A method and system for collecting debris flow channel data based on drone

Abstract

The present application provides a method and system for collecting debris flow channel data based on a drone. By performing item dimension analysis and specific local dimension analysis on target items in the target debris flow channel collection data, item debris flow hazard point data for the target item and local debris flow hazard point data for the first item local analysis result of the target item can be obtained. Then, based on the item debris flow hazard point data, local debris flow hazard point data and sample dimension, the target item in the target debris flow channel collection data can be dimensionally analyzed. The important feature description content of the local hazard missing from the target item in the target debris flow channel collection data can be repaired, thereby ensuring the integrity and rationality of the debris flow channel data collection result of the target item finally obtained, thereby improving the accuracy and reliability of the debris flow channel data collection result.

Description

Technical Field

[0001] The present application relates to the field of data acquisition technology, and more specifically, to a method and system for collecting debris flow channel data based on an unmanned aerial vehicle (UAV). Background Art

[0002] Debris flows often occur in areas with complex geological structures, developed faults and folds, intense neotectonic activity, and high seismic intensity, resulting in surface rock fragmentation and collapse. The development of adverse geological phenomena such as landslides and landslides provides a rich source of solid material for debris flows. Furthermore, areas with loose, weak, easily weathered rock formations, well-developed joints, or alternating soft and hard strata can also provide a rich source of debris for debris flows due to their susceptibility to damage. Soil erosion caused by deforestation, mining, quarrying waste, and other human engineering activities often provide a significant source of material for debris flows. Water is both a crucial component of debris flows and their triggering condition and transport medium (power source). Water sources for debris flows include heavy rain, snowmelt, and reservoir (pond) outbursts. Most debris flows in China are caused by heavy rain and prolonged, continuous rainfall.

[0003] At present, the situation in debris flow channels is very complicated. Manual surveys require a lot of manpower and time, and it is impossible to accurately survey every location. With the rapid development of drones, drone technology is specifically applied to the survey of debris flow channels. It can survey locations that cannot be surveyed manually. However, how to accurately collect data through drones is a technical problem that is difficult to solve at present. Summary of the Invention

[0004] In order to improve the technical problems existing in the relevant technologies, the present application provides a method and system for collecting debris flow channel data based on drones.

[0005] In a first aspect, a method for collecting debris flow channel data based on a drone is provided, comprising:

[0006] Obtaining event debris flow hazard point data and local debris flow hazard point data corresponding to the target debris flow channel collection data; the event debris flow hazard point data matches the target event in the target debris flow channel collection data, and the local debris flow hazard point data matches the first event local analysis result of the target event;

[0007] Obtain a sample dimension that matches the target event, and count the number of first hidden danger important feature descriptions corresponding to the sample dimension, and the number of second hidden danger important feature descriptions corresponding to the debris flow hidden danger point data of the event;

[0008] When the number of the first hidden danger important feature description contents exceeds the number of the second hidden danger important feature description contents, analyzing and processing the debris flow hidden danger point data according to the sample dimension to obtain a first pending matter dimension analysis result;

[0009] The first pending item dimensional analysis result is analyzed and processed according to the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item.

[0010] In this application, the acquisition of the debris flow potential point data and local debris flow potential point data corresponding to the target debris flow channel acquisition data includes:

[0011] Obtain the target debris flow channel collection data from the channel information data set, load the target debris flow channel collection data into the event intelligent analysis thread, and output the event debris flow hazard point data corresponding to the target debris flow channel collection data through the event intelligent analysis thread;

[0012] The target debris flow channel acquisition data is loaded into a local intelligent analysis thread, and the local debris flow hazard point data corresponding to the target debris flow channel acquisition data is output through the local intelligent analysis thread.

[0013] In the present application, the target debris flow channel collection data is loaded into the event intelligent analysis thread, and the event debris flow hazard point data corresponding to the target debris flow channel collection data is output through the event intelligent analysis thread, including:

[0014] The target debris flow channel acquisition data is loaded into the matter intelligent analysis thread, and the matter intelligent analysis thread obtains the matter dimension feature corresponding to the target matter in the target debris flow channel acquisition data, and reads the first classification result corresponding to the matter dimension feature; the first classification result is used to indicate the type of matter local analysis result corresponding to the description content of the important hidden danger feature of the target matter;

[0015] generating a first data intersection description set according to the first classification result and key features of the target debris flow channel collected data;

[0016] Obtaining a descriptive attribute mean corresponding to the first data intersection description set, and determining a location description of important feature descriptions of hidden dangers in the target item in the target debris flow channel collected data based on the descriptive attribute mean;

[0017] According to the type of the local analysis result of the event and the content of the location description, the event debris flow potential point data corresponding to the target debris flow channel collection data is determined.

