A noise-sensitive building concentrated area division method and device and a storage medium

Abstract

This invention discloses a method, apparatus, and storage medium for delineating concentrated areas of noise-sensitive buildings, belonging to the field of geographic information big data processing technology. The method includes: correcting the acquired original multi-source data of the target area; constructing non-overlapping basic geographic units based on the corrected geospatial data; classifying the basic geographic units by attribute to identify different types of target sensitive units; determining differentiated protection distances for different types of target sensitive units based on a preset acoustic model; generating an initial spatial range of the noise-sensitive area based on the differentiated protection distances; correcting the initial spatial range of the noise-sensitive area based on pre-acquired historical noise complaint data; performing morphological optimization processing on the corrected spatial range; and outputting the final delineation result. This invention effectively solves the management pain point of traditional static planning lagging behind the actual disturbance situation, achieving people-oriented and precise governance.

Description

Technical Field

[0001] This invention relates to a method, apparatus, and storage medium for dividing areas of noise-sensitive buildings, belonging to the fields of urban planning, environmental engineering, and geographic information big data processing technology. Background Technology

[0002] With the acceleration of urbanization, environmental noise pollution has become a major issue affecting the quality of life of residents. Accurately delineating areas is the foundation for implementing noise limit control.

[0003] Existing technologies for delineating sensitive areas have the following significant drawbacks:

[0004] The disconnect between basic data and the current situation: Existing methods often directly use historical remote sensing imagery or land use boundary maps from planning departments. However, imagery suffers from projection distortion and cannot reflect the internal functions of buildings, while planning maps often lag behind urban development (e.g., "planned green space" has actually been converted into "residential" buildings, and "office buildings" are actually "commercial and residential apartments"). The lack of vector correction based on on-site surveys results in inherent biases in the basic data sources themselves.

[0005] Lack of acoustic basis: Existing delineation methods mostly rely on experience, manually drawing circles or simple administrative divisions, lacking quantitative analysis of the propagation attenuation patterns of different types of sound sources (traffic, industry). How large should the delineation area be? Currently, there is a lack of a data-supported calculation model, resulting in delineation results that are either too small to provide effective protection or too large, increasing management costs.

[0006] Ignoring "social perception" feedback: failing to use noise complaint data to discover "hidden" areas that are not planning-sensitive but actually cause serious disturbances to residents.

[0007] Therefore, there is an urgent need for a method that can combine on-site survey correction data, acoustic attenuation laws, and social perception data to achieve scientific and precise partitioning through vectorized spatial analysis algorithms. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, device and storage medium for dividing concentrated areas of noise-sensitive buildings. By introducing a "site survey-vector correction" mechanism, the timeliness of basic data is ensured, and by combining computer spatial algorithms and complaint heat maps, a refined delineation that conforms to the standards and fits the current situation is achieved.

[0009] To achieve the above objectives, the present invention is implemented using the following technical solution:

[0010] In a first aspect, the present invention provides a method for dividing a concentrated area of ​​noise-sensitive buildings, comprising:

[0011] The original multi-source data of the target area is corrected to obtain corrected geospatial data.

[0012] Based on the corrected geospatial data, construct non-overlapping basic geographic units;

[0013] Attribute classification is performed on basic geographic units to identify different types of target sensitive units;

[0014] Differentiated protection distances are determined for different types of target sensitive units based on a pre-set acoustic model;

[0015] Based on the differentiated protection distance, the initial spatial range of the noise-sensitive area is generated;

[0016] Based on previously acquired historical noise complaint data, the initial spatial range of the noise-sensitive area is corrected to obtain the corrected spatial range;

[0017] The corrected spatial extent is then subjected to morphological optimization to output the final segmentation result.

[0018] Furthermore, the step of correcting the acquired original multi-source data of the target area to obtain corrected geospatial data includes:

[0019] Acquire raw, multi-source data, including original remote sensing imagery, original planned road network data, and original building outline vector data;

[0020] Based on the real survey data collected on-site, the original remote sensing image is geometrically corrected. Using the corrected remote sensing image as a reference, the deformed, occluded, or outdated outlines in the original building outline vector data are vectorized and redrawn and their positions are corrected. At the same time, the functional attributes of the building outline are updated according to the on-site survey records to obtain the corrected building patch.

[0021] Based on the real survey data collected from the on-site reconnaissance, the original planned road network data was geometrically corrected and the alignment was adjusted to obtain the corrected road network data.

