Dike feature identification method based on cross section elevation data

Abstract

The invention relates to the technical field of geographic information recognition, and provides a dike feature recognition method and system based on cross section elevation data, and the method comprises the steps: obtaining the cross section data of a river channel, and carrying out the preprocessing of the cross section data of the river channel; identifying candidate peak values serving as levee crest candidate points in the preprocessed river cross section data and outputting a candidate peak value list; checking whether the dike characteristics form an effective double-dike structure or not based on the candidate peak values; when an effective double-embankment structure is formed, attribution bank distribution is carried out; when the effective double-embankment structure is not formed, whether a single-embankment structure or a non-embankment structure is formed or not is judged according to the highest peak value in the candidate peak values; and outputting an embankment feature recognition result. According to the scheme, automation, accuracy and robustness can be considered, and the urgent demand of modern intelligent water conservancy for dike asset digital management can be effectively met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information recognition, and in particular to a dike feature recognition method and system based on cross-section elevation data. BACKGROUND

[0002] In water conservancy infrastructure management, flood risk prevention and control, and smart river basin construction, as a key flood control barrier, the geometric parameters of dikes (such as dike top elevation, dike shoulder position, left and right bank distribution, etc.) are important basic data for evaluating flood control capacity, developing digital twin modeling, and formulating emergency dispatching schemes.

[0003] With the development of unmanned aerial photography, airborne / ground laser radar (LiDAR) and other surveying and mapping technologies, high-precision and high-density river cross-section elevation data (i.e., profile point cloud along the direction perpendicular to the flow direction) can be efficiently obtained. Such data is usually stored in the form of (distance DIST, elevation ELEV), covering from the riverbed to the highlands on both banks, and contains rich topographic semantic information.

[0004] However, how to automatically, accurately and robustly extract dike features from massive, discrete and possibly noisy cross-section data is still a technical difficulty in current water conservancy informatization.

[0005] Currently, dike feature recognition mainly relies on the following methods: 1. Manual field survey: measuring dike top points by using a level and a total station. This method is highly accurate but extremely inefficient, making it difficult to meet the needs of large-scale and high-frequency monitoring.

[0006] 2. Remote sensing image visual interpretation: using high-resolution satellite or aerial images to manually delineate the dike line by professional personnel. This method is highly subjective, has low automation, and is severely affected by vegetation and shadow obstruction.

[0007] 3. Simple peak detection algorithm: directly applying a local maximum value method to the cross-section elevation curve to identify "high points" as dike top candidates. This method has obvious defects: (1) Susceptible to noise interference: shrubs, temporary soil deposits, and measurement errors can all form false peaks; (2) Lack of topographic semantic understanding: does not consider the typical "double-dike sandwiched river channel" landform structure, and cannot distinguish between dike tops and non-dike elevations; (3) Ambiguous left and right bank allocation: only outputs coordinate points without establishing a physical correspondence with hydrological bank types; (4) Weak fault tolerance: when facing data loss, asymmetric cross-sections, or plain sections without dikes, it is prone to produce incorrect results or crashes.

[0008] In summary, the prior art cannot balance automation, accuracy and robustness, and is difficult to support the urgent needs of modern intelligent water conservancy for digital management of embankment assets. SUMMARY

[0009] The present application aims to solve at least one of the technical problems in the background art, and provides a method and system for identifying embankment features based on cross-section elevation data.

[0010] To achieve the above-mentioned purpose, the present application provides a method for identifying embankment features based on cross-section elevation data, comprising: obtaining river cross-section data, and preprocessing the river cross-section data; identifying candidate peak values in the preprocessed river cross-section data as embankment top candidate points and outputting a candidate peak value list; checking whether the embankment features constitute an effective double-embankment structure based on the candidate peak values; when the effective double-embankment structure is constituted, performing attribution bank allocation; when the effective double-embankment structure is not constituted, judging whether a single-embankment structure or no-embankment structure is constituted according to the highest peak value in the candidate peak values; outputting the embankment feature identification result.

