CN116828156B - Geospatial event acquisition method, system, equipment, medium and acquisition box - Google Patents
Geospatial event acquisition method, system, equipment, medium and acquisition box Download PDFInfo
- Publication number
- CN116828156B CN116828156B CN202311107558.5A CN202311107558A CN116828156B CN 116828156 B CN116828156 B CN 116828156B CN 202311107558 A CN202311107558 A CN 202311107558A CN 116828156 B CN116828156 B CN 116828156B
- Authority
- CN
- China
- Prior art keywords
- object detection
- aerial vehicle
- unmanned aerial
- detection model
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000001514 detection method Methods 0.000 claims abstract description 135
- 238000012544 monitoring process Methods 0.000 claims abstract description 74
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000002372 labelling Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000012732 spatial analysis Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 2
- 230000004044 response Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 6
- 230000008878 coupling Effects 0.000 abstract description 2
- 238000010168 coupling process Methods 0.000 abstract description 2
- 238000005859 coupling reaction Methods 0.000 abstract description 2
- 125000004122 cyclic group Chemical group 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method, a system, equipment, a medium and a box for collecting geospatial events, and relates to the technical field of spatial information. It comprises the following steps: executing a circulation process until the preset condition that the object detection model is converged is met; wherein the cyclic process comprises: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; and constructing and training a corresponding object detection model in the cloud server according to sample data obtained by manually labeling the first image data. And carrying out calculation and reasoning on the second image data according to the converged object detection model to obtain the space data corresponding to the monitoring target, wherein the second image data is the image data comprising the monitoring target acquired by the unmanned aerial vehicle after the object detection model is converged. And generating corresponding geospatial events according to the spatial data. The scheme can ensure that the geospatial event data is generated in real time under the condition of low coupling.
Description
Technical Field
The invention relates to the technical field of spatial information, in particular to a method, a system, equipment, a medium and a collection box for collecting geospatial events.
Background
With the continuous development of geospatial information theory and technology, smart city construction is also advancing gradually. In this context, the demand of society for geospatial data is also gradually increasing from historical, current, base data to real-time data.
The method adopted at present is to firstly utilize the unmanned aerial vehicle to carry out field aerial survey, then return to a machine room to carry out a series of processing on aerial survey data of the unmanned aerial vehicle by using professional software so as to obtain standard products such as DOM, DEM and the like. Finally, applications and analyses were performed using these standard products. This approach not only affects the real-time nature of the data, but also makes it difficult to form event-type data.
Disclosure of Invention
The invention aims to provide a method, a system, equipment, a medium and a box for collecting geospatial events, which can generate geospatial event data in real time under the condition of ensuring low coupling.
The invention is realized in the following way:
in a first aspect, the present application provides a method for collecting geospatial events, including the steps of:
Executing a circulation process until a preset condition is met; the above-mentioned preset condition is that the object detection model is converged, and the above-mentioned circulation process includes: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; and constructing and training a corresponding object detection model in the cloud server according to the sample data. And carrying out calculation and reasoning on the second image data according to the converged object detection model to obtain the space data corresponding to the monitoring target, wherein the second image data is the image data comprising the monitoring target acquired by the unmanned aerial vehicle after the object detection model is converged. And generating a corresponding geospatial event according to the spatial data.
Further, based on the foregoing, the method further includes the steps of: and carrying out spatial analysis on the geospatial events according to a GIS spatial analysis algorithm to obtain corresponding event analysis results.
Further, based on the foregoing, the spatial data includes at least one of geometric information, location information, event identification, event category, and time information.
In a second aspect, the present application provides a method for collecting geospatial events, including the steps of:
Executing a circulation process until a preset condition is met; the preset condition is convergence of the object detection model, and the circulation process comprises the following steps: based on a real-time picture of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle in the flight line and comprises a monitoring target to a cloud server; and manually labeling based on the third image data to obtain corresponding sample data so as to train and verify a corresponding object detection model in the cloud server. After receiving the object detection model trained to be converged, the acquisition box carries out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, by utilizing the object detection model, so as to obtain corresponding space data, and sends a geospatial event generated based on the space data to a cloud server for space analysis by a cloud service.
Further, based on the foregoing aspect, when the geospatial event generated based on the spatial data is sent to the cloud server, the method includes: and converting the space data into data conforming to the OGC space data standard based on a preset GIS event model, and storing the data into a corresponding memory and sending the data to a cloud server.
