Dry snow compactness detection method and system based on vibration liquefaction
By acquiring images and temperature data of the snow layer, combined with vibration and resistance data of the probe, and utilizing a snow layer recognition model, the problem of low accuracy and low efficiency caused by sample changes in traditional detection methods is solved, achieving more efficient and accurate dry snow compaction detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- POLAR RES INST OF CHINA
- Filing Date
- 2026-02-02
- Publication Date
- 2026-05-19
AI Technical Summary
Traditional methods for testing the compaction of dry snow cannot guarantee that the sample volume will not change during the sampling process, resulting in low accuracy and low efficiency.
By acquiring image and temperature data of the target snow layer, recording vibration and resistance data of the probe, and combining this with a snow layer identification model, the snow layer distribution and compaction degree are determined.
It improves the accuracy and efficiency of dry snow compaction testing, reduces errors caused by manual operation, and can effectively identify snow layer distribution and calculate compaction degree.
Smart Images
Figure CN122065083A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of environmental monitoring, and in particular to a method and system for detecting the compaction degree of dry snow based on vibration liquefaction. Background Technology
[0002] With the increasing demand for monitoring water resources and the ecological environment, as well as the need for monitoring snowfield environments, dry snow density, or dry snow compaction, has become an important monitoring indicator. Currently, traditional monitoring methods determine dry snow density by collecting snow samples and measuring their volume and mass. However, this method cannot guarantee that the sample volume will not change during sampling, and its detection efficiency is too low for multi-layered snow samples, resulting in low accuracy and reduced detection efficiency.
[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention
[0004] The main objective of this invention is to provide a method and system for detecting the compaction degree of dry snow based on vibration liquefaction, which aims to improve the accuracy and efficiency of dry snow compaction degree monitoring.
[0005] To achieve the above objectives, the present invention provides a method for detecting the compaction degree of dry snow based on vibration liquefaction, the method comprising the following steps: Acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. Based on the image data and the first resistance data, determine the snow layer distribution data corresponding to the preset location coordinates within the target area; Based on the snow layer distribution data, the first vibration data, and the first resistance data, determine the second vibration data and the second resistance data at the preset location; The compaction degree of the target area is determined based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
[0006] Optionally, the image data is a snow profile of the target snow layer, and the step of determining the snow layer distribution data corresponding to the preset location coordinates within the target area based on the image data and the first resistance data includes: Based on the snow body profile, determine the type of snow layer in the profile at the location of the target snow layer and the corresponding snow layer distribution height for each type of snow layer in the profile; Based on the first resistance data, determine the type of snow layer at the probe point location and the corresponding snow layer distribution height at each probe point. A snow layer distribution model is generated based on the snow layer type in the profile, the snow layer distribution height in the profile, the snow layer type at the probe point, and the snow layer distribution height at the probe point. The snow layer distribution data are determined based on the snow layer distribution model.
[0007] Optionally, the step of determining the type of profile snow layer at the location of the target snow layer and the corresponding profile snow layer distribution height for each type of profile snow layer based on the snow body profile includes: Extract the color and edge features of the snow body profile; The snow body profile is divided into multiple recognition regions based on the color and edge features; The corresponding snow layer type in the profile is determined based on the correlation between multiple identification regions and features; The corresponding profile snow layer distribution height is determined based on the pixel position of each recognition area.
[0008] Optionally, the step of determining the second vibration data and the second resistance data at the preset location based on the snow layer distribution data, the first vibration data, and the first resistance data includes: Based on the first vibration data and the first resistance data, determine the first vibration characteristics and the first resistance characteristics of the snow layer type at each probe point; The simulation time for each snow layer type at the preset location is determined based on snow layer distribution data; The second vibration data and the second resistance data are determined based on the first vibration characteristic, the second vibration characteristic, and the simulation time.
[0009] Optionally, before the step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, the method further includes: Historical dry snow detection data is obtained, including historical temperature data, historical vibration data, historical resistance data, and historical compaction data.
[0010] The historical dry snow detection data is divided into a training set and a test set; The preset deep learning model is trained based on the training set to obtain the trained model; The trained model is tested using the test set to obtain test results; The snow layer recognition model is determined based on the test results.
[0011] Optionally, after the step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, the method further includes: When the compaction degree is greater than or equal to a preset threshold, it is determined that there is no risk of avalanche in the current target area; When the compaction degree is less than a preset threshold, it is determined that there is an avalanche risk in the current target area.