[0011] According to one aspect of the present application, the obtaining of the river cross-section data and the preprocessing of the river cross-section data comprises: obtaining cross-section data of one or more rivers, each data consisting of a plurality of point pairs of DIST and ELEV, wherein DIST represents the distance along the cross-section, and ELEV is the corresponding elevation; performing preprocessing on each cross-section data, comprising: de-duplication processing: removing duplicate points with the same DIST; sorting: arranging in ascending order of DIST; optional interpolation: if the distance between adjacent points is greater than a threshold, linear or spline interpolation is used to supplement the intermediate points.

[0012] According to one aspect of the present application, the identification of candidate peak values in the preprocessed river cross-section data as embankment top candidate points and the output of the candidate peak value list comprises: using a sliding window combined with a local maximum value determination strategy to identify all candidate peak values in the preprocessed river cross-section data, comprising: the window size is adaptively adjusted according to the density of the river cross-section data; a data point is determined as a candidate peak value when it satisfies: its ELEV value is greater than the ELEV values of all data points in the left and right neighborhoods within the window, and the distance between adjacent peak values is greater than or equal to 20m, and the relative height difference is greater than or equal to 0.5m; outputting the candidate peak value list.

[0013] According to one aspect of the present invention, verifying whether the levee features based on candidate peaks constitute an effective double-levee structure includes: If the number of candidate peaks ≥ 2, traverse all peak pairs formed by adjacent candidate peaks; For each peak pair, search for the minimum ELEV point C within its DIST interval as the lowest point of the river channel; Calculate the river channel depth based on the lowest point of the river channel; If the river channel depth > the preset threshold, determine that the corresponding peak pair constitutes an effective double-levee structure.

[0014] According to one aspect of the present invention, when constituting an effective double-levee structure, shore assignment is performed, including: Taking the DIST coordinate DIST_C of the lowest point of the river channel as the boundary: Assign the peak corresponding to the DIST < DIST_C of the peaks in the peak pair to the right bank levee top; Assign the peak corresponding to the DIST > DIST_C of the peaks in the peak pair to the left bank levee top.

[0015] According to one aspect of the present invention, when it does not constitute an effective double-levee structure, it is determined whether it constitutes a single-levee structure or a non-levee structure based on the highest peak among the candidate peaks, including: If there is no effective double-levee structure, select the highest peak and determine whether the highest peak is greater than the preset threshold. If so, determine that the selected highest peak constitutes a single-levee structure; If there is no highest peak exceeding the preset threshold or the river channel depth is less than the preset threshold, mark the corresponding river channel cross-section as a non-levee section or an invalid section.

[0016] According to one aspect of the present invention, it further includes: When the highest peak constitutes a single-levee structure, determine the shore to which the single-levee structure belongs based on the coordinate DIST_C.

[0017] To achieve the above object, the present invention further provides a levee feature recognition system based on cross-sectional elevation data, including: A data acquisition and preprocessing module, which acquires river channel cross-sectional data and preprocesses the river channel cross-sectional data; A candidate peak recognition and output module, which recognizes candidate peaks as levee top candidate points in the preprocessed river channel cross-sectional data and outputs a list of candidate peaks; A double-levee structure judgment module, which verifies whether the levee features based on candidate peaks constitute an effective double-levee structure; A shore assignment module, which performs shore assignment when an effective double-levee structure is constituted; The single-dike or no-dike determination module determines whether a single-dike or no-dike structure is formed when an effective double-dike structure is not constituted, based on the highest peak value among the candidate peak values. The results output module outputs the levee feature recognition results.

[0018] To achieve the above objectives, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the dike feature recognition method based on cross-sectional elevation data as described above.

[0019] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the dike feature recognition method based on cross-sectional elevation data as described above.

