Cloud computing-based intelligent early warning system for monitoring land type change at high altitude

Abstract

The invention discloses a cloud computing-based high-altitude monitoring land type change intelligent early warning system, and the system comprises a target detection module which is used for carrying out the detection of a monitoring region through a target detection model, and carrying out the statistics of the number of persons and the number of vehicles in unit time; the abnormity judgment module is used for obtaining a carbon emission influence index according to the cultivated land area of the monitoring area and the number of people and the number of vehicles in unit time, and when the carbon emission influence index exceeds a preset threshold value, the data acquisition module is started; the data acquisition module is used for acquiring image data of the monitoring area and transmitting the image data to the cloud platform; the land type change detection module is used for acquiring a historical image of the previous stage and judging whether the cultivated land area is abnormally reduced or not by utilizing a cultivated land change detection model; if yes, sending an early warning signal; and if not, sending a normal signal. The invention relates to the technical field of land resource monitoring, and solves the technical problems of low detection efficiency, long time consumption and insufficient intelligence of the existing cultivated land change detection method.

Description

Technical Field

[0001] The present invention belongs to the field of land resource monitoring and relates to deep learning technology, and specifically is an intelligent early warning system for high-altitude monitoring of land type changes based on cloud computing. Background Art

[0002] Land is a basic resource for human survival and development, and land type change monitoring is of vital importance in modern society. Land type change not only affects the balance and stability of the ecological environment, but is also closely related to many aspects such as economic development and food security. Among them, cultivated land is the core element of agricultural production, and its protection is of paramount importance.

[0003] Existing methods for detecting cultivated land changes mainly include traditional field survey methods, detection methods based on satellite remote sensing images, and detection methods based on geographic information systems (GIS).

[0004] Among them, the traditional field survey method relies on staff to visit the monitoring area on the spot, and regularly monitor the status of cultivated land through field measurements, detailed records, etc., which requires a lot of manpower, financial resources and time resources; the detection method based on satellite remote sensing images uses satellites to obtain remote sensing images of different periods, and then conducts in-depth analysis and processing of these images to identify the changes in cultivated land. Its detection accuracy is seriously dependent on the resolution of satellite remote sensing images, and the acquisition cycle of remote sensing images is long, the data processing process is complex, and there is a lack of intelligent automatic analysis capabilities. It is also difficult to timely discover the non-agricultural behavior of cultivated land. GIS technology can integrate a variety of geographic data, perform spatial analysis of cultivated land changes, and display them in a visual way. However, the establishment and maintenance of GIS databases requires a lot of resources in the early stage, including data collection, collation and entry, which is costly. Moreover, the GIS-based method has obvious lag in data updating, and it is difficult to reflect the dynamic changes of cultivated land in real time. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a cloud computing-based high-altitude monitoring land type change intelligent early warning system, which is used to solve the technical problems of existing cultivated land change detection methods such as low detection efficiency, long time consumption and lack of intelligence.

[0006] To achieve the above object, the present invention provides a cloud computing-based high-altitude monitoring land type change intelligent early warning system, comprising:

[0007] Target detection module: used to detect people and vehicles in the monitoring area using a deep learning-based target detection model, and to count the number of people and vehicles per unit time;

[0008] Abnormal judgment module: used to obtain the cultivated land area in the monitoring area and obtain the carbon emission impact index based on the number of personnel, number of vehicles and cultivated land area per unit time; and,

[0009] When the carbon emission impact index exceeds the preset threshold, the data collection module is started;

[0010] Data acquisition module: used to obtain image data of the monitoring area using high-altitude measurement tools, obtain several current images, and transmit the current images to the cloud platform;

[0011] Land type change detection module: used to obtain historical images of the previous stage, and use the cultivated land change detection model to determine whether there is an abnormal decrease in the cultivated land area between the current images and the historical images of the previous stage; if yes, a warning signal is sent; if not, a normal signal is sent; wherein, the cultivated land change detection model is constructed based on a deep learning algorithm, and the abnormal decrease indicates that the pixel area output by the cultivated land change detection model is greater than the preset area threshold.

[0012] Based on the above-mentioned technical modules, the present invention can use the target detection model based on deep learning to obtain the carbon emission impact index of the monitored area, so as to intelligently judge whether there may be abnormal situations of illegal use of cultivated land, and then start the data acquisition module in a targeted manner to use high-altitude measurement tools for further detection, thereby avoiding the frequent start-up of high-altitude measurement tools, saving resources and improving monitoring efficiency; at the same time, with the help of the cloud platform to transmit and compare cultivated land data, it facilitates data storage, call and large-scale calculations, which is conducive to the efficient implementation of land change detection work, and provides strong support for timely and accurate early warning.

[0013] Furthermore, the process of constructing the target detection model based on deep learning includes:

[0014] A1, collect a number of pictures through surveillance cameras, pre-process and manually annotate the pictures, and obtain an annotation set containing the categories of people and vehicles;

[0015] A2, divide the images and annotation sets according to the preset ratio to obtain the training set, validation set and test set;

[0016] A3, build a lightweight target detection network based on deep learning algorithm, use training set and verification set to iteratively train and verify the lightweight target detection network, and obtain the detection model with the best verification accuracy;

[0017] A4: Input the test set into the detection model with the best verification accuracy to evaluate the accuracy, obtain the test accuracy, and compare whether the test accuracy reaches the preset accuracy threshold; if yes, use the detection model with the best verification accuracy as the output to obtain the target detection model; if no, adjust the parameters of the lightweight target detection network and jump to A3.