[0018] In this application, the item dimension features corresponding to the target item in the target debris flow channel collection data are obtained through the item intelligent analysis thread, including:

[0019] Obtaining, in the intelligent analysis thread of the matter, a matter description feature corresponding to the target matter in the target debris flow channel collected data, and outputting, according to a classification unit in the intelligent analysis thread of the matter, a second classification result corresponding to the matter description feature;

[0020] Obtaining a key feature of the matter for the target debris flow channel collected data output by the target feature extraction unit in the matter intelligent analysis thread, performing function processing on the second classification result and the key feature of the matter to obtain a second data intersection description set corresponding to the target debris flow channel collected data;

[0021] The target debris flow channel collected data is bucketed according to the second data intersection description set to obtain geological state description contents within the scope of Z item local analysis results, and local description features corresponding to the geological state description contents within the scope of the Z item local analysis results are obtained according to the item intelligent analysis thread; Z is a positive integer;

[0022] The event description feature and the local description features corresponding to the geological state description content within the local analysis result range of the Z events are integrated into the event dimension feature.

[0023] In the present application, the target debris flow channel acquisition data is loaded into a local intelligent analysis thread, and the local debris flow hazard point data corresponding to the target debris flow channel acquisition data is output through the local intelligent analysis thread, including:

[0024] Loading the target debris flow channel acquisition data into a local intelligent analysis thread, and analyzing the first item local analysis result of the target item in the target debris flow channel acquisition data in the local intelligent analysis thread;

[0025] If the local analysis result of the first issue is analyzed in the target debris flow channel collected data, a range geological state description content covering the local analysis result of the first issue is obtained from the target debris flow channel collected data, a location of a local hidden danger important feature description content corresponding to the local analysis result of the first issue is obtained based on the range geological state description content, and local debris flow hidden danger point data corresponding to the target debris flow channel collected data is determined based on the location of the local hidden danger important feature description content;

[0026] If the local analysis result of the first item is not analyzed in the target debris flow channel collection data, it is determined that the local debris flow hazard point data corresponding to the target debris flow channel collection data is a null value.

[0027] In the present application, if the local analysis result of the first matter is analyzed in the target debris flow channel acquisition data, a range geological state description content covering the local analysis result of the first matter is obtained from the target debris flow channel acquisition data, a location of a local hidden danger important feature description content corresponding to the local analysis result of the first matter is obtained based on the range geological state description content, and local debris flow hidden danger point data corresponding to the target debris flow channel acquisition data is determined based on the location of the local hidden danger important feature description content, including:

[0028] If the local analysis result of the first item is analyzed in the target debris flow channel collection data, the target debris flow channel collection data is filtered to obtain a range of geological state description content covering the local analysis result of the first item;

[0029] Obtaining local edge features corresponding to the geological state description content of the range, and regressing and analyzing the location of the important feature description content of the local hidden danger corresponding to the local analysis result of the first matter based on the local edge features;

[0030] Based on the location of the important feature description content of the local hidden danger, the important feature description content of the hidden danger of the local analysis result of the first matter is associated to obtain the local debris flow hidden danger point data corresponding to the target debris flow channel collection data.

[0031] In the present application, the analysis and processing of the first pending item dimensional analysis result based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item includes:

[0032] If the debris flow hazard point data of the item covers the dimension of the local analysis result of the second item, and the debris flow hazard point data of the item does not cover the dimension of the local analysis result of the third item, then the first local dimension corresponding to the local analysis result of the third item is determined based on the location of the hazard important feature description content of the local analysis result of the first item covered by the local debris flow hazard point data; the local analysis result of the second item and the local analysis result of the third item are in a mirror relationship;

[0033] Obtaining a first local data volume of the local analysis result of the second item in the dimensional analysis result of the first pending item, and determining a location of a description of important characteristics of hidden dangers in the local analysis result of the third item based on the first local data volume and the first local dimension;

[0034] The location of the important feature description content of the hidden danger of the local analysis result of the third matter is loaded into the dimensional analysis result of the first pending matter to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

[0035] In the present application, the location of the important feature description content of the hidden danger of the local analysis result of the third matter is loaded into the dimensional analysis result of the first pending matter to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data, including:

[0036] Loading the location of the important feature description content of the hidden danger of the local analysis result of the third issue into the first pending issue dimensional analysis result, obtaining the second pending issue dimensional analysis result corresponding to the target issue in the target debris flow channel collection data, and obtaining the dimensional difference value between the sample dimension and the second pending issue dimensional analysis result;

[0037] If the dimension difference value exceeds the target difference value, the important feature description content of the hidden danger is debugged for the second pending matter dimension analysis result based on the sample dimension to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

[0038] In the present application, the target debris flow channel collection data is the ath debris flow channel collection data in the channel information data set, where a is a positive integer; the first pending item dimensional analysis result is analyzed and processed based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item, including:

[0039] If the debris flow hazard point data does not include the dimensions of the second and third item local analysis results, then determine the second local dimension corresponding to the second item local analysis result and the third local dimension corresponding to the third item local analysis result based on the location of the important hazard feature description content of the first item local analysis result covered in the local debris flow hazard point data; the second item local analysis result and the third item local analysis result are in a mirror image relationship;

[0040] In the a-1th debris flow channel data collection, a second local data volume corresponding to the second-item local analysis result and a third local data volume corresponding to the third-item local analysis result are obtained, and the location of the important characteristic description content of the hidden danger in the second-item local analysis result is determined based on the second local data volume and the second local dimension;

[0041] According to the third local data volume and the third local dimension, the location of the important feature description content of the hidden danger of the local analysis result of the third matter is determined, and the location of the important feature description content of the hidden danger of the local analysis result of the second matter and the location of the important feature description content of the hidden danger of the local analysis result of the third matter are loaded into the first pending matter dimension analysis result to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

[0042] In a second aspect, a debris flow channel data acquisition system based on a drone is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above method.