[0020] According to the present invention, a three-in-one levee feature recognition framework integrating "shape-semantic guidance + adaptive peak detection + multi-level fault tolerance verification" is proposed. The core components include: 1. Constructing a one-dimensional topographic profile curve: arranging elevations (ELEV) in ascending order of distance from the starting point (DIST); 2. Dynamic peak detection: adaptively setting a prominence threshold based on the elevation standard deviation; 3. Topographic semantic rule verification: only when there is a significant low-lying riverbed area between two candidate peaks is it considered a valid double-levee structure; 4. Intelligent allocation of left and right banks: automatically determining the left / right bank levee crests based on the distance from the starting point; 5. Multi-level fault tolerance mechanism: initiating a graded processing strategy for abnormal situations such as no peak, single peak, and multiple peaks; 6. Outputting a structured feature set: including left / right bank levee crest elevation, riverbed elevation, and cross-section type identifier.

[0021] This invention overcomes the limitations of traditional pure mathematical extreme value detection by introducing prior knowledge of "double levees sandwiching a riverbed" topography. It uses a riverbed depth threshold (e.g., >1.0m) for physical plausibility verification, significantly improving recognition accuracy. A combination of sliding window and minimum spacing / elevation difference constraints effectively suppresses noise interference, preventing misidentification of shrubs and mounds as levee tops. Using the lowest point of the riverbed as a natural boundary, it clearly defines the physical meaning of the left and right bank levees without relying on external water flow direction data. It supports various river scenarios, including double levees, single levees, and no levees, exhibiting strong robustness and suitability for complex real-world conditions. Attached Figure Description

[0022] Figure 1 A flowchart illustrating a method for identifying levee features based on cross-sectional elevation data according to an embodiment of the present invention; Figure 2 This is a cross-sectional view of the PCCS0 channel in Example 1. Detailed Implementation

[0023] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.

[0024] As used herein, the term "comprising" and its variations are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment".

[0025] Figure 1 The flowchart schematically illustrates a method for identifying levee features based on cross-sectional elevation data according to an embodiment of the present invention. Figure 1 As shown, in this embodiment, the levee feature identification method based on cross-sectional elevation data includes: Obtain river channel cross-sectional data and preprocess the river channel cross-sectional data; Identify candidate peak values ​​as candidate points for levee crests in the preprocessed river cross-section data and output a list of candidate peak values. Based on the candidate peak value, verify whether the dike features constitute an effective double dike structure; When an effective double-dike structure is formed, ownership of the designated bank is determined. If an effective double-dike structure is not formed, the highest peak value among the candidate peak values ​​is used to determine whether a single-dike structure or a dike-less structure is formed. Output the results of the levee feature recognition.

[0026] Furthermore, according to one embodiment of the present invention, acquiring river channel cross-sectional data and preprocessing the river channel cross-sectional data includes: Obtain cross-sectional data for one or more river channels. Each data point consists of several pairs of DIST and ELEV points, where DIST represents the distance along the cross-section (in meters) and ELEV represents the corresponding elevation (in meters). Preprocessing is performed on each cross-sectional data, including: Deduplication: Remove duplicate points from the DIST; Sort by DIST in ascending order; Optional interpolation: If the distance between adjacent points is greater than the threshold (e.g., >5m), linear or spline interpolation is used to supplement intermediate points to improve continuity.

[0027] Furthermore, according to one embodiment of the present invention, identifying candidate peak values ​​as candidate points for levee crests in the preprocessed river cross-section data and outputting a list of candidate peak values ​​includes: Adopt a sliding window combined with a local maximum determination strategy to identify all candidate peaks (candidate points for the dike crest) in the preprocessed river cross-section data, including: The window size is adaptively adjusted according to the density of the river cross-section data (for example, take 10 times the average point distance); A data point is determined to be a candidate peak when its ELEV value is greater than the ELEV values of all data points in the left and right neighborhoods within the window, and the distance from the adjacent peak is ≥ 20 m, and the relative height difference is ≥ 0.5 m; Output the candidate peak list: {(DIST1, ELEV1), (DIST2, ELEV2),...}.