[0018] Furthermore, the carbon emission impact index is obtained according to the number of personnel, the number of vehicles and the area of ​​cultivated land in a unit time, including:

[0019] B1, collects the per capita carbon emission coefficient k1, the carbon emission coefficient of a single vehicle k2, and the carbon emission coefficient per unit of cultivated land area k3;

[0020] B2, the maximum number of personnel Pmax and the maximum number of vehicles Vmax required per unit area of ​​cultivated land in the monitoring area;

[0021] B3, according to the carbon emission impact index formula ICEI = [((P×k1)+(V×k2)+(A×k3)) / (P+V+A)]×√[(P / Pmax) 2 +(V / Vmax) 2 ]Get the carbon emission impact index ICEI; where P represents the number of people per unit time, V represents the number of vehicles per unit time, and A represents the cultivated land area.

[0022] The linear combination part of the carbon emission impact index formula focuses on the carbon emission contribution and relative proportion of each factor, and the root part focuses on the relationship between activity intensity and carrying capacity. The multiplication of the two can obtain a more comprehensive and integrated indicator, which is used to measure the possible impact of various activities in the monitoring area on carbon emissions and cultivated land.

[0023] Furthermore, the method for obtaining the preset threshold includes:

[0024] C1, collect data on the number of people, vehicles and cultivated land area in a certain period of time in history, and obtain a number of carbon emission impact values ​​according to the carbon emission impact index formula;

[0025] C2, dividing a number of carbon emission impact values ​​according to a preset division rule to obtain a number of data sequences; wherein the data sequences are a number of carbon emission impact values ​​in the same time period on different dates;

[0026] C3, calculate the upper quartile Q3 and lower quartile Q1 of several carbon emission impact values ​​in each data series, subtract Q3 from Q1, and obtain the quartile range IQR of each data series;

[0027] C4, calculate the preset threshold θ of each data sequence according to the formula θ=Q3+α×IQR; where α represents the adjustment coefficient;

[0028] C5, using database technology to store the preset threshold of each data sequence to obtain a dynamic threshold table; wherein the dynamic threshold table contains a month field, a time period field and a corresponding preset threshold field, and the values ​​of the month and time period are defined according to a preset division rule;

[0029] C6, obtaining the preset threshold value of the corresponding time period from the dynamic threshold table according to the acquisition time of the number of people and the number of vehicles in the target detection module.

[0030] Furthermore, the preset division rules include:

[0031] Divide a number of carbon emission impact values ​​according to preset monthly intervals to obtain a number of data groups;

[0032] A number of carbon emission impact values ​​in a number of data groups are divided according to preset time periods to obtain a number of data sequences in each data group.

[0033] In agricultural production, due to the significant differences in agricultural activities at different times of the day and in different life cycle stages of crops, the activities of people and vehicles and carbon emissions also change accordingly. Therefore, setting a dynamic threshold table divided by month and time period can flexibly adjust the threshold according to the actual situation, accurately reflect the carbon emissions in the monitoring area at different times, and more accurately judge whether there are abnormal conditions, effectively avoid the problem of missed judgment or misjudgment caused by the use of fixed thresholds, and provide a more scientific and accurate basis for abnormal judgment for the intelligent early warning system for high-altitude monitoring of land changes based on cloud computing.

[0034] Furthermore, the transmitting of the current plurality of images to the cloud platform includes:

[0035] D1, dividing each of the plurality of images into a plurality of image blocks, and performing color space conversion on pixel values ​​of the plurality of image blocks to obtain a plurality of converted image blocks;

[0036] D2, performing discrete cosine transform on each color component of the converted image blocks to obtain a number of frequency domain coefficient matrices, and encoding the number of frequency domain coefficient matrices using a Huffman coding algorithm to obtain coded data of the number of image blocks;

[0037] D3, using Logistic chaotic mapping to generate a chaotic sequence, and quantizing the chaotic sequence to obtain a quantized chaotic sequence;

[0038] D4, performing bit-wise XOR operation on the coded data of the plurality of image blocks and the quantized chaotic sequence to obtain a plurality of encrypted data, and transmitting the plurality of encrypted data to the cloud platform.

[0039] Encryption processing is one of the key links to ensure system security. Through discrete cosine transform and Huffman coding, image data compression and feature extraction are achieved, redundancy is reduced, transmission speed is improved, and key information is not lost. Then, the chaotic sequence is generated by Logistic chaotic mapping, and its randomness provides a reliable basis for data encryption and enhances security. Finally, the encoded data and the chaotic sequence are XOR-encrypted and transmitted to ensure the confidentiality of image data, prevent illegal acquisition and tampering, and enable the image to be safely and efficiently transmitted to the cloud platform.

