Geological park geological relic information acquisition method and system based on multi-source data

Abstract

The invention discloses a geological park geological relics information acquisition method and system based on multi-source data, and the method comprises the steps: obtaining a GIS ground surface image, geological relics environment parameters and geological relics updating data, updating the flight path of an unmanned aerial vehicle, executing the flight strategy of the unmanned aerial vehicle, obtaining a low-altitude aerial image, carrying out the data matching and data correction, and obtaining the geological park geological relics information. Determining a data fusion area according to the multi-source correction data, constructing a geological relic multi-source data fusion model based on the multi-source correction data, and inputting to-be-collected geological park multi-source sensing data into the geological relic multi-source data fusion model to obtain geological relic collection information, and determining an acquisition scheme according to the data fusion area and the acquisition time. The method not only can improve the efficiency and accuracy of geological park geological relic information acquisition based on multi-source data, but also has good interpretability, and can be directly applied to a geological park geological relic information acquisition system based on multi-source data.

Description

Technical Field

[0001] The present invention relates to the field of data collection, and in particular to a method and system for collecting geological heritage information in a geological park based on multi-source data. Background Art

[0002] As an important place to display the earth's evolutionary history, geological relics and natural landscapes, geological parks have important scientific, educational and tourism values. The improvement of geological relic information collection requirements and the emergence of new technologies have also promoted the development of geological relic information collection methods, which plays an important role in improving data collection efficiency and accuracy.

[0003] Traditional geological relic information collection methods mainly rely on manual investigation and single data source, and have the following problems: low data collection efficiency, and the dynamic changes of geological relic information require the system to have incremental learning capabilities to adapt to the addition of new data and the update of old data, and the existing methods do not update data in time; the diversity and complexity of geological relics make it difficult for a single data source to fully reflect its true state; there are spatiotemporal inconsistencies and modal differences between different data sources, making it difficult to effectively match and fuse these data; multimodal data has modal imbalance and uneven features, and the accuracy and reliability of the fusion results are difficult to guarantee. Therefore, the present invention integrates multi-source perception data, and designs a geological park geological relic information collection method and system based on multi-source data through dynamic incremental learning, spatiotemporal attention mechanism and cross-modal fusion technology, which overcomes the shortcomings of traditional geological relic information collection technology, comprehensively collects and efficiently manages geological relic information, and provides strong support for scientific research and tourism development of geological parks. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for collecting geological heritage information in a geological park based on multi-source data.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Construct a multi-source perception network to obtain multi-source perception data of the Geopark;

[0008] Performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion region according to the multi-source corrected data; the data fusion region includes a first fusion region and a second fusion region;

[0009] Constructing a geological heritage multi-source data fusion model based on the multi-source corrected data;

[0010] The multi-source perception data of the geological park to be collected is input into the multi-source data fusion model of the geological relics to obtain the geological relics collection information, and the collection plan is determined according to the data fusion area and the collection time.

[0011] Furthermore, the method of constructing the multi-source perception network to obtain multi-source perception data of the geological park includes:

[0012] Acquire GIS surface images through satellite remote sensing technology, and generate a hierarchical navigation map of geological relics based on the GIS surface images and corresponding geographic coordinates; the hierarchical navigation map of geological relics is divided into levels according to continents, countries, administrative regions and park projects;

[0013] Ground sensors are set at representative monitoring points inside the Geopark to collect environmental parameters of geological relics, and the environmental parameters of geological relics are allocated to the corresponding levels of the geological relics hierarchical navigation map according to the geographical coordinates of the ground sensors; the representative monitoring points are determined by a clustering algorithm;

[0014] Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on user spatiotemporal information, and review user uploaded data to obtain geological heritage update data; the tourist trajectory includes the coordinates and elevation information of all tourists when uploading data;

[0015] Update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images;

[0016] The multi-source perception data of the geological park is composed of GIS surface images, geological heritage environmental parameters, geological heritage update data and low-altitude aerial images and transmitted to the transit database.

[0017] Furthermore, the method for obtaining the updated data of the geological relics comprises:

[0018] Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on spatiotemporal information, process user uploaded data to obtain audit data, and retrieve the audit data based on user identity to obtain geological heritage update data; the user identity includes researchers and tourists; the spatiotemporal information is obtained from the EXIF ​​data of the images uploaded by the user;

[0019] The specific method of verifying the user identity and spatiotemporal information is: determining the user identity according to the user code, and filtering out the spatiotemporal information and user uploaded data other than the target geological park according to the spatiotemporal information;

[0020] The specific method for processing the user uploaded data to obtain the audit data is: using a language model to process the text information uploaded by the user to obtain description features, using a lightweight image model to process the relic image uploaded by the user to obtain image features and relic feature images, fusing the description features with the image features to obtain relic features, and combining the relic features and the relic feature images to form the audit data; the language model includes the TF-IDF method and the mutual information method; the lightweight image model includes the CNN convolutional neural network, the PCA principal component analysis method and the activation maximization method;

[0021] The specific method of retrieving the audit data according to the user identity to obtain the geological heritage update data is as follows: when the user identity is a researcher, the audit data is directly determined to be the geological heritage update data and the audit result is fed back to the user; when the user identity is a tourist, the audit data is compared and retrieved with the platform database; if there is no duplicate data, the audit data is determined to be the geological heritage update data and the audit result is fed back to the user; if the data is duplicated, the geological heritage update data is not generated and the audit result is fed back to the user; the platform database is composed of the geological heritage update data generated historically;

[0022] The specific method for comparing and retrieving the audit data with the platform database is: setting a distance threshold, calculating the upload distance between the audit data and the platform data based on the geographic coordinates, screening the platform data with an upload distance less than the distance threshold as fuzzy matching data, calculating the comprehensive similarity between the audit data and the fuzzy matching data, and determining whether the data is repeated based on the comprehensive similarity; the comprehensive similarity is the sum of the cosine similarity and Jaccard similarity weighted values ​​of the two sets of data heritage feature vectors.