[0043] The embodiment of the present application provides a method and system for collecting debris flow channel data based on a drone. By performing item dimension analysis and specific local dimension analysis on the target items in the target debris flow channel collection data, item debris flow hazard point data for the target item and local debris flow hazard point data for the first item local analysis result of the target item can be obtained. Then, based on the item debris flow hazard point data, the local debris flow hazard point data and the sample dimension, the target item in the target debris flow channel collection data can be dimensionally analyzed. The important feature description content of the local hazard missing from the target item in the target debris flow channel collection data can be repaired, thereby ensuring the integrity and rationality of the debris flow channel data collection result of the target item finally obtained, thereby improving the accuracy and reliability of the debris flow channel data collection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A flowchart of a method for collecting debris flow channel data based on a drone is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0047] See also Figure 1 , shows a method for collecting debris flow channel data based on a drone, which may include the technical solutions described in the following steps S101 to S104.

[0048] Step S101, obtain the event debris flow hazard point data and local debris flow hazard point data corresponding to the target debris flow channel collection data; the event debris flow hazard point data matches the target event in the target debris flow channel collection data, and the local debris flow hazard point data matches the first event local analysis result of the target event.

[0049] The formation of debris flows requires the simultaneous presence of the following three conditions: steep terrain and landforms that facilitate the collection of water and debris; abundant loose material; and a large amount of water in a short period of time. Debris flow landforms can generally be divided into three parts: the formation zone, the flow zone, and the accumulation zone. The terrain in the upstream formation zone is often gourd-shaped or funnel-shaped, surrounded by mountains on three sides and with an outlet on one side. The terrain is relatively open, with high and steep mountains, broken mountains, and poor vegetation growth, which is conducive to the concentration of water and debris. The terrain in the midstream flow zone is mostly narrow, steep, and deep canyons, with a large longitudinal slope of the valley bed, allowing debris flows to rush down rapidly. The terrain in the downstream accumulation zone is usually an open and flat piedmont plain or river valley terrace, which provides a place for the accumulated materials to accumulate.

[0050] For example, debris flow potential point data includes material source points, soil softness, and water sources. Data on specific and local debris flow potential points is collected using drones, which are equipped with not only cameras but also geophysical equipment, capable of collecting both surface and underground data.

[0051] For example, a channel information dataset or geological state description content data of a target event photographed in a mobile terminal scenario can be obtained; when performing dimensional analysis on the channel information dataset or geological state description content data, the debris flow channel collection data in the geological state description content data or the channel information dataset can be determined as the target debris flow channel collection data, and by performing event analysis on the target debris flow channel collection data, event debris flow hazard point data for the target event can be obtained; at the same time, local analysis can also be performed on the target debris flow channel collection data to obtain local debris flow hazard point data of the first event local analysis result for the target event.

[0052] Among them, the computer can obtain the event intelligent analysis thread and the local intelligent analysis thread, load the target debris flow channel collection data into the event intelligent analysis thread, and output the event debris flow hazard point data corresponding to the target debris flow channel collection data through the event intelligent analysis thread; at the same time, the target debris flow channel collection data can also be loaded into the local intelligent analysis thread, and output the local debris flow hazard point data corresponding to the target debris flow channel collection data through the local intelligent analysis thread.

[0053] Optionally, the intelligent analysis thread of the matter used in the embodiment of the present application can be a decision-making thread with a trust factor. For example, the intelligent analysis thread of the matter can be used to regress and analyze the important feature description content of the target matter hidden danger in the target debris flow channel collection data. Each important feature description content of the matter hidden danger obtained by regression analysis can correspond to a first trust factor. The first trust factor can be used to indicate the regression analysis accuracy of each important feature description content of the matter hidden danger obtained by regression analysis. The important feature description content of the matter hidden danger obtained by regression analysis and the corresponding first trust factor can be called the matter mudslide hidden danger point data corresponding to the target mudslide channel collection data.

[0054] Step S102: obtain a sample dimension that matches the target event, count the number of first hidden danger important feature description contents corresponding to the sample dimension, and count the number of second hidden danger important feature description contents corresponding to the debris flow hidden danger point data of the event.

[0055] Illustratively, the sample dimension is the direction of historical data stored in the database.

[0056] Among them, dimensional analysis is to analyze through different directions, which can analyze the data more comprehensively.

[0057] The first description of the important characteristics of the hidden danger can be understood as the description of the important characteristics of the current hidden danger, and the second description of the important characteristics of the hidden danger can be understood as the description of the important characteristics of the historical hidden danger.

[0058] Step S103: When the number of the first hidden danger important feature description contents exceeds the number of the second hidden danger important feature description contents, the debris flow hidden danger point data is analyzed and processed according to the sample dimension to obtain the first pending matter dimension analysis result.

[0059] Step S104: analyzing and processing the first pending item dimensional analysis result according to the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item.