[0040] Furthermore, the farmland change detection model is constructed based on a deep learning algorithm, including:

[0041] F1, using an aerial surveying tool to collect a number of cultivated land images; wherein the number of cultivated land images include a number of first time phase images and a number of second time phase images, and the first time phase images and the second time phase images correspond one to one in the shooting area;

[0042] F2, using an image annotation tool, annotating the cultivated land change areas in a number of first phase images and a number of second phase images to obtain a number of cultivated land change annotation sets;

[0043] F3, dividing the plurality of cultivated land images and the corresponding plurality of cultivated land change annotation sets according to a preset division ratio to obtain a change training set, a change verification set and a change test set;

[0044] F4, build a change detection model based on the deep learning algorithm, input the change training set and the change verification set into the change detection model for training and verification, and use the change test set to test the trained and verified model to obtain a change detection model that meets the preset test requirements;

[0045] F5, takes the change detection model that meets the preset test requirements as output to obtain the cultivated land change detection model.

[0046] Furthermore, the farmland change detection model includes a target detection branch, a semantic segmentation branch and a fusion module; wherein,

[0047] The target detection branch is used to detect non-cultivated land objects;

[0048] The semantic segmentation branch is used to classify the image at the pixel level to obtain a cultivated land distribution map; wherein the target detection branch and the semantic segmentation branch use a shared backbone network to extract features;

[0049] The fusion module is used to use the attention mechanism to fuse the output result of the target detection branch with the output result of the semantic segmentation branch to obtain the cultivated land change detection result.

[0050] The cultivated land change detection model of the present invention comprises a target detection branch, a semantic segmentation branch and a fusion module; wherein the target detection branch focuses on detecting non-cultivated land objects, can accurately locate non-cultivated land objects in the image, and enhances the pertinence of the detection; the semantic segmentation branch can classify the image at the pixel level, generate a detailed cultivated land distribution map, and display the actual range and distribution of cultivated land with fine pixel-level division, making up for the deficiency of target detection in detail presentation; the fusion module integrates the output results of the first two by using the attention mechanism, and the attention mechanism enables the model to focus on the key areas and features of cultivated land changes, fully integrates information at different levels, and combines the advantages of target detection and semantic segmentation, so that the final cultivated land change detection result can more accurately and comprehensively reflect the actual situation, effectively improve the overall detection efficiency, and provide technical support for cultivated land change monitoring.

[0051] Furthermore, the architecture of the target detection branch includes:

[0052] Backbone network: Use the Focus module to slice the input data to obtain several slice images, and use the CSP-Darknet53 network as a shared backbone network to extract features from several slice images to obtain multi-scale features;

[0053] Neck network: including fast spatial pyramid pooling layer SPPF, feature pyramid network FPN and path aggregation network PAN; among them, SPPF is used to fuse multi-scale features, FPN is used to transfer semantic information of the fused multi-scale features from top to bottom, and PAN is used to transfer positioning information of the output of FPN from bottom to top;

[0054] Detection head: Use the YOLOv3 detection head to output the detection results.

[0055] The backbone network of the target detection branch uses the Focus module for slicing operations, which enriches the image feature dimensions while retaining key information. The CSP-Darknet53 network, as a shared backbone network, has powerful multi-scale feature extraction capabilities and can accurately capture target-related features of different scales. The fast spatial pyramid pooling layer SPPF in the neck network effectively integrates multi-scale features to avoid feature fragmentation and ensure information integrity. The feature pyramid network FPN transmits semantic information from top to bottom to enhance the semantic expression of low-level features. The path aggregation network PAN transmits positioning information from bottom to top. The two work together to improve the feature quality, so that the detection head can work based on high-quality features. The detection head adopts the YOLOv3 detection head, which has the advantages of fast detection speed and relatively balanced detection capabilities for targets of different scales. On the premise of ensuring a certain detection accuracy, it can quickly output the detection results of non-arable land objects to meet the needs of real-time monitoring scenarios and improve the practicality and work efficiency of the target detection branch.

[0056] Furthermore, the land type change detection module is deployed on a cloud platform, and the cloud platform includes an image database for storing historical image data of several stages; the target detection module, anomaly judgment module and data acquisition module are deployed in a monitoring center, and the monitoring center monitors the monitoring area through several monitoring cameras, and the monitoring center and the cloud platform transmit data and signals through a communication network.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] First, the target detection module is used to identify the people and vehicles in the monitoring area and other activities related to the change of cultivated land use, and the potential change area is accurately located. Then, the land type change detection module is activated to detect the change of cultivated land in time, realize rapid early warning, avoid indiscriminate detection of the entire monitoring area, and improve detection efficiency.

[0059] In the process of transmitting images to the cloud platform, strict data encryption operations are used to effectively compress the data volume, increase the transmission speed, enhance the security and confidentiality of data transmission, prevent data from being stolen or tampered with, and ensure the security and reliability of monitoring data while ensuring data integrity.