[0023] Furthermore, the method for updating the flight path of the drone includes:

[0024] The original flight path of the drone was converted into UTM coordinates, and the DBSCAN clustering was used to process the tourist trajectories to form hotspot areas. The GIS surface image was divided into m blocks of geological heritage areas according to different pixel segments, and the statistical method was used to set the regional weights according to the importance of the geological heritage.

[0025] Determine the objective function of the UAV flight path update, the expression is:

[0026] AIM min =α 1 ·C cost +α 2 ·(1-C cover )+α 3 ·R risk +α 4 ·C tem

[0027]

[0028]

[0029]

[0030] Where AIM min is the objective function for updating the flight path of the UAV, α 1 is the path cost weight, C cost is the path cost, n is the number of waypoints, P i is the UTM coordinate of the ith waypoint, ‖·‖ is the Euclidean distance between adjacent waypoints, and w turn is the steering angle penalty weight, θ i is the heading angle of the ith waypoint, w alt is the height change penalty weight, h i is the flight altitude of the ith waypoint, α 2 is the coverage weight, C cover is the coverage, A ver is the area of ​​tourist hotspots verified by drones, A total is the total area of ​​tourist hotspots, λ is the blind spot coverage weight coefficient, A bli A is the newly covered historical blind area. his is the total area of ​​historical blind spots, α 3 is the risk factor, R risk is the risk factor, r k is the area weight of the kth area, T k is the dwell time of the UAV in the kth area, d k is the minimum distance from the path to the center of the kth block, ε is the smoothing factor, α 4 is the time weight, is time consistency, v i is the flight speed of the i-th path, ΔT i is the flight time of the i-th path;

[0031] The original flight path of the drone is used as the initial path of the ant colony, and the adaptive ant colony algorithm is used to update the pheromone concentration:

[0032]

[0033]

[0034] where τ ij (t+1) is the pheromone concentration between the t+1th update time points i and j, τ ij (t) is the pheromone concentration between the tth update time points i and j, ρ is the pheromone volatility, p is the number of ants in the ant colony, is the pheromone concentration increment of the kth ant between the tth update time points i and j, also representing the adaptive weight, w 1 is the path weight of the elite ant e, is the pheromone concentration increment of the elite ant e between the tth update time points i and j, R min , R max is the minimum and maximum value of the ant path to the end point in this iteration, Q is the pheromone intensity coefficient, L is t is the path length of the kth ant at the tth update, is the coverage adaptive weight, N ver is the number of unverified trajectory points, N total is the number of all trajectory points, w 3 is the cost adaptive weight, w 2 +w 3 =1;

[0035] The elite strategy is used to retain the top three preferred paths in each generation and to multiply the pheromone concentration of the preferred paths. The Bayesian optimization parameter combination is adopted; the parameter combination includes α 1 , α 2 , α 3 , α 4 , ρ and Q;

[0036] The pheromone concentration is updated multiple times, and the path with the highest pheromone concentration is selected as the optimal path. The objective function value is calculated based on the optimal path until the objective function is minimized and the output UAV flight path is stopped from being updated.

[0037] Furthermore, the method for determining the data fusion area includes:

[0038] The multi-source correction data includes macroscopic geological relics correction images, geological relics environment correction parameters and geological relics update data;

[0039] Based on the geographic coordinate matching of GIS surface images and low-altitude aerial images in the transfer database, the matching results are imported into ArcGIS software for image synthesis to output macroscopic geological relic images. The tourist trajectory and the macroscopic geological relic image are located according to the geographic coordinates. The elevation information and time information of the tourist trajectory are used to correct the corresponding information of the macroscopic geological relic image to obtain the macroscopic geological relic corrected image. The macroscopic geological relic corrected image collected this time is compared with the last time to determine the image change area, and the geographic coordinate range corresponding to the image change area is set as the first fusion area.

[0040] Match the representative monitoring point in the transit database that is closest to the geographical coordinates of the tourist trajectory point, use the relic characteristics of the tourist trajectory point to correct the corresponding data of the geological relic environmental parameters of the representative monitoring point to obtain the geological relic environmental correction parameters, and set the geographical coordinates corresponding to the geological relic update data as the second fusion area.

[0041] Furthermore, the method for constructing the multi-source data fusion model of geological relics includes:

[0042] The updated data of geological relics, the environmental correction parameters of geological relics and the corrected images of macroscopic geological relics are combined according to geographic coordinates and aligned in time series to form a multi-source data set. The multi-source data are divided into a training set and a validation set in a ratio of 7:3 using random forest.

[0043] The multi-source data fusion model of geological relics includes dynamic incremental learning module, spatiotemporal attention module and cross-modal fusion module;

[0044] The dynamic incremental learning module uses elastic weight solidification to dynamically adjust model parameters and retain important weights, and uses a memory playback mechanism to store old data and conduct joint training with new data;

[0045] The spatiotemporal attention module uses the Transformer encoder to capture the temporal dependency of environmental parameters and determine the temporal attention weights, uses CBAM to focus on the feature map of the relics and the key areas of the macroscopic geological relics to correct the image, and performs weighted fusion of the outputs of temporal attention and spatial attention to generate spatiotemporal features.

[0046] The cross-modal fusion module adopts a cross-modal attention mechanism to align the features of different modalities, and adopts a gated multimodal fusion mechanism to dynamically adjust the contribution of each modality to output a unified fusion feature; the gated multimodal fusion mechanism includes a gated unit and a feature fusion module, the gated unit generates different modal weights based on Softmax, and the feature fusion module integrates the weighted modal features; the unified fusion feature includes a point cloud map of the spatial distribution of geological relics, a time series map of the evolution of geological relics, a feature description of geological relics, and a feature vector of geological relics;

[0047] The output layer extracts the multi-source data index associated with the unified fusion feature, and finally outputs the geological relic collection information; the geological relic collection information includes the unified fusion feature and the corresponding multi-source data index;

[0048] The loss functions include cross entropy loss function and cosine similarity loss function. The LAMB optimizer is used to adjust the model hyperparameters and improve the convergence speed, and the verification machine is used to verify the model performance. The cross entropy loss function is used to classify geological relics into predefined categories; the cosine similarity loss function ensures the consistency of multimodal features after fusion.