[0022] The geometric correction includes: registering the original multi-source data using an affine transformation model based on control point residuals, wherein the affine transformation model is:

[0023] ;

[0024] Where θ is the rotation factor, S x S y Δ is the scaling factor. x Δ y This is the translation increment; , These are the x and y coordinates of the original multi-source data before correction. , These are the corrected x and y axes of the original multi-source data, respectively.

[0025] And / or, the construction of non-overlapping basic geographic units based on the corrected geospatial data includes: spatially segmenting the corrected building patches using the corrected road network data to generate the basic geographic units.

[0026] Furthermore, the method also includes: uniformly performing projection transformation on the acquired raw multi-source data to convert the geographic coordinate system into a planar projected coordinate system, so that the coordinates of the vector points are represented as plane rectangular coordinates in meters, providing a unified planar measurement benchmark for subsequent spatial analysis based on Euclidean distance.

[0027] Furthermore, the attribute classification of basic geographic units to identify different types of target sensitive units includes:

[0028] Spatially linking the basic geographic units with pre-acquired raw point-of-interest data, the spatial linking including:

[0029] The "point within polygon" judgment logic is adopted. If the coordinates of the point of interest are within the outline of the modified building patch, the functional attributes of the point of interest are assigned to the corresponding building patch. For building patches that do not directly match the point of interest, a search buffer with a set radius is established to capture the attributes of its adjacent points of interest and obtain the preliminary attribute results after association.

[0030] The preliminary attribute results after association are compared with the field survey records and manually verified to determine the attribute category of each basic geographic unit.

[0031] The attribute categories include Class I sensitive units and Class II sensitive units; Class I sensitive units refer to units mainly for residential and medical and health functions, while Class II sensitive units refer to units mainly for scientific research, education, office, and welfare functions.

[0032] Furthermore, the determination of differentiated protection distances for different types of target sensitive units based on a preset acoustic model includes:

[0033] Based on the noise propagation attenuation model of typical urban sound sources, the minimum distance required for the sound source to attenuate to meet the nighttime equivalent sound level limit of the first type of sound environment functional area is calculated, which is used as the protection distance D1 of a sensitive unit.

[0034] Based on the noise propagation attenuation model of typical urban sound sources, the minimum distance required for the sound source to attenuate to meet the daytime equivalent sound level limit of the second type of sound environment functional area is calculated, which is used as the protection distance D2 of the second type of sensitive unit.

[0035] The protection distances D1 and D2 are determined using the 85th percentile method: the probability distribution of sound source intensity within the target area is collected, the sound level covering 85% of typical high-noise periods is selected as the model input value, and the corresponding protection distance is calculated in reverse.

[0036] For a class of sensitive units, if the required distance sequence for achieving the target at different time periods is calculated using a noise propagation attenuation model as {d1, d2, ... d...}, then... n}, where n is the total number of time periods and d is the distance to meet the standard corresponding to a certain time period, then the value that satisfies the probability condition P(d≤D1)=0.85 is selected as the recommended value of D1, where P represents the probability that the distance to meet the standard d is less than or equal to the protection distance D1;

[0037] For a type II sensitive unit, if the required distance sequence for achieving the target at different time periods is calculated using a noise propagation attenuation model as {d1', d2', ..., d...}, then... m Let m be the total number of time periods and d' be the distance to meet the standard for a certain time period. Then, the value that satisfies the probability condition P'(d'≤D2) = 0.85 is selected as the recommended value of D2, where P' represents the probability that the distance to meet the standard d' is less than or equal to the protection distance D2.

[0038] Furthermore, the generation of the initial noise-sensitive area spatial range based on the differentiated protection distance includes:

[0039] Based on the Cartesian coordinates obtained by projecting and transforming the original multi-source data, spatial buffer analysis is performed on the verified Class I and Class II sensitive units, using the protection distances D1 and D2 as buffer radii respectively, to obtain the corresponding Class I and Class II buffer patches; wherein, the buffer analysis is based on Euclidean distance calculation, and the formula is:

[0040] ;

[0041] in, This represents the generated buffer area vector map. The original sensitive unit polygon, For buffer distance, Let be any point in the planar space. For point To polygon The minimum Euclidean distance to the boundary;

[0042] A vector union fusion operation is performed on the first type of buffer patch and the second type of buffer patch to eliminate the internal boundaries of the overlapping parts and form a continuous initial noise-sensitive region spatial range.