[0060] The cultivated land change detection model adopts a dual-branch structure with a shared backbone network, which can make full use of the same underlying feature information while performing specialized feature learning and optimization on their respective tasks. The target detection branch can accurately locate non-cultivated land objects, and the semantic segmentation branch can divide the cultivated land distribution map in detail. The fusion module uses the attention mechanism to fuse the results of the two to obtain accurate cultivated land change detection results. It can timely discover abnormal reductions in cultivated land data, provide strong support for protecting cultivated land resources, accurately send early warning signals, and assist relevant departments to take timely measures to deal with problems such as illegal use of cultivated land. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A schematic diagram of the technical process of a cloud computing-based high-altitude monitoring land type change intelligent early warning system provided by the present invention;

[0063] Figure 2 The process of constructing the dynamic threshold table provided by the present invention;

[0064] Figure 3A schematic diagram of the process of transmitting image data to a cloud platform provided by the present invention;

[0065] Figure 4 A schematic diagram of the framework of a cloud computing-based high-altitude monitoring land type change intelligent early warning system provided by the present invention. DETAILED DESCRIPTION

[0066] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] See also Figure 1-Figure 4 The first embodiment of the present invention provides a cloud computing-based high-altitude monitoring land type change intelligent early warning system, comprising:

[0068] Target detection module: used to detect people and vehicles in the monitoring area using a deep learning-based target detection model, and to count the number of people and vehicles per unit time;

[0069] Abnormal judgment module: used to obtain the cultivated land area in the monitoring area, and obtain the carbon emission impact index based on the number of personnel, number of vehicles and cultivated land area per unit time. When the carbon emission impact index exceeds the preset threshold, the data collection module is started;

[0070] Data acquisition module: used to obtain image data of the monitoring area using high-altitude measurement tools to obtain several current images;

[0071] Land type change detection module: used to transmit the current images to the cloud platform and obtain the historical images of the previous stage, and use the cultivated land change detection model to compare whether there is an abnormal decrease in the cultivated land data in the current images and the historical images of the previous stage; if yes, a warning signal is sent; if not, a normal signal is sent; among them, the cultivated land change detection model is built based on a deep learning algorithm.

[0072] It should be noted that the target detection module, anomaly judgment module, data acquisition module and land type change detection module of the present invention are communicatively connected, and the target detection module, anomaly judgment module and data acquisition module are deployed in a monitoring center. The monitoring center monitors the monitoring area through a number of monitoring cameras, and the monitoring center and the cloud platform transmit data and signals through a communication network.

[0073] In this embodiment, in order to efficiently and accurately conduct preliminary screening of activities in the monitoring area, a lightweight target detection model based on a deep learning algorithm is deployed in the target detection module of the monitoring center to identify the number of people and vehicles in the monitoring area, thereby indirectly reflecting the frequency of human activities in the area and the possible resource allocation involved.

[0074] The construction process of the target detection model of the present invention is as follows:

[0075] First, in the data collection stage, a number of images are collected through surveillance cameras, and a number of images are pre-processed and manually labeled to obtain a label set containing the categories of people and vehicles;

[0076] Next, several images and annotation sets are divided according to a preset ratio to obtain training sets, validation sets, and test sets. The training set occupies a larger proportion and is used for the initial learning and parameter adjustment of the model, so that it can fully learn the various characteristic patterns of people and vehicles. The validation set is used to evaluate and verify the performance of the model in real time during the model training process, to promptly discover problems such as overfitting or underfitting that may occur in the model, and to optimize and adjust the hyperparameters of the model accordingly to ensure the generalization ability and stability of the model. The test set is independent of the training and verification process and is used to objectively and accurately evaluate the overall performance of the model. Its data distribution is kept as consistent as possible with the data distribution in the actual monitoring scenario to truly reflect the performance of the model in actual applications.

[0077] Then, a lightweight target detection network is constructed based on a deep learning algorithm, such as optimizing and improving the YOLO series network architecture, and iteratively training and verifying the lightweight target detection network using training sets and verification sets. In each iteration, the model parameters are fine-tuned according to the pre-set loss function and optimizer, so that the error between the model's prediction results and the real labels in the annotation set is continuously reduced, and the detection accuracy and performance of the model are gradually improved until a detection model with the best verification accuracy is obtained.

[0078] Finally, the test set is input into the detection model with the best verification accuracy for accuracy evaluation to obtain the test accuracy, and then the test accuracy is compared to see whether it reaches the preset accuracy threshold (for example, the F1 value is used as the final evaluation accuracy value). If yes, the detection model with the best verification accuracy is used as the output to obtain the target detection model. If not, the parameters of the lightweight target detection network are adjusted, and training and verification are performed again.

[0079] In normal agricultural production activities, the movement of people and vehicles follows certain rules and quantity ranges. Once there are people and vehicle activities beyond the norm, it may indicate the occurrence of abnormal behaviors such as illegal construction, excessive reclamation or unreasonable land use changes. By accurately counting the number of people and vehicles in real time and using it as the key input data for the subsequent abnormal judgment module, it can provide timely and valuable clues for the entire monitoring system, thereby improving the system's early warning ability and response speed for cultivated land change monitoring, ensuring the rational use and effective protection of land resources, protecting them from illegal or improper activities, and further maintaining the stable order of agricultural production and the balanced development of the ecological environment.

[0080] Since starting the high-altitude measurement equipment to acquire farmland images and conducting subsequent complex algorithm analysis and data processing requires a lot of resources, it not only places extremely high demands on the hardware equipment performance of the monitoring system, but also increases the system's operating costs and energy consumption.

