Self-adaptive threshold optimization method and system for wild city junction region division

Abstract

The invention belongs to the cross field of remote sensing image processing and disaster risk management, and provides a self-adaptive threshold value optimization method and system for district division of a wild city junction domain, and the technical scheme is that the building density is calculated according to a building segmentation result; respectively calculating vegetation coverage and field plaque area and distance measurement; determining a WUI judgment rule, and determining the type of the WUI in combination with the judgment rule; setting threshold ranges of building density, vegetation coverage, field patch area and buffer area distance measurement, and calculating WUI areas of different types of WUIs under different thresholds; a fire exposure index is defined in combination with historical burned area data and a WUI area, a WUI area spatial distribution feature serves as an independent variable of an RF model, the fire exposure indexes under different threshold values serve as dependent variables of the RF model, and an optimal threshold value is obtained through fitting; the technical bottlenecks of low element extraction precision, single quantitative standard, high threshold setting subjectivity and the like in traditional WUI recognition are effectively solved.

Description

Technical Field

[0001] The present invention belongs to the intersection field of remote sensing image processing and disaster risk management, and in particular relates to an adaptive threshold optimization method and system for wild-city boundary area demarcation. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The Wildland-Urban Interface (WUI) is a transition zone between natural ecosystems and human urbanization, and has important ecological sensitivity. Due to the close contact or mixing of natural vegetation and human activity land, this area has become a high-incidence area for forest fires, posing a serious threat to the safety of residents. At the same time, the WUI and its surrounding areas are rich in natural resources, cultural resources, and high-value ecological and environmental assets. With climate change and frequent forest fires, these resources and assets are facing increasingly severe threats to survival.

[0004] The wild-urban junction area in the urban-rural fringe area has shown a significant expansion trend. On the one hand, the rapid expansion of urban space has led to close contact or mixing of high-frequency land use such as communities, enterprises, and facilities with vegetation such as forests, grasslands, and shrubs, forming a mosaic landscape structure; on the other hand, the continuous implementation of greening projects and ecological protection projects has effectively improved the vegetation coverage level in the city and surrounding areas, providing the necessary ecological support for the expansion of the wild-urban junction area. This development trend has led to significant distribution characteristics in the wild-urban junction area: high building density, large area of ​​combustible vegetation coverage, small area of ​​natural vegetation patches and scattered distribution. These characteristics have caused the frequent forest fires in the region to show obvious regional aggregation characteristics and dynamic change trends.

[0005] At present, the existing technology has established a relatively complete set of wild-urban boundary demarcation standards and fire risk assessment methods, and has established a demarcation system based on regional division (WUI-Z) and point division (WUI-P) respectively; however, it has not taken into account the particularities of the natural and cultural landscapes in different regions, resulting in significant differences in the distribution pattern and dynamic changes of WUI. Summary of the invention

[0006] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides an adaptive threshold optimization method and system for wild-city boundary zoning, which takes into account the actual characteristics of different regions and innovatively constructs a technical framework integrating "high-precision extraction of elements-multidimensional indicator quantification-dynamic threshold optimization", effectively solving the technical bottlenecks of low element extraction accuracy, single quantification standard, and strong subjectivity in threshold setting in traditional WUI identification.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: The first aspect of the present invention provides an adaptive threshold optimization method for wild city junction area demarcation, comprising the following steps: Segment the image of the target area to obtain the building segmentation result; Calculate building density based on building segmentation results; Based on the obtained vegetation dataset, the wildland vegetation types were screened, and the vegetation coverage and wildland patch area and distance measurements were calculated respectively; Determine the WUI determination rules, and determine the type of WUI by combining building density, vegetation coverage, wild patch area, buffer zone distance measurement and determination rules; The threshold ranges of building density, vegetation coverage, wildland patch area and buffer distance measurement were set, and the WUI areas of different types of WUI under different thresholds were calculated; The fire exposure index was defined by combining historical burn site data and the WUI region. The spatial distribution characteristics of the WUI region were used as the independent variable of the RF model, and the fire exposure index under different thresholds was used as the dependent variable of the RF model to obtain the optimal threshold.

