aircraft and GPS location information corresponding to the observation image, and the water body recognition model is obtained after training based on training samples and predetermined water body labels. 5.根据权利要求4所述的基于航空应急模式的机上洪水数据处理装置,其特征在于,所述装置还包括:5. The onboard flood data processing device based on aviation emergency mode according to claim 4, characterized in that the device further comprises: 机上数据发送模块,用于在所述飞行器的飞行过程中,将所述综合洪水分析信息发送至远程终端,以使得所述远程终端接收所述综合洪水分析信息,对灾情进行初步研判,并指导生成救援指挥决策。The onboard data sending module is used to send the comprehensive flood analysis information to a remote terminal during the flight of the aircraft, so that the remote terminal receives the comprehensive flood analysis information, conducts a preliminary assessment of the disaster situation, and guides the generation of rescue command decisions. 6.一种基于航空应急模式的机上洪水数据处理系统,包括一个或多个如权利要求5所述的基于航空应急模式的机上洪水数据处理装置,其特征在于,还包括:远程终端;6. An onboard flood data processing system based on aviation emergency mode, comprising one or more onboard flood data processing devices based on aviation emergency mode as claimed in claim 5, characterized in that it also comprises: a remote terminal; 所述远程终端与所述落地数据发送模块或者所述机上数据发送模块通信连接;The remote terminal is communicatively connected with the landing data sending module or the onboard data sending module; 所述远程终端,用于接收所述综合洪水分析信息,对灾情进行初步研判,并指导生成救援指挥决策。The remote terminal is used to receive the comprehensive flood analysis information, conduct a preliminary assessment of the disaster situation, and guide the generation of rescue command decisions. 7.一种电子设备,包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序,其特征在于,所述处理器执行所述程序时实现如权利要求1至3任一项所述基于航空应急模式的机上洪水数据处理方法的步骤。7. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the onboard flood data processing method based on the aviation emergency mode as described in any one of claims 1 to 3 are implemented. 8.一种非暂态计算机可读存储介质,其上存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现如权利要求1至3任一项所述基于航空应急模式的机上洪水数据处理方法的步骤。8. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the onboard flood data processing method based on the aviation emergency mode as described in any one of claims 1 to 3 are implemented. 9.一种计算机程序产品,包括计算机程序,其特征在于,所述计算机程序被处理器执行时实现如权利要求1至3任一项所述基于航空应急模式的机上洪水数据处理方法的步骤。9. A computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of the onboard flood data processing method based on the aviation emergency mode as claimed in any one of claims 1 to 3 are implemented.
CN202111520821.4A 2021-12-13 2021-12-13 Onboard flood data processing method, device and system based on aviation emergency mode Active CN114357227B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111520821.4A CN114357227B (en) 2021-12-13 2021-12-13 Onboard flood data processing method, device and system based on aviation emergency mode

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111520821.4A CN114357227B (en) 2021-12-13 2021-12-13 Onboard flood data processing method, device and system based on aviation emergency mode

Publications (2)

Publication Number Publication Date
CN114357227A CN114357227A (en) 2022-04-15
CN114357227B true CN114357227B (en) 2025-03-11

Family

ID=81098894

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111520821.4A Active CN114357227B (en) 2021-12-13 2021-12-13 Onboard flood data processing method, device and system based on aviation emergency mode

Country Status (1)

Country Link
CN (1) CN114357227B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108447123A (en) * 2018-03-27 2018-08-24 贵州电网有限责任公司输电运行检修分公司 A kind of power transmission line corridor geological disaster investigation method and system
CN110209847A (en) * 2019-04-29 2019-09-06 中国科学院遥感与数字地球研究所 Quasi real time processing method, device and storage medium on Airborne Data Classification machine

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110110641B (en) * 2019-04-29 2020-11-27 中国水利水电科学研究院 A UAV monitoring method and system for watershed flood scene
CN110310248B (en) * 2019-08-27 2019-11-26 成都数之联科技有限公司 A kind of real-time joining method of unmanned aerial vehicle remote sensing images and system
CN112330537B (en) * 2020-06-19 2023-09-29 中国科学院空天信息创新研究院 Method for quickly splicing unmanned aerial vehicle aerial images in emergency rescue activities
CN112099016A (en) * 2020-11-09 2020-12-18 中国水利水电科学研究院 Heaven-earth collaborative flood situation emergency monitoring system and method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108447123A (en) * 2018-03-27 2018-08-24 贵州电网有限责任公司输电运行检修分公司 A kind of power transmission line corridor geological disaster investigation method and system
CN110209847A (en) * 2019-04-29 2019-09-06 中国科学院遥感与数字地球研究所 Quasi real time processing method, device and storage medium on Airborne Data Classification machine

Also Published As

Publication number Publication date
CN114357227A (en) 2022-04-15

Similar Documents

Publication Publication Date Title
US11599689B2 (en) Methods and apparatus for automatically defining computer-aided design files using machine learning, image analytics, and/or computer vision
Hashemi-Beni et al. Flood extent mapping: An integrated method using deep learning and region growing using UAV optical data
Chen et al. A methodology for automated segmentation and reconstruction of urban 3-D buildings from ALS point clouds
CN107735794B (en) Condition detection using image processing
CN112307884B (en) Forest fire spreading prediction method based on continuous time sequence remote sensing situation data and electronic equipment
CN107835997B (en) Vegetation Management for Powerline Corridor Monitoring Using Computer Vision
CN110443862B (en) Lithologic map filling method and system based on unmanned aerial vehicle and electronic equipment
Hormese et al. Automated road extraction from high resolution satellite images
JP7153820B2 (en) Method, System and Apparatus for Forced Landing Path Planning of Aircraft Based on Image Identification
CN112445241A (en) Ground surface vegetation identification method and system based on unmanned aerial vehicle remote sensing technology and readable storage medium
Ding et al. Building detection in remote sensing image based on improved YOLOv5
Yang et al. Flood detection based on unmanned aerial vehicle system and deep learning
CN117274375A (en) Target positioning method and system based on transfer learning network model and image matching
KR102237097B1 (en) Transformation system of DEM with aircraft photographing image from DEM by using AI
CN114357227B (en) Onboard flood data processing method, device and system based on aviation emergency mode
CN117351359B (en) Mining area unmanned aerial vehicle image sea-buckthorn identification method and system based on improved Mask R-CNN
De La Cruz et al. Near-realtime flood detection from multi-temporal sentinel radar images using artificial intelligence
CN110910496B (en) VR natural environment automatic construction method based on big data and AI
KR20230026916A (en) 3d mapping method with time series information using drone
CN113222015A (en) Cloud identification method and device, computing equipment and storage medium
CN118298326B (en) Ocean garbage area estimation method based on deep learning and unmanned aerial vehicle remote sensing
CN118129713B (en) A monitoring system for natural resource changes
Mishra et al. Lidar-based building damage detection in edge-cloud continuum
CN119293742B (en) Adverse geological detection method, system and device based on multi-source aerial remote sensing data fusion
CN111666959A (en) Vector image matching method and device

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