[0081] Therefore, in order to optimize the intelligent early warning process of cultivated land changes and reduce the early warning cost, an abnormality judgment module is set in the present invention, which is used to obtain the carbon emission impact index based on the cultivated land area of ​​the monitoring area obtained and the number of people and vehicles per unit time counted by the target detection module. The carbon emission impact index is used to judge whether abnormal behavioral activities occur in the monitoring area, thereby providing a decision-making basis for the startup of the data acquisition module.

[0082] In the abnormal judgment module, the carbon emission impact index is obtained according to the number of people, vehicles and cultivated land area per unit time, including:

[0083] B1, through scientific research data and agricultural-related statistical data, collect per capita carbon emission coefficient k1, single vehicle carbon emission coefficient k2, and carbon emission coefficient per unit of cultivated land area k3 that are suitable for the characteristics of this monitoring area;

[0084] B2, the maximum number of personnel Pmax and the maximum number of vehicles Vmax required per unit area of ​​cultivated land in the monitoring area;

[0085] B3, according to the carbon emission impact index formula ICEI = [((P×k1)+(V×k2)+(A×k3)) / (P+V+A)]×√[(P / Pmax) 2 +(V / Vmax) 2 ]Get the carbon emission impact index ICEI; where P represents the number of people per unit time, V represents the number of vehicles per unit time, and A represents the cultivated land area.

[0086] When the carbon emission impact index exceeds the preset threshold, it indicates that there are abnormal behaviors in the monitoring area, such as excessive non-agricultural construction activities, land compaction and damage caused by frequent entry and exit of large vehicles, and illegal reclamation or excavation caused by the gathering of people beyond the normal range.

[0087] In this embodiment, whether the carbon emission impact index exceeds the preset threshold is determined by comparing the corresponding thresholds in the dynamic threshold table obtained according to the current time period.

[0088] Specifically, we first need to collect data on the number of people, vehicles, and cultivated land in a certain period of time in history (more than one year), and then obtain a number of carbon emission impact values ​​based on the carbon emission impact index formula;

[0089] Then, several carbon emission impact values ​​are divided according to the preset division rules:

[0090] Divide a number of carbon emission impact values ​​into preset monthly intervals, for example, divide a year into quarters to obtain four data groups;

[0091] Then, the carbon emission impact values ​​in the data group are divided according to the preset time periods, for example, a day is divided into a daytime interval and a nighttime interval, the daytime interval is from 7:00-19:00, and every two hours is a time period, and the nighttime interval is from 19:00 to 7:00 the next day, which is a time period (there are usually fewer activities at night), to obtain a number of data sequences in each data group; wherein the data sequence is a number of carbon emission impact values ​​of the same time period on different dates, for example, the carbon emission impact values ​​from 7:00 to 9:00 every day in the first quarter are taken as a data sequence;

[0092] Next, calculate the upper quartile Q3 and lower quartile Q1 of several carbon emission impact values ​​in each data series, and subtract Q3 from Q1 to obtain the quartile range IQR of each data series;

[0093] The preset threshold θ of each data sequence is calculated according to the formula θ=Q3+α×IQR; where α represents the adjustment coefficient, which is obtained based on practical experience;

[0094] Finally, the preset threshold of each data sequence is stored using database technology to obtain a dynamic threshold table; wherein the dynamic threshold table contains a month field, a time period field and a corresponding preset threshold field, and the values ​​of the month and time period are defined according to the preset division rules;

[0095] For example, the month field in the dynamic threshold table is January-March, April-June, etc., and the time period field is 7:00-9:00, 9:00-11:00, etc., and then the preset thresholds in the corresponding time periods are stored to obtain the dynamic threshold table.

[0096] In this embodiment, by dividing the data in detail according to the time dimension, from months to specific time periods, different data sequences are formed. Each data sequence reflects the distribution law of the carbon emission impact value in a specific time interval, and can capture the activity patterns and carbon emission characteristics that change over time, and then more accurately judge whether an abnormality occurs based on the time background of the real-time monitoring data, which is in line with the actual time laws and helps to improve the accuracy and timeliness of the early warning.

[0097] When the carbon emission impact index exceeds the preset threshold, the data acquisition module will be automatically started, and then the data acquisition module will start the high-altitude measurement tool (such as a drone) to obtain image data of the monitoring area and obtain the current images;

[0098] Then, in the land type change detection module, the current images are transmitted to the cloud platform, and the historical images of the previous stage are obtained from the image database of the cloud platform, and input into the cultivated land change detection model for cloud computing to compare whether there is an abnormal decrease in the cultivated land data; if so, an early warning signal is sent; if not, a normal signal is sent; among them, the image database of the cloud platform is used to store historical image data of several stages and deploy the land type change detection module.