[0008] Furthermore, the segmenting of the image of the target area to obtain a building segmentation result includes: Pre-train the ResNet-50 backbone network based on the source domain dataset to obtain universal image features; Transfer the learned general image features to the target domain task; The ResNet-50 backbone network is connected to the corresponding layer of the U-Net decoder through cross-stage feature connection, and the dynamic weighted fusion of multi-scale features is realized through the spatial attention mechanism. The building segmentation result is obtained based on the fused features.

[0009] Furthermore, the calculating of building density according to the building segmentation result includes: Convert the building raster data corresponding to the building segmentation result into vector surface data; Generate spatial point features representing buildings based on vector surface data; Based on the spatial point features, spatial density calculation is performed, a buffer zone is constructed with each building point as the center, and the building distribution density around each analysis point is counted.

[0010] Furthermore, the method of screening wildland vegetation types based on the obtained vegetation data set and calculating vegetation coverage and wildland patch area and distance measurement respectively includes: The moving window statistical method is used to count the number of wild vegetation pixels in the moving window pixel by pixel, and the wild vegetation pixel number / the total number of pixels in the buffer zone are divided to obtain the regional wild vegetation coverage; The selected wildland grid data is converted into vector surface data through GDAL, the areas of each vector patch are calculated, and the wildland patches with areas larger than the set area are selected to obtain the wildland patch areas. Generate n -level concentric ring buffers along the boundaries of the wildland patches, and obtain the distance measure according to the buffer distance and the level threshold.

[0011] Furthermore, the threshold ranges of building density, vegetation coverage, wildland patch area, and buffer distance measure include: For building density, the threshold range is set from 1 per square kilometer to the maximum building density, with a step size of 5 per square kilometer; For vegetation coverage, the threshold range is set from 0% to 100%, with a gradient step size of 1%; For wildland patch area, the threshold range is set from 0.1 square kilometer to the maximum patch area, with a step size of 0.1 square kilometer; For buffer distance measure, the threshold range is from 0.1 kilometer to 5.0 kilometers, with a step size of 0.1 kilometer.

[0012] Furthermore, calculate the WUI areas of different types of WUIs under different thresholds, including: The calculation process of the WUI area of the mixed-type WUI under different thresholds includes: Generate candidate areas based on the building density threshold, extract all connected areas with building density ≥ x per square kilometer, and then, overlay the vegetation coverage threshold, and extract sub-areas with vegetation coverage ≥ y% within the candidate areas; The calculation process of the WUI area of the mixed-type WUI under different thresholds includes: First, candidate areas sharing the building density threshold with the mixed-type -WUI, then, reverse the vegetation coverage constraint, extract sub-areas with vegetation coverage < y% within the candidate areas, and in the third step, conduct wildland patch spatial association analysis, screen wildland patches with an area ≥ m square kilometers, and generate a strip buffer with a width of n kilometers based on the wildland patch boundaries, and retain the candidate areas of the interface-type WUI that intersect with the buffer.

[0013] Furthermore, the fire exposure index WEI is expressed as: 。

[0014] The second aspect of the present invention provides an adaptive threshold optimization system for wild-urban boundary zoning, including: A segmentation module, which is used to segment the image of the target area to obtain the building segmentation result; The parameter calculation module is used to calculate the building density according to the building segmentation results; screen the wild vegetation types based on the obtained vegetation data set, and calculate the vegetation coverage and wild patch area and distance measurement respectively; The WUI type determination module is used to determine the WUI determination rules, and the type of WUI is determined by combining the building density, vegetation coverage, wild patch area, buffer zone distance measurement and determination rules; The WUI area determination module is used to set the threshold range of building density, vegetation coverage, wild patch area and buffer distance measurement, and calculate the WUI area of ​​different types of WUI under different thresholds; The threshold adaptive optimization module is used to define the fire exposure index by combining historical burn site data and the WUI area. The spatial distribution characteristics of the WUI area are used as the independent variable of the RF model, and the fire exposure index under different thresholds is used as the dependent variable of the RF model to obtain the optimal threshold by fitting.