[0060] The target debris flow channel collection data may not cover the complete target item. For example, the local hazard range of the target item is not included in the target debris flow channel collection data. Then, the target debris flow channel collection data corresponds to the debris flow hazard point data. A portion of the important feature description content of the hazard is missing. The sample dimension can be used to repair the important feature description content of the hazard in the debris flow hazard point data corresponding to the target item, and the missing important feature description content of the hazard is completed to obtain the first pending item dimension analysis result corresponding to the target item. When the local debris flow hazard point data includes the important feature description content of the local hazard in the local analysis result of the first item, the important feature description content of the local hazard in the local debris flow hazard point data and the important feature description content of the hazard in the item debris flow hazard point data can be combined to adjust the first pending item dimension analysis result to obtain the debris flow channel data collection result of the target item in the target debris flow channel collection data. After obtaining the debris flow channel data collection result corresponding to the current target debris flow channel collection data, you can continue to perform event dimension analysis on the next debris flow channel collection data in the channel information data set to obtain the debris flow channel data collection results of the target event in each debris flow channel collection data in the channel information data set.

[0061] In an embodiment of the present application, by performing item dimension analysis and specific local dimension analysis on the target items in the target debris flow channel collection data respectively, the item debris flow hazard point data for the target item and the local debris flow hazard point data of the first item local analysis result of the target item can be obtained. Then, based on the item debris flow hazard point data, the local debris flow hazard point data and the sample dimension, the target item in the target debris flow channel collection data can be dimensionally analyzed, and the important feature description content of the local hazard missing from the target item in the target debris flow channel collection data can be repaired, so as to ensure the integrity and rationality of the debris flow channel data collection result of the target item, and thus improve the accuracy and reliability of the debris flow channel data collection result.

[0062] Another method for collecting debris flow channel data based on a drone is provided in an embodiment of the present application. The method for collecting debris flow channel data based on a drone may include the following steps S201 to S208:

[0063] Step S201: Load the target debris flow channel collection data into the matter intelligent analysis thread, obtain the matter dimension features corresponding to the target matter in the target debris flow channel collection data through the matter intelligent analysis thread, and read the first classification result corresponding to the matter dimension features; the first classification result is used to indicate the type of matter local analysis result corresponding to the important feature description content of the hidden danger of the target matter.

[0064] For example, the intelligent analysis thread of matters can be understood as an artificial intelligence analysis thread, specifically including CNN, etc.

[0065] For example, after obtaining a channel information data set shot in a mobile terminal scenario, a debris flow channel collection data can be selected from the channel information data set as the target debris flow channel collection data, and the target debris flow channel collection data can be loaded into the trained event intelligent analysis thread. The event intelligent analysis thread can obtain the event dimension features corresponding to the target event in the target debris flow channel collection data. Through the classification unit of the event intelligent analysis thread, the first classification result corresponding to the event dimension features can be output. The first classification result can be used to represent the type of event local analysis result corresponding to the important feature description content of the hidden danger of the target event.

[0066] Optionally, if in the process of using the matter intelligent analysis thread to extract features of the target debris flow channel collection data, the target debris flow channel collection data can be loaded into the matter intelligent analysis thread, and the matter description features corresponding to the target matter in the target debris flow channel collection data are obtained in the matter intelligent analysis thread, and according to the classification unit in the matter intelligent analysis thread, the second classification result corresponding to the matter description feature is output; the matter key features for the target debris flow channel collection data output by the target feature extraction unit in the matter intelligent analysis thread are obtained, and the second classification results and the matter key features are functionally processed to obtain a second data intersection description set corresponding to the target debris flow channel collection data; the target debris flow channel collection data is bucketed according to the second data intersection description set to obtain Z geological state description contents within the scope of the local analysis results of the matter, and the local description features corresponding to the geological state description contents within the scope of the local analysis results of the matter are obtained according to the matter intelligent analysis thread, where Z is a positive integer; the matter description features and the local description features corresponding to the geological state description contents within the scope of the local analysis results of the matter are integrated into matter dimension features.

[0067] Among them, the item description feature can be considered as a feature representation extracted from the target debris flow channel acquisition data to represent the target item; the second classification result can also be used to represent the type of item local analysis result corresponding to the important feature description content of the item hidden danger covered in the target debris flow channel acquisition data; the target feature extraction unit can refer to the last feature extraction unit in the item intelligent analysis thread, and the item key feature can represent the key feature for the target debris flow channel acquisition data output by the last feature extraction unit of the item intelligent analysis thread; the second data intersection description set can be the class data intersection description set corresponding to the target debris flow channel acquisition data. The item key feature output by the last feature extraction unit in the item intelligent analysis thread and the second classification result are weighted (the second classification result can be considered as the weight corresponding to the item key feature), and a second data intersection description set can be obtained. The second data intersection description set can be considered as the result of visualizing the item key feature output by the target feature extraction unit, and can be used to represent the description attribute point range of the geological state description content concerned by the item intelligent analysis thread.

[0068] It is planned to use the class data intersection description set (second data intersection description set) of the important feature description contents of each hidden danger in the target debris flow channel collection data as the prior information of the range position, and perform bucket processing on the target debris flow channel collection data, that is, filter the target debris flow channel collection data according to the second data intersection description set to obtain the geological state description content of the local analysis result range of the matter covering a single local area; then, feature extraction can be performed on the geological state description content of each local analysis result range of the matter through the matter intelligent analysis thread to obtain the local description features corresponding to the geological state description content of each local analysis result range of the matter, and the aforementioned matter description features and the local description features corresponding to the geological state description content of each local analysis result range of the matter can be integrated into the matter dimension features for the target matter; the local description features can be considered as the feature representation extracted from the geological state description content of the local analysis result range of the matter for representing the local analysis result of the matter.