[0099] In the process of transferring image data to the cloud platform, a rigorous data encryption process is adopted to prevent data from being stolen. The specific operations are as follows:

[0100] First, unique identifiers are assigned to a number of images to obtain a number of image IDs;

[0101] Then, each image is divided into several image blocks, and the pixel values ​​of several image blocks are converted into color space, for example, from the original color space to the YUV color space, so that the feature information of the image blocks can be better extracted and several converted image blocks can be obtained to reduce the complexity of data processing;

[0102] Next, discrete cosine transform is performed on each color component of the converted image blocks to obtain a number of frequency domain coefficient matrices, and the frequency domain coefficient matrices are encoded using a Huffman coding algorithm to obtain encoded data of the image blocks;

[0103] The function of discrete cosine transform (DCT) is to convert image blocks from the spatial domain to the frequency domain. In the frequency domain, the energy of the image is often concentrated on a few low-frequency coefficients, which can effectively remove redundant information in the image data, achieve data compression, and highlight the main features of the image. Afterwards, the Huffman coding algorithm is used to encode the obtained frequency domain coefficient matrices. Huffman coding is a variable-length coding method based on the probability of data occurrence. It will assign codewords of different lengths according to the probability of occurrence of each element in the frequency domain coefficient matrix. Elements with high probability of occurrence are assigned shorter codewords, and vice versa. Longer codewords are assigned, thereby further compressing the amount of data, reducing the scale of data that needs to be processed during transmission, and improving transmission efficiency. The final encoded data contains the key information of the image block after compression and feature extraction, which becomes the basis for subsequent encryption operations;

[0104] Afterwards, the chaotic sequence is generated by using Logistic chaotic mapping, and the chaotic sequence is quantized to obtain a quantized chaotic sequence;

[0105] Logistic chaotic mapping is a typical chaotic system, which has the characteristics of good randomness, ergodicity, and high sensitivity to initial conditions. Based on specific initial values ​​and parameters, a chaotic sequence that seems disordered but actually has internal rules can be generated through iterative operations. The randomness of this chaotic sequence makes it difficult to predict and crack, providing an ideal encryption material for data encryption. Then, the generated chaotic sequence is quantized, and its value range is mapped to a discrete value range suitable for subsequent operations with the image block encoding data, ensuring that the chaotic sequence can accurately cooperate with the encoded data in the subsequent bitwise XOR operation, further enhancing the encryption effect, and ensuring that the encrypted data has higher security;

[0106] Finally, the coded data of several image blocks and the quantized chaotic sequence are XORed bit by bit to obtain several encrypted data, and the encrypted data are transmitted to the cloud platform. The bitwise XOR operation is a simple and effective encryption method. It performs XOR operation on the binary values ​​of the corresponding bits of the coded data and the quantized chaotic sequence (the same is 0, and the different is 1), so that the original coded data is "masked" by the chaotic sequence. The generated encrypted data is difficult to restore the original image block information without the correct chaotic sequence (i.e., the decryption key), thereby realizing the encryption protection of the image data.

[0107] After the image data of the monitored area is transmitted to the cloud platform for decryption, the cloud platform will retrieve the image data taken in the previous stage, and then match the current image with the image of the previous stage one by one according to the image ID, and then input it into the change detection model to output the cultivated land change map of the two time periods; when the pixel area in the cultivated land change map exceeds the preset threshold, the early warning signal will be immediately activated.

[0108] In the present invention, the farmland change detection model consists of a target detection branch, a semantic segmentation branch and a fusion module; wherein,

[0109] The target detection branch is used to detect non-cultivated land objects and consists of a backbone network, a neck network, and a detection head:

[0110] In the backbone network, the Focus module is first used to slice the input data to expand the number of input channels and reduce the spatial dimension of the feature map, thereby obtaining several slice images. Next, the CSP-Darknet53 network is used as a shared backbone network to extract features from the slice images. The CSP structure of the CSP-Darknet53 network has a unique advantage. It divides the feature map into two parts for processing. One part performs the convolution operation, and the other part is directly spliced ​​with the result of the convolution operation. In this way, the diversity of feature information can be retained, allowing the network to capture richer image features, while significantly reducing the amount of calculation and improving computing efficiency, ultimately obtaining multi-scale features;

[0111] Then in the neck network, there are several important components, including the fast spatial pyramid pooling layer SPPF, the feature pyramid network FPN, and the path aggregation network PAN. Among them, SPPF is responsible for fusing multi-scale features. It efficiently fuses features of different scales by serially passing through multiple 5x5 maxpooling layers, which greatly improves the computational efficiency compared to the traditional correlation structure; FPN is responsible for top-down semantic information transmission, propagating high-level features with rich semantic information downward, so that features at different levels can obtain more accurate semantic guidance, which helps to better identify targets; PAN performs bottom-up positioning information transmission, further strengthening the ability of feature fusion, allowing the network to locate targets more accurately;

[0112] Finally, the detection head of YOLOv3 is used to output the detection results. The detection head of YOLOv3 adds the loss of the detection frame scale based on DIoULoss, so that the predicted frame can be more consistent with the real frame, thereby improving the accuracy of target detection and more accurately detecting non-cultivated objects in the image.

[0113] The semantic segmentation branch is used to classify the image at the pixel level to obtain the cultivated land distribution map. The backbone network of the semantic segmentation branch uses the same backbone network as the target detection branch to obtain multi-scale features. Then, in the decoder part, the multi-scale features are upsampled through multiple serial upsampling modules, and skip connections are added after each upsampling to fuse the multi-scale features to obtain fused features. Then, multiple convolutional layers and activation functions are used as classifiers to classify the fused features at the pixel level. Finally, a semantic segmentation map with the same size as the input image is output to obtain the cultivated land distribution map.