[0043] Furthermore, based on pre-acquired historical noise complaint data, the initial spatial range of the noise-sensitive area is corrected to obtain the corrected spatial range, including:

[0044] The target area is divided into statistical grids of a set area. Historical noise complaint vector data for a set month is imported. A global noise complaint heatmap is generated using a kernel density estimation algorithm. The mathematical expectation average A of the heatmap values ​​for the entire region is calculated. vg ;

[0045] Set statistical filtering criteria to automatically extract thermal values ​​that are higher than the mathematically expected average value A. vg Twice the size of the closed area was identified as a potentially sensitive patch requiring correction.

[0046] For each potentially sensitive map patch, retrieve its underlying original complaint records and substitute them into the weighting formula for numerical verification:

[0047] ;

[0048] in, This represents the comprehensive index of complaints within a map patch, where n is the total number of complaints within that map patch. Weighted by time, if the complaint occurs at night, then... The value is 1.5. If it occurs during the daytime, then... The value is 1.0; As for the weight of the nature, if it is a single person and a single complaint, then The value is 1.0. If there are repeated complaints from the same sound source more than 3 times a week, then... The value is 1.2. If it is a group complaint with more than a set number of signatures, then... The value is 2.0;

[0049] The initial spatial range was corrected based on the verification results:

[0050] If 5 ≤ If the number of points is less than 10 and the patch is located outside the initial spatial range, the outline of the building within the patch will be automatically identified, and the patch will be vector-merged with the initial spatial range to determine it as a hidden sensitive area formed due to functional changes or building occlusion.

[0051] like If the value is ≥ 10, it is determined that there is a high-intensity noise exposure risk in the area. The boundary of the initial spatial range is driven to expand adaptively along the direction of the sound source. The expansion step is based on touching the nearest urban road network centerline, and the maximum expansion distance is limited to a set distance.

[0052] Furthermore, the morphological optimization processing of the corrected spatial extent, outputting the final segmentation result, includes:

[0053] The corrected spatial range and the target area are divided into square grids of uniform area and then spatially overlaid.

[0054] If more than 50% of the area within a grid is covered by the corrected spatial range, the entire grid is considered a sensitive area; if less than 50%, it is considered a non-sensitive area.

[0055] For the meshed spatial range, calculate the area S of all independent connected regions, and set a minimum area threshold S. min If S < S min Then remove the fragmented image patch;

[0056] Inspect the spatial area enclosed within a large sensitive area; if the area of ​​the internal blank area is S... hole If the value is less than the set first threshold, then hole filling will be performed;

[0057] Calculate the distance S between the final boundary and the adjacent main traffic artery. tra If S tra If the value is less than the set second threshold, the final boundary will be snapped to the center line of the adjacent traffic artery to complete the boundary regularization and obtain the final division result.

[0058] Secondly, the present invention provides a device for dividing a concentrated area of ​​noise-sensitive buildings, used to implement the method for dividing a concentrated area of ​​noise-sensitive buildings as described in any one of the preceding claims, comprising:

[0059] The first correction module is used to correct the original multi-source data of the target area to obtain corrected geospatial data.

[0060] The building module is used to construct non-overlapping basic geographic units based on the corrected geospatial data;

[0061] The attribute classification module is used to classify the attributes of basic geographic units in order to identify different types of target sensitive units;

[0062] The determination module is used to determine differentiated protection distances for different types of target sensitive units based on a preset acoustic model;

[0063] The generation module is used to generate the initial spatial range of the noise-sensitive area based on the differentiated protection distance;

[0064] The second correction module is used to correct the initial spatial range of the noise-sensitive area based on the pre-acquired historical noise complaint data, so as to obtain the corrected spatial range.

[0065] The optimization processing module is used to perform morphological optimization processing on the corrected spatial range and output the final segmentation result.

[0066] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0067] Fourthly, the present invention provides an electronic device, comprising:

[0068] Memory, used to store computer programs / instructions;

[0069] A processor for executing the computer program / instructions to implement the steps of any of the methods described above.

[0070] Fifthly, the present invention provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0071] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0072] This invention provides a method, device, and storage medium for delineating concentrated areas of noise-sensitive buildings. It utilizes an acoustic attenuation model to scientifically derive protection distances and combines this with on-site surveys to correct basic data, ensuring the scientific quantification and objective accuracy of the delineation results. Simultaneously, it innovatively introduces a noise complaint heatmap for dynamic verification, effectively addressing the management pain point of traditional static planning lagging behind the actual disturbance situation, and achieving people-centered, precise governance. Attached Figure Description

[0073] Figure 1 This is a flowchart of a method for dividing a concentrated area of ​​noise-sensitive buildings according to an embodiment of the present invention. Detailed Implementation

[0074] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0075] like Figure 1 As shown in Example 1, this example introduces a method for dividing a concentrated area of ​​noise-sensitive buildings, including:

[0076] The original multi-source data of the target area is corrected to obtain corrected geospatial data.