[0049] Furthermore, the method for determining the acquisition scheme includes:

[0050] Determine the change degree of geological relic information according to the fusion area and the deviation of geological relic collection information. When the change degree of geological relic information is greater than the change degree threshold or the collection interval is greater than the set collection period, store the geological relic collection information in the local database and back it up to the cloud database. Otherwise, back up the geological relic collection information in the cloud database.

[0051] Calculate the change degree of the geological relics information, the expression is:

[0052]

[0053] Where D chang is the degree of change of geological heritage information, β 1 , β 2 is the fusion area weight, s 1 is the number of the first fusion regions, s 2 is the number of the second fusion region, A 1i is the area of ​​the first fusion region of the i-th region, ε 1i is the information deviation of geological relics collected in the first fusion area of ​​the i-th region, A 2j The area of ​​the jth second fusion region, ε 2j The information deviation of the geological heritage collection for the jth second fusion area.

[0054] Secondly, the geological park geological heritage information collection system based on multi-source data includes:

[0055] Perception network module: used to construct a multi-source perception network to obtain multi-source perception data of the geological park; the multi-source perception network includes satellite remote sensing technology to obtain GIS surface images, ground sensors to collect geological relics environmental parameters, geological relics information update platform to obtain geological relics update data and drones to obtain low-altitude aerial images;

[0056] Platform module: used to verify user identity and spatiotemporal information, generate tourist trajectories based on the user's spatiotemporal information, and review user uploaded data to obtain updated data of the geological relics;

[0057] Drone module: used to update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images;

[0058] Data processing module: used for performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion area according to the multi-source corrected data; the data fusion area includes a first fusion area and a second fusion area;

[0059] Model module: used to construct a geological heritage multi-source data fusion model based on the multi-source correction data, and input the multi-source perception data of the geological park to be collected into the geological heritage multi-source data fusion model to obtain geological heritage collection information;

[0060] Management module: used to view and manage the multi-source perception data and the geological relics collection information, and determine the collection plan according to the data fusion area and collection time.

[0061] The beneficial effects of the present invention are:

[0062] The present invention is a method and system for collecting geological heritage information in a geological park based on multi-source data. Compared with the prior art, the present invention has the following technical effects:

[0063] The present invention can improve the data preprocessing capability and enhance the model adaptability in the geological relic information collection of geological parks by constructing a multi-source perception network, setting up a platform, updating the flight path, matching data, correcting data and building a model, and can realize the accurate matching and intelligent fusion of multi-source heterogeneous data, thereby improving the efficiency and accuracy of geological relic information collection in geological parks, optimizing the geological relic information collection technology in geological parks, greatly saving resources, improving work efficiency, realizing the collection of geological relic information in geological parks, and providing strong support for scientific research and tourism development in geological parks. It can adapt to different geological relic information collection systems based on multi-source data in geological parks and terminal collection needs of geological relic information in geological parks based on multi-source data of different users, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 The present invention is a flowchart of the steps of the method for collecting geological heritage information in a geological park based on multi-source data. DETAILED DESCRIPTION

[0065] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0066] The method and system for collecting geological heritage information of a geological park based on multi-source data of the present invention include the following steps:

[0067] like Figure 1 As shown, in this embodiment, the following steps are included:

[0068] Construct a multi-source perception network to obtain multi-source perception data of the Geopark;

[0069] Performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion region according to the multi-source corrected data; the data fusion region includes a first fusion region and a second fusion region;

[0070] Constructing a geological heritage multi-source data fusion model based on the multi-source corrected data;

[0071] The multi-source perception data of the geological park to be collected is input into the multi-source data fusion model of the geological relics to obtain the geological relics collection information, and the collection plan is determined according to the data fusion area and the collection time.

[0072] In this embodiment, the method for constructing the multi-source perception network to obtain multi-source perception data of the geological park includes:

[0073] Acquire GIS surface images through satellite remote sensing technology, and generate a hierarchical navigation map of geological relics based on the GIS surface images and corresponding geographic coordinates; the hierarchical navigation map of geological relics is divided into levels according to continents, countries, administrative regions and park projects;

[0074] Ground sensors are set at representative monitoring points inside the Geopark to collect environmental parameters of geological relics, and the environmental parameters of geological relics are allocated to the corresponding levels of the geological relics hierarchical navigation map according to the geographical coordinates of the ground sensors; the representative monitoring points are determined by a clustering algorithm; the environmental parameters of geological relics include temperature, humidity, vibration, magnetic field and noise;

[0075] Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on user spatiotemporal information, and review user uploaded data to obtain geological heritage update data; the tourist trajectory includes the coordinates and elevation information of all tourists when uploading data;

[0076] Update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images;

[0077] The multi-source perception data of the Geopark is composed of GIS surface images, geological heritage environmental parameters, geological heritage update data and low-altitude aerial images and transmitted to the transit database;

[0078] In the actual evaluation, taking a geological park with an area of ​​100 square kilometers as an example, the GIS surface image obtained by satellite remote sensing technology has a resolution of 1m / pixel and is divided into m=10,000 areas;

[0079] Through the clustering algorithm, 20 representative monitoring points and locations in the Geopark were determined. Ground sensors were set at the monitoring points to collect the environmental parameters of the geological relics. The monitoring data of two monitoring points were taken as examples: Monitoring point 1 (temperature 25°C, humidity 60%, vibration 0.5m / s 2 , magnetic field 45μT, noise 40dB), monitoring point 2 (temperature 24℃, humidity 62%, vibration 0.4m / s 2 , magnetic field 43μT, noise 42dB).