[0069] Step S202 : generating a first data intersection description set based on the first classification result and key features of the target debris flow channel collected data.

[0070] For example, the key features of the matter can be understood as the degree of soil dryness, the state of earthquake, etc.

[0071] For example, after obtaining the first classification result, the first classification result and the key features of the target debris flow channel collection data can be multiplied to generate a first data intersection description set. Among them, the first data intersection description set and the second data intersection description set are both class data intersection description sets for the target debris flow channel collection data, but the first data intersection description set uses the first classification result as the weight of the key features of the matter output by the target feature extraction unit (here it is assumed that the first classification result combines the matter description feature and the local description feature), while the second data intersection description set uses the second classification result as the weight of the key features of the matter output by the target feature extraction unit, and the second classification result is only related to the matter description feature.

[0072] Step S203, obtain the descriptive attribute mean corresponding to the first data intersection description set, determine the position description content of the important feature description content of the hidden danger in the target matter in the target debris flow channel collection data based on the descriptive attribute mean, and determine the debris flow hidden danger point data of the matter corresponding to the target debris flow channel collection data based on the type and position description content of the local analysis result of the matter.

[0073] For example, the descriptive attribute mean is understood as the numerical value of the factor that affects the occurrence of debris flow. The larger the numerical value, the greater the possibility of debris flow.

[0074] For example, the mean of the description attributes of the first data intersection description set can be taken, and the mean of the description attributes can be determined as the location description content of the important characteristic description content of the hidden dangers in the target matter in the target debris flow channel collection data. According to the type and location description content of the local analysis results of the matter, the matter structure of the target matter in the target debris flow channel collection data can be determined. The matter structure can be used as the debris flow hidden danger point data corresponding to the target matter in the target debris flow channel collection data.

[0075] Step S204: loading the target debris flow channel acquisition data into the local intelligent analysis thread, and analyzing the first item local analysis result of the target item in the target debris flow channel acquisition data in the local intelligent analysis thread.

[0076] For example, the target debris flow channel acquisition data can also be loaded into a local intelligent analysis thread, in which the target debris flow channel acquisition data is first analyzed to see whether the local analysis results of the first item of the target item are included. The local intelligent analysis thread can be used to analyze the important characteristic description content of the hidden dangers in the local analysis results of the first item. Therefore, it is necessary to analyze the local analysis results of the first item in the target debris flow channel acquisition data. If the local analysis results of the first item of the target item are not analyzed in the target debris flow channel acquisition data, the local debris flow hidden danger point data corresponding to the target debris flow channel acquisition data can be directly determined to be null, without the need to perform the subsequent steps of analyzing the important characteristic description content of the hidden dangers in the local analysis results of the first item.

[0077] Step S205: If the local analysis result of the first matter is analyzed in the target debris flow channel collection data, the scope geological state description content covering the local analysis result of the first matter is obtained from the target debris flow channel collection data, and the location of the local hidden danger important feature description content corresponding to the local analysis result of the first matter is obtained based on the scope geological state description content. Based on the location of the local hidden danger important feature description content, the local debris flow hidden danger point data corresponding to the target debris flow channel collection data is determined.

[0078] For example, if the local analysis result of the first issue is analyzed in the target debris flow channel collection data, the position range of the local analysis result of the first issue in the target debris flow channel collection data can be determined. Based on the position range of the local analysis result of the first issue in the target debris flow channel collection data, the target debris flow channel collection data is filtered to obtain the range geological state description content covering the local analysis result of the first issue. In the local intelligent analysis thread, feature extraction can be performed on the range geological state description content to obtain the local edge features corresponding to the local analysis result of the first issue in the range geological state description content. Based on the local edge features, the position of the local hidden danger important feature description content corresponding to the local analysis result of the first issue can be regressed and analyzed; based on the position of the local hidden danger important feature description content, the hidden danger important feature description content of the local analysis result of the first issue can be associated to obtain the local debris flow hidden danger point data corresponding to the target debris flow channel collection data.

[0079] Step S206: obtain a sample dimension that matches the target event, count the number of important characteristic description contents of the first hidden danger corresponding to the sample dimension, and count the number of important characteristic description contents of the second hidden danger corresponding to the debris flow hidden danger point data.

[0080] For example, the calculation can obtain the sample dimension corresponding to the target event and count the number of first-level important characteristic descriptions of the important characteristic descriptions of hidden dangers covered in the sample dimension, as well as the number of second-level important characteristic descriptions of the important characteristic descriptions of hidden dangers covered in the debris flow hazard point data. The number of first-level important characteristic descriptions of hidden dangers is known when the sample dimension is constructed, while the number of second-level important characteristic descriptions of hidden dangers is the number of important characteristic descriptions of hidden dangers obtained through regression analysis by the intelligent analysis thread of the event.