[0077] Based on the corrected geospatial data, construct non-overlapping basic geographic units;

[0078] Attribute classification is performed on basic geographic units to identify different types of target sensitive units;

[0079] Differentiated protection distances are determined for different types of target sensitive units based on a pre-set acoustic model;

[0080] Based on the differentiated protection distance, the initial spatial range of the noise-sensitive area is generated;

[0081] Based on previously acquired historical noise complaint data, the initial spatial range of the noise-sensitive area is corrected to obtain the corrected spatial range;

[0082] The corrected spatial extent is then subjected to morphological optimization to output the final segmentation result.

[0083] The method for dividing concentrated areas of noise-sensitive buildings provided in this embodiment involves the following steps in its application:

[0084] Step S1: Vector correction and element construction based on site survey;

[0085] First, acquire the raw remote sensing imagery and road network data of the target area. Then, perform a projection transformation on the acquired raw remote sensing imagery and road network data. Convert the geographic coordinate system (such as WGS84 or the encrypted GCJ-02 coordinate system) to a planar projective coordinate system (such as CGCS2000 Gauss-Kruger projection), so that the coordinates of vector points are represented as Cartesian coordinates (x, y) in meters. This step ensures the linear accuracy of subsequent buffer distance calculations D1 and D2. Conduct a gridded on-site survey to verify the actual outlines and functions of buildings in the imagery. Using handheld surveying equipment or UAV data, vectorize and redraw and correct the outlines of buildings that are deformed, occluded, or outdated. Use the corrected road network as cutting lines to construct non-overlapping basic dividing units.

[0086] Considering that different data sources (such as Internet POI data and high-precision UAV imagery) may have systematic offsets (such as the deflection between GCJ-02 and WGS84), this invention uses an affine transformation model based on control point residuals for registration:

[0087]

[0088] Where θ is the rotation factor, S x S y Δ is the scaling factor. x Δ y This is the translation increment. By obtaining at least four corresponding feature control points, the transformation matrix is ​​solved using the least squares method, thereby eliminating the nonlinear deflection between heterogeneous data.

[0089] Step S2: Semantic mapping and classification verification of unit attributes;

[0090] The spatial connectivity algorithm was used to map POI data to the corrected building patches; combined with the reconnaissance records, the unit attributes were verified and defined, as follows:

[0091] (1) Automatic attribute attachment: The 'point inside polygon' judgment logic is adopted. If the POI coordinates are within the outline of the corrected building patch, the functional attributes of the POI are assigned to the corresponding building patch.

[0092] (2) Error compensation correction: For patches that do not directly match POIs, a search buffer with a radius of 5 meters is established to capture the attributes of their adjacent POIs in order to eliminate the omissions caused by data offset;

[0093] (3) Category determination: Based on the on-site survey records, the unit attributes are finally determined:

[0094] Category 1 Sensitive Units: Buildings primarily used for residential, medical, and health purposes;

[0095] Category II Sensitive Units: Buildings primarily used for scientific research, education, government and institutional offices, and social welfare functions.

[0096] Step S3: Distance threshold calculation and vector buffering based on sound source attenuation characteristics;

[0097] Propagation attenuation models for typical urban noise sources (traffic noise, industrial noise, and construction noise) were constructed. The models adopted the point source, line source, and area source prediction models from the acoustic environment guidelines.

[0098] Model calculation: Combining Cadna-A acoustic simulation or historical monitoring data, analyze the physical distance required for various sound sources to attenuate to the Class I limit (50dB at night) and the Class II limit (60dB during the day).

[0099] Threshold Determination: Based on the measurement results and considering the fluctuation of urban sound source intensity, the 85th percentile method is used to determine the protection distance. Specifically, the probability distribution of sound source intensity within the target area is collected, and the sound level covering 85% of typical high-noise periods is selected as the model input value to calculate the corresponding protection distance. If the calculated sequence of required compliance distances for a class of sensitive units at different time periods is {d1, d2, ... d...}, then... n Let n be the total number of time periods, and d be the acceptable distance for a certain time period. Then, a value satisfying P(d≤D1) = 0.85 is selected as the recommendation, where P represents the probability that the acceptable distance d is less than or equal to the protection distance D1. The protection buffer distance for Class I sensitive units is determined to be D1 (recommended value 300 meters), and the protection buffer distance for Class II sensitive units is determined to be D2 (recommended value 200 meters).