[0012] Optionally, before the step of recording the first vibration data and the first resistance data detected by the probe, the method further includes: The vibration device is controlled to operate based on the control data from the preset vibration test.
[0013] Furthermore, to achieve the above objectives, the present invention also provides a dry snow compaction degree detection system based on vibration liquefaction, the system comprising: The acquisition module is used to acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and the first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. The identification module is used to determine the snow layer distribution data corresponding to the preset position coordinates within the target area based on the image data and the first resistance data; The simulation module is used to determine the second vibration data and the second resistance data at the preset location based on the snow layer distribution data, the first vibration data, and the first resistance data.
[0014] The analysis module is used to determine the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
[0015] In addition, to achieve the above objectives, the present invention also provides a monitoring device, the device comprising: a memory, a processor, and a vibration-liquefaction-based dry snow compaction detection program stored in the memory and executable on the processor, the vibration-liquefaction-based dry snow compaction detection program being configured to implement the steps of the vibration-liquefaction-based dry snow compaction detection method described in any of the above claims.
[0016] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a dry snow compaction test program based on vibration liquefaction, wherein when the dry snow compaction test program based on vibration liquefaction is executed by a processor, it implements the steps of the dry snow compaction test method based on vibration liquefaction described above.
[0017] This invention proposes a method for detecting the compaction degree of dry snow based on vibration liquefaction. This method acquires image and temperature data of the target snow layer in a target area, and records the first vibration and first resistance data detected by a probe. Compared to traditional snow sampling methods, probe detection and image acquisition effectively reduce alterations to the snow body and minimize errors caused by manual operation. Based on the image data and the first resistance data, the snow layer distribution data corresponding to preset coordinates within the target area is determined. Compared to traditional detection methods, this method effectively identifies the overall distribution of the snow layer. Furthermore, based on the snow layer distribution data, the first vibration data, and the first resistance data, second vibration and second resistance data are determined at the preset location. Using this large amount of data, the compaction degree of the target area can be determined based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and a snow layer identification model. This improves the monitoring of the overall compaction degree of the entire target area, thereby increasing detection efficiency and accuracy. Attached Figure Description
[0018] Figure 1 This is a schematic diagram of the structure of a monitoring device for the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the dry snow compaction detection system based on vibration liquefaction of the present invention. Figure 3 This is a flowchart illustrating the second embodiment of the dry snow compaction detection system based on vibration liquefaction of the present invention. Figure 4 This is a flowchart illustrating the third embodiment of the dry snow compaction detection system based on vibration liquefaction of the present invention. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0019] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0020] Reference Figure 1 , Figure 1 This is a schematic diagram of the monitoring device structure for the hardware operating environment involved in the embodiments of the present invention.
[0021] like Figure 1As shown, the monitoring device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0022] In addition, the monitoring equipment may also be equipped with a device for performing preset vibration tests, specifically an ECT impact head and a laminate, wherein the ECT impact head is set at the center of the target area, specifically at the geometric center.
[0023] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the monitoring device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0024] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a dry snow compaction detection program based on vibration liquefaction.
[0025] exist Figure 1 In the monitoring device shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the monitoring device of the present invention can be set in the monitoring device. The monitoring device calls the dry snow compaction degree detection program based on vibration liquefaction stored in the memory 1005 through the processor 1001 and executes the dry snow compaction degree detection method based on vibration liquefaction provided in the embodiment of the present invention.
[0026] This invention provides a method for detecting the compaction degree of dry snow based on vibration liquefaction, referring to... Figure 2 , Figure 2This is a flowchart illustrating the first embodiment of a method for detecting the compaction degree of dry snow based on vibration liquefaction according to the present invention.
[0027] In this embodiment, the dry snow compaction degree detection method based on vibration liquefaction includes: Step S1: Acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. In this embodiment, a flat area is typically selected in the ski resort as the target area, generally 90 cm long and 30 cm wide, with the depth of the target area being the actual depth of the snow layer. However, this embodiment does not limit the range of the target area. Furthermore, after determining the target area, a snow pit is dug in the vicinity of the target area, and the target snow block is obtained by cutting within the pit. The target snow layer is generally part or the entirety of the target snow block. In this embodiment, the image data includes: image data of the target snow block after performing a preset vibration test. It should be noted that this image data is an image of the side of the target snow block, thus obtaining image data including the arrangement of various snow layers in the target area. Optionally, the corresponding image data includes: image data of the target snow block before performing the preset vibration test. The first pixel of the image data of the target snow block after performing the preset vibration test and the second pixel of the image data of the target snow block before performing the preset vibration test are associated, so that the change features of the snow layer corresponding to each image can be extracted subsequently. The probe here collects vibration data and resistance data while being inserted into the target snow layer at a constant speed, thereby obtaining the first vibration data and the first resistance data.