[0015] A third aspect of the present invention provides a computer-readable storage medium.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned adaptive threshold optimization method for wild-city junction area demarcation.

[0017] A fourth aspect of the present invention provides a computer device.

[0018] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the adaptive threshold optimization method for wild-city junction area demarcation as described above are implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention utilizes deep learning and machine learning technologies to extract WUI elements with high precision (qualitative) and to adaptively quantify WUI judgment elements (quantitative). Thus, a technical framework integrating "high-precision extraction of elements-quantification of multi-dimensional indicators-dynamic threshold optimization" is innovatively constructed, which effectively solves the technical bottlenecks of low element extraction precision, single quantification standard, and strong subjectivity in threshold setting in traditional WUI identification. The present invention is based on the semantic segmentation method of high-resolution remote sensing image buildings based on transfer learning and improved U-Net. By constructing a cross-stage feature fusion architecture and spatial attention mechanism, the building recognition accuracy in complex urban scenes is significantly improved. The pre-training strategy of the ResNet-50 backbone network on the ImageNet dataset, combined with the parameter freezing mechanism in the transfer learning technology, enables the model to effectively extract general image features while avoiding overfitting problems. The improved dynamic weighted fusion formula reduces the positioning error of the building edge through the spatial attention guidance of multi-scale features. At the same time, in the small sample training scenario, the composite data enhancement strategy of random rotation, elastic deformation and adversarial generation samples is integrated to improve the generalization ability of the model, greatly reduce the annotation cost of training, and provide feasibility support for large-scale regional WUI element extraction. 3. The hybrid and interface WUI influencing factor quantification method based on the WUI-P model of the present invention solves the applicability defects of the traditional static threshold method in complex terrain areas by constructing a dynamic calculation system that is adaptive to spatial heterogeneity. The introduction of the initial buffer zone and the dynamic radius contraction mechanism for the calculation of building density effectively overcomes the sensitivity of the fixed window method to uneven spatial distribution. The calculation of vegetation coverage combined with existing data sets greatly reduces the amount of calculated data and reduces the dependence on remote sensing data. The composite constraints (area threshold, shape index, spatial distribution) integrated in the wild patch screening link lay an accurate data foundation for subsequent fire risk modeling. The intelligent construction strategy of the multi-level buffer zone uses a circular gradient division mechanism to make the spatiotemporal consistency of the fire risk spread simulation better match the local fire risk situation than the traditional buffer zone.

[0020] 4. The technical solution of the present invention is based on the WUI threshold dynamic optimization method of random forest. By constructing a multi-dimensional parameter space and an intelligent decision-making system, it breaks through the subjective limitations of traditional threshold setting that relies on human experience. By defining a spatiotemporal weighted fire exposure index (WEI), integrating the spatial alignment and resolution matching mechanism of long-term historical burn site data, the spatial distribution characteristics of fire risks are innovatively dynamically associated with threshold parameters. In the threshold decision link, by analyzing the partial dependence curve, the geographic spatial rationality and practical operability of the threshold scheme are significantly improved. It overcomes the timeliness lag problem of traditional static threshold schemes in different geographical scenarios.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] Figure 1 It is a flow chart of an adaptive threshold optimization method for wild city junction area demarcation provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of a building semantic segmentation and recognition model based on transfer learning and U-Net network provided by an embodiment of the present invention; Figure 3 Schematic diagram of the improved U-Net network structure provided by an embodiment of the present invention; Figure 4 The present invention provides a schematic diagram of an existing standard WUI determination process based on a WUI-P model. DETAILED DESCRIPTION