In a third aspect, the present application provides a collection cassette comprising:
A receiving module configured to: receiving an object detection model trained by a cloud server to be converged, wherein the cloud server trains the object detection model by the steps of: continuously receiving fourth image data including a monitoring target, which is acquired in real time by the unmanned aerial vehicle in the corresponding flight line, and training and verifying a corresponding object detection model based on sample data obtained by continuously manually marking the fourth image data by corresponding personnel until the object detection model converges. A processing module configured to: and training the received cloud server to a converged object detection model, and detecting a target object on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, so as to obtain space data corresponding to the target event. A transmission module configured to: and sending the spatial data to a cloud server and/or target terminal equipment so as to carry out spatial analysis on the cloud service and/or the target terminal equipment.
In a fourth aspect, the present application provides a real-time acquisition system for geospatial events comprising:
A model training module configured to: executing a circulation process until a preset condition is met; the above-mentioned preset condition is that the object detection model is converged, and the above-mentioned circulation process includes: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; and constructing and training a corresponding object detection model in the cloud server according to the sample data. A spatial data generation module configured to: and carrying out calculation and reasoning on the second image data according to the converged object detection model to obtain the space data corresponding to the monitoring target, wherein the second image data is the image data comprising the monitoring target acquired by the unmanned aerial vehicle after the object detection model is converged. A spatial event generation module configured to: and generating a corresponding geospatial event according to the spatial data.
In a fifth aspect, the present application provides a real-time acquisition system for geospatial events comprising: unmanned aerial vehicle, collection box, ground station and cloud server.
The unmanned aerial vehicle is used for receiving a control signal of a ground station, executing a corresponding flight line in an event area to be monitored, transmitting an acquired real-time picture to the ground station for display, and sending acquired image data comprising a monitoring target to the cloud service. The ground station is used for receiving and displaying real-time pictures acquired by the unmanned aerial vehicle, and responding to a preset operation instruction and sending a corresponding control signal to the unmanned aerial vehicle. The acquisition box is used for receiving an object detection model trained by the cloud server to be converged, detecting a target object on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, based on the object detection model, so as to obtain corresponding space data, and sending the space data to the cloud server. The cloud server is used for continuously receiving fifth image data including a monitoring target, which is acquired in real time by the unmanned aerial vehicle in the execution of a corresponding flight line, and training and verifying a corresponding object detection model based on sample data obtained by continuously manually marking the fifth image data by a corresponding person until the object detection model is converged; and the object detection model trained to be converged is sent to the acquisition box; and the system is also used for receiving the space data sent by the acquisition box so as to perform space analysis.
In a sixth aspect, the application provides an electronic device comprising at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete communication with each other through the data bus; the memory stores program instructions for execution by the processor, the processor invoking the program instructions to perform the method of any of the first and second aspects.
In a seventh aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described in any of the first and second aspects above.
Compared with the prior art, the invention has at least the following advantages or beneficial effects:
According to the method, firstly, according to a real-time picture transmitted by an unmanned aerial vehicle, the unmanned aerial vehicle is controlled to continuously collect image data comprising a monitoring target, then after the image data is manually marked, a corresponding object detection model is trained in a cloud server, so that a converged object detection model related to the monitoring target can be quickly obtained. Further, the converged object detection model may be used to calculate and infer image data acquired by the unmanned aerial vehicle, so as to obtain spatial data corresponding to a detection target that can be used to generate a geospatial event. That is, the technical scheme can simply and conveniently acquire the geospatial event with strong real-time performance, and is convenient for monitoring the sudden event.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for collecting geospatial events according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for collecting geospatial events in accordance with yet another embodiment of the present invention;
FIG. 3 is a block diagram illustrating a structure of an acquisition box according to an embodiment of the present invention;
FIG. 4 is a block diagram illustrating a real-time acquisition system for geospatial events according to an embodiment of the present invention;
FIG. 5 is a corresponding signaling diagram of an embodiment of a real-time acquisition system for geospatial events according to an embodiment of the present invention;
Fig. 6 is a block diagram of an electronic device according to an embodiment of the present invention.
Icon: 101. a processor; 102. a memory; 103. a data bus.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The various embodiments and features of the embodiments described below may be combined with one another without conflict. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
In the prior art, a model is trained in advance on an object of interest, then the model is arranged on an unmanned aerial vehicle, and then the unmanned aerial vehicle is utilized to monitor the object on site. However, the method cannot utilize the unmanned aerial vehicle to monitor in real time, is only suitable for monitoring the universal target object, and cannot be used for monitoring the sudden event.
In order to cope with the above-mentioned problems, in a first aspect of the embodiments of the present application, a geospatial event collection method is provided, which can obtain a geospatial event with strong real-time performance by optimizing a processing flow, so as to facilitate monitoring of sudden events.