[0100] Vector Buffer: Based on the determined D1 and D2, perform differentiated vector buffering and fusion operations on each sensitive unit to generate an initial concentrated region.

[0101] ;

[0102]

[0103] S: Represents the original sensitive unit polygon (building outline);

[0104] D: Represents the buffer distance (i.e., D1 or D2 calculated in step S3);

[0105] p: represents any point in a planar space;

[0106] This represents the minimum Euclidean distance from point p to the boundary of polygon S.

[0107] Step S4: Vectorization correction based on complaint heatmap;

[0108] (1) Spatial gridding and thermal field construction:

[0109] The target area was divided into a 50m × 50m statistical grid, and noise complaint vector data from the past 12 months was imported. A global noise complaint heatmap was generated using a kernel density estimation algorithm, and the expected value (average value) A of the heatmap for the entire region was calculated. vg .

[0110] (2) Automatic identification of potential sensitive patches:

[0111] Set statistical filtering criteria to automatically extract calorific values ​​that are more than twice the mean (i.e., Density > 2 × A). vg The closed region of the map is identified as a "potentially sensitive patch to be corrected". This mechanism is used to automatically lock areas with abnormally high complaint values ​​on a large scale, eliminating interference from low-frequency random complaints.

[0112] (3) Weight determination and verification: For each potential sensitive patch, retrieve its underlying original complaint records and substitute them into the formula for numerical verification.

[0113] ;

[0114] in, This represents the comprehensive index of complaints within a map patch, where n is the total number of complaints within the map patch. The weighting parameters are defined as follows:

[0115] Time weight If the complaint occurs at night (22:00-06:00), The value is 1.5; if it occurs during the daytime (06:00-22:00), The value is 1.0.

[0116] Property weight If it is a single complaint by a single person, The value is 1.0; if it is a repeated complaint from the same sound source (more than 3 times a week), The value is 1.2; if it is a group complaint signed by 10 or more people, The value is 2.0.

[0117] (4) Weight determination and verification:

[0118] If 5≤I c If the value is less than 10 and the patch is located outside the initial concentration area, the system automatically identifies the building outline within the patch and performs a vector merging operation, determining it as a "hidden sensitive area formed due to functional changes or building occlusion".

[0119] If I c A value ≥10 indicates a high-intensity noise exposure risk in the area. The initial concentration area boundary is adaptively expanded along the direction of the sound source, with the expansion step size determined by reaching the nearest urban road network centerline, and the maximum expansion distance limited to within 100 meters.

[0120] Step S5: Boundary optimization based on mesh aggregation and area threshold;

[0121] Perform hole filling, debris removal (area <0.1km²) and road network adsorption, and output the final results.

[0122] (1) Spatial gridding processing

[0123] Procedure: Divide the target area into a uniform square grid (small squares of 20m×20m).

[0124] Rule: Determine whether each small square is covered by the initial area generated in steps S3 and S4. If more than 50% of the area of ​​a grid is covered, the entire grid is determined to be a "sensitive area"; if less than 50%, it is determined to be a "non-sensitive area".

[0125] (2) Automatic removal of fragmented patches

[0126] Procedure: Calculate the area S of all independent connected regions.

[0127] Judgment rule: Set a minimum area threshold S. min =0.01km 2 If S < S min If so, then delete the image patch.

[0128] (3) The internal holes close automatically.

[0129] Procedure: Inspect the enclosed space within a large sensitive area.

[0130] Judgment rule: If the area S of the internal blank region is... hole <1000m 2 If so, then fill will be performed.

[0131] (4) Forced alignment of road network

[0132] Procedure: Calculate the distance S between the final boundary and the adjacent main traffic artery. tra .

[0133] Judgment rule: If S tra If the distance is less than 20m, the final boundary will be directly located at the center line of the adjacent main road.

[0134] This embodiment has the following beneficial effects:

[0135] Scientific Quantification, Based on Evidence: This embodiment does not blindly follow fixed standards, but rather deduces the distance based on acoustic attenuation characteristics. The model proves the scientific validity of "300 meters" and "200 meters," ensuring that the delineation results meet both environmental protection requirements and conform to physical laws.

[0136] Data authenticity: "On-site survey - vector correction" ensures that all calculations are based on the actual urban conditions.

[0137] Dynamic closed loop: The complaint heatmap correction mechanism effectively compensates for occasional or complex social noise problems that are difficult to cover by acoustic models.