[0024] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0025] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0026] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0027] At present, the existing technology has established a relatively complete set of standards for demarcation of wildland-urban interface and fire risk assessment methods. For example, WUI is divided into mixed-WUI (building density ≥6.17 / km², combustible vegetation ≥50%) and interface-WUI (building density ≥6.17 / km², combustible vegetation <50%, wildland patch area ≥5km², distance measurement ≤2.4km) two types of division methods, and the demarcation system based on regional division (WUI-Z) and point division (WUI-P) is established respectively. However, it does not take into account the particularity of natural-human landscapes in different regions, resulting in significant differences in the distribution pattern and dynamic changes of WUI.

[0028] The present invention combines the actual characteristics of the area to be evaluated to establish a scientific and practical method for calculating the dynamic threshold value of the wild-urban boundary, providing technical support for the scientific demarcation of the wild-urban boundary, fire risk assessment and regional planning management.

[0029] Embodiment 1 like Figure 1 As shown, this embodiment provides an adaptive threshold optimization method for wild city junction area demarcation, comprising the following steps: Step 1: Obtain source domain dataset, target domain dataset and auxiliary data; In this embodiment, the source domain dataset uses the ImageNet dataset; The process of acquiring the target domain dataset includes: determining the target area to be analyzed, such as selecting an area with a high incidence of historical wildfires; acquiring high-resolution remote sensing image data of the target area, and annotating the buildings in the high-resolution remote sensing image data to construct the target domain dataset; In this embodiment, high-resolution remote sensing image data with a resolution of 512×512 pixels are annotated, and the sample size is expanded to 5 times the original data through data enhancement methods such as random rotation (±30°), mirror flipping, and Gaussian noise injection (σ=0.01), so as to construct a target domain dataset with a set style; Ancillary data include ASTER DEM, e.g., 30-meter resolution, for building screening; ESA WorldCover vegetation dataset, for example, 10-meter resolution, for building screening and field feature extraction; A historical fire exposure dataset was constructed based on the fire exposure calculation mechanism, integrating the burnt area data of the target area over the past 20 years. The burnt area data were superimposed with a unified spatial resolution of 10 meters for WUI threshold calculation.

[0030] Step 2: Segment the image of the target area to obtain the building segmentation result; like Figure 2 and Figure 3 As shown, the specific steps include: The specific steps include: Step 201: pre-train the ResNet-50 backbone network based on the source domain dataset to obtain general image features; In this embodiment, the initial learning rate is set to 0.001 in the pre-training stage, the cosine annealing learning rate scheduling strategy is adopted, the batch size is 32, and the number of iterations is 100 epochs; Step 202: Migrating the learned general image features to the target domain task, specifically including: The parameters of the first three convolutional stages (stage1-stage3) of ResNet-50 are frozen, and only stage4 is fine-tuned. The pre-trained ResNet-50 is used as the encoder of the improved U-Net, and its output multi-scale feature map is passed to the decoder through cross-stage connections; In this embodiment, the output of stage 1 (256 channels) is connected to the 4th layer of the decoder; the output of stage 2 (512 channels) is connected to the 3rd layer of the decoder; the output of stage 3 (1024 channels) is connected to the 2nd layer of the decoder; the output of stage 4 (2048 channels) is used as the input reference of the decoder; Step 203: Connect the ResNet-50 backbone network to the corresponding layer of the U-Net decoder through cross-stage feature connection, and realize dynamic weighted fusion of multi-scale features through the spatial attention mechanism. The output features are directly used as the input basis for subsequent decoding upsampling; the formula is expressed as: (1), in, and They represent the feature maps of the encoder and decoder respectively, σ represents the Sigmoid function, Conv is a 1×1 convolution operation, and ⊙ represents element-by-element multiplication.

[0031] The Focal Loss dynamic loss function is used to optimize the model training process, setting the adjustment factor γ=2 and the category balance parameter α=0.25. The mathematical expression is: (2), in, Represents the model prediction probability value.