[0080] In this embodiment, the method for obtaining the updated data of the geological relics includes:

[0081] Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on spatiotemporal information, process user uploaded data to obtain audit data, and retrieve the audit data based on user identity to obtain geological heritage update data; the user identity includes researchers and tourists; the spatiotemporal information is obtained from the EXIF ​​data of the user uploaded image, including geographic coordinates, coordinate elevation and time information;

[0082] The specific method of verifying the user identity and spatiotemporal information is: determining the user identity according to the user code, and filtering out the spatiotemporal information and user uploaded data other than the target geological park according to the spatiotemporal information;

[0083] The specific method for processing the user uploaded data to obtain the audit data is: using a language model to process the text information uploaded by the user to obtain description features, using a lightweight image model to process the relic image uploaded by the user to obtain image features and relic feature images, fusing the description features with the image features to obtain relic features, and combining the relic features and the relic feature images to form the audit data; the language model includes a TF-IDF method and a mutual information method, the TF-IDF method performs feature extraction on the text information, and the mutual information method performs feature selection on the extracted features to obtain description features; the lightweight image model includes a CNN convolutional neural network, a PCA principal component analysis method, and an activation maximization method, the CNN convolutional neural network performs feature extraction and classification on the relic image uploaded by the user, the PCA principal component analysis method performs feature selection and dimensionality reduction on the extracted features to obtain image features, and the activation maximization method generates a relic feature image according to the extracted features;

[0084] The specific method of retrieving the audit data according to the user identity to obtain the geological heritage update data is as follows: when the user identity is a researcher, the audit data is directly determined to be the geological heritage update data and the audit result is fed back to the user; when the user identity is a tourist, the audit data is compared and retrieved with the platform database; if there is no duplicate data, the audit data is determined to be the geological heritage update data and the audit result is fed back to the user; if the data is duplicated, the geological heritage update data is not generated and the audit result is fed back to the user; the platform database is composed of the geological heritage update data generated historically;

[0085] The specific method for comparing and retrieving the audit data with the platform database is as follows: setting a distance threshold, calculating the upload distance between the audit data and the platform data according to the geographic coordinates, screening the platform data whose upload distance is less than the distance threshold as fuzzy matching data, calculating the comprehensive similarity between the audit data and the fuzzy matching data, and determining whether the data is repeated according to the comprehensive similarity; the comprehensive similarity is the sum of the cosine similarity and the Jaccard similarity weighted values ​​of the two sets of data heritage feature vectors;

[0086] In the actual evaluation, the geological heritage information update platform received 50 user-uploaded data within a week, of which 10 were uploaded by researchers (10 data were directly uploaded after being processed by the language model and lightweight image model and fed back to the researchers), and 40 were uploaded by tourists (40 data were processed by the language model and lightweight image model and compared with the platform database for retrieval, 15 data were judged as non-duplicate and directly uploaded, and 25 data were judged as duplicate and not uploaded, and fed back to the researchers). Take one of the tourist-uploaded data as an example : Its EXIF ​​data shows that the shooting location coordinates are (10.5, 20.3, 150), and the time is 10:00 on May 1, 2023. The uploaded text information is processed by TF-IDF method and mutual information method to obtain the description feature vector [0.2, 0.3, 0.1]. The image feature vector obtained by the lightweight image model is [0.4, 0.2, 0.3]. The fused ruins feature is [0.3, 0.25, 0.2]. The ruins feature image is composed of pixel matrix data;

[0087] The distance threshold is set to 100m, and the upload distance between the audit data and the platform data is calculated to select 5 platform data that meet the distance requirement. The comprehensive similarity between the audit data and the 5 groups of fuzzy matching data is calculated to be 0.77, 0.59, 0.32, 0.6, and 0.15. The comprehensive similarity of the five groups of data is less than the comprehensive similarity threshold of 0.90. In this case, there is no duplicate data in the audit data, and it is determined to be the updated data of geological relics and fed back to tourists and uploaded to the transit database.

[0088] In this embodiment, the method for updating the flight path of the drone includes:

[0089] The original flight path of the drone was converted into UTM coordinates, and the DBSCAN clustering was used to process the tourist trajectories to form hotspot areas. The GIS surface image was divided into m blocks of geological heritage areas according to different pixel segments, and the statistical method was used to set the regional weights according to the importance of the geological heritage.

[0090] Determine the objective function of the UAV flight path update, the expression is:

[0091] AIM min =α 1 ·C cost +α 2 ·(1-C cover )+α 3 ·R risk +α 4 ·C tem

[0092]

[0093]

[0094]

[0095] Where AIM min is the objective function for updating the flight path of the UAV, α 1 is the path cost weight, C cost is the path cost, n is the number of waypoints, P i is the UTM coordinate of the ith waypoint, ‖·‖ is the Euclidean distance between adjacent waypoints, and w turn is the steering angle penalty weight, θ i is the heading angle of the ith waypoint, w alt is the height change penalty weight, h i is the flight altitude of the ith waypoint, α 2 is the coverage weight, C cover is the coverage, A ver is the area of ​​tourist hotspots verified by drones, A total is the total area of ​​tourist hotspots, λ is the blind spot coverage weight coefficient, which is 0.8, A bli A is the newly covered historical blind area. his is the total area of ​​historical blind spots, α 3 is the risk factor, R risk is the risk factor, r k is the area weight of the kth area, T k is the dwell time of the UAV in the kth area, d k is the minimum distance from the path to the center of the kth block, ε is the smoothing factor, α 4 is the time weight, is time consistency, v i is the flight speed of the i-th path, ΔT i is the flight time of the i-th path;

[0096] The original flight path of the drone is used as the initial path of the ant colony, and the adaptive ant colony algorithm is used to update the pheromone concentration:

