Survey delimiting data acquisition and transmission control system

Abstract

The invention relates to the technical field of data acquisition and transmission, and discloses a survey delimiting data acquisition and transmission control system, which comprises a central control module, an unmanned aerial vehicle data acquisition module, an unmanned aerial vehicle communication module and a database, the central control module is connected with the unmanned aerial vehicle data acquisition module; the surveying and delimiting unmanned aerial vehicle comprises a mother unmanned aerial vehicle and a son unmanned aerial vehicle; the child-mother unmanned aerial vehicle performs data transmission through the unmanned aerial vehicle communication module; the unmanned aerial vehicle data acquisition module acquires path dynamic planning data from the wireless communication module and the database, the path dynamic planning data comprises surveying initial unmanned aerial vehicle path planning data and data acquired by the unmanned aerial vehicle, and the data acquired by the unmanned aerial vehicle comprises landform images, meteorological data and position and flight state information of the unmanned aerial vehicle; the central control module is used for executing the task of controlling the surveying and delimiting unmanned aerial vehicle. The problems are solved through cooperation of the child unmanned aerial vehicle and the mother unmanned aerial vehicle, the land survey delimiting result is more accurate, and real-time autonomous route adjustment is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and transmission, and more specifically, to a survey and demarcation data acquisition and transmission control system. Background Art

[0002] Since traditional land survey and demarcation technology has high overlap and large point error values, the existing method is to first use drones to obtain images in different survey areas and design routes for test areas of different shapes. Then calibrate the camera error to avoid distortion, measure elevation points in flat terrain, constrain the mapping accuracy by setting image control points, calculate the relative orientation elements of the image, adjust the light position according to the correlation of the image, establish a target stereo model to calculate the orientation parameters, eliminate the registration error near the stitching line to smooth the overlapping area, and perform IHS (Intensity, Hue, Saturation) transformation on the RGB (Red, Green, Blue) band to generate a new fused image. Finally, in ArcGIS (Environment System Research Institute), all land survey and demarcation information is processed in the industry based on overlay analysis to complete the land survey and demarcation.

[0003] However, this method still has some defects. For example, the survey relies on the UAV path designed in advance according to the topographic map. If there are problems such as terrain changes or meteorological influences that are not considered when designing the path, the collected images will be missing information after fusion and stitching, and the land survey and demarcation results input into ArcGIS for analysis will have large errors. Summary of the invention

[0004] The present invention provides a survey and demarcation data acquisition, transmission and control system to solve the technical problem that the terrain changes or meteorological influences that are not considered when designing the path in the related technology will lead to missing information after the collected images are fused and spliced, and the land survey and demarcation results input into ArcGIS for analysis will have large errors.

[0005] The present invention provides a survey and demarcation data acquisition and transmission control system, comprising:

[0006] Central control module, UAV data collection module, UAV communication module and database;

[0007] The central control module is connected to the drone data acquisition module, the drone communication module is connected to the survey and demarcation drone, and the drone data acquisition module is connected to the database. The survey and demarcation drone includes a mother drone and a child drone. A mother drone carries more than one child drone. The mother drone can perform the release operation of the child drone, and the child drone has the function of independent flight and image shooting.

[0008] The mother-child drones transmit data through the drone communication module;

[0009] The UAV data acquisition module obtains the path dynamic planning data from the wireless communication module and the database. The path dynamic planning data includes: the initial UAV path planning data of the survey and the data obtained by the UAV. The data obtained by the UAV includes: terrain images, meteorological data, and its own position and flight status information;

[0010] Meteorological data include: temperature, humidity, air pressure, wind speed, and cloud cover;

[0011] The central control module is used to perform the task of controlling the survey and demarcation drone.

[0012] In a preferred embodiment, the central control module specifically includes:

[0013] The data structuring module is used to structure the data acquired by the drone to obtain ordered information in two structural dimensions. The basic structural elements included in the first structural dimension are objects, including landforms, weather, and drones; the basic structural elements included in the second structural dimension are time series units;

[0014] Objects for extracting orderliness information;

[0015] Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the data collection cycle, and map one part to a time sequence unit. The order of the time sequence units is consistent with the time order of the collection cycle of the specific features;

[0016] Establishing a mapping between the extracted objects and their associated specific features;

[0017] For any two objects, if there is a correlation between the associated specific features related to the data structuring task or there is a correlation between the objects related to the data structuring task, an object relationship is established between the two objects.