[0032] The attention weight matrix calculated by formula (1) and the Focal Loss function of formula (2) form a joint optimization target, where the spatial attention mechanism prioritizes retaining the significant feature areas related to buildings in the encoder, and Focal Loss strengthens the gradient return of difficult samples (such as the edges of buildings) by adjusting the factor γ=2.

[0033] Finally, the three indicators of intersection over union (IoU), F1-score, and overall accuracy (OA) were used to evaluate the model performance on the test set, and the threshold judgment conditions were set to IoU ≥ 0.75 and F1-score ≥ 0.85 as the model compliance criteria.

[0034] The semantic segmentation method of high-resolution remote sensing image buildings based on transfer learning and improved U-Net significantly improves the accuracy of building recognition in complex urban scenes by constructing a cross-stage feature fusion architecture and spatial attention mechanism. The pre-training strategy of the ResNet-50 backbone network on the ImageNet dataset, combined with the parameter freezing mechanism in the transfer learning technology, enables the model to effectively extract common image features while avoiding overfitting problems. The improved dynamic weighted fusion formula reduces the positioning error of the building edge through the spatial attention guidance of multi-scale features. At the same time, in the small sample training scenario, the composite data enhancement strategy of integrating random rotation, elastic deformation and adversarial generation samples improves the generalization ability of the model, greatly reduces the annotation cost of training, and provides feasibility support for large-scale regional WUI feature extraction.

[0035] Step 3: Calculate building density based on the building segmentation results; The specific steps include: Step 301, vectorizing the obtained building segmentation result; In this embodiment, the building raster data obtained in step 2 is converted into vector surface data through the Polygonize function of the GDAL library; Step 302: Generate spatial point elements representing buildings based on vector surface data; In this embodiment, the geometric centroid coordinates are calculated according to the coordinates of the polygon vertices formed by the vector surface data, and the centroid point is projected to the UTM coordinate system to generate a spatial point element representing the building.

[0036] Step 303: Based on the spatial point elements, perform spatial density calculation, construct a buffer zone with each building point as the center, and count the building distribution density around each analysis point.

[0037] In this embodiment, a buffer zone is constructed with an initial radius of 500 meters, and the building distribution density around each analysis point is counted.

[0038] Step 4: Screen wildland vegetation types based on the vegetation dataset, and calculate vegetation coverage and wildland patch area based on wildland vegetation types; In this embodiment, for vegetation coverage, wild vegetation types are screened based on ESA WorldCover 10-meter resolution data, including woodland, shrubs, grassland, herbaceous wetland, mangrove, moss and lichen, etc. The number of wild vegetation pixels in a 500-meter × 500-meter moving window is counted pixel by pixel using a moving window statistical method, and the number of wild vegetation pixels / total number of pixels in the buffer zone is divided to obtain the regional wild vegetation coverage; For the area of ​​wildland patches, the selected wildland raster data were converted into vector surface data through GDAL, the area of ​​each vector patch was calculated, and wildland patches with an area greater than 0.1 square kilometers were selected; For distance measures, generate n The distance and number of levels of the buffer zone depend on the threshold setting.

[0039] Step 5: Determine the rules for determining the wildland-urban interface, and determine the type of the wildland-urban interface by combining building density, vegetation coverage, wildland patch area, and buffer zone distance measurement and determination rules; In this embodiment, the wilderness-urban boundary determination rule adopts the traditional determination rule, and the specific determination process includes: Determine whether the building density is greater than 6.17 / km². If so, further determine the vegetation coverage. Otherwise, it is a non-boundary area. Determine whether the vegetation coverage is greater than 50%. If so, the buffer zone is a mixed type-WUI. Otherwise, determine whether the wild patch area is greater than 5km² and the distance measurement is less than 2.4km. If it is satisfied, the buffer zone is an interface type-WUI. If not, it is a non-intersection area.