[0097]

[0098]

[0099] where τ ij (t+1) is the pheromone concentration between the t+1th update time points i and j, τ ij (t) is the pheromone concentration between the tth update time points i and j, ρ is the pheromone volatility, p is the number of ants in the ant colony, is the pheromone concentration increment of the kth ant between the tth update time points i and j, also representing the adaptive weight, w 1 is the path weight of the elite ant e, is the pheromone concentration increment of the elite ant e between the tth update time points i and j, R min , R max is the minimum and maximum value of the ant path to the end point in this iteration, Q is the pheromone intensity coefficient, L is t is the path length of the kth ant at the tth update, is the coverage adaptive weight, N ver is the number of unverified trajectory points, N total is the number of all trajectory points, w 3 is the cost adaptive weight, w 2 +w 3 =1;

[0100] The elite strategy is used to retain the top three preferred paths in each generation and to multiply the pheromone concentration of the preferred paths. The Bayesian optimization parameter combination is adopted; the parameter combination includes α 1 , α 2 , α 3 , α 4 , ρ and Q;

[0101] Update the pheromone concentration multiple times, select the path with the highest pheromone concentration as the optimal path, calculate the objective function value based on the optimal path, and stop updating the output UAV flight path when the objective function is minimized;

[0102] In the actual evaluation, the UTM plane coordinates of the 12 waypoints of the original path of the drone are {(50,80), (120,150), (200,210), (300,320), (400,450), (500,530), (600,680), (700,750), (800,820), (900,900), (1000,1050), (1100,1180)}, and the DBSCAN clustering was used to process the tourists’ trajectories to form five hotspots with areas of 8, 12, 10, 15, and 9 square kilometers, respectively;

[0103] Take the path cost weight α 1 =0.002, coverage weight α 2 =5, risk factor α 3 =0.2, time weight α 4 =0.1, steering angle penalty weight w turn =0.3, height change penalty weight w alt =0.2, blind area coverage weight coefficient λ=0.8, pheromone evaporation intensity ρ=0.5, pheromone intensity coefficient Q=100, smoothing factor ε=0.1; calculate the objective function AIM of the original path of the drone min =21.9, where: path cost C cost =3500, coverage C cover =0.92(A ver =30, A total =54, A bli =8, A his =15, unit square kilometer), risk factor R risk =55, time consistency C tem =35;

[0104] After several iterations, the path with the highest pheromone concentration was selected as the optimal path, and the new waypoint coordinates were {(45,75), (110,140), (190,220), (290,310), (390,440), (490,520), (590,670), (690,740), (790,820), (890,895), (1000,1040), (1090,1170)}.

[0105] In this embodiment, the method for determining the data fusion area includes:

[0106] The multi-source correction data includes macroscopic geological relics correction images, geological relics environment correction parameters and geological relics update data;

[0107] Based on the geographic coordinate matching of GIS surface images and low-altitude aerial images in the transfer database, the matching results are imported into ArcGIS software for image synthesis to output macroscopic geological relic images. The tourist trajectory and the macroscopic geological relic image are located according to the geographic coordinates. The elevation information and time information of the tourist trajectory are used to correct the corresponding information of the macroscopic geological relic image to obtain the macroscopic geological relic corrected image. The macroscopic geological relic corrected image collected this time is compared with the last time to determine the image change area, and the geographic coordinate range corresponding to the image change area is set as the first fusion area.

[0108] Match the representative monitoring point in the transit database that is closest to the geographical coordinates of the tourist trajectory point, use the heritage characteristics of the tourist trajectory point to correct the corresponding data of the geological heritage environmental parameters of the representative monitoring point to obtain the geological heritage environmental correction parameters, and set the geographical coordinates corresponding to the geological heritage update data as the second fusion area;

[0109] In the actual evaluation, taking the multi-source sensor data of a geological park with an area of ​​100 square kilometers within a week as an example, by comparing the macro geological relics correction map collected this time with the last time, it was found that there was a change in the image of a region with a geographic coordinate range of (X: 100-200, Y: 300-400) and an area of ​​10,000 square meters, and this region was set as the first fusion region;

[0110] Taking the tourist trajectory point (10.5, 20.3, 150) as an example, the geological relic environmental parameters of the nearest representative monitoring point are matched to correct the temperature to 25.5℃ and the humidity to 61%, and the 5m area centered on the tourist trajectory point (10.5, 20.3, 150) is set as the second fusion area.

[0111] In this embodiment, the method for constructing the multi-source data fusion model of geological relics includes:

[0112] The updated data of geological relics, the environmental correction parameters of geological relics and the corrected images of macroscopic geological relics are combined according to geographic coordinates and aligned in time series to form a multi-source data set. The multi-source data are divided into a training set and a validation set in a ratio of 7:3 using random forest.

[0113] The multi-source data fusion model of geological relics includes dynamic incremental learning module, spatiotemporal attention module and cross-modal fusion module;

[0114] The dynamic incremental learning module uses the elastic weight solidification method to dynamically adjust the model parameters and retain important weights, and uses the memory playback mechanism to store old data and jointly train with new data; the spatiotemporal attention module uses the Transformer encoder to capture the temporal dependency of environmental parameters and determine the temporal attention weights, uses CBAM to focus on the relic feature map and the key areas of the macroscopic geological relics correction image, and performs weighted fusion of the outputs of temporal attention and spatial attention to generate spatiotemporal features;

[0115] The cross-modal fusion module adopts a cross-modal attention mechanism to align the features of different modalities, and adopts a gated multimodal fusion mechanism to dynamically adjust the contribution of each modality to output a unified fusion feature; the gated multimodal fusion mechanism includes a gated unit and a feature fusion module, the gated unit generates different modal weights based on Softmax, and the feature fusion module integrates the weighted modal features; the unified fusion feature includes a point cloud map of the spatial distribution of geological relics, a time series map of the evolution of geological relics, a feature description of geological relics, and a feature vector of geological relics;

[0116] The output layer extracts the multi-source data index associated with the unified fusion feature, and finally outputs the geological relic collection information; the geological relic collection information includes the unified fusion feature and the corresponding multi-source data index;

[0117] The loss functions include cross entropy loss function and cosine similarity loss function. The LAMB optimizer is used to adjust the model hyperparameters and improve the convergence speed, and the verification machine is used to verify the model performance. The cross entropy loss function is used to classify geological relics into predefined categories. The cosine similarity loss function ensures the consistency of multimodal features after fusion.