[0138] The following description, in conjunction with a preferred embodiment, illustrates the content involved in the above embodiments.

[0139] This embodiment selects a city center area as the object.

[0140] Step 1: Parameter calculation (determining the origin of 300m / 200m); Before delineation, the technical team first selected typical urban main roads (such as Zhongshan East Road) and the vicinity of industrial enterprises in the area to conduct noise attenuation tests.

[0141] Monitoring and Simulation: Using Cadna-A software for modeling and prediction, combined with field monitoring data, it was found that nighttime traffic noise (source strength of about 75dB) needs to travel about 280-300 meters in open areas to attenuate to 50dB (nighttime limit for Class I areas); while daytime noise needs to travel about 180-200 meters to attenuate to 60dB (daytime limit for Class II areas).

[0142] Parameter settings: Based on this analysis, the system sets the buffer distance for Class I sensitive units in this area to D1 = 30m and the buffer distance for Class II sensitive units to D2 = 200m.

[0143] Step 2: Site survey and vector correction; Technicians verified on-site and found that an "abandoned factory" in the image had been converted into a "creative office park" (Category II sensitive). The attributes and outline of the land parcel were corrected in the system.

[0144] Step 3: Vector Buffering and Initial Delineation; The system calls the parameters determined in Step 1 to perform a 200-meter outward buffer for the "Creative Office Park" and a 300-meter outward buffer for the surrounding "Residential Area". Through Union operations, a contiguous initial protected area is formed.

[0145] Step 4: Heatmap Correction; Complaint data was imported, revealing a highlighted complaint hotspot outside the buffer boundary. This was found to be a "private kindergarten" not included in the POI data. Based on the heatmap indication, the system added this area to the centralized data set.

[0146] Step 5: Boundary Output; Remove fragments smaller than 0.1 km² and snap the boundary to the nearest road to generate the final map.

[0147] In a further embodiment, the parameter adaptive adjustment is defined as follows:

[0148] This embodiment selects a mountainous urban area with complex terrain.

[0149] Step 1: Parameter Calculation;

[0150] Due to the undulating terrain and the barrier effect of buildings in this area, Cadna-A simulations show that noise attenuation is rapid. Calculations indicate that only 220 meters is needed to meet the standards for Class I areas.

[0151] Parameter Adjustment: The system flexibly adjusts parameters, setting D1 = 220m. This demonstrates the advantage of this invention based on characteristic inference, rather than rigidly applying data.

[0152] Steps 2 to 5: Same as above, perform reconnaissance correction, buffering, heatmap correction and regularization output.

[0153] Example 2: This example provides a device for dividing a concentrated area of ​​noise-sensitive buildings, including:

[0154] The first correction module is used to correct the original multi-source data of the target area to obtain corrected geospatial data.

[0155] The building module is used to construct non-overlapping basic geographic units based on the corrected geospatial data;

[0156] The attribute classification module is used to classify the attributes of basic geographic units in order to identify different types of target sensitive units;

[0157] The determination module is used to determine differentiated protection distances for different types of target sensitive units based on a preset acoustic model;

[0158] The generation module is used to generate the initial spatial range of the noise-sensitive area based on the differentiated protection distance;

[0159] The second correction module is used to correct the initial spatial range of the noise-sensitive area based on the pre-acquired historical noise complaint data, so as to obtain the corrected spatial range.

[0160] The optimization processing module is used to perform morphological optimization processing on the corrected spatial range and output the final segmentation result.

[0161] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0162] Example 3: This example provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in Example 1.

[0163] Example 4: This example provides an electronic device, including:

[0164] Memory, used to store computer programs / instructions;

[0165] A processor for executing the computer program / instructions to implement the steps of any of the methods described in Embodiment 1.

[0166] Example 5: This example provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in any one of Examples 1.

[0167] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0168] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0169] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0170] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0171] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure and not to limit its protection scope. Although this disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this disclosure, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims.

Claims

1. A method for delineating concentrated areas of noise-sensitive buildings, characterized in that, include: The original multi-source data of the target area are corrected to obtain corrected geospatial data. Based on the corrected geospatial data, construct non-overlapping basic geographic units; Attribute classification is performed on basic geographic units to identify different types of target sensitive units; Differentiated protection distances are determined for different types of target sensitive units based on a pre-set acoustic model; Based on the differentiated protection distance, the initial spatial range of the noise-sensitive area is generated; Based on previously acquired historical noise complaint data, the initial spatial range of the noise-sensitive area is corrected to obtain the corrected spatial range; The corrected spatial extent is then subjected to morphological optimization to output the final segmentation result.