[0081] Step S207: When the number of the first hidden danger important feature description contents exceeds the number of the second hidden danger important feature description contents, the debris flow hidden danger point data is analyzed and processed according to the sample dimension to obtain the first pending matter dimension analysis result.

[0082] Example, the analysis results of the first pending items dimension

[0083] For example, when the number of description contents of important characteristics of the first hidden danger exceeds the number of description contents of important characteristics of the second hidden danger, it means that there are missing description contents of important characteristics of the hidden danger in the data of the debris flow hidden danger point. The important characteristics of the hidden danger description content of the debris flow hidden danger point data of the matter can be repaired through the sample dimension (repair means to complete the defective data) to improve the missing important characteristics of the hidden danger description content, so as to obtain the first pending matter dimension analysis result corresponding to the target matter.

[0084] Step S208: Analyze and process the dimensional analysis result of the first pending item based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item.

[0085] For example, the local analysis results of the first pending item dimensional analysis results that match the local analysis results of the first item can be analyzed and processed based on the local debris flow hazard point data to obtain the debris flow channel data collection results corresponding to the target item. Alternatively, if the local debris flow hazard point data is null (i.e., the local analysis results of the first item are not included in the target debris flow channel data collection), the first pending item dimensional analysis results can be directly determined as the debris flow channel data collection results corresponding to the target item.

[0086] If the debris flow hazard point data does not include the dimensions of the second matter local analysis results and the third matter local analysis results, that is, the target debris flow channel collection data does not cover the second matter local analysis results nor the third matter local analysis results, then the second local dimension corresponding to the second matter local analysis result and the third local dimension corresponding to the third matter local analysis result can be determined based on the location of the important hazard feature description content of the first matter local analysis result covered in the local debris flow hazard point data; and then the second local data volume corresponding to the second matter local analysis result and the third local data volume corresponding to the third matter local analysis result can be obtained in the a-1th debris flow channel collection data; in other words, the data volume of the second matter local analysis result in the previous debris flow channel collection data can be used as the data volume of the second matter local analysis result in the target debris flow channel collection data, and the geological state description content of the third matter local analysis result in the previous debris flow channel collection data can be used as the data volume of the third matter local analysis result in the target debris flow channel collection data. That is, the location of the important characteristic description content of the hidden danger in the local analysis result of the second matter can be determined based on the second local data volume and the second local dimension; the location of the important characteristic description content of the hidden danger in the local analysis result of the third matter can be determined based on the third local data volume and the third local dimension. The location of the important characteristic description content of the hidden danger in the local analysis result of the second matter and the location of the important characteristic description content of the hidden danger in the local analysis result of the third matter can be loaded into the analysis result of the first pending matter dimension, thereby obtaining the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data. If the a-1th debris flow channel collection data also includes the second matter local analysis result and the third matter local analysis result, then it is possible to continue backtracking to obtain the data volume of the second matter local analysis result and the third matter local analysis result in the a-2th debris flow channel collection data, respectively, to determine the location of the important characteristic description content of the hidden danger in the target debris flow channel collection data. If the local analysis results of the second matter and the local analysis results of the third matter are not analyzed in the debris flow channel collection data before the target debris flow channel collection data, an approximate data amount can be set for the local analysis results of the second matter and the local analysis results of the third matter respectively according to the analysis results of the first pending matter dimension to determine the location of the important feature description content of the hidden dangers of the local analysis results of the second matter and the local analysis results of the third matter in the target debris flow channel collection data.

[0087] Optionally, the dimension obtained after analyzing and processing the first pending item dimension analysis result based on the local debris flow hazard point data may contain some unreasonable descriptions of the important features of the item hidden danger. Therefore, the unreasonable descriptions of the important features of the item hidden danger can be debugged in combination with the sample dimension to obtain the final debris flow channel data collection result of the target item. For example, assuming that the local analysis result of the third item is not analyzed in the target debris flow channel collection data, the first pending item dimension analysis result with the important feature description of the hidden danger content of the local analysis result of the third item added can be determined as the second pending item dimension analysis result; and then the dimension difference value between the sample dimension and the second pending item dimension analysis result can be obtained. If the dimension difference value exceeds the target difference value (which can be understood as the target item has a large difference value under normal circumstances), the second pending item dimension analysis result is debugged based on the sample dimension to obtain the debris flow channel data collection result corresponding to the target item in the target debris flow channel collection data.

[0088] The channel information data set captured in the mobile scenario usually cannot cover the entire target item. The dimension of the target item obtained through the regression analysis of the item intelligent analysis thread is incomplete. The rationality of the debris flow channel data collection results can be improved through the analysis of the important feature description content of the hidden danger and the debugging of the important feature description content of the hidden danger. Through the local debris flow hidden danger point data, the location of the important feature description content of the item hidden danger that matches the local analysis result of the first item can be calculated, which can improve the accuracy of the debris flow channel data collection results.

[0089] In an embodiment of the present application, by performing item dimension analysis and specific local dimension analysis on the target items in the target debris flow channel collection data respectively, the item debris flow hazard point data for the target item and the local debris flow hazard point data of the first item local analysis result of the target item can be obtained. Then, based on the item debris flow hazard point data, the local debris flow hazard point data and the sample dimension, the target item in the target debris flow channel collection data can be dimensionally analyzed. The important feature description content of the local hazards that is missing from the target item in the target debris flow channel collection data can be repaired, and the important feature description content of the item hazards that does not conform to the sample dimension can be debugged. This can ensure the integrity and rationality of the debris flow channel data collection result of the target item, and thus improve the accuracy and reliability of the debris flow channel data collection result.