[0028] Step S2: Determine the snow layer distribution data corresponding to the preset position coordinates within the target area based on the image data and the first resistance data; Because the snow layer, weak layer, and stable layer have different densities, especially in the weak layer where liquefaction due to vibration can occur, the resistance experienced by the probe can suddenly decrease, resulting in inconsistent resistance during probe insertion into the snow layer. Furthermore, the snow layers in the image data are not perfectly parallel; the same type of snow layer may exhibit different thicknesses at different locations on the cross-section. Based on the variation trend of the snow layers at different locations on the cross-section and the first resistance data, linear fitting can be used to fit the distribution and corresponding thickness of each snow layer type at a predetermined location in the target area, thus obtaining the snow layer distribution data.
[0029] Step S3: Determine the second vibration data and the second resistance data at the preset position based on the snow layer distribution data, the first vibration data, and the first resistance data; In this embodiment, the second vibration data and the second resistance data are simulated data. Optionally, the first vibration data and the first resistance data are grouped into multiple first sub-vibration data and multiple first sub-resistance data according to the snow layer type. The first sub-vibration features of each first sub-vibration data and the first sub-resistance data features of each first sub-resistance data are extracted respectively, and fitted according to the first sub-vibration features and the first sub-resistance data features to obtain the second sub-vibration data and the second sub-resistance data corresponding to each snow layer type. The proportion of the second sub-vibration data and the second sub-resistance data corresponding to each snow layer type in the preset location is determined according to the snow layer distribution data, thereby obtaining the second vibration data and the second resistance data.
[0030] Step S4: Determine the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
[0031] In this embodiment, the temperature data, the first vibration data, the first resistance data, the second vibration data, and the second resistance data are specifically constructed as the input vector of the input model, and the snow layer identification model calculates based on the input vector to obtain the compaction degree of the target area.
[0032] In this embodiment, by acquiring image data and temperature data of the target snow layer in the target area, and recording the first vibration data and first resistance data detected by the probe, compared with traditional snow sampling methods, probe detection and image acquisition can effectively reduce changes to the snow body and reduce errors caused by manual operation. Based on the image data and the first resistance data, snow layer distribution data corresponding to preset position coordinates within the target area is determined. Compared with traditional detection methods, this can effectively identify the overall distribution of the snow layer. Based on the snow layer distribution data, the first vibration data, and the first resistance data, second vibration data and second resistance data at the preset position are determined. Based on the aforementioned large amount of data, the compaction degree of the target area can be determined according to the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, improving the monitoring of the overall compaction degree of the entire target area, thereby improving detection efficiency and the accuracy of compaction degree detection.
[0033] Furthermore, based on the first embodiment, a second embodiment of the present invention for detecting the compaction degree of dry snow based on vibration liquefaction is proposed. In this embodiment, referring to... Figure 3The image data is a snow profile of the target snow layer. The step of determining the snow layer distribution data corresponding to the preset location coordinates within the target area based on the image data and the first resistance data includes: Step S21: Determine the type of snow layer at the profile location of the target snow layer and the corresponding snow layer distribution height for each type of snow layer based on the snow body profile diagram. Specifically, since the image data here is a snow profile, it includes data reflecting the type of snow layer in the profile. Image processing is used to extract relevant information from the image, thereby identifying the type of snow layer at each location in the image. This embodiment does not limit the type of image processing algorithm.
[0034] Step S22: Determine the type of snow layer at the probe point location and the corresponding snow layer distribution height at each probe point based on the first resistance data. In this embodiment, the characteristics of the first resistance data are matched with the preset resistance characteristics. Based on the matching result, the snow layer corresponding to each first sub-resistance data in the first resistance data is determined. Based on the time corresponding to the first sub-resistance data and the speed of inserting the snow layer, the snow layer distribution height of each probe point corresponding to the snow layer type is determined.