[0018] An initial path recognition module is used to identify the initial UAV path planning data of the survey to obtain the initial path features;

[0019] A time sequence unit recognition module, which is used to recognize the time sequence unit of the object to obtain the representation features of the object;

[0020] An environment recognition module, which is used to fuse the representation features of the object to obtain the representation features of the environment;

[0021] The path dynamic planning module is used to identify the environmental representation features and the initial path features to obtain the route adjustment decision for controlling the survey and demarcation UAV.

[0022] In a preferred embodiment, the method for processing and obtaining order information includes: Convolutional Neural Networks algorithm, Word Embedding algorithm;

[0023] In a preferred embodiment, the specific features associated with the landform are: a landform image;

[0024] Specific characteristics of meteorological associations: temperature, humidity, air pressure, wind speed, cloud cover;

[0025] Specific characteristics associated with the drone: location, flight status;

[0026] In a preferred embodiment, the associations related to the data structuring task include:

[0027] The landforms are adjacent in spatial location;

[0028] The connection between weather and drones is that weather can affect the flight path of drones;

[0029] The connection between topography and drones is that topographic features affect the flight path of drones.

[0030] In a preferred embodiment, the route adjustment decision includes whether the mother drone releases the child drone, the route adjustment parameters of the mother drone, and the route of the released child drone.

[0031] In a preferred embodiment, RNN is used as the initial path recognition module, GRU is used as the sequential unit recognition module, GCN is used as the environment recognition module, and full connection is used to execute the path dynamic planning module.

[0032] In a preferred embodiment, the aforementioned RNN, GRU and GCN all need to update parameters through training, and they are jointly trained with the full connection of the path dynamic planning module.

[0033] In a preferred embodiment, the reward function of the joint training as follows:

[0034] ;

[0035] represents the data quality score, represents the energy consumption of the drone, Indicates the task completion time. , , Represent the first, second, and third weight coefficients respectively.

[0036] In a preferred embodiment, a survey and demarcation data collection and transmission control method comprises the following steps:

[0037] Plan initial routes and collect information;

[0038] Process information and assess whether the route is feasible;

[0039] When the route is not feasible, obtain the route adjustment decision and decide whether to release the sub-UAV for high-precision mapping tasks;

[0040] After completion, data fusion processing is performed to generate high-quality surveying and mapping results.

[0041] The beneficial effects of the present invention are as follows: the present invention solves the above-mentioned problems through the collaboration of mother and child UAVs, obtains route adjustment decisions through dynamic path planning, realizes autonomous route adjustment, and can perform high-precision surveying and mapping tasks by releasing child UAVs, making land survey and demarcation results more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a module schematic diagram of survey and demarcation data collection, transmission and control of the present invention;

[0043] Figure 2 It is a specific module schematic diagram of a central control module for survey and demarcation data collection, transmission and control of the present invention;

[0044] Figure 3 It is an example of survey and demarcation data collection, transmission and control data collection of the present invention;

[0045] Figure 4 It is an example of survey and demarcation data collection, transmission and control route adjustment of the present invention. DETAILED DESCRIPTION

[0046] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. In addition, the features described in some examples may also be combined in other examples.

[0047] At least one embodiment of the present invention discloses a survey and demarcation data collection and transmission control system, such as Figure 1 As shown, it includes: a central control module, a UAV data acquisition module, a UAV communication module and a database;

[0048] The central control module is connected to the drone data acquisition module, the drone communication module is connected to the survey and demarcation drone, and the drone data acquisition module is connected to the database. The survey and demarcation drone includes a mother drone and a child drone. A mother drone carries more than one child drone. The mother drone can perform the release operation of the child drone, and the child drone has the function of independent flight and image shooting.

[0049] The mother-child drones transmit data through the drone communication module;

[0050] The UAV data acquisition module obtains the path dynamic planning data from the wireless communication module and the database. The path dynamic planning data includes: the initial UAV path planning data of the survey and the data obtained by the UAV. The data obtained by the UAV includes: terrain images, meteorological data, and its own position and flight status information;

[0051] Meteorological data include: temperature, humidity, air pressure, wind speed, wind direction, and cloud distribution;

[0052] The central control module is used to perform the task of controlling the survey and demarcation drone.