[0090] Based on the above, a device for collecting debris flow channel data based on a drone is provided, which includes:

[0091] a data acquisition module, configured to obtain event debris flow hazard point data and local debris flow hazard point data corresponding to target debris flow channel collected data; the event debris flow hazard point data matches the target event in the target debris flow channel collected data, and the local debris flow hazard point data matches the first event local analysis result of the target event;

[0092] A number acquisition module is used to obtain a sample dimension that matches the target event, and count the number of first hidden danger important feature description contents corresponding to the sample dimension, and the number of second hidden danger important feature description contents corresponding to the debris flow hidden danger point data of the event;

[0093] A result analysis module is configured to analyze and process the debris flow hazard point data according to the sample dimension to obtain a first pending item dimension analysis result when the number of the first hazard important feature description contents exceeds the number of the second hazard important feature description contents;

[0094] The result collection module is used to analyze and process the first pending item dimensional analysis result based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item.

[0095] Based on the above, a debris flow channel data acquisition system based on a drone is shown, which includes a processor and a memory that communicate with each other. The processor is used to read a computer program from the memory and execute it to implement the above method.

[0096] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0097] In summary, based on the above scheme, by performing item dimension analysis and specific local dimension analysis on the target items in the target debris flow channel collection data respectively, the item debris flow hazard point data for the target item and the local debris flow hazard point data of the first item local analysis result of the target item can be obtained. Then, based on the item debris flow hazard point data, the local debris flow hazard point data and the sample dimension, the target item in the target debris flow channel collection data can be dimensionally analyzed, and the important feature description content of the local hazards missing from the target item in the target debris flow channel collection data can be repaired, which can ensure the integrity and rationality of the debris flow channel data collection results of the target item, and thus improve the accuracy and reliability of the debris flow channel data collection results.

[0098] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of the present application. Not only can hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, they can also be implemented using software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0099] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

Claims

1. A method for collecting debris flow channel data based on drones, characterized in that: include: Obtaining the data of the debris flow potential point and the local debris flow potential point corresponding to the target debris flow channel collection data; The debris flow potential point data matches the target item in the target debris flow channel collection data, and the local debris flow potential point data matches the first item local analysis result of the target item; Obtain a sample dimension that matches the target event, and count the number of first hidden danger important feature descriptions corresponding to the sample dimension, and the number of second hidden danger important feature descriptions corresponding to the debris flow hidden danger point data of the event; When the number of the first hidden danger important feature description contents exceeds the number of the second hidden danger important feature description contents, analyzing and processing the debris flow hidden danger point data according to the sample dimension to obtain a first pending matter dimension analysis result; Analyze and process the first pending item dimensional analysis result according to the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item; The step of analyzing and processing the first pending item dimension analysis result based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item includes: If the debris flow hazard point data of the item covers the dimension of the local analysis result of the second item, and the debris flow hazard point data of the item does not cover the dimension of the local analysis result of the third item, then the first local dimension corresponding to the local analysis result of the third item is determined based on the location of the hazard important feature description content of the local analysis result of the first item covered by the local debris flow hazard point data; the local analysis result of the second item and the local analysis result of the third item are in a mirror relationship; Obtaining a first local data volume of the local analysis result of the second item in the dimensional analysis result of the first pending item, and determining a location of a description of important characteristics of hidden dangers in the local analysis result of the third item based on the first local data volume and the first local dimension; The location of the important feature description content of the hidden danger of the local analysis result of the third matter is loaded into the dimensional analysis result of the first pending matter to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

2. The method according to claim 1, characterized in that The obtaining of the debris flow potential point data and local debris flow potential point data corresponding to the target debris flow channel acquisition data includes: Obtain the target debris flow channel collection data from the channel information data set, load the target debris flow channel collection data into the event intelligent analysis thread, and output the event debris flow hazard point data corresponding to the target debris flow channel collection data through the event intelligent analysis thread; The target debris flow channel acquisition data is loaded into a local intelligent analysis thread, and the local debris flow hazard point data corresponding to the target debris flow channel acquisition data is output through the local intelligent analysis thread.

3. The method according to claim 2, characterized in that The step of loading the target debris flow channel collected data into the event intelligent analysis thread, and outputting event debris flow hazard point data corresponding to the target debris flow channel collected data through the event intelligent analysis thread, includes: The target debris flow channel acquisition data is loaded into the matter intelligent analysis thread, and the matter intelligent analysis thread obtains the matter dimension feature corresponding to the target matter in the target debris flow channel acquisition data, and reads the first classification result corresponding to the matter dimension feature; the first classification result is used to indicate the type of matter local analysis result corresponding to the description content of the important hidden danger feature of the target matter; generating a first data intersection description set according to the first classification result and key features of the target debris flow channel collected data; Obtaining a descriptive attribute mean corresponding to the first data intersection description set, and determining a location description of important feature descriptions of hidden dangers in the target item in the target debris flow channel collected data based on the descriptive attribute mean; According to the type of the local analysis result of the event and the content of the location description, the event debris flow potential point data corresponding to the target debris flow channel collection data is determined.