[0028] Furthermore, according to an embodiment of the present invention, based on the candidate peaks, verify whether the dike features form an effective double-dike structure, including: Based on the hydrological common sense - an effective dike usually shows a double-peak structure of "high on both sides and low in the middle", perform the following verification: If the number of candidate peaks ≥ 2, traverse all peak pairs formed by adjacent candidate peaks; For each pair of peak pairs (Pᵢ, Pⱼ), search for the minimum ELEV point C within its DIST interval as the lowest point of the river channel; Calculate the river channel depth based on the lowest point of the river channel; If the river channel depth > the preset threshold (such as 1.0 m), then determine that the corresponding peak pair forms an effective double-dike structure.

[0029] Furthermore, according to an embodiment of the present invention, when an effective double-dike structure is formed, perform the attribution bank assignment, including: Taking the DIST coordinate DIST_C of the lowest point of the river channel as the boundary: Assign the corresponding peak with DIST < DIST_C among the peaks in the peak pair to the right bank dike crest; Assign the corresponding peak with DIST > DIST_C among the peaks in the peak pair to the left bank dike crest.

[0030] Furthermore, according to an embodiment of the present invention, when an effective double-dike structure is not formed, judge whether a single-dike structure or a non-dike structure is formed according to the highest peak among the candidate peaks, including: If there is no effective double-dike structure, then select the highest peak and judge whether the highest peak is greater than the preset threshold. If so, determine that the selected highest peak forms a single-dike structure; If there is no highest peak exceeding the preset threshold or the river channel depth is less than the preset threshold, then mark the corresponding river cross-section as a non-dike section or an invalid cross-section.

[0031] Furthermore, according to an embodiment of the present invention, it further includes: When the highest peak constitutes a single dike structure, the bank to which the single dike structure belongs is determined based on the coordinate DIST_C. At this time, the second highest peak can be used to complete the other bank.

[0032] Furthermore, according to one embodiment of the present invention, the output of the dike feature recognition result includes: Section number (e.g., PCCS0); The location of the left bank levee crest, DIST_L, and its elevation, ELEV_L; The location of the right bank levee crest, DIST_R, and its elevation, ELEV_R; The lowest point of the river channel is located at DIST_C, and its elevation is ELEV_C. Identify status (valid double dike / single dike / no dike).

[0033] According to the above-mentioned scheme of the present invention, the present invention proposes a three-in-one levee feature recognition framework of "shape-semantic guidance + adaptive peak detection + multi-level fault tolerance verification", the core of which includes: 1. Constructing a one-dimensional topographic profile curve: arranging the elevations (ELEV) in ascending order of distance from the starting point (DIST); 2. Dynamic peak detection: adaptively setting the prominence threshold based on the elevation standard deviation; 3. Topographic semantic rule verification: only when there is a significant low-lying river channel area between two candidate peaks is it recognized as a valid double levee structure; 4. Intelligent allocation of left and right banks: automatically determining the left / right bank levee crests based on the relationship between the distances from the starting points; 5. Multi-level fault tolerance mechanism: activating a graded processing strategy for abnormal situations such as no peak, single peak, and multiple peaks; 6. Outputting a structured feature set: including the left / right bank levee crest elevation, riverbed elevation, cross-section type identifier, etc.

[0034] This invention overcomes the limitations of traditional pure mathematical extreme value detection by introducing prior knowledge of "double levees sandwiching a riverbed" topography. It uses a riverbed depth threshold (e.g., >1.0m) for physical plausibility verification, significantly improving recognition accuracy. A combination of sliding window and minimum spacing / elevation difference constraints effectively suppresses noise interference, preventing misidentification of shrubs and mounds as levee tops. Using the lowest point of the riverbed as a natural boundary, it clearly defines the physical meaning of the left and right bank levees without relying on external water flow direction data. It supports various river scenarios, including double levees, single levees, and no levees, exhibiting strong robustness and suitability for complex real-world conditions.

[0035] Furthermore, to achieve the above objectives, the present invention also provides a levee feature recognition system based on cross-sectional elevation data, comprising: The data acquisition and preprocessing module acquires river cross-section data and preprocesses the river cross-section data. The candidate peak identification and output module identifies the candidate peaks in the preprocessed river cross-section data that serve as candidate points for the levee crest and outputs a list of candidate peaks. The double-dike structure judgment module verifies whether the dike features constitute a valid double-dike structure based on candidate peak values. When the ownership shore allocation module forms an effective double-dike structure, ownership shore allocation is performed. The single-dike or no-dike determination module determines whether a single-dike or no-dike structure is formed when an effective double-dike structure is not constituted, based on the highest peak value among the candidate peak values. The results output module outputs the levee feature recognition results.