[0118] In the actual evaluation, the elastic weight solidification method uses EWC and playback buffer, and the expression is:

[0119]

[0120]

[0121]

[0122] Among them, F i is the Fisher information matrix value of the i-th parameter, For the old task dataset D old The expectation of sample x in the model is logp(y|x,ξ), logp(y|x,ξ) is the maximum likelihood that the model outputs label y for sample x under parameter ξ, ξ i is the parameter of the ith model, is the likelihood parameter ξ i The gradient of L EWC is the EWC regularization loss term, is the regularization strength, ξ old,i is the parameter of the i-th old model, B t+1 is the playback buffer at time t+1, UpdateBuffer(·) is the buffer update function, x i is the i-th data sample, f(x i ) is the sample x i The characteristic vector of , G is the total number of buffer samples;

[0123] The spatiotemporal attention module introduces the spatiotemporal attenuation term and uses the spatiotemporal attenuation term to modify the attention score expression as follows:

[0124] Decay(d,Δt)=δ 1 ·exp{-δ 2 ·d}+δ 3 ·exp{-δ 4 ·Δt}

[0125]

[0126] Where Decay(d,t) is the spatiotemporal decay term, d is the geographical distance, Δt is the time difference, δ 1 , δ 2 , δ 3 , δ 4 is an adjustable attenuation parameter, AttentionScor is the corrected attention score, Q is the satellite feature, and K is the drone feature;

[0127] The multi-source perception data of the geological park to be collected is input into the multi-source data fusion model of the geological relics to obtain the geological relics collection information: the spatial distribution point cloud map of the geological relics, the time series map of the geological relics evolution, the characteristic description of the geological relics and the characteristic vector of the geological relics; taking the characteristic description of some geological relics as an example: tourist 001zzy found a columnar rock with a height of 15 meters and a diameter of about 3 meters at (10.5, 20.3, 150). The surface of the rock is gray-black and has a honeycomb texture. There are fossils with a complete clover outline on the bottom surface of the rock. The corresponding geological relic characteristic vector [regional weight, morphological uniqueness weight, texture and color feature weight, geological structure feature weight, paleontological information weight] is [0.4, 0.35, 0.3, 0.2, 0.18].

[0128] In this embodiment, the method for determining the acquisition scheme includes:

[0129] Determine the change degree of geological relic information according to the fusion area and the deviation of geological relic collection information. When the change degree of geological relic information is greater than the change degree threshold or the collection interval is greater than the set collection period, store the geological relic collection information in the local database and back it up to the cloud database. Otherwise, back up the geological relic collection information in the cloud database.

[0130] Calculate the change degree of the geological relics information, the expression is:

[0131]

[0132] Where D chang is the degree of change of geological heritage information, β 1 , β 2 is the fusion area weight, s 1 is the number of the first fusion regions, s 2 is the number of the second fusion region, A 1i is the area of ​​the first fusion region of the i-th region, ε 1i is the information deviation of geological relics collected in the first fusion area of ​​the i-th region, A 2j The area of ​​the jth second fusion region, ε 2j The information deviation of the geological heritage collection for the jth second fusion area;

[0133] In the actual evaluation, there are 4 first fusion regions in this acquisition, and the corresponding regional areas and information deviations are (10000, 0.2), (8000, 0.18), (12000, 0.22), (9000, 0.15), and there are 8 first fusion regions, and the corresponding regional areas and information deviations are (78.5, 0.8), (12.56, 0.88), (12.56, 0.75), (50.24, 0.66), (78.5, 0.58), (50.24, 0.92), (28.26, 0.82), (28.26, 0.79), and the fusion region weight β 1 =0.6, β 2 =0.4, the change degree of geological heritage information D is calculated chang =4559.47, which is greater than the change degree threshold of 3000. The geological heritage collection information is stored in the local database and backed up to the cloud database.

[0134] Secondly, the geological park geological heritage information collection system based on multi-source data includes:

[0135] Perception network module: used to construct a multi-source perception network to obtain multi-source perception data of the geological park; the multi-source perception network includes satellite remote sensing technology to obtain GIS surface images, ground sensors to collect geological relics environmental parameters, geological relics information update platform to obtain geological relics update data and drones to obtain low-altitude aerial images;

[0136] Platform module: used to verify user identity and spatiotemporal information, generate tourist trajectories based on the user's spatiotemporal information, and review user uploaded data to obtain updated data of the geological relics;

[0137] Drone module: used to update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images;

[0138] Data processing module: used for performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion area according to the multi-source corrected data; the data fusion area includes a first fusion area and a second fusion area;

[0139] Model module: used to construct a geological heritage multi-source data fusion model based on the multi-source correction data, and input the multi-source perception data of the geological park to be collected into the geological heritage multi-source data fusion model to obtain geological heritage collection information;

[0140] Management module: used to view and manage the multi-source perception data and the geological relics collection information, and determine the collection plan according to the data fusion area and collection time.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for collecting geological heritage information in a geological park based on multi-source data, characterized in that: The following steps are involved: S1. Construct a multi-source perception network to obtain multi-source perception data of the Geopark; S2, performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion region according to the multi-source corrected data; the data fusion region includes a first fusion region and a second fusion region; S3, constructing a geological heritage multi-source data fusion model based on the multi-source corrected data; S4. Input the multi-source perception data of the geological park to be collected into the multi-source data fusion model of the geological relics to obtain the geological relics collection information, and determine the collection plan according to the data fusion area and collection time.