Referring to fig. 1, the method for collecting geospatial events includes the following steps:
Step S101: executing a circulation process until a preset condition is met; the preset condition is that the object detection model converges, and the circulation process comprises: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; and constructing and training a corresponding object detection model in a cloud server according to the sample data.
In the above steps, when the unmanned aerial vehicle is controlled to fly to the event area to be detected (the area including the monitoring target), image data including the monitoring target is collected in real time, and then the collected image data including the monitoring target is utilized to know the specific situation of the site. Then, the unmanned aerial vehicle can be controlled to execute the corresponding flight line according to the real-time image of the observation image of the monitoring target, and the first image data comprising the monitoring target is continuously collected in the middle. By way of example, the real-time image of the unmanned aerial vehicle image transmission can be observed on the display of the ground station by an operator, then the real-time image of the image transmission can be observed manually, and then the unmanned aerial vehicle is controlled in real time according to the observed condition to execute the corresponding flight line, so that a large amount of first image data including the monitoring target can be accurately acquired by the unmanned aerial vehicle by combining with manual factors.
After the first image data is uploaded to the cloud server, corresponding staff can manually label the first image data in the cloud server, or can continuously acquire the latest first image data from the cloud server by using a client tool and label the latest first image data so as to obtain corresponding sample data. Then, on the basis of obtaining the sample data, the corresponding object detection model can be built and trained in the cloud server by utilizing the sample data, new sample data are required to be continuously obtained in the training process, and the model is trained and verified until the model jumps out of circulation after convergence.
It should be noted that, the object detection model needs to be trained mainly because the monitoring target is not determined in advance, and the monitoring target needs to be selected according to the actual situation, so that the object detection model trained in advance cannot be acquired for detection and identification. For example, the monitoring target may be a specific object target temporarily determined in the case of a natural disaster, a traffic accident, a fire, a public security event, or the like, and it is impossible to perform recognition detection using a general object detection model, thereby monitoring it.
Step S102: calculating and reasoning the second image data according to the converged object detection model to obtain spatial data corresponding to the monitoring target, wherein the second image data are image data which are acquired by the unmanned aerial vehicle and comprise the monitoring target after the object detection model is converged;
Step S103: and generating a corresponding geospatial event according to the spatial data.
After the converged object detection model is obtained, the unmanned aerial vehicle can be further utilized to monitor the area to be monitored including the monitoring target, and the second image data acquired by the unmanned aerial vehicle can be calculated and inferred, so that the space data corresponding to the monitoring target is obtained, and the space data is further utilized to generate a corresponding geospatial event. Wherein in some implementations of the invention, the spatial data includes at least one of geometry information, location information, event identification, event category, and time information. Of course, the specific spatial data may be selected independently according to needs, and specific data included in the spatial data is not strictly limited. For example, the spatial data acquired by recognition may be not only coordinates but also a shape, wherein if the shape is a point, its representation may be coordinates, but the shape may also be a line, or a plane, and the corresponding representation is adopted. In short, the spatial data includes what is needed to be selected and applied according to the actual situation. For example, the subsequent processing may also be performing coordinate processing by using the detected image coordinates of the target object and the unmanned aerial vehicle instantaneous POS data, and then packaging the monitored coordinate data with time, ID and the like into an EVENT, and sending the EVENT to the cloud.
The first image data and the second image data are both image data including a monitoring target acquired by the unmanned aerial vehicle, and only the first image data is the image data acquired during the process of training the object model, and the second image data is the image data provided to the object detection model for target object detection after the converged object detection model is obtained. Therefore, if the acquisition process based on the first image data is: an operator observes a real-time picture of the unmanned aerial vehicle on a display of the ground station, then manually observes the real-time picture of the unmanned aerial vehicle, and further controls the unmanned aerial vehicle to execute a corresponding flight line, so that a large amount of first image data comprising a monitoring target can be accurately acquired by the unmanned aerial vehicle by combining manual factors; correspondingly, the second image data acquisition process may be: after the converged object detection model is obtained, the corresponding operator is notified, and then the operator can start planning the flight line of the unmanned aerial vehicle again, then acquire second image data, and perform target object detection by using the converged object detection model.
In addition, for geospatial events, in some embodiments, it may be understood that specific things occur at a certain time and place, such as natural disasters, traffic accidents, fires, security events, and the like. At this point, it is a type of spatial data organized and described using a geographic information spatial data model, generally having spatial, attribute, and temporal features. Wherein the spatial features mainly describe the geographic position spatial coordinates, geometric shapes and the like thereof; the attribute features mainly describe its industry business information, e.g., name, type, etc.; the time feature describes the time information of occurrence of the event, including information on specific time, duration, time sequence of the event and the like.