[0036] Furthermore, according to one embodiment of the present invention, acquiring river channel cross-sectional data and preprocessing the river channel cross-sectional data includes: Obtain cross-sectional data for one or more river channels. Each data point consists of several pairs of DIST and ELEV points, where DIST represents the distance along the cross-section (in meters) and ELEV represents the corresponding elevation (in meters). Preprocessing is performed on each cross-sectional data, including: Deduplication: Remove duplicate points from the DIST; Sort by DIST in ascending order; Optional interpolation: If the distance between adjacent points is greater than the threshold (e.g., >5m), linear or spline interpolation is used to supplement intermediate points to improve continuity.

[0037] Furthermore, according to one embodiment of the present invention, identifying candidate peak values ​​as candidate points for levee crests in the preprocessed river cross-section data and outputting a list of candidate peak values ​​includes: A sliding window combined with a local maximum determination strategy is used to identify all candidate peak values ​​(candidate points on the levee crest) in the preprocessed river cross-section data, including: The window size is adaptively adjusted according to the density of the river cross-section data (e.g., taking 10 times the average point spacing). A data point is considered a candidate peak when it meets the following conditions: its ELEV value is greater than the ELEV values ​​of all data points in its left and right neighboring regions within the window, and the distance between it and its neighboring peak is ≥20m, and the relative height difference is ≥0.5m. Output candidate peak list: {(DIST1, ELEV1),(DIST2, ELEV2),…}.

[0038] Furthermore, according to one embodiment of the present invention, verifying whether the dike features constitute an effective double-dike structure based on candidate peak values ​​includes: Based on basic hydrological knowledge—effective dikes typically exhibit a bimodal structure with high elevations on both sides and a low elevation in the middle—the following verification is performed: If the number of candidate peaks is greater than or equal to 2, then iterate through all peak pairs formed by adjacent candidate peaks. For each pair of peak pairs (Pᵢ, Pⱼ), search for the minimum point C of ELEV within its DIST interval as the lowest point of the river channel; Calculate the river channel depth based on the lowest point of the river channel; If the river channel depth > the preset threshold (e.g., 1.0 m), then determine that the corresponding peak pair constitutes an effective double-dike structure.

[0039] Further, according to an embodiment of the present invention, when an effective double-dike structure is formed, shore assignment is performed, including: Taking the DIST coordinate DIST_C of the lowest point of the river channel as the boundary: Assign the peak corresponding to the DIST < DIST_C of the peak in the peak pair to the right bank dike top; Assign the peak corresponding to the DIST > DIST_C of the peak in the peak pair to the left bank dike top.

[0040] Further, according to an embodiment of the present invention, when an effective double-dike structure is not formed, it is determined whether a single-dike structure or a dike-free structure is formed based on the highest peak among the candidate peaks, including: If there is no effective double-dike structure, then select the highest peak and determine whether the highest peak is greater than the preset threshold. If so, determine that the selected highest peak constitutes a single-dike structure; If there is no highest peak exceeding the preset threshold or the river channel depth is less than the preset threshold, then mark the corresponding river channel cross-section as a dike-free section or an invalid section.

[0041] Further, according to an embodiment of the present invention, it further includes: When the highest peak constitutes a single-dike structure, determine the belonging shore of the single-dike structure based on the coordinate DIST_C. At this time, the sub-highest peak can be used to complete the other shore.

[0042] Further, according to an embodiment of the present invention, output the dike feature recognition result, including: Cross-section number (such as PCCS0); Left bank dike top position DIST_L and elevation ELEV_L; Right bank dike top position DIST_R and elevation ELEV_R; River channel lowest point position DIST_C and elevation ELEV_C; Recognition status (effective double-dike / single-dike / dike-free).