2. The method for collecting geological relics information in a geological park based on multi-source data according to claim 1 is characterized in that: The method for constructing the multi-source perception network to obtain multi-source perception data of the geological park includes: Acquire GIS surface images through satellite remote sensing technology, and generate a hierarchical navigation map of geological relics based on the GIS surface images and corresponding geographic coordinates; the hierarchical navigation map of geological relics is divided into levels according to continents, countries, administrative regions and park projects; Ground sensors are set at representative monitoring points inside the Geopark to collect environmental parameters of geological relics, and the environmental parameters of geological relics are allocated to the corresponding levels of the geological relics hierarchical navigation map according to the geographical coordinates of the ground sensors; the representative monitoring points are determined by a clustering algorithm; Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on user spatiotemporal information, and review user uploaded data to obtain geological heritage update data; the tourist trajectory includes the coordinates and elevation information of all tourists when uploading data; Update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images; The multi-source perception data of the geological park is composed of GIS surface images, geological heritage environmental parameters, geological heritage update data and low-altitude aerial images and transmitted to the transit database.

3. The method for collecting geological relics information in a geological park based on multi-source data according to claim 2 is characterized in that: The method for obtaining the updated data of the geological relics comprises: Build a geological heritage information update platform, verify user identity and spatiotemporal information, generate tourist trajectories based on spatiotemporal information, process user uploaded data to obtain audit data, and retrieve the audit data based on user identity to obtain geological heritage update data; the user identity includes researchers and tourists; the spatiotemporal information is obtained from the EXIF ​​data of the images uploaded by the user; The specific method of verifying the user identity and spatiotemporal information is: determining the user identity according to the user code, and filtering out the spatiotemporal information and user uploaded data other than the target geological park according to the spatiotemporal information; The specific method for processing the user uploaded data to obtain the audit data is: using a language model to process the text information uploaded by the user to obtain description features, using a lightweight image model to process the relic image uploaded by the user to obtain image features and relic feature images, fusing the description features with the image features to obtain relic features, and combining the relic features and the relic feature images to form the audit data; the language model includes the TF-IDF method and the mutual information method; the lightweight image model includes the CNN convolutional neural network, the PCA principal component analysis method and the activation maximization method; The specific method of retrieving the audit data according to the user identity to obtain the geological heritage update data is as follows: when the user identity is a researcher, the audit data is directly determined to be the geological heritage update data and the audit result is fed back to the user; when the user identity is a tourist, the audit data is compared and retrieved with the platform database; if there is no duplicate data, the audit data is determined to be the geological heritage update data and the audit result is fed back to the user; if the data is duplicated, the geological heritage update data is not generated and the audit result is fed back to the user; the platform database is composed of the geological heritage update data generated historically; The specific method for comparing and retrieving the audit data with the platform database is: setting a distance threshold, calculating the upload distance between the audit data and the platform data based on the geographic coordinates, screening the platform data with an upload distance less than the distance threshold as fuzzy matching data, calculating the comprehensive similarity between the audit data and the fuzzy matching data, and determining whether the data is repeated based on the comprehensive similarity; the comprehensive similarity is the sum of the cosine similarity and Jaccard similarity weighted values ​​of the two sets of data heritage feature vectors.

4. The method for collecting geological relics information in a geological park based on multi-source data according to claim 2 is characterized in that: The method for updating the flight path of the drone comprises: The original flight path of the drone was converted into UTM coordinates, and the DBSCAN clustering was used to process the tourist trajectories to form hotspot areas. The GIS surface image was divided into m blocks of geological heritage areas according to different pixel segments, and the statistical method was used to set the regional weights according to the importance of the geological heritage. Determine the objective function of the UAV flight path update, the expression is: AIM min =α1·C cost +α2·(1-C cover )+α3·R risk +α4·C tem Where AIM min is the objective function for updating the flight path of the UAV, α1 is the path cost weight, C cost is the path cost, n is the number of waypoints, P i is the UTM coordinate of the ith waypoint, ‖·‖ is the Euclidean distance between adjacent waypoints, and w turn is the steering angle penalty weight, θ i is the heading angle of the ith waypoint, w alt is the height change penalty weight, h i is the flight altitude of the ith waypoint, α2 is the coverage weight, C cover is the coverage, A ver is the area of ​​tourist hotspots verified by drones, A total is the total area of ​​tourist hotspots, λ is the blind spot coverage weight coefficient, A bli A is the newly covered historical blind area. his is the total area of ​​historical blind spots, α3 is the risk coefficient, R risk is the risk factor, r k is the area weight of the kth area, T k is the dwell time of the UAV in the kth area, d k is the minimum distance from the path to the center of the kth block area, ε is the smoothing factor, α4 is the time weight, is time consistency, v i is the flight speed of the i-th path, ΔT i is the flight time of the i-th path; The original flight path of the drone is used as the initial path of the ant colony, and the adaptive ant colony algorithm is used to update the pheromone concentration: where τ ij (t+1) is the pheromone concentration between the t+1th update time points i and j, τ ij (t) is the pheromone concentration between the tth update time point i and time j, ρ is the pheromone volatility intensity, p is the number of ants in the ant colony, is the pheromone concentration increment between i and j of the kth ant at the tth update time, also representing the adaptive weight, w1 is the path weight of the elite ant e, is the pheromone concentration increment of the elite ant e between the tth update time point i and time j, R min , R max is the minimum and maximum value of the ant path to the end point in this iteration, Q is the pheromone intensity coefficient, L is t is the path length of the kth ant at the tth update, is the coverage adaptive weight, N ver is the number of unverified trajectory points, N total is the number of all trajectory points, w3 is the cost adaptive weight, w2+w3=1; The elite strategy is used to retain the top three preferred paths in each generation and to multiply the pheromone concentration of the preferred paths. A Bayesian optimization parameter combination is used; the parameter combination includes α1, α2, α3, α4, ρ and Q; The pheromone concentration is updated multiple times, and the path with the highest pheromone concentration is selected as the optimal path. The objective function value is calculated based on the optimal path until the objective function is minimized and the output UAV flight path is stopped from being updated.