[0040] By constructing a dynamic calculation system that is adaptive to spatial heterogeneity, the applicability defects of the traditional static threshold method in complex terrain areas are solved. The introduction of a 500-meter initial buffer and a dynamic radius contraction mechanism for building density calculations effectively overcomes the sensitivity of the fixed window method to uneven spatial distribution. The calculation of vegetation coverage combined with existing data sets greatly reduces the amount of calculation data and reduces dependence on remote sensing data. The integrated composite constraints (area threshold, shape index, spatial distribution) in the wild patch screening link lay an accurate data foundation for subsequent fire risk modeling. The intelligent construction strategy of the multi-level buffer zone uses a circular gradient division mechanism to make the spatiotemporal consistency of the fire risk spread simulation more compatible with the local fire risk situation than the traditional buffer zone.

[0041] Step 6: Set gradient thresholds for the hybrid-WUI and interface-WUI, and calculate the WUI areas of the hybrid-WUI and interface-WUI at different thresholds respectively; Step 601: Set threshold gradients for hybrid-WUI (building density, vegetation coverage) and interface-WUI (building density, wildland patch area, distance measure), specifically including: For building density, the lower threshold is set to 1 per square kilometer (a fixed value), and the upper limit is dynamically calculated as the maximum value of building density statistics in the study area (extracted from the density raster generated in Step 3), with a step size of 5 per square kilometer; For vegetation coverage, the threshold range remains 0% to 100% (a fixed range that conforms to the physical definition). During actual calculation, it is truncated according to the vegetation distribution characteristics of the study area (e.g., automatically limited to 0 - 30% in desert areas). The gradient step size is 1%, and in high-precision scenarios, it can be refined to 0.5%; For wildland patch area, the lower threshold is set to 0.1 square kilometers (a fixed value to avoid interference from too small areas), and the upper limit is dynamically calculated as the largest continuous wildland patch area in the study area, with a step size of 0.1 square kilometers; For buffer distance measure, the lower threshold is set to 0.1 kilometers (a fixed value for accuracy requirements), and the upper limit is dynamically set to 10% of the diagonal length of the study area, with a step size of 0.1 kilometers. The formula is: ; Step 602: Calculate the WUI areas of hybrid-WUI and interface-WUI under different thresholds; Among them, the calculation process of the WUI area of hybrid-WUI under different thresholds includes: Generate candidate areas based on the building density threshold (x), extract all connected areas with a building density ≥ x per square kilometer. Subsequently, overlay the vegetation coverage threshold (y), and within the candidate areas, extract sub-areas with a vegetation coverage ≥ y%. Among them, the calculation process of the WUI area of hybrid-WUI under different thresholds includes: First, candidate areas that share the building density threshold (x) with hybrid-WUI. Subsequently, reverse the vegetation coverage constraint and extract sub-areas with a vegetation coverage < y% within the candidate areas. In the third step, conduct spatial association analysis of wildland patches, screen wildland patches with an area ≥ m square kilometers, and generate a buffer zone with a width of n kilometers based on the boundaries of the wildland patches, and retain the candidate areas of interface-WUI that intersect with the buffer zone; Step 7: Combine historical burned area data and the WUI area to define the fire exposure index. Use the spatial distribution characteristics of the WUI area as the independent variable of the RF model, and the fire exposure index under different thresholds as the dependent variable of the RF model to fit and obtain the optimal threshold; Specifically, it includes the following steps: Step 701: define the fire exposure index (WEI), which is expressed as an index of the spatial correlation intensity between historical fires and WUI areas: ; Step 702: The historical burn site data are uniformly converted to the same coordinate system as the WUI region (WGS_1984_UTM), and the spatial resolution is uniformly resampled to 10 meters; Step 703: The spatial distribution characteristics of the WUI region generated by the threshold combination are used as the independent variable (X) of the RF model, and the fire exposure index (WEI) under different thresholds is used as the dependent variable (Y) of the RF model; A stratified sampling strategy was used to randomly divide the training set (80%) and the validation set (20%) to ensure the randomness of the selection of the training set and the validation set; The RF hyperparameter search space is defined as follows: 'n_estimators': [100, 200, 300], 'learning_rate': [0.01, 0.05, 0.1], 'max_depth': [3, 4, 5, 6], 'min_samples_split': [2, 3, 4], 'min_samples_leaf': [1, 2, 3], A univariate scanning strategy is adopted, that is, other parameters are fixed as the current optimal values, and the partial dependence curve (PDP) under the threshold change is calculated using the RF model for all candidate values ​​of the target parameter generated by step size within its full range, and the peak point of the curve is taken as the optimal threshold of the influencing factor.