[0035] Step S23: Generate a snow layer distribution model based on the snow layer type in the profile, the snow layer distribution height in the profile, the snow layer type at the probe point, and the snow layer distribution height at the probe point. In this embodiment, the snow layer distribution model can be point cloud data, where each point in the point cloud data corresponds to a snow layer type, thus accurately reflecting the distribution of various snow layers in the snow body of the entire target area based on the point cloud data.
[0036] Step S24: Determine the snow layer distribution data based on the snow layer distribution model.
[0037] In this embodiment, a corresponding coordinate system is constructed based on the snow layer distribution model, thereby obtaining snow layer distribution data based on the coordinate system.
[0038] Furthermore, the step of determining the type of snow layer at the profile location of the target snow layer and the corresponding snow layer distribution height for each type of snow layer based on the snow body profile includes: Extract the color and edge features of the snow body profile; The snow body profile is divided into multiple recognition regions based on the color and edge features; The corresponding snow layer type in the profile is determined based on the correlation between multiple identification regions and features; The corresponding profile snow layer distribution height is determined based on the pixel position of each recognition area.
[0039] In this embodiment, different types of snow layers exhibit different data differences in the image. For example, the color characteristics of deep frost layers are yellowish-white, the color characteristics of ice crust layers are low saturation, and the color characteristics of new snow layers are high brightness. This embodiment also identifies the distribution of different types of snow layers by extracting edge features. Specifically, the snow profile is divided into multiple recognition regions based on color and edge features, and the corresponding snow layer type is determined according to the relationship between the recognition regions and features. This feature relationship is a mapping between the color and edge features of the recognition regions and the types of snow layers in the profile, specifically a mapping table. The corresponding snow layer distribution height is determined based on the pixel position of each recognition region.
[0040] In this embodiment, by extracting the color and edge features of the snow body profile, the snow body profile is divided into multiple recognition regions based on the color and edge features. The corresponding snow layer type is determined based on the correlation between the multiple recognition regions and features. The corresponding snow layer distribution height is determined based on the pixel position of each recognition region. This improves the accuracy of snow layer distribution height recognition based on the color and edge features of the snow body profile.
[0041] Furthermore, based on the first or second embodiment, a third embodiment of the present invention for detecting the compaction degree of dry snow based on vibration liquefaction is proposed. In this embodiment, reference is made to... Figure 4 The step of determining the second vibration data and second resistance data at the preset location based on the snow layer distribution data, the first vibration data, and the first resistance data includes: Step S31: Determine the first vibration characteristics and second vibration characteristics of each snow layer type at each probe point based on the first vibration data and the first resistance data. In this embodiment, the vibration frequency, vibration amplitude, and abnormal vibration waveform location of the first vibration data are extracted. Furthermore, the resistance change frequency, resistance change amplitude, and abnormal resistance change waveform location of the first resistance data are extracted.
[0042] Step S32: Determine the simulation time for each snow layer type at the preset location based on the snow layer distribution data; Based on the snow layer distribution data, specifically the simulation time for each snow layer type is calculated according to the depth of the snow layer distribution and the probe speed. Optionally, in other embodiments, a functional relationship between each first sub-vibration data and each first sub-drag data can be fitted.
[0043] Step S33: Determine the second vibration data and the second resistance data based on the first vibration characteristic, the second vibration characteristic, and the simulation time.
[0044] Simulations are performed based on the functional relationships between the first sub-vibration data and the first sub-resistance data, and the second vibration data and the second resistance data are determined based on the simulation time.
[0045] In this embodiment, the first vibration characteristics and first resistance characteristics of each snow layer type at each probe point are determined by the first vibration data and the first resistance data. The simulation time of each snow layer type at the preset location is determined based on the snow layer distribution data. The second vibration data and second resistance data are determined based on the first vibration characteristics, the second vibration characteristics, and the simulation time. This allows for the acquisition of virtual vibration data and resistance data obtained by simulating probe detection at each location, thereby expanding the amount of data input to the snow layer identification model and avoiding the problem of data detection anomalies caused by multiple probe detections.
[0046] Furthermore, based on any of the above embodiments, a fourth embodiment of the dry snow compaction degree detection method based on vibration liquefaction of the present invention is proposed. Before the step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, the method further includes: Historical dry snow detection data is obtained, including historical temperature data, historical vibration data, historical resistance data, and historical compaction data.