[0053] Central control module such as Figure 2 As shown, including:

[0054] The data structuring module is used to structure the data acquired by the drone to obtain ordered information in two structural dimensions. The basic structural elements included in the first structural dimension are objects, including landforms, weather, and drones; the basic structural elements included in the second structural dimension are time series units;

[0055] In some embodiments of the present invention, methods for processing and obtaining order information include: CNN (Convolutional Neural Networks) algorithm and Word Embedding algorithm.

[0056] Objects for extracting orderliness information;

[0057] Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the data collection cycle, and map one part to a time sequence unit. The order of the time sequence units is consistent with the time order of the collection cycle of the specific features;

[0058] Establishing a mapping between the extracted objects and their associated specific features;

[0059] For any two objects, if there is a correlation between the associated specific features related to the data structuring task or there is a correlation between the objects related to the data structuring task, an object relationship is established between the two objects.

[0060] In some embodiments of the present invention, specific features of landform associations: landform images;

[0061] Specific characteristics of meteorological associations: temperature, humidity, air pressure, wind speed, cloud cover;

[0062] Specific characteristics associated with the drone: location, flight status;

[0063] In some embodiments of the present invention, the associations related to the data structuring task include:

[0064] The landforms are adjacent in spatial location;

[0065] The connection between weather and drones is that weather can affect the flight path of drones;

[0066] The connection between topography and drones is that topographic features affect the flight path of drones.

[0067] An initial path recognition module is used to identify the initial UAV path planning data of the survey to obtain the initial path features;

[0068] In some embodiments of the present invention, RNN (Recurrent Neural Network) is used as the initial path identification module:

[0069]

[0070]

[0071]

[0072] in represents the tth first hidden feature, represents the t-1th first hidden feature, and denote the first and second intermediate features respectively, represents the UAV path planning data at step t, and is the serial recognition weight matrix, is the serial identification bias parameter, Represents the Sigmoid function.

[0073] A time sequence unit recognition module, which is used to recognize the time sequence unit of the object to obtain the representation features of the object;

[0074] In some embodiments of the present invention, GRU is used as a sequential unit recognition module, and the expression is as follows:

[0075] ;

[0076] ;

[0077] ;

[0078] ;

[0079] , : The activation vector of the reset gate and update gate at step t;

[0080] : Candidate state generated in step t;

[0081] : The representation feature of the tth step;

[0082] : The representation feature of the t-1th step;

[0083] , , , , , : First, second, third, fourth, fifth, sixth transformation matrices (trainable parameters);

[0084] , , : First, second and third deviations (trainable parameters);

[0085] , hour ;

[0086] : Activation function;

[0087] : Activation function;

[0088] : The tth time unit associated with the object;

[0089] , When the specific features of all sequential units associated with the u-th object are input into the RNN, the last second hidden feature is output;

[0090] An environment recognition module, which is used to fuse the representation features of the object to obtain the representation features of the environment;

[0091] In some embodiments of the present invention, GCN is used as an environment recognition module, and the expression of the lth layer of GCN is as follows:

[0092] ;

[0093] : The hidden features of the vth object in the lth layer;

[0094] : The hidden features of the vth object in the l-1th layer;

[0095] : The hidden features of the u-th object in the l-1th layer;

[0096] : A collection of objects that have object relationships with object v;

[0097] : The l-th layer weight matrix applied to the neighbor node feature transformation;

[0098] : The l-th layer weight matrix applied to the feature transformation of its own node;

[0099] : normalization constant;

[0100] , E represents the total number of layers, when l=1 ;

[0101] : The representation features of object u;

[0102] When l=E is equal to the fused features of object v;

[0103] ;

[0104] : The fusion features of object v;

[0105] : The collection of all objects;

[0106] : Environmental representation characteristics.

[0107] The path dynamic planning module is used to identify the environmental representation features and the initial path features to obtain the route adjustment decision of the control survey and demarcation UAV. The route adjustment decision includes whether the mother UAV releases the child UAV, the route adjustment parameters of the mother UAV and the route of the released child UAV.

[0108] In one embodiment of the present invention, full connectivity is applied to execute the path dynamic planning module:

[0109] ;

[0110] in Represents an action of route adjustment decision, Indicates the environment and characteristics. Indicates full connection.

[0111] The aforementioned RNN, GRU and GCN all need to be trained to update parameters. They can be jointly trained with the full connection of the path dynamic planning module. In one embodiment of the present invention, the joint training is performed by reinforcement learning. Reinforcement learning uses the information collected by the drone data collection module as the state and the route adjustment decision as the action. It comprehensively considers positive and negative rewards and designs a reward function that balances safety and cost. ,like:

[0112] ;

[0113] represents the data quality score, represents the energy consumption of the drone, Indicates the task completion time. , , Represent the first, second, and third weight coefficients respectively.

