CN118115866A - A processing system for remote sensing image data of urban rail transit - Google Patents

Abstract

The invention discloses a processing system for urban rail transit remote sensing image data, which relates to the technical field of image data processing, and comprises a data acquisition module, a data preprocessing module, a feature extraction module, a data analysis module, a decision support module, a user interface module and a data storage and management module; the invention greatly improves the acquisition efficiency of urban rail transit system data, and can quickly collect detailed spatial information through remote sensing images; it greatly enriches the digitization degree of urban rail transit, and the extraction of various key features provides a data basis for planning analysis.

Description

A processing system for remote sensing image data of urban rail transit

Technical Field

The invention relates to the technical field of image data processing, and in particular to a system for processing remote sensing image data of urban rail transit.

Background technique

Urban rail transit remote sensing image processing systems started relatively late, and began to develop gradually after about 2000. Early systems were mainly used for line security inspections, using simple video surveillance systems to identify and extract security inspection targets in images. After about 2010, with the advancement of image processing technology, especially deep learning, rail transit image processing systems began to achieve more complex functions.

After 2020, designs integrating multiple image processing tasks into one system have emerged to achieve richer monitoring and analysis functions within the car, but the following defects still exist: In the existing technology, rail transit system data is mainly obtained through ground surveys, which is costly and inefficient, and cannot quickly obtain spatial information covering a wide area; the existing technology cannot effectively extract key features of rail transit, such as track lines, stations, surrounding environment, etc., and data support is insufficient; volume forecasts rely on static allocation models, cannot consider dynamic factors, and have limited prediction accuracy; it is difficult to conduct a three-dimensional study of the interactive relationship between rail transit and urban development, and planning analysis is not scientific enough; decision support relies on manual experience, different plans are difficult to evaluate, and there is a lack of quantitative analysis.

Summary of the invention

In view of the above-mentioned problems existing in the existing urban rail transit remote sensing image processing, the present invention is proposed.

Therefore, the problem to be solved by the present invention is how to provide a system for improving the intelligence level of urban rail transit planning.

In order to solve the above technical problems, the present invention provides the following technical solutions:

In the first aspect, an embodiment of the present invention provides a system for processing urban rail transit remote sensing image data, which includes a data acquisition module, a data preprocessing module, a feature extraction module, a data analysis module, a decision support module, a user interface module and a data storage and management module; the data acquisition module is responsible for collecting remote sensing images of urban rail transit; the data preprocessing module is used to preprocess the original remote sensing images; the feature extraction module is used to extract features, and finally key features, and output structured feature annotation results; the data analysis module is used to process image data; the decision support module is used to provide decision support; the user interface module is used to provide an interface for users to view analysis results and reports or input new query request; the data storage and management module is responsible for storing all collected raw data, processed data and analysis results; the data acquisition module transmits the collected data to the data preprocessing module; the data preprocessing module sends the preprocessed data to the feature extraction module; the feature extraction module passes the extracted feature data to the data analysis module; the analysis results of the data analysis module are used for report generation or passed to the decision support module; the output of the decision support module is used to provide reports to relevant decision makers; the user interface module directly interacts with the user, obtains user input, and displays the results of processing by other modules; the data storage and management module provides data access and storage services for other modules.

As a preferred solution of the processing system of urban rail transit remote sensing image data of the present invention, the data acquisition module includes: collecting rail transit line map data, M = {m ₁ ,m ₂ ,...,m _n }, wherein M represents the set of all rail transit lines, and _mi represents the i-th line; for each line _mi , marking its path range P( _mi ), if the line mi is an underground line, marking the station location; if it is an above-ground line, marking the entire line; for each line _mi , analyzing its turning and intersection points, if there is a planned but unopened line _mj , then, and marking P( _mj ); using the minimum bounding box algorithm, calculating the minimum rectangular or polygonal area B containing all paths P( _mi ), the formula is as follows:

When calculating B, it is necessary to ensure that the ranges of the paths overlap.

As a preferred solution of the processing system of urban rail transit remote sensing image data described in the present invention, the data preprocessing module includes the following contents: checking whether the image data is distorted and performing geometric correction; analyzing the noise distribution of the image and designing a filtering method to remove noise; adjusting the image color balance and performing histogram equalization to reduce the brightness impact; cropping, scaling and rotating the image to adjust the image to a uniform size; applying sorting and normalization to map the image values to a fixed numerical range.

As a preferred solution of the processing system of urban rail transit remote sensing image data of the present invention, the step of performing geometric correction is as follows: collecting a data set containing various tilted and distorted images, annotating these images, and indicating the correct geometric shape or the corrected image; designing a CNN model, the input of the CNN model is the original distorted image, and the output is the correction parameter of the image; defining a loss function MSE, the formula is as follows:

Among them, _Yi is the real parameter, is the prediction parameter and n is the number of samples.