[0047] The historical dry snow detection data is divided into a training set and a test set; The preset deep learning model is trained based on the training set to obtain the trained model; The trained model is tested using the test set to obtain test results; The snow layer recognition model is determined based on the test results.
[0048] Among them, the historical temperature data refers to the ambient temperature and / or near-surface snow temperature at the time of data collection. Preferably, the historical vibration data and historical resistance data are actual collected data. For a region, multiple probes are set up for monitoring, or data is collected through multiple detections.
[0049] The preprocessed and feature-engineered historical dry snow detection data is divided into training and testing sets. A random partitioning method is typically used, such as 70%-30% or 80%-20%, to ensure that the training set is used for model learning and the testing set is used to independently evaluate the model's generalization ability. During the partitioning process, care must be taken to maintain a balanced data distribution to avoid introducing bias. In this embodiment, the type of deep learning model is not limited; a deep learning model can be selected based on the actual situation.
[0050] Furthermore, based on any of the above embodiments, a fifth embodiment of the dry snow compaction degree detection method based on vibration liquefaction of the present invention is proposed. After the step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, the method further includes: When the compaction degree is greater than or equal to a preset threshold, it is determined that there is no risk of avalanche in the current target area; When the compaction degree is less than a preset threshold, it is determined that there is an avalanche risk in the current target area.
[0051] In this embodiment, specifically, a preset threshold is set, and the compaction degree is compared with the preset threshold to determine whether there is an avalanche risk. In other embodiments, the first vibration data, the first resistance data, and the second vibration data and the second resistance data are divided into multiple groups according to depth, and each group is input into the snow layer identification model to obtain the compaction degree corresponding to each depth. By using multiple compaction degrees, the presence and number of liquefaction layers in the snow layer can be identified. When a liquefaction layer is identified, the current target area and a preset range of the target area are marked as having a moderate avalanche risk. When more than one liquefaction layer is identified, the current target area and a preset range of the target area are marked as having a significant avalanche risk. Specifically, a common structure with a significant avalanche risk is: hard snowboard, first easily liquefiable layer, relatively stable layer, second easily liquefiable layer, and base layer. This structure has multiple potential sliding surfaces, and vibration energy can trigger liquefaction of easily liquefiable layers at different depths. When vibration acts on the snow surface, the energy propagates downwards, and the first easily liquefiable layer liquefies first, bearing the greatest vibration energy and being the most prone to instability. The liquefaction of the first liquefaction layer causes it to lose its load-bearing capacity. The load of the snowboards above it will suddenly transfer to the snow layer below, causing the second liquefaction layer to be subjected to additional stress impacts and continuous vibration energy, resulting in multi-level simultaneous damage and thus a greater risk of avalanches.
[0052] Furthermore, prior to the step of recording the first vibration data and the first resistance data detected by the probe, the method further includes: The vibration device is controlled to operate based on the control data from the preset vibration test.
[0053] In this embodiment, by pre-setting a vibration test, the easily liquefiable layer is stimulated to become a liquefiable layer, thereby improving the difference between the resistance data and vibration data of different snow layers obtained by the probe and improving the accuracy of data identification.
[0054] Furthermore, this invention also proposes a dry snow compaction degree detection system based on vibration liquefaction, the system comprising: The acquisition module is used to acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and the first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. The identification module is used to determine the snow layer distribution data corresponding to the preset position coordinates within the target area based on the image data and the first resistance data; The simulation module is used to determine the second vibration data and the second resistance data at the preset location based on the snow layer distribution data, the first vibration data, and the first resistance data.
[0055] The analysis module is used to determine the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
[0056] Furthermore, this embodiment of the invention also proposes a monitoring device, the device comprising: a memory, a processor, and a vibration-liquefied dry snow compaction degree detection program stored in the memory and executable on the processor, the vibration-liquefied dry snow compaction degree detection program being configured to implement the steps of the vibration-liquefied dry snow compaction degree detection method described above.
[0057] Furthermore, this embodiment of the invention also proposes a storage medium storing a dry snow compaction test program based on vibration liquefaction, wherein when the dry snow compaction test program based on vibration liquefaction is executed by a processor, it implements the steps of the dry snow compaction test method based on vibration liquefaction described above.
[0058] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0059] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0060] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0061] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.