2. The method for dividing concentrated areas of noise-sensitive buildings according to claim 1, characterized in that, The step of correcting the acquired original multi-source data of the target area to obtain corrected geospatial data includes: Acquire raw, multi-source data, including original remote sensing imagery, original planned road network data, and original building outline vector data; Based on the real survey data collected on-site, the original remote sensing image is geometrically corrected. Using the corrected remote sensing image as a reference, the deformed, occluded, or outdated outlines in the original building outline vector data are vectorized and redrawn and their positions are corrected. At the same time, the functional attributes of the building outline are updated according to the on-site survey records to obtain the corrected building patch. Based on the real survey data collected from the on-site reconnaissance, the original planned road network data was geometrically corrected and the alignment was adjusted to obtain the corrected road network data. The geometric correction includes: registering the original multi-source data using an affine transformation model based on control point residuals, wherein the affine transformation model is: ； Where θ is the rotation factor, S x S y Δ is the scaling factor. x Δ y This is the translation increment; , These are the x and y coordinates of the original multi-source data before correction. , These are the corrected x and y axes of the original multi-source data, respectively. And / or, the construction of non-overlapping basic geographic units based on the corrected geospatial data includes: spatially segmenting the corrected building patches using the corrected road network data to generate the basic geographic units.

3. The method for dividing concentrated areas of noise-sensitive buildings according to claim 2, characterized in that, The method further includes: uniformly projecting the acquired raw multi-source data to convert the geographic coordinate system into a planar projected coordinate system, so that the coordinates of the vector points are represented as plane rectangular coordinates in meters, providing a unified planar measurement benchmark for subsequent spatial analysis based on Euclidean distance.

4. The method for dividing concentrated areas of noise-sensitive buildings according to claim 3, characterized in that, The attribute classification of basic geographic units to identify different types of target sensitive units includes: Spatially linking the basic geographic units with pre-acquired raw point-of-interest data, the spatial linking including: The "point within polygon" judgment logic is adopted. If the coordinates of the point of interest are within the outline of the modified building patch, the functional attributes of the point of interest are assigned to the corresponding building patch. For building patches that do not directly match the point of interest, a search buffer with a set radius is established to capture the attributes of its adjacent points of interest and obtain the preliminary attribute results after association. The preliminary attribute results after association are compared with the field survey records and manually verified to determine the attribute category of each basic geographic unit. The attribute categories include Class I sensitive units and Class II sensitive units; Class I sensitive units refer to units mainly for residential and medical and health functions, while Class II sensitive units refer to units mainly for scientific research, education, office, and welfare functions.

5. The method for dividing noise-sensitive building concentrated areas according to claim 4, characterized in that, The method for determining differentiated protection distances for different types of target sensitive units based on a preset acoustic model includes: Based on the noise propagation attenuation model of typical urban sound sources, the minimum distance required for the sound source to attenuate to meet the nighttime equivalent sound level limit of the first type of sound environment functional area is calculated, which is used as the protection distance D1 of a sensitive unit. Based on the noise propagation attenuation model of typical urban sound sources, the minimum distance required for the sound source to attenuate to meet the daytime equivalent sound level limit of the second type of sound environment functional area is calculated, which is used as the protection distance D2 of the second type of sensitive unit. The protection distances D1 and D2 are determined using the 85th percentile method: the probability distribution of sound source intensity in the target area is collected, the sound level covering 85% of typical high-noise periods is selected as the model input value, and the corresponding protection distance is calculated in reverse. For a class of sensitive units, if the required distance sequence for achieving the target at different time periods is calculated using a noise propagation attenuation model as {d1, d2, ... d...}, then... n }, where n is the total number of time periods and d is the distance to meet the standard corresponding to a certain time period, then the value that satisfies the probability condition P(d≤D1)=0.85 is selected as the recommended value of D1, where P represents the probability that the distance to meet the standard d is less than or equal to the protection distance D1; For a type II sensitive unit, if the required distance sequence for achieving the target at different time periods is calculated using a noise propagation attenuation model as {d1', d2', ..., d...}, then... m Let m be the total number of time periods and d' be the distance to meet the standard for a certain time period. Then, the value that satisfies the probability condition P'(d'≤D2) = 0.85 is selected as the recommended value of D2, where P' represents the probability that the distance to meet the standard d' is less than or equal to the protection distance D2.