As a preferred solution of the processing system of urban rail transit remote sensing image data described in the present invention, the data analysis module includes the following contents: according to the characteristics of the rail line, statistically analyzing the distribution information of each line; using the station distribution information, combined with the population distribution data, to establish a flow prediction model to predict the passenger flow of each station in the future; analyzing the characteristic changes in different years, judging the direction of new lines, and predicting future development trends; studying the mutual influence relationship between rail transit and urban development; applying the traffic assignments prediction model to evaluate the impact of new lines on the overall rail transit network.

As a preferred solution of the processing system of urban rail transit remote sensing image data described in the present invention, the analysis of characteristic changes in different years, determination of the direction of new lines, and prediction of future development trends include the following steps: collecting rail transit line map data of the city in the past 10 years; comparing changes in line structure, and analyzing the location distribution characteristics of new lines, including: superimposing and comparing line maps of different years, marking newly added line segments in previous years, analyzing the spatial distribution of new lines, and determining whether they are concentrated in certain areas; calculating the statistical characteristics of the directional distribution of new lines; fitting the distribution function of the direction of new lines to determine the main development direction; correcting the directional distribution function according to urban development planning and population distribution prediction; sampling and generating possible new lines based on the corrected directional distribution, and predicting future development trends.

As a preferred solution of the urban rail transit remote sensing image data processing system of the present invention, the calculation of the directional distribution statistical characteristics of the newly added lines includes the following steps: calculating the direction angle:

θ _i =arctan2(Δy _i , Δxi ₎

Where θ _i is the direction angle of the i-th line segment; Δy _i and _Δxi are the coordinate differences of the line segment on the vertical axis and the horizontal axis respectively; calculate the main direction and variance:

S＝1-C

Where N is the total number of line segments and C is the length of the result vector.

As a preferred solution of the processing system of urban rail transit remote sensing image data of the present invention, the steps of fitting the distribution function of the newly added line direction and judging the main development direction are as follows: using the kernel density estimation formula:

The kernel function K _h is usually a Gaussian kernel, and h is the bandwidth; the modified directional distribution function includes: obtaining the city's long-term development plan and the population distribution forecast data for the next 10 years, and adjusting f(θ). The correction factor is as follows:

H(θ)＝1-α.I(θ∈θ _restricted )

Adjusted density function:

f'(θ)＝H(θ).f(θ)

Among them, α is the correction intensity parameter, between 0 and 1; I is the indicator function, which is 1 if the direction θ falls within the restricted area, otherwise it is 0; the calculation formula of population weight is:

W(θ)＝β.P(θ)

Adjusted density function:

f”(θ)＝W(θ).f'(θ)

Among them, β is the population influence parameter, and P(θ) is the population distribution density in direction θ. Combining the restricted area adjustment of urban development planning and the influence of population distribution, the final line direction distribution function is obtained:

G(θ)＝f”(θ)

Among them, G(θ) is the final line direction distribution function.

The beneficial effects of the present invention are as follows: the present invention greatly improves the efficiency of acquiring data of the urban rail transit system, and detailed spatial information can be quickly collected through remote sensing images; the degree of digitization of urban rail transit is greatly enriched, and the extraction of various key features provides a data basis for planning and analysis; a comprehensive and quantitative traffic volume forecast is provided to provide support for future demand assessment and line planning; the dynamic relationship between rail transit and urban development can be deeply studied to make planning more scientific; more intelligent decision-making support is provided for rail transit construction, the advantages and disadvantages of different planning schemes are evaluated, and the effective use and in-depth mining and analysis of multi-source heterogeneous data in the field of rail transit are promoted.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

FIG. 1 is a structural diagram of a system for processing urban rail transit remote sensing image data in Example 1.

Detailed ways

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

Example 1

Referring to FIG. 1 , which is a first embodiment of the present invention, a system for processing urban rail transit remote sensing image data is provided, including the following contents:

Data acquisition module, data preprocessing module, feature extraction module, data analysis module, decision support module, user interface module and data storage and management module; the data acquisition module transmits the collected data to the data preprocessing module; the data preprocessing module sends the preprocessed data to the feature extraction module; the feature extraction module passes the extracted feature data to the data analysis module; the analysis results of the data analysis module can be used for report generation or passed to the decision support module; the output of the decision support module is used to provide reports to relevant decision makers; the user interface module directly interacts with the user, obtains user input, and displays the results of processing by other modules; the data storage and management module provides data access and storage services for other modules of the system.

The data acquisition module is responsible for collecting remote sensing images of urban rail transit. Remote sensing images usually come from satellites, drones or aerial photography.

Specifically, the urban rail transit route is determined, the range of areas where images need to be collected is determined, commercial satellite companies are contacted to obtain high-resolution satellite images covering the area, drones are used to take detailed photos of key areas, and drone overhead images are obtained. Aerial photography is performed on the rail transit area to obtain images from a bird's-eye view. The above multi-source remote sensing images are uniformly cropped and spliced to construct an image dataset for the urban rail transit. After the image dataset is processed, it is sent to the data preprocessing module.