Claims
1. A method for detecting the compaction degree of dry snow based on vibration liquefaction, characterized in that, The method for detecting dry snow compaction based on vibration liquefaction includes the following steps: Acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. Based on the image data and the first resistance data, determine the snow layer distribution data corresponding to the preset location coordinates within the target area; Based on the snow layer distribution data, the first vibration data, and the first resistance data, determine the second vibration data and the second resistance data at the preset location; The compaction degree of the target area is determined based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
2. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in claim 1, characterized in that, The image data is a snow profile of the target snow layer. The step of determining the snow layer distribution data corresponding to the preset location coordinates within the target area based on the image data and the first resistance data includes: Based on the snow body profile, determine the type of snow layer in the profile at the location of the target snow layer and the corresponding snow layer distribution height for each type of snow layer in the profile; Based on the first resistance data, determine the type of snow layer at the probe point location and the corresponding snow layer distribution height at each probe point. A snow layer distribution model is generated based on the snow layer type in the profile, the snow layer distribution height in the profile, the snow layer type at the probe point, and the snow layer distribution height at the probe point. The snow layer distribution data are determined based on the snow layer distribution model.
3. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in claim 2, characterized in that, The steps of determining the type of snow layer at the profile location of the target snow layer and the corresponding snow layer distribution height for each type of snow layer based on the snow body profile diagram include: Extract the color and edge features of the snow body profile; The snow body profile is divided into multiple recognition regions based on the color and edge features; The corresponding snow layer type in the profile is determined based on the correlation between multiple identification regions and features; The corresponding profile snow layer distribution height is determined based on the pixel position of each recognition area.
4. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in claim 1, characterized in that, The step of determining the second vibration data and second resistance data of the preset position based on the snow layer distribution data, the first vibration data, and the first resistance data includes: Based on the first vibration data and the first resistance data, determine the first vibration characteristics and the first resistance characteristics of the snow layer type at each probe point; The simulation time for each snow layer type at the preset location is determined based on snow layer distribution data; The second vibration data and the second resistance data are determined based on the first vibration characteristic, the second vibration characteristic, and the simulation time.
5. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in claim 1, characterized in that, Before the step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model, the method further includes: Acquire historical dry snow detection data, which includes: historical temperature data, historical vibration data, historical resistance data, and historical compaction data; The historical dry snow detection data is divided into a training set and a test set; The preset deep learning model is trained based on the training set to obtain the trained model; The trained model is tested using the test set to obtain test results; The snow layer recognition model is determined based on the test results.
6. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in claim 1, characterized in that, The step of determining the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model further includes: When the compaction degree is greater than or equal to a preset threshold, it is determined that there is no risk of avalanche in the current target area; When the compaction degree is less than a preset threshold, it is determined that there is an avalanche risk in the current target area.
7. The method for detecting the compaction degree of dry snow based on vibration liquefaction as described in any one of claims 1 to 6, characterized in that, Before the step of recording the first vibration data and the first resistance data detected by the probe, the method further includes: The vibration device is controlled to operate based on the control data from the preset vibration test.
8. A dry snow compaction degree detection system based on vibration liquefaction, characterized in that, The vibration-liquefaction-based dry snow compaction testing system includes: The acquisition module is used to acquire image data and temperature data of the target snow layer in the target area, and record the first vibration data and the first resistance data detected by the probe. The first vibration data and the first resistance data are data of the probe being inserted into the target snow layer at a constant speed after a preset vibration test has been performed. The identification module is used to determine the snow layer distribution data corresponding to the preset position coordinates within the target area based on the image data and the first resistance data; The simulation module is used to determine the second vibration data and the second resistance data at the preset location based on the snow layer distribution data, the first vibration data, and the first resistance data. The analysis module is used to determine the compaction degree of the target area based on the temperature data, the first vibration data, the first resistance data, the second vibration data, the second resistance data, and the snow layer identification model.
9. A monitoring device, characterized in that, The device includes: a memory, a processor, and a vibration-liquefaction-based dry snow compaction testing program stored in the memory and executable on the processor, the vibration-liquefaction-based dry snow compaction testing program being configured to implement the steps of the vibration-liquefaction-based dry snow compaction testing method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium stores a dry snow compaction test program based on vibration liquefaction, which, when executed by a processor, implements the steps of the dry snow compaction test method based on vibration liquefaction as described in any one of claims 1 to 7.