[0043] According to the above-mentioned scheme of the present invention, the present invention proposes a three-in-one levee feature recognition framework of "shape-semantic guidance + adaptive peak detection + multi-level fault tolerance verification", the core of which includes: 1. Constructing a one-dimensional topographic profile curve: arranging the elevations (ELEV) in ascending order of distance from the starting point (DIST); 2. Dynamic peak detection: adaptively setting the prominence threshold based on the elevation standard deviation; 3. Topographic semantic rule verification: only when there is a significant low-lying river channel area between two candidate peaks is it recognized as a valid double levee structure; 4. Intelligent allocation of left and right banks: automatically determining the left / right bank levee crests based on the relationship between the distances from the starting points; 5. Multi-level fault tolerance mechanism: activating a graded processing strategy for abnormal situations such as no peak, single peak, and multiple peaks; 6. Outputting a structured feature set: including the left / right bank levee crest elevation, riverbed elevation, cross-section type identifier, etc.

[0044] This invention overcomes the limitations of traditional pure mathematical extreme value detection by introducing prior knowledge of "double levees sandwiching a riverbed" topography. It uses a riverbed depth threshold (e.g., >1.0m) for physical plausibility verification, significantly improving recognition accuracy. A combination of sliding window and minimum spacing / elevation difference constraints effectively suppresses noise interference, preventing misidentification of shrubs and mounds as levee tops. Using the lowest point of the riverbed as a natural boundary, it clearly defines the physical meaning of the left and right bank levees without relying on external water flow direction data. It supports various river scenarios, including double levees, single levees, and no levees, exhibiting strong robustness and suitability for complex real-world conditions.

[0045] Furthermore, to achieve the above objectives, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the dike feature recognition method based on cross-sectional elevation data as described above.

[0046] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the dike feature recognition method based on cross-sectional elevation data as described above.

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely one preferred embodiment of the invention and are only used to explain the invention. They do not limit the scope of protection of the invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0048] Example 1 Taking the PCCS0 section of a certain flood channel as an example, the PCCS0 section data is shown in Table 1 below, and the PCCS0 section diagram is shown below. Figure 2As shown.

[0049] Table 1. Data of PCCS0 section of a certain floodway Based on the PCCS0 section data in Table 1, the following features were identified for the dike: (1) Input data points: 54 (as shown in Table 1, DIST range: -75~816m); (2) The algorithm identified two significant peaks: DIST=-3 (ELEV=59.6) and DIST=750 (ELEV=60.2); (3) Lowest point of the middle channel: ELEV=49.4 (located at DIST=513); (4) If the river channel depth is >1.0m, it is determined to be an effective double levee; (5) Output: Right bank top elevation = 59.6m, left bank top elevation = 60.2m.

[0050] Those skilled in the art will recognize that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0051] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method implementation, and will not be repeated here.

[0052] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0053] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0054] In addition, the functional modules in the embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0055] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the sending / receiving methods of various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0056] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.

[0057] It should be understood that the sequence number of each step in the invention and its embodiments does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A method of identifying embankment features based on cross- sectional elevation data, characterized by, The method comprises the following steps: obtaining river cross-section data, and preprocessing the river cross-section data; identifying candidate peak values in the preprocessed river cross-section data as candidate points of embankment tops and outputting a candidate peak value list; checking whether the embankment features constitute an effective double-embankment structure based on the candidate peak values; when the effective double-embankment structure is constituted, performing attribution bank allocation; when the effective double-embankment structure is not constituted, judging whether a single-embankment structure or a no-embankment structure is constituted according to the highest peak value in the candidate peak values; outputting an embankment feature recognition result.

2. The method of identifying levee features based on cross- sectional elevation data of claim 1, wherein, The method comprises the following steps of obtaining river cross-section data and preprocessing the river cross-section data: obtaining cross-section data of one or more rivers, each cross-section data being composed of a plurality of point pairs of DIST and ELEV, wherein DIST represents the distance along the cross-section, and ELEV represents the corresponding elevation; performing preprocessing on each cross-section data, which comprises the following steps: de-duplication processing: removing duplicate points with the same DIST; sorting: arranging in ascending order of DIST; optional interpolation: if the distance between adjacent points is greater than a threshold, linear or spline interpolation is used to supplement the intermediate points.