[0114] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

Claims

1. A survey and demarcation data collection and transmission control system, characterized in that: A survey and demarcation data acquisition and transmission control system comprises: a central control module, an unmanned aerial vehicle data acquisition module, an unmanned aerial vehicle communication module and a database; The central control module is connected to the drone data acquisition module, the drone communication module is connected to the survey and demarcation drone, and the drone data acquisition module is connected to the database. The survey and demarcation drone includes a mother drone and a child drone. A mother drone carries more than one child drone. The mother drone can perform the release operation of the child drone, and the child drone has the function of independent flight and image shooting. The mother-child drones transmit data through the drone communication module; The UAV data acquisition module obtains the path dynamic planning data from the wireless communication module and the database. The path dynamic planning data includes: the initial UAV path planning data of the survey and the data obtained by the UAV. The data obtained by the UAV includes: terrain images, meteorological data, and its own position and flight status information; Meteorological data include: temperature, humidity, air pressure, wind speed, and cloud cover; The central control module is used to perform the task of controlling the survey and demarcation drone.

2. A survey and demarcation data acquisition and transmission control system according to claim 1, characterized in that: The central control module specifically includes: The data structuring module is used to structure the data acquired by the drone to obtain ordered information in two structural dimensions. The basic structural elements included in the first structural dimension are objects, including landforms, weather, and drones; the basic structural elements included in the second structural dimension are time series units; Objects for extracting orderliness information; Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the data collection cycle, and map one part to a time sequence unit. The order of the time sequence units is consistent with the time order of the collection cycle of the specific features; Establishing a mapping between the extracted objects and their associated specific features; For any two objects, if there is a correlation between the associated specific features related to the data structuring task or there is a correlation between the objects related to the data structuring task, then an object relationship is established between the two objects; An initial path recognition module is used to identify the initial UAV path planning data of the survey to obtain the initial path features; A time sequence unit recognition module, which is used to recognize the time sequence unit of the object to obtain the representation features of the object; An environment recognition module, which is used to fuse the representation features of the object to obtain the representation features of the environment; The path dynamic planning module is used to identify the environmental representation features and the initial path features to obtain the route adjustment decision for controlling the survey and demarcation UAV.

3. A survey and demarcation data acquisition and transmission control system according to claim 2, characterized in that: Methods for processing and obtaining ordered information include: Convolutional Neural Networks algorithm and Word Embedding algorithm.

4. The survey and demarcation data acquisition and transmission control system according to claim 2 is characterized in that: Specific features associated with landforms: landform images; Specific characteristics of meteorological associations: temperature, humidity, air pressure, wind speed, cloud cover; Specific characteristics associated with the drone: location, flight status.

5. The survey and demarcation data acquisition and transmission control system according to claim 2 is characterized in that: Relevance to data structuring tasks include: The landforms are adjacent in spatial location; The connection between weather and drones is that weather can affect the flight path of drones; The connection between topography and drones is that topographic features affect the flight path of drones.

6. The survey and demarcation data acquisition and transmission control system according to claim 2 is characterized in that: The route adjustment decision includes whether the mother UAV releases the child UAV, the route adjustment parameters of the mother UAV and the route of the released child UAV.

7. The survey and demarcation data acquisition and transmission control system according to claim 2 is characterized in that: RNN is used as the initial path recognition module, GRU is used as the timing unit recognition module, GCN is used as the environment recognition module, and full connection is used to execute the path dynamic planning module.

8. The survey and demarcation data acquisition and transmission control system according to claim 7 is characterized in that: The aforementioned RNN, GRU and GCN all need to update parameters through training, and they are jointly trained with the fully connected path dynamic planning module.

9. The survey and demarcation data collection and transmission control system according to claim 8, characterized in that: Reward function for joint training as follows: ； represents the data quality score, represents the energy consumption of the drone, Indicates the task completion time. , , Represent the first, second, and third weight coefficients respectively.

10. A survey and demarcation data collection and transmission control method, characterized in that: The following steps are involved: Plan initial routes and collect information; Process information and assess whether the route is feasible; When the route is not feasible, obtain the route adjustment decision and decide whether to release the sub-UAV for high-precision mapping tasks; After completion, data fusion processing is performed to generate high-quality surveying and mapping results.

Images