4. The method according to claim 3, characterized in that The obtaining of the item dimension features corresponding to the target item in the target debris flow channel collected data through the item intelligent analysis thread includes: Obtaining, in the intelligent analysis thread of the matter, a matter description feature corresponding to the target matter in the target debris flow channel collected data, and outputting, according to a classification unit in the intelligent analysis thread of the matter, a second classification result corresponding to the matter description feature; Obtaining a key feature of the matter for the target debris flow channel collected data output by the target feature extraction unit in the matter intelligent analysis thread, performing function processing on the second classification result and the key feature of the matter to obtain a second data intersection description set corresponding to the target debris flow channel collected data; The target debris flow channel collected data is bucketed according to the second data intersection description set to obtain geological state description contents within the scope of Z item local analysis results, and local description features corresponding to the geological state description contents within the scope of the Z item local analysis results are obtained according to the item intelligent analysis thread; Z is a positive integer; The event description feature and the local description features corresponding to the geological state description content within the local analysis result range of the Z events are integrated into the event dimension feature.

5. The method according to claim 2, characterized in that The step of loading the target debris flow channel collected data into a local intelligent analysis thread and outputting local debris flow hazard point data corresponding to the target debris flow channel collected data through the local intelligent analysis thread includes: Loading the target debris flow channel acquisition data into a local intelligent analysis thread, and analyzing the first item local analysis result of the target item in the target debris flow channel acquisition data in the local intelligent analysis thread; If the local analysis result of the first issue is analyzed in the target debris flow channel collected data, a range geological state description content covering the local analysis result of the first issue is obtained from the target debris flow channel collected data, a location of a local hidden danger important feature description content corresponding to the local analysis result of the first issue is obtained based on the range geological state description content, and local debris flow hidden danger point data corresponding to the target debris flow channel collected data is determined based on the location of the local hidden danger important feature description content; If the local analysis result of the first item is not analyzed in the target debris flow channel collection data, it is determined that the local debris flow hazard point data corresponding to the target debris flow channel collection data is a null value.

6. The method according to claim 5, characterized in that If the local analysis result of the first matter is analyzed in the target debris flow channel collection data, a range geological state description content covering the local analysis result of the first matter is obtained from the target debris flow channel collection data, a location of a local hidden danger important feature description content corresponding to the local analysis result of the first matter is obtained based on the range geological state description content, and local debris flow hidden danger point data corresponding to the target debris flow channel collection data is determined based on the location of the local hidden danger important feature description content, including: If the local analysis result of the first item is analyzed in the target debris flow channel collection data, the target debris flow channel collection data is filtered to obtain a range of geological state description content covering the local analysis result of the first item; Obtaining local edge features corresponding to the geological state description content of the range, and regressing and analyzing the location of the important feature description content of the local hidden danger corresponding to the local analysis result of the first matter based on the local edge features; Based on the location of the important feature description content of the local hidden danger, the important feature description content of the hidden danger of the local analysis result of the first matter is associated to obtain the local debris flow hidden danger point data corresponding to the target debris flow channel collection data.

7. The method according to claim 1, characterized in that The method of loading the location of the important feature description of the hidden danger of the local analysis result of the third matter into the dimensional analysis result of the first pending matter to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data includes: Loading the location of the important feature description content of the hidden danger of the local analysis result of the third issue into the first pending issue dimensional analysis result, obtaining the second pending issue dimensional analysis result corresponding to the target issue in the target debris flow channel collection data, and obtaining the dimensional difference value between the sample dimension and the second pending issue dimensional analysis result; If the dimension difference value exceeds the target difference value, the important feature description content of the hidden danger is debugged for the second pending matter dimension analysis result based on the sample dimension to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

8. The method according to claim 1, characterized in that The target debris flow channel collection data is the ath debris flow channel collection data in the channel information data set, where a is a positive integer; the first pending item dimensional analysis result is analyzed and processed based on the local debris flow hazard point data to obtain the debris flow channel data collection result corresponding to the target item, including: If the debris flow hazard point data does not include the dimensions of the second and third item local analysis results, then determine the second local dimension corresponding to the second item local analysis result and the third local dimension corresponding to the third item local analysis result based on the location of the important hazard feature description content of the first item local analysis result covered in the local debris flow hazard point data; the second item local analysis result and the third item local analysis result are in a mirror image relationship; In the a-1th debris flow channel data collection, a second local data volume corresponding to the second-item local analysis result and a third local data volume corresponding to the third-item local analysis result are obtained, and the location of the important characteristic description content of the hidden danger in the second-item local analysis result is determined based on the second local data volume and the second local dimension; According to the third local data volume and the third local dimension, the location of the important feature description content of the hidden danger of the local analysis result of the third matter is determined, and the location of the important feature description content of the hidden danger of the local analysis result of the second matter and the location of the important feature description content of the hidden danger of the local analysis result of the third matter are loaded into the first pending matter dimension analysis result to obtain the debris flow channel data collection result corresponding to the target matter in the target debris flow channel collection data.

9. A debris flow channel data acquisition system based on drones, characterized in that: The method comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 8.

Images