6. The method for dividing concentrated areas of noise-sensitive buildings according to claim 5, characterized in that, The initial noise-sensitive area spatial range, generated based on differentiated protection distances, includes: Based on the Cartesian coordinates obtained by projecting and transforming the original multi-source data, spatial buffer analysis is performed on the verified Class I and Class II sensitive units, using the protection distances D1 and D2 as buffer radii respectively, to obtain the corresponding Class I and Class II buffer patches; wherein, the buffer analysis is based on Euclidean distance calculation, and the formula is: ； in, This represents the generated buffer area vector map. For the original sensitive unit polygon, For buffer distance, Let be any point in the planar space. For point To polygon The minimum Euclidean distance to the boundary; A vector union fusion operation is performed on the first type of buffer patch and the second type of buffer patch to eliminate the internal boundaries of the overlapping parts and form a continuous initial noise-sensitive region spatial range.

7. The method for dividing a concentrated area of ​​noise-sensitive buildings according to claim 1, characterized in that, The initial spatial range of the noise-sensitive area is corrected based on pre-acquired historical noise complaint data to obtain a corrected spatial range, including: The target area is divided into statistical grids of a set area. Historical noise complaint vector data for a set month is imported. A global noise complaint heatmap is generated using a kernel density estimation algorithm. The mathematical expectation average A of the heatmap values ​​for the entire region is calculated. vg ; Set statistical filtering criteria to automatically extract thermal values ​​that are higher than the mathematically expected average value A. vg Twice the size of the closed area was identified as a potentially sensitive patch requiring correction. For each potentially sensitive map patch, retrieve its underlying original complaint records and substitute them into the weighting formula for numerical verification: ； in, This represents the comprehensive complaint index for a map patch, where n is the total number of complaints within that map patch. Weighted by time, if the complaint occurs at night, then... The value is 1.

5. If it occurs during the daytime, then... The value is 1.0; As for the nature of the complaint, if it is a single person and a single complaint, then... The value is 1.

0. If there are repeated complaints from the same sound source more than 3 times a week, then... The value is 1.

2. If it is a group complaint with more than a set number of signatures, then... The value is 2.0; The initial spatial range was corrected based on the verification results: If 5 ≤ If the number of points is less than 10 and the patch is located outside the initial spatial range, the outline of the building within the patch will be automatically identified and vector-merged with the initial spatial range to determine it as a hidden sensitive area formed due to functional changes or building occlusion. like If the value is ≥ 10, it is determined that there is a high-intensity noise exposure risk in the area. The boundary of the initial spatial range is driven to expand adaptively along the direction of the sound source. The expansion step is based on touching the nearest urban road network centerline, and the maximum expansion distance is limited to a set distance.

8. The method for dividing a concentrated area of ​​noise-sensitive buildings according to claim 1, characterized in that, The morphological optimization process performed on the corrected spatial extent, outputting the final segmentation result, includes: The corrected spatial range and the target area are divided into square grids of uniform area and then spatially overlaid. If more than 50% of the area within a grid is covered by the corrected spatial range, the entire grid is considered a sensitive area; if less than 50%, it is considered a non-sensitive area. For the meshed spatial range, calculate the area S of all independent connected regions, and set a minimum area threshold S. min If S < S min Then remove the fragmented image patch; Inspect the spatial area enclosed within a large sensitive area; if the area of ​​the internal blank area is S... hole If the value is less than the set first threshold, then hole filling will be performed; Calculate the distance S between the final boundary and the adjacent main traffic artery. tra If S tra If the value is less than the set second threshold, the final boundary will be snapped to the center line of the adjacent traffic artery to complete the boundary regularization and obtain the final division result.

9. A device for dividing a concentrated area of ​​noise-sensitive buildings, used to implement the method for dividing a concentrated area of ​​noise-sensitive buildings as described in any one of claims 1-8, characterized in that, include: The first correction module is used to correct the original multi-source data of the target area to obtain corrected geospatial data. The building module is used to construct non-overlapping basic geographic units based on the corrected geospatial data; The attribute classification module is used to classify the attributes of basic geographic units in order to identify different types of target sensitive units; The determination module is used to determine differentiated protection distances for different types of target sensitive units based on a preset acoustic model; The generation module is used to generate the initial spatial range of the noise-sensitive area based on the differentiated protection distance; The second correction module is used to correct the initial spatial range of the noise-sensitive area based on the pre-acquired historical noise complaint data, so as to obtain the corrected spatial range. The optimization processing module is used to perform morphological optimization processing on the corrected spatial range and output the final segmentation result.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program implements the steps of the method according to any one of claims 1-8.

Images