Based on the foregoing, in some implementations of the invention, after obtaining the geospatial event, the method further includes the steps of: and carrying out spatial analysis on the geospatial event according to a GIS spatial analysis algorithm to obtain a corresponding event analysis result. Therefore, the event analysis result can be used for directly carrying out the application event in the server later, and the application event can also be sent or copied to the stand-alone equipment. That is, various application analyses can be performed subsequently on the corresponding server or terminal device in a manner of spatial analysis of the geographic information system.
As shown in fig. 2, in a second aspect of the present embodiment, based on the same inventive concept, an embodiment of the present application further provides a method for collecting a geospatial event, which includes the following steps:
Step S201: executing a circulation process until a preset condition is met; the preset condition is convergence of the object detection model, and the circulation process comprises: based on a real-time picture of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle in the flight line and comprises a monitoring target to a cloud server; manually labeling based on the third image data to obtain corresponding sample data so as to train and verify a corresponding object detection model in a cloud server;
Step S202: after receiving the object detection model trained to be converged, the acquisition box carries out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, by utilizing the object detection model, so as to obtain corresponding space data, and sends a geospatial event generated based on the space data to a cloud server for space analysis by a cloud service. If the spatial data only includes coordinates and geometry of the target object, the spatial data may be further packaged in combination with attributes of the target object to generate a geospatial event.
On the basis of the geospatial event acquisition method disclosed in the first aspect, the ground station and the acquisition box are combined in the scheme of the second aspect, and the technical scheme is further optimized and limited. However, if the unmanned aerial vehicle only autonomously executes a predetermined flight path to acquire image data including a monitoring target in a region to be monitored, the accuracy of image data acquisition may be affected by the selection of the flight path, which may be disadvantageous for rapid convergence of the object detection model. Therefore, in the above embodiment, by planning the flight path of the unmanned aerial vehicle based on the real-time image of the unmanned aerial vehicle image captured by the ground station during the training of the object detection model, the unmanned aerial vehicle can be controlled to more accurately and effectively acquire the third image data including the monitoring target. It should be noted that, the third image data and the first image data are image data, which are merely described herein for distinguishing the image data acquired by the unmanned aerial vehicle under two different flight control conditions.
In addition, after the cloud server is trained to obtain the converged object detection model, the object detection model can be downloaded and received by the acquisition box, and then the object detection model is utilized at the acquisition box end to detect the target object on the real-time picture of the event area to be monitored, which is newly acquired by the unmanned aerial vehicle, so that the calculated amount of target object detection is shared to the acquisition box end, the real-time performance of the subsequent calculation of detection, tracking and the like of the monitoring target can be improved, and the timeliness of the monitoring target is not reduced due to the influence of too much network fluctuation.
Based on the foregoing, in some implementations of the present invention, when sending the geospatial event generated based on the spatial data to the cloud server, the method includes: and converting the space data into data conforming to the OGC space data standard (including converting the space data in structure and format) based on a preset GIS event model, and storing the data into a corresponding memory and sending the data to a cloud server.
Example 2
As shown in fig. 3, based on the same inventive concept as embodiment 1, an embodiment of the present application provides a collection cartridge including:
a receiving module configured to: receiving an object detection model trained by a cloud server to be converged, wherein the step of training the object detection model by the cloud server comprises the following steps: continuously receiving fourth image data including a monitoring target, which are acquired in real time by the unmanned aerial vehicle in the corresponding flight line, and training and verifying a corresponding object detection model based on sample data obtained by continuously manually marking the fourth image data by corresponding personnel until the object detection model converges;
a processing module configured to: training to a converged object detection model by utilizing the received cloud server, and detecting a target object on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, so as to obtain space data corresponding to a target event;
a transmission module configured to: and sending the spatial data to a cloud server and/or target terminal equipment so as to carry out spatial analysis on the cloud service and/or the target terminal equipment.
On the basis of the method for collecting the geospatial event disclosed in embodiment 1, embodiment 2 above discloses a collecting box, which comprises a receiving module, a processing module and a sending model, so as to receive an object detection model trained by a cloud server to be converged, and based on the object detection model, perform target object detection on a real-time picture of an event area to be monitored, which is newly collected by an unmanned aerial vehicle, so as to obtain spatial data corresponding to a target event, and then send the spatial data to the cloud server and/or target terminal equipment for spatial analysis by the cloud server and/or the target terminal equipment. The target terminal equipment comprises terminal equipment such as a computer, a tablet, a mobile phone and the like.
It should be noted that, the fourth image data and the first image data and the third image data are all image data in nature, and only the description is made herein for distinguishing the image data acquired by the received unmanned aerial vehicle for the convenience of understanding and distinguishing the technical solution of the acquisition box.