[0114] Finally, the fusion module based on the attention mechanism is used to fuse the output of the target detection branch and the output of the semantic segmentation branch to obtain a more accurate map of cultivated land type changes.

[0115] It should be noted that the input of the cultivated land change detection model is a dual-phase image, namely the current image and the image of the previous stage. Therefore, the target detection branch and the semantic segmentation branch process the two image data at the same time, and then obtain the non-cultivated land increase result of the target detection branch and the cultivated land reduction result of the semantic segmentation branch; the two are further fused using the fusion module to more accurately identify the cultivated land changes.

[0116] The construction process of the cultivated land change detection model in this embodiment specifically includes:

[0117] F1, using a high-altitude measurement tool to collect a number of cultivated land images; wherein the number of cultivated land images include a number of first-phase images and a number of second-phase images, and the first-phase images and the second-phase images correspond one to one in the shooting area;

[0118] F2, using an image annotation tool, annotating the cultivated land change areas in a number of first phase images and a number of second phase images to obtain a number of cultivated land change annotation sets;

[0119] F3, dividing the plurality of cultivated land images and the corresponding plurality of cultivated land change annotation sets according to a preset division ratio to obtain a change training set, a change verification set and a change test set;

[0120] F4, build a change detection model based on the deep learning algorithm, input the change training set and the change verification set into the change detection model for training and verification, and use the change test set to test the trained and verified model to obtain a change detection model that meets the preset test requirements;

[0121] F5, takes the change detection model that meets the preset test requirements as output to obtain the cultivated land change detection model.

[0122] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0123] Working principle of the present invention:

[0124] Use the deep learning-based target detection model to identify the activities of people and vehicles in the monitoring area, and determine whether non-agricultural abnormal activities may occur in the monitoring area by calculating the carbon emission impact index and comparing it with the dynamic threshold;

[0125] In the process of transmitting image data to the cloud platform, a variety of data processing and encryption technologies are used to achieve data compression, feature extraction and encryption protection, ensure data integrity and confidentiality, prevent data from being stolen or tampered with, and ensure the security and reliability of monitoring data;

[0126] The cultivated land change detection model utilizes the efficient processing capabilities of cloud computing and adopts a dual-branch structure with a shared backbone network to process image data from different angles. It then uses the attention mechanism to fuse the two results through a fusion module, making full use of multi-scale feature information to improve the accuracy and comprehensiveness of cultivated land change detection, timely discover abnormal changes in cultivated land and issue warnings, and assist in protecting cultivated land resources.

[0127] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A cloud computing-based high-altitude monitoring land type change intelligent early warning system, characterized in that: include: Target detection module: used to detect people and vehicles in the monitoring area using a deep learning-based target detection model, and to count the number of people and vehicles per unit time; Abnormal judgment module: used to obtain the cultivated land area in the monitoring area and obtain the carbon emission impact index based on the number of personnel, number of vehicles and cultivated land area per unit time; and, When the carbon emission impact index exceeds the preset threshold, the data collection module is started; Data acquisition module: used to obtain image data of the monitoring area using high-altitude measurement tools, obtain several current images, and transmit the current images to the cloud platform; Land type change detection module: used to obtain the historical images of the previous stage, and use the cultivated land change detection model to determine whether there is an abnormal decrease in the cultivated land area between the current images and the historical images of the previous stage; If yes, an early warning signal is sent; If not, a normal signal is sent; wherein, the cultivated land change detection model is constructed based on a deep learning algorithm, and the abnormal reduction indicates that the pixel area output by the cultivated land change detection model is greater than a preset area threshold.

2. According to the cloud computing-based high-altitude monitoring land type change intelligent early warning system of claim 1, it is characterized by: The process of building the target detection model based on deep learning includes: A1, collect a number of pictures through surveillance cameras, pre-process and manually annotate the pictures, and obtain an annotation set containing the categories of people and vehicles; A2, divide the images and annotation sets according to the preset ratio to obtain the training set, validation set and test set; A3, build a lightweight target detection network based on deep learning algorithm, use training set and verification set to iteratively train and verify the lightweight target detection network, and obtain the detection model with the best verification accuracy; A4: Input the test set into the detection model with the best verification accuracy to evaluate the accuracy, obtain the test accuracy, and compare whether the test accuracy reaches the preset accuracy threshold; if yes, use the detection model with the best verification accuracy as the output to obtain the target detection model; if no, adjust the parameters of the lightweight target detection network and jump to A3.

3. According to the cloud computing-based high-altitude monitoring land type change intelligent early warning system of claim 1, it is characterized in that: The carbon emission impact index is obtained according to the number of personnel, the number of vehicles and the area of ​​cultivated land per unit time, including: B1, collects the per capita carbon emission coefficient k1, the carbon emission coefficient of a single vehicle k2, and the carbon emission coefficient per unit of cultivated land area k3; B2, the maximum number of personnel Pmax and the maximum number of vehicles Vmax required per unit area of ​​cultivated land in the monitoring area; B3, according to the carbon emission impact index formula ICEI = [((P×k1)+(V×k2)+(A×k3)) / (P+V+A)]×√[(P / Pmax) 2 +(V / Vmax) 2 ]Get the carbon emission impact index ICEI; where P represents the number of people per unit time, V represents the number of vehicles per unit time, and A represents the cultivated land area.