[0042] By defining a spatiotemporal weighted fire exposure index (WEI), integrating the spatial alignment and resolution matching mechanism of long-term historical fire scar data, the spatial distribution characteristics of fire risk are innovatively dynamically associated with threshold parameters. In the threshold decision link, the geographic spatial rationality and practical operability of the threshold scheme are significantly improved by analyzing the partial dependence curve. The timeliness lag problem of the traditional static threshold scheme in different geographical scenarios is overcome.

[0043] Embodiment 2 This embodiment provides an adaptive threshold optimization system for wild city junction area demarcation, including: A segmentation module is used to segment the image of the target area to obtain a building segmentation result; The parameter calculation module is used to calculate the building density according to the building segmentation results; screen the wild vegetation types based on the obtained vegetation data set, and calculate the vegetation coverage and wild patch area and distance measurement respectively; The WUI type determination module is used to determine the WUI determination rules, and the type of WUI is determined by combining the building density, vegetation coverage, wild patch area, buffer zone distance measurement and determination rules; The WUI area determination module is used to set the threshold range of building density, vegetation coverage, wild patch area and buffer distance measurement, and calculate the WUI area of ​​different types of WUI under different thresholds; The threshold adaptive optimization module is used to define the fire exposure index by combining historical burn site data and the WUI area. The spatial distribution characteristics of the WUI area are used as the independent variable of the RF model, and the fire exposure index under different thresholds is used as the dependent variable of the RF model to obtain the optimal threshold by fitting.

[0044] It should be noted that the specific implementation method of an adaptive threshold optimization system for wild-city boundary zoning according to an embodiment of the present invention is similar to the specific implementation method of an adaptive threshold optimization method for wild-city boundary zoning according to an embodiment of the present invention. Please refer to the description of the method part for details. In order to reduce redundancy, it will not be repeated here.

[0045] Embodiment 3 This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the adaptive threshold optimization method for wild-city boundary area demarcation as described above are implemented.

[0046] Embodiment 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the adaptive threshold optimization method for wild-city boundary zoning as described above are implemented.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive threshold optimization method for wild city boundary zoning, characterized in that: The steps include: Segment the image of the target area to obtain the building segmentation result; Calculate building density based on building segmentation results; Based on the obtained vegetation dataset, the wildland vegetation types were screened, and the vegetation coverage and wildland patch area and distance measurements were calculated respectively; Determine the WUI determination rules, and determine the type of WUI by combining building density, vegetation coverage, wild patch area, buffer zone distance measurement and determination rules; The threshold ranges of building density, vegetation coverage, wildland patch area and buffer distance measurement were set, and the WUI areas of different types of WUI under different thresholds were calculated; The fire exposure index was defined by combining historical burn site data and the WUI region. The spatial distribution characteristics of the WUI region were used as the independent variable of the RF model, and the fire exposure index under different thresholds was used as the dependent variable of the RF model to obtain the optimal threshold.

2. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: The step of segmenting the image of the target area to obtain a building segmentation result includes: Pre-train the ResNet-50 backbone network based on the source domain dataset to obtain universal image features; Transfer the learned general image features to the target domain task; The ResNet-50 backbone network is connected to the corresponding layer of the U-Net decoder through cross-stage feature connection, and the dynamic weighted fusion of multi-scale features is realized through the spatial attention mechanism. The building segmentation result is obtained based on the fused features.

3. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: The calculating of building density according to the building segmentation result includes: Convert the building raster data corresponding to the building segmentation result into vector surface data; Generate spatial point features representing buildings based on vector surface data; Based on the spatial point features, spatial density calculation is performed, a buffer zone is constructed with each building point as the center, and the building distribution density around each analysis point is counted.

4. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: The method of screening the wildland vegetation type based on the obtained vegetation data set and calculating the vegetation coverage and the wildland patch area and distance measurement respectively includes: The moving window statistical method is used to count the number of wild vegetation pixels in the moving window pixel by pixel, and the wild vegetation pixel number / the total number of pixels in the buffer zone are divided to obtain the regional wild vegetation coverage; The selected wildland raster data is converted into vector surface data through GDAL, the area of ​​each vector patch is calculated, and the wildland patches with an area larger than the set area are selected to obtain the wildland patch area; Generated along wild patch boundaries n The distance measure is obtained by setting the buffer distance and the level threshold.

5. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: Threshold ranges for building density, vegetation cover, wildland patch area, and buffer distance measures include: For building density, the threshold range is set from 1 / km2 to the maximum building density, with a step size of 5 / km2; For vegetation cover, the threshold range was set from 0% to 100% with a gradient step of 1%; For wild patch area, the threshold range was set from 0.1 km2 to the maximum patch area, with a step size of 0.1 km2; For the buffer distance measure, the threshold range is 0.1 km to 5.0 km, with a step size of 0.1 km.

6. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: Calculate the WUI area for different types of WUI at different thresholds, including: The calculation process of the WUI area under different thresholds for mixed WUI includes: Generate candidate areas based on building density thresholds, extract all connected areas with building density ≥ x / km2, then superimpose vegetation coverage thresholds, and extract sub-areas with vegetation coverage ≥ y% within the candidate areas; The calculation process of the WUI area under different thresholds for mixed WUI includes: First, candidate areas that share the building density threshold with the mixed-WUI are selected. Then, the vegetation coverage constraint is reversed to extract sub-areas with vegetation coverage < y% within the candidate areas. In the third step, spatial association analysis of wildland patches is performed to screen wildland patches with an area ≥ m square kilometers. A strip buffer with a width of n kilometers is generated based on the boundary of the wildland patch, and the interface-type WUI candidate areas that intersect with the buffer are retained.

7. The adaptive threshold optimization method for wild city junction area demarcation as claimed in claim 1 is characterized in that: The fire exposure index WEI is expressed as: 。 8. An adaptive threshold optimization system for wild city boundary zoning, characterized in that: include: A segmentation module is used to segment the image of the target area to obtain a building segmentation result; A parameter calculation module, which is used to calculate the building density according to the building segmentation result; Based on the obtained vegetation dataset, the wildland vegetation types were screened, and the vegetation coverage and wildland patch area and distance measurements were calculated respectively; The WUI type determination module is used to determine the WUI determination rules, and the type of WUI is determined by combining the building density, vegetation coverage, wild patch area, buffer zone distance measurement and determination rules; The WUI area determination module is used to set the threshold range of building density, vegetation coverage, wild patch area and buffer distance measurement, and calculate the WUI area of ​​different types of WUI under different thresholds; The threshold adaptive optimization module is used to define the fire exposure index by combining historical burn site data and the WUI area. The spatial distribution characteristics of the WUI area are used as the independent variable of the RF model, and the fire exposure index under different thresholds is used as the dependent variable of the RF model to obtain the optimal threshold by fitting.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of an adaptive threshold optimization method for wild-urban boundary zoning as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the adaptive threshold optimization method for wild-city boundary zoning as described in any one of claims 1-7 are implemented.

Images