Additionally, in some implementations of the invention, the collection box includes:
A receiving module configured to: receiving an object detection model trained by a cloud server to be converged, wherein the step of training the object detection model by the cloud server comprises the following steps: executing a circulation process until a preset condition is met; the preset condition is that the object detection model converges, and the circulation process comprises: based on a real-time picture of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle in the flight line and comprises a monitoring target to a cloud server; and manually labeling based on the third image data to obtain corresponding sample data so as to train and verify a corresponding object detection model in a cloud server.
A processing module configured to: and training the received cloud server to a converged object detection model, and detecting a target object on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, so as to obtain space data corresponding to the target event.
A transmission module configured to: and sending the spatial data to a cloud server and/or target terminal equipment so as to carry out spatial analysis on the cloud service and/or the target terminal equipment.
The specific implementation process of the above-mentioned acquisition box refers to the method for acquiring geospatial events provided in embodiment 1, and is not described herein.
Example 3
Referring to fig. 4, based on the same inventive concept as the geospatial event acquisition method disclosed in the first aspect of embodiment 1, an embodiment of the present application provides a real-time geospatial event acquisition system, which includes:
a model training module configured to: executing a circulation process until a preset condition is met; the preset condition is that the object detection model converges, and the circulation process comprises: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; constructing and training a corresponding object detection model in a cloud server according to the sample data;
a spatial data generation module configured to: calculating and reasoning the second image data according to the converged object detection model to obtain spatial data corresponding to the monitoring target, wherein the second image data are image data which are acquired by the unmanned aerial vehicle and comprise the monitoring target after the object detection model is converged;
A spatial event generation module configured to: and generating a corresponding geospatial event according to the spatial data.
The specific implementation process of the above system refers to a method for collecting geospatial events provided in embodiment 1, and is not described herein.
Based on the same inventive concept as the geospatial event acquisition method disclosed in the second aspect of embodiment 1, as shown in fig. 5, an embodiment of the present application further provides a real-time geospatial event acquisition system, which includes: unmanned aerial vehicle, collection box, ground station and cloud server;
the unmanned aerial vehicle is used for receiving a control signal of a ground station, executing a corresponding flight line in an event area to be monitored, transmitting an acquired real-time picture to the ground station for display, and transmitting acquired image data comprising a monitoring target to the cloud service;
the ground station is used for receiving and displaying real-time pictures acquired by the unmanned aerial vehicle and responding to a preset operation instruction to send corresponding control signals to the unmanned aerial vehicle;
the acquisition box is used for receiving an object detection model trained by the cloud server to be converged, carrying out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, based on the object detection model, so as to obtain corresponding space data, and sending the space data to the cloud server;
The cloud server is used for continuously receiving fifth image data including a monitoring target, which is acquired in real time by the unmanned aerial vehicle in the execution of a corresponding flight line, and training and verifying a corresponding object detection model based on sample data obtained by continuously manually marking the fifth image data by corresponding personnel until the object detection model converges; and sending the object detection model trained to converge to the acquisition box; and the system is also used for receiving the space data sent by the acquisition box so as to perform space analysis.
As shown in fig. 5, the real-time acquisition system for geospatial events includes an unmanned aerial vehicle, an acquisition box, a ground station and a cloud server, wherein the unmanned aerial vehicle is used for acquiring image data including a monitoring target, then an operator can control the unmanned aerial vehicle to execute a corresponding flight line in real time at the ground station (whether in a model training stage or in a later stage by utilizing a converged model stage, the unmanned aerial vehicle can be controlled to execute the corresponding flight line at the ground station as required), and the cloud server is used for receiving the image data including the monitoring target, and training and verifying a corresponding object detection model after the image data is marked manually until the model converges. Then, the object detection model which is received and converged by the acquisition box is downloaded, and object detection is carried out on image data which is acquired by the unmanned aerial vehicle and comprises a monitoring object, so that corresponding space data is obtained, and the space data is used for space analysis by the cloud server.
The specific implementation process of the above system refers to a method for collecting geospatial events provided in embodiment 1, and is not described herein.
Example 4
Referring to fig. 6, an embodiment of the present application provides an electronic device including at least one processor 101, at least one memory 102, and a data bus 103; wherein: the processor 101 and the memory 102 complete communication with each other through the data bus 103; the memory 102 stores program instructions executable by the processor 101, which the processor 101 invokes to perform a method of collecting geospatial events. For example, implementation:
Executing a circulation process until a preset condition is met; the above-mentioned preset condition is that the object detection model is converged, and the above-mentioned circulation process includes: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; and constructing and training a corresponding object detection model in the cloud server according to the sample data. And carrying out calculation and reasoning on the second image data according to the converged object detection model to obtain the space data corresponding to the monitoring target, wherein the second image data is the image data comprising the monitoring target acquired by the unmanned aerial vehicle after the object detection model is converged. And generating a corresponding geospatial event according to the spatial data.