3. The method of claim 2, wherein, The method comprises the following steps of identifying candidate peak values in the preprocessed river cross-section data as candidate points of embankment tops and outputting a candidate peak value list: using a sliding window combined with a local maximum value determination strategy to identify all candidate peak values in the preprocessed river cross-section data, which comprises the following steps: the window size is adaptively adjusted according to the density of the river cross-section data; when a data point is determined as a candidate peak value, it satisfies the following conditions: the ELEV value of the data point is greater than the ELEV values of all data points in the left and right neighborhoods in the window, the distance between the data point and the adjacent peak value is greater than or equal to 20 m, and the relative height difference is greater than or equal to 0.5 m; outputting the candidate peak value list.

4. The method of claim 3, wherein, The method comprises the following steps of checking whether the embankment features constitute an effective double-embankment structure based on the candidate peak values: if the number of candidate peak values is greater than or equal to 2, then all peak value pairs formed by adjacent candidate peak values are traversed; for each peak value pair, searching for a minimum ELEV point C in the DIST interval of the peak value pair as a river channel lowest point; calculating the river channel depth based on the river channel lowest point; if the river channel depth is greater than a preset threshold, then it is determined that the corresponding peak value pair constitutes an effective double-embankment structure.

5. The method of claim 4, wherein, The method comprises the following steps of performing attribution bank allocation when the effective double-embankment structure is constituted: taking the DIST coordinate DIST_C of the river channel lowest point as a boundary: assigning the corresponding peak value of the peak value pair with a DIST less than DIST_C as a right bank embankment top; assigning the corresponding peak value of the peak value pair with a DIST greater than DIST_C as a left bank embankment top.

6. The method of identifying levee features based on cross-sectional elevation data according to any one of claims 1-5, wherein, The method comprises the following steps of judging whether a single-embankment structure or a no-embankment structure is constituted according to the highest peak value in the candidate peak values when the effective double-embankment structure is not constituted: if there is no effective double-embankment structure, then the highest peak value is selected, and it is judged whether the highest peak value is greater than a preset threshold, if yes, then it is determined that the selected highest peak value constitutes a single-embankment structure; if there is no highest peak value greater than the preset threshold or the river channel depth is less than the preset threshold, then the corresponding river cross-section is marked as a no-embankment section or an invalid cross-section.

7. The method of identifying embankment features from cross- sectional elevation data of claim 6, wherein, The method further comprises the following steps: when the highest peak value constitutes a single-embankment structure, determining the attribution bank of the single-embankment structure based on the coordinate DIST_C.

8. A levee feature identification system based on cross-sectional elevation data, characterized by, The method comprises the following steps: a data acquisition and preprocessing module is configured to obtain river cross-section data and preprocess the river cross-section data; a candidate peak identification output module, which identifies candidate peaks in the preprocessed river cross-section data as candidate points of the embankment crest and outputs a candidate peak list; a double-embankment structure judgment module, which checks whether the embankment features constitute an effective double-embankment structure based on the candidate peaks; an attribution bank allocation module, which performs attribution bank allocation when the effective double-embankment structure is constituted; a single-embankment or no-embankment judgment module, which judges whether a single-embankment structure or a no-embankment structure is constituted according to the highest peak in the candidate peaks when the effective double-embankment structure is not constituted; a result output module, which outputs the embankment feature recognition result.

9. An electronic device, characterized by A computer program is stored on the computer readable storage medium and is executed by the processor to implement the method for recognizing embankment features based on cross-section elevation data according to any one of claims 1-7.

10. A computer readable storage medium, characterized in that, A computer program is stored on the computer readable storage medium and is executed by the processor to implement the method for recognizing embankment features based on cross-section elevation data according to any one of claims 1-7.

Images