4. According to the cloud computing-based high-altitude monitoring land type change intelligent early warning system of claim 1, it is characterized in that: The method for obtaining the preset threshold value includes: C1, collect data on the number of people, vehicles and cultivated land area in a certain period of time in history, and obtain a number of carbon emission impact values ​​according to the carbon emission impact index formula; C2, dividing a number of carbon emission impact values ​​according to a preset division rule to obtain a number of data sequences; wherein the data sequences are a number of carbon emission impact values ​​in the same time period on different dates; C3, calculate the upper quartile Q3 and lower quartile Q1 of several carbon emission impact values ​​in each data series, subtract Q3 from Q1, and obtain the quartile range IQR of each data series; C4, calculate the preset threshold θ of each data sequence according to the formula θ=Q3+α×IQR; where α represents the adjustment coefficient; C5, using database technology to store the preset threshold of each data sequence to obtain a dynamic threshold table; wherein the dynamic threshold table contains a month field, a time period field and a corresponding preset threshold field, and the values ​​of the month and time period are defined according to a preset division rule; C6, obtaining the preset threshold value of the corresponding time period from the dynamic threshold table according to the acquisition time of the number of people and the number of vehicles in the target detection module.

5. According to the cloud computing-based high-altitude monitoring land type change intelligent early warning system of claim 4, it is characterized in that: The preset division rules include: Divide a number of carbon emission impact values ​​according to preset monthly intervals to obtain a number of data groups; A number of carbon emission impact values ​​in a number of data groups are divided according to preset time periods to obtain a number of data sequences in each data group.

6. The cloud computing-based high-altitude monitoring land type change intelligent early warning system according to claim 1 is characterized in that: The transmitting of the current plurality of images to the cloud platform includes: D1, dividing each of the plurality of images into a plurality of image blocks, and performing color space conversion on pixel values ​​of the plurality of image blocks to obtain a plurality of converted image blocks; D2, performing discrete cosine transform on each color component of the converted image blocks to obtain a number of frequency domain coefficient matrices, and encoding the number of frequency domain coefficient matrices using a Huffman coding algorithm to obtain coded data of the number of image blocks; D3, using Logistic chaotic mapping to generate a chaotic sequence, and quantizing the chaotic sequence to obtain a quantized chaotic sequence; D4, performing bit-wise XOR operation on the coded data of the plurality of image blocks and the quantized chaotic sequence to obtain a plurality of encrypted data, and transmitting the plurality of encrypted data to the cloud platform.

7. The cloud computing-based high-altitude monitoring land type change intelligent early warning system according to claim 1 is characterized in that: The farmland change detection model includes a target detection branch, a semantic segmentation branch and a fusion module; wherein, The target detection branch is used to detect non-cultivated land objects; The semantic segmentation branch is used to classify the image at the pixel level to obtain a cultivated land distribution map; wherein the target detection branch and the semantic segmentation branch use a shared backbone network to extract features; The fusion module is used to use the attention mechanism to fuse the output result of the target detection branch with the output result of the semantic segmentation branch to obtain the cultivated land change detection result.

8. The cloud computing-based high-altitude monitoring land type change intelligent early warning system according to claim 7 is characterized in that: The architecture of the target detection branch includes: Backbone network: Use the Focus module to slice the input data to obtain several slice images, and use the CSP-Darknet53 network as a shared backbone network to extract features from several slice images to obtain multi-scale features; Neck network: including fast spatial pyramid pooling layer SPPF, feature pyramid network FPN and path aggregation network PAN; among them, SPPF is used to fuse multi-scale features, FPN is used to transfer semantic information of the fused multi-scale features from top to bottom, and PAN is used to transfer positioning information of the output of FPN from bottom to top; Detection head: Use the YOLOv3 detection head to output the detection results.

9. The cloud computing-based high-altitude monitoring land type change intelligent early warning system according to claim 1 is characterized in that: The farmland change detection model is built based on a deep learning algorithm and includes: F1, using an aerial surveying tool to collect a number of cultivated land images; wherein the number of cultivated land images include a number of first time phase images and a number of second time phase images, and the first time phase images and the second time phase images correspond one to one in the shooting area; F2, using an image annotation tool, annotating the cultivated land change areas in a number of first phase images and a number of second phase images to obtain a number of cultivated land change annotation sets; F3, dividing the plurality of cultivated land images and the corresponding plurality of cultivated land change annotation sets according to a preset division ratio to obtain a change training set, a change verification set and a change test set; F4, build a change detection model based on the deep learning algorithm, input the change training set and the change verification set into the change detection model for training and verification, and use the change test set to test the trained and verified model to obtain a change detection model that meets the preset test requirements; F5, takes the change detection model that meets the preset test requirements as output to obtain the cultivated land change detection model.

10. The cloud computing-based high-altitude monitoring land type change intelligent early warning system according to claim 1 is characterized in that: The land type change detection module is deployed on a cloud platform, and the cloud platform includes an image database for storing historical image data of several stages; the target detection module, anomaly judgment module and data acquisition module are deployed in a monitoring center, and the monitoring center monitors the monitoring area through several monitoring cameras, and the monitoring center and the cloud platform transmit data and signals through a communication network.

Images