Or realize:
Executing a circulation process until a preset condition is met; the preset condition is convergence of the object detection model, and the circulation process comprises the following steps: based on a real-time picture of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle in the flight line and comprises a monitoring target to a cloud server; and manually labeling based on the third image data to obtain corresponding sample data so as to train and verify a corresponding object detection model in the cloud server. After receiving the object detection model trained to be converged, the acquisition box carries out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, by utilizing the object detection model, so as to obtain corresponding space data, and sends a geospatial event generated based on the space data to a cloud server for space analysis by a cloud service.
The Memory 102 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
It will be appreciated that the configuration shown in fig. 6 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 6, or have a different configuration than shown in fig. 6. The components shown in fig. 6 may be implemented in hardware, software, or a combination thereof.
Example 5
The present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor 101 implements a method of collecting geospatial events. For example, implementation:
Executing a circulation process until a preset condition is met; the above-mentioned preset condition is that the object detection model is converged, and the above-mentioned circulation process includes: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target; manually marking according to the first image data to obtain corresponding sample data; and constructing and training a corresponding object detection model in the cloud server according to the sample data. And carrying out calculation and reasoning on the second image data according to the converged object detection model to obtain the space data corresponding to the monitoring target, wherein the second image data is the image data comprising the monitoring target acquired by the unmanned aerial vehicle after the object detection model is converged. And generating a corresponding geospatial event according to the spatial data.
Or realize:
Executing a circulation process until a preset condition is met; the preset condition is convergence of the object detection model, and the circulation process comprises the following steps: based on a real-time picture of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle in the flight line and comprises a monitoring target to a cloud server; and manually labeling based on the third image data to obtain corresponding sample data so as to train and verify a corresponding object detection model in the cloud server. After receiving the object detection model trained to be converged, the acquisition box carries out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, by utilizing the object detection model, so as to obtain corresponding space data, and sends a geospatial event generated based on the space data to a cloud server for space analysis by a cloud service.
The above functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application 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 application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A method for collecting geospatial events, comprising the steps of:
executing a circulation process until a preset condition is met; the preset condition is that the object detection model converges, and the circulation process comprises: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target, wherein the monitoring target is not established in advance; manually marking according to the first image data to obtain corresponding sample data; constructing and training a corresponding object detection model in a cloud server according to the sample data;
responding to the convergence of the object detection model, re-planning according to the latest image of the unmanned aerial vehicle and controlling the unmanned aerial vehicle to execute a corresponding flight line based on the re-planned flight line;
Calculating and reasoning the second image data according to the converged object detection model to obtain spatial data corresponding to the monitoring target, wherein the second image data are image data which are acquired by the unmanned aerial vehicle and comprise the monitoring target after the object detection model is converged;
and generating a corresponding geospatial event according to the spatial data, wherein the geospatial event is a sudden event.
2. The method for collecting geospatial events according to claim 1, further comprising:
and carrying out spatial analysis on the geospatial event according to a GIS spatial analysis algorithm to obtain a corresponding event analysis result.
3. The method of claim 1, wherein the spatial data comprises at least one of geometric information, location information, event identification, event category, and temporal information.
4. A method for collecting geospatial events, comprising the steps of:
Executing a circulation process until a preset condition is met; the preset condition is convergence of the object detection model, and the circulation process comprises: based on a real-time image of unmanned aerial vehicle image transmission observed by a ground station, planning a flight line of the unmanned aerial vehicle, and sending third image data which is continuously collected by the unmanned aerial vehicle on the flight line and comprises a monitoring target to a cloud server, wherein the monitoring target is not established in advance; manually labeling based on the third image data to obtain corresponding sample data, and constructing and training a corresponding object detection model in a cloud server according to the sample data;
responding to the convergence of the object detection model, downloading the object detection model trained to be converged from the cloud server to the acquisition box, and re-planning and controlling the unmanned aerial vehicle to execute a corresponding flight line based on the re-planned flight line according to the latest image of the unmanned aerial vehicle;
after receiving the object detection model trained to be converged, the acquisition box carries out target object detection on a real-time picture of an event area to be monitored, which is acquired by the unmanned aerial vehicle newly, by utilizing the object detection model, so as to obtain corresponding space data, and sends a geospatial event generated based on the space data to a cloud server for space analysis by a cloud service, wherein the geospatial event is a sudden event.