5. The method for collecting geological relics information in a geological park based on multi-source data according to claim 1 is characterized in that: The method for determining the data fusion area includes: The multi-source correction data includes macroscopic geological relics correction images, geological relics environment correction parameters and geological relics update data; Based on the geographic coordinate matching of GIS surface images and low-altitude aerial images in the transfer database, the matching results are imported into ArcGIS software for image synthesis to output macroscopic geological relic images. The tourist trajectory and the macroscopic geological relic image are located according to the geographic coordinates. The elevation information and time information of the tourist trajectory are used to correct the corresponding information of the macroscopic geological relic image to obtain the macroscopic geological relic corrected image. The macroscopic geological relic corrected image collected this time is compared with the last time to determine the image change area, and the geographic coordinate range corresponding to the image change area is set as the first fusion area. Match the representative monitoring point in the transit database that is closest to the geographical coordinates of the tourist trajectory point, use the relic characteristics of the tourist trajectory point to correct the corresponding data of the geological relic environmental parameters of the representative monitoring point to obtain the geological relic environmental correction parameters, and set the geographical coordinates corresponding to the geological relic update data as the second fusion area.

6. The method for collecting geological relics information in a geological park based on multi-source data according to claim 1 is characterized in that: The method for constructing the multi-source data fusion model of geological relics comprises: The updated data of geological relics, the environmental correction parameters of geological relics and the corrected images of macroscopic geological relics are combined according to geographic coordinates and aligned in time series to form a multi-source data set. The multi-source data are divided into a training set and a validation set in a ratio of 7:3 using random forest. The multi-source data fusion model of geological relics includes dynamic incremental learning module, spatiotemporal attention module and cross-modal fusion module; The dynamic incremental learning module uses elastic weight solidification to dynamically adjust model parameters and retain important weights, and uses a memory playback mechanism to store old data and conduct joint training with new data; The spatiotemporal attention module uses the Transformer encoder to capture the temporal dependency of environmental parameters and determine the temporal attention weights, uses CBAM to focus on the relic feature map and the key areas of the macroscopic geological relics correction image, and performs weighted fusion of the outputs of temporal attention and spatial attention to generate spatiotemporal features; The cross-modal fusion module adopts a cross-modal attention mechanism to align the features of different modalities, and adopts a gated multimodal fusion mechanism to dynamically adjust the contribution of each modality to output a unified fusion feature; the gated multimodal fusion mechanism includes a gated unit and a feature fusion module, the gated unit generates different modal weights based on Softmax, and the feature fusion module integrates the weighted modal features; the unified fusion feature includes a point cloud map of the spatial distribution of geological relics, a time series map of the evolution of geological relics, a feature description of geological relics, and a feature vector of geological relics; The output layer extracts the multi-source data index associated with the unified fusion feature, and finally outputs the geological relic collection information; the geological relic collection information includes the unified fusion feature and the corresponding multi-source data index; The loss functions include cross entropy loss function and cosine similarity loss function. The LAMB optimizer is used to adjust the model hyperparameters and improve the convergence speed, and the verification machine is used to verify the model performance. The cross entropy loss function is used to classify geological relics into predefined categories; the cosine similarity loss function ensures the consistency of multimodal features after fusion.

7. The method for collecting geological relics information in a geological park based on multi-source data according to claim 1 is characterized in that: The method for determining the acquisition scheme comprises: Determine the change degree of geological relic information according to the fusion area and the deviation of geological relic collection information. When the change degree of geological relic information is greater than the change degree threshold or the collection interval is greater than the set collection period, store the geological relic collection information in the local database and back it up to the cloud database. Otherwise, back up the geological relic collection information in the cloud database. Calculate the change degree of the geological relics information, the expression is: Where D chang is the degree of change of geological heritage information, β1 and β2 are the weights of fusion regions, s1 is the number of the first fusion regions, s2 is the number of the second fusion regions, A 1i is the area of ​​the first fusion region of the i-th region, ε 1i is the information deviation of geological relics collected in the first fusion area of ​​the i-th region, A 2j The area of ​​the jth second fusion region, ε 2j The information deviation of the geological heritage collection for the jth second fusion area.

8. A geological park geological heritage information acquisition system based on multi-source data, used to execute the method described in any one of claims 1 to 7, characterized in that: include: Perception network module: used to construct a multi-source perception network to obtain multi-source perception data of the geological park; the multi-source perception network includes satellite remote sensing technology to obtain GIS surface images, ground sensors to collect geological relics environmental parameters, geological relics information update platform to obtain geological relics update data and drones to obtain low-altitude aerial images; Platform module: used to verify user identity and spatiotemporal information, generate tourist trajectories based on the user's spatiotemporal information, and review user uploaded data to obtain updated data of the geological relics; Drone module: used to update the drone flight path according to the tourist trajectory and the original flight path of the drone, and execute the drone flight strategy based on the updated flight path to obtain low-altitude aerial images; Data processing module: used for performing multi-source data matching on the multi-source perception data, correcting the multi-source perception data to obtain multi-source corrected data, and determining a data fusion area according to the multi-source corrected data; the data fusion area includes a first fusion area and a second fusion area; Model module: used to construct a geological heritage multi-source data fusion model based on the multi-source correction data, and input the multi-source perception data of the geological park to be collected into the geological heritage multi-source data fusion model to obtain geological heritage collection information; Management module: used to view and manage the multi-source perception data and the geological relics collection information, and determine the collection plan according to the data fusion area and collection time.

Images