5. The method for collecting geospatial events according to claim 4, wherein when sending the geospatial events generated based on the spatial data to a cloud server, the method comprises:
And converting the space data into data conforming to the OGC space data standard based on a preset GIS event model, and storing the data into a corresponding memory and sending the data to a cloud server.
6. A collection box, comprising:
a receiving module configured to: receiving an object detection model trained by a cloud server to be converged, wherein the step of training the object detection model by the cloud server comprises the following steps: continuously receiving fourth image data including a monitoring target, which are acquired in real time by the unmanned aerial vehicle in the execution of the corresponding flight line, and continuously constructing and training a corresponding object detection model in a cloud server based on sample data obtained by manually marking the fourth image data by corresponding personnel until the object detection model converges; wherein the monitoring target is not predetermined in advance;
A processing module configured to: training to a converged object detection model by utilizing the received cloud server, and detecting a target object on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, so as to obtain space data corresponding to a target event; the method comprises the steps that a real-time picture of an event area to be monitored, which is acquired newly by an unmanned aerial vehicle, is a picture acquired in real time when an operator responds to convergence of an object detection model, and the unmanned aerial vehicle is controlled to execute a corresponding flight line by re-planning and based on the re-planned flight line according to the latest image of the unmanned aerial vehicle;
a transmission module configured to: and sending the space data to a cloud server and/or target terminal equipment, and generating sudden geospatial events according to the space data for space analysis by the cloud service and/or the target terminal equipment.
7. A real-time acquisition system for geospatial events, comprising:
A model training module configured to: executing a circulation process until a preset condition is met; the preset condition is that the object detection model converges, and the circulation process comprises: according to a real-time picture transmitted by the unmanned aerial vehicle, controlling the unmanned aerial vehicle to continuously acquire first image data comprising a monitoring target, wherein the monitoring target is not established in advance; manually marking according to the first image data to obtain corresponding sample data; constructing and training a corresponding object detection model in a cloud server according to the sample data;
A route planning module configured to: responding to the convergence of the object detection model, re-planning according to the latest image of the unmanned aerial vehicle and controlling the unmanned aerial vehicle to execute a corresponding flight line based on the re-planned flight line;
a spatial data generation module configured to: calculating and reasoning the second image data according to the converged object detection model to obtain spatial data corresponding to the monitoring target, wherein the second image data are image data which are acquired by the unmanned aerial vehicle and comprise the monitoring target after the object detection model is converged;
a spatial event generation module configured to: and generating a corresponding geospatial event according to the spatial data, wherein the geospatial event is a sudden event.
8. The real-time acquisition system for the geospatial events is characterized by comprising an unmanned plane, an acquisition box, a ground station and a cloud server;
The unmanned aerial vehicle is used for receiving a control signal of a ground station, executing a corresponding flight line in an event area to be monitored, transmitting an acquired real-time picture to the ground station for display, and sending acquired image data comprising a monitoring target to the cloud service, wherein the monitoring target is not established in advance;
The ground station is used for receiving and displaying real-time pictures acquired by the unmanned aerial vehicle and responding to a preset operation instruction to send corresponding control signals to the unmanned aerial vehicle; the control signal comprises a signal for controlling the unmanned aerial vehicle to continuously collect image data comprising a detection target according to a real-time picture acquired by the unmanned aerial vehicle, and a signal for controlling the unmanned aerial vehicle to execute a corresponding flight line according to a newly mapped real-time picture of the unmanned aerial vehicle, re-planning and based on the re-planned flight line in response to the convergence of the object detection model;
the acquisition box is used for receiving an object detection model trained by the cloud server to be converged, carrying out target object detection on a real-time picture of an event area to be monitored, which is acquired newly by the unmanned aerial vehicle, based on the object detection model, so as to obtain corresponding space data, and sending the space data to the cloud server;
The cloud server is used for continuously receiving fifth image data including a monitoring target, which is acquired by the unmanned aerial vehicle in real time in the execution of a corresponding flight line, and constructing and training a corresponding object detection model in the cloud server based on sample data obtained by continuously manually marking the fifth image data by corresponding personnel until the object detection model converges; and sending the object detection model trained to converge to the acquisition box; and the system is also used for receiving the spatial data sent by the acquisition box for spatial analysis, wherein the spatial data is data used for generating sudden geospatial events.
9. An electronic device comprising at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete communication with each other through the data bus; the memory stores program instructions for execution by the processor, the processor invoking the program instructions to perform the method of any of claims 1-5.
10. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311107558.5A CN116828156B (en) | 2023-08-31 | 2023-08-31 | Geospatial event acquisition method, system, equipment, medium and acquisition box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311107558.5A CN116828156B (en) | 2023-08-31 | 2023-08-31 | Geospatial event acquisition method, system, equipment, medium and acquisition box |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116828156A CN116828156A (en) | 2023-09-29 |
| CN116828156B true CN116828156B (en) | 2024-05-03 |
Family
ID=88117047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311107558.5A Active CN116828156B (en) | 2023-08-31 | 2023-08-31 | Geospatial event acquisition method, system, equipment, medium and acquisition box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116828156B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112414405A (en) * | 2020-10-22 | 2021-02-26 | 武汉大学 | Unmanned aerial vehicle cluster flight path planning method considering emergency task of DSM |
| CN114373138A (en) * | 2021-12-28 | 2022-04-19 | 北京交通大学 | Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway |
| CN114429594A (en) * | 2022-01-26 | 2022-05-03 | 华北电力大学 | Power transmission line typical target detection method and system based on unmanned aerial vehicle federal learning |
| US11565807B1 (en) * | 2019-06-05 | 2023-01-31 | Gal Zuckerman | Systems and methods facilitating street-level interactions between flying drones and on-road vehicles |
| CN115880591A (en) * | 2022-11-04 | 2023-03-31 | 宁波大学 | Real-time target detection method based on unmanned aerial vehicle video stream |
| CN115905450A (en) * | 2023-01-04 | 2023-04-04 | 深圳联和智慧科技有限公司 | Unmanned aerial vehicle monitoring-based water quality abnormity tracing method and system |
-
2023
- 2023-08-31 CN CN202311107558.5A patent/CN116828156B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11565807B1 (en) * | 2019-06-05 | 2023-01-31 | Gal Zuckerman | Systems and methods facilitating street-level interactions between flying drones and on-road vehicles |
| CN112414405A (en) * | 2020-10-22 | 2021-02-26 | 武汉大学 | Unmanned aerial vehicle cluster flight path planning method considering emergency task of DSM |
| CN114373138A (en) * | 2021-12-28 | 2022-04-19 | 北京交通大学 | Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway |
| CN114429594A (en) * | 2022-01-26 | 2022-05-03 | 华北电力大学 | Power transmission line typical target detection method and system based on unmanned aerial vehicle federal learning |
| CN115880591A (en) * | 2022-11-04 | 2023-03-31 | 宁波大学 | Real-time target detection method based on unmanned aerial vehicle video stream |
| CN115905450A (en) * | 2023-01-04 | 2023-04-04 | 深圳联和智慧科技有限公司 | Unmanned aerial vehicle monitoring-based water quality abnormity tracing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116828156A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11393212B2 (en) | System for tracking and visualizing objects and a method therefor | |
| CN109461142B (en) | Line hidden danger analysis method and device and electronic terminal | |
| US20130272569A1 (en) | Target identification system target identification server and target identification terminal | |
| CN116298701B (en) | Power distribution network fault detection method and related device based on digital twin system | |
| CN113032249B (en) | Test method, device and equipment of traffic flow monitoring system | |
| CN114706933A (en) | Spraying area determining method and device based on unmanned aerial vehicle operation | |
| CN104992254B (en) | Mountain fire based on power grid GIS and the meteorological trend pre-judging method combined | |
| CN111738558B (en) | Visualization method, device, equipment and storage medium for behavior risk identification | |
| CN113312963A (en) | Inspection method and inspection device for photovoltaic power station and storage medium | |
| CN117216341B (en) | Visualization method and system for distributed space-time data of power grid | |
| CN111993415A (en) | Autonomous patrol robot, mobile monitoring method and device thereof, and autonomous patrol system | |
| CN113990034A (en) | Transmission maintenance safety early warning method, system and terminal based on RTK positioning | |
| CN112822070A (en) | Internet of things equipment monitoring method | |
| CN112885054A (en) | Early warning method and device | |
| CN114363815B (en) | Network quality determining method, equipment control method, device, medium and equipment | |
| CN109462818A (en) | A kind of method, apparatus and terminal of identification user trip track | |
| CN116828156B (en) | Geospatial event acquisition method, system, equipment, medium and acquisition box | |
| CN114338430A (en) | Data visualization display method and system | |
| CN105828367B (en) | A kind of determination method and device of network failure information | |
| CN116737483B (en) | Assembly test interaction method, device, equipment and storage medium | |
| CN116647032B (en) | Real-time protection system and method for power transmission line of target construction vehicle | |
| CN113225678B (en) | Ground rod management method and system | |
| CN115797406A (en) | Out-of-range warning method, device, equipment and storage medium | |
| CN115567873A (en) | Internet of things asset equipment positioning tracking and emergency response method and device | |
| CN115064982A (en) | Intelligent inspection system and method for ultra-high voltage transmission line and related equipment |
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 |