Furthermore, the process of determining the range of areas where images need to be collected is as follows:

Collect rail transit line map data, M = {m ₁ ,m ₂ ,...,m _n }, where M represents the set of all rail transit lines, _mi represents the i-th line; for each line _mi , mark its path range P(m _i ), these paths can be represented by a set of line segments, curves or points; if line _mi is an underground line, mark the station location; if it is an above-ground line, mark the entire line; for each line _mi , analyze its turns and intersections, and adjust P(m _i ) to ensure completeness; if there is a line m _j that is planned but not opened, then, and mark P(m _j ).

Use the minimum bounding box algorithm to calculate the minimum rectangular or polygonal area B that contains all paths P(m _i ). The formula is as follows:

When calculating B, ensure that the ranges of each path overlap to facilitate subsequent image stitching. The final spatial range B is the data area where remote sensing images need to be collected.

The data preprocessing module is used to preprocess the original remote sensing images, including image correction, denoising, standardization, etc., to facilitate subsequent analysis.

Specifically, the data preprocessing module includes the following contents: checking whether the image data has distortions such as tilt and local distortion, and performing geometric correction; analyzing the noise distribution of the image and designing a filtering method to remove noise; adjusting the image color balance and performing histogram equalization to reduce the impact of brightness; cropping, scaling and rotating the image to adjust the image to a uniform size; applying sorting and normalization to map the image values to a fixed numerical range; the preprocessed image data is sent to the feature extraction module for subsequent analysis.

Furthermore, the steps for geometric correction are as follows:

Collect a dataset containing various tilted and distorted images, annotate these images, and indicate the correct geometric shape or the corrected image; design a CNN model whose input is the original distorted image and whose output is the correction parameters of the image, such as rotation angle, distortion degree, etc.; define a loss function MSE:

Among them, _Yi is the real parameter, is the prediction parameter and n is the number of samples.

The correction algorithm uses the parameters predicted by the CNN to correct the image. For example, if the predicted output is a tilt angle, an affine transformation is used to correct the image. The model performance is evaluated on an independent test dataset, and the model structure and training process are iteratively optimized based on the performance results.

The steps of cropping, scaling and rotating the image are as follows: identify key points in the image, which represent significant features in the image, such as corners, edges or unique textures; use the key points to generate a saliency map, where the saliency map can be generated by evaluating the density and distribution of the feature points, such as using methods such as Gaussian blur to enhance the area around the feature points; analyze the saliency map to determine the key areas in the image, as shown in the following formula:

R = argmax _x,y S(x,y)

Among them, S(x,y) is the saliency value of the point (x,y) in the saliency map, R is the determined key area; the cropping window is determined using a bounding box or minimum closed area algorithm.

The feature extraction module includes the following contents: using the Canny edge detection algorithm to detect the line contours in the image; applying the Hough transform to extract the track lines in the image through line combination analysis; using the template matching technology and the preset station template to identify the station location in the image; using the segmentation and classification algorithms to distinguish different types of ground targets such as roads and buildings; using deep learning technologies such as convolutional neural networks to achieve intelligent recognition of various types of ground targets; finally summarizing key features such as tracks, stations, and buildings, and outputting structured feature labeling results.

Preferably, using template matching technology and a preset station template to identify the station location in the image includes the following steps: selecting a standard template for the station, wherein the template selection should cover different station types and viewing angles to improve the breadth and accuracy of recognition; preprocessing the template and the image to be analyzed; sliding the template on the image to be analyzed, and calculating the matching degree between the template and each position of the image, the specific formula is as follows:

Where T is the template and F is the image. When the matching score exceeds the set threshold e, it is considered that the station is found at that location. Once a match is found, the location of the matching area is recorded. This location can be used for further analysis, such as the geographic positioning of the station and its relationship with other urban facilities.

The data analysis module includes the following contents: according to the characteristics of the rail lines, statistically analyze the distribution information of each line, such as the length, intersection, coverage, etc.; use the station distribution information, combined with the population distribution data, to establish a flow prediction model to predict the passenger flow of each station in the future; analyze the changes in characteristics in different years, determine the direction of new lines, and predict future development trends; study the mutual influence between rail transit and urban development; apply the traffic assignments prediction model to evaluate the impact of new lines on the overall rail transit network.

Specifically, the station distribution information is combined with the population distribution data to establish a flow prediction model. The following steps are included to predict the passenger flow of each station in the future: collect rail transit line map data, mark the location coordinates of each station and adjacent stations; collect the population distribution heat map data of the city to indicate the population distribution density in different areas; map the station location to the population distribution heat map, and count the number of people within the service area as the potential passenger flow of the station; use historical passenger flow data as training samples, and use station location, surrounding population, etc. as features to establish a regression model; for future new stations, input their coordinates and service coverage population, and the model predicts the future passenger flow of the station.

Analyzing the changes in characteristics in different years, determining the direction of new lines, and predicting future development trends include the following steps: collecting rail transit line map data for the city over the past 10 years; comparing changes in line structure, and analyzing the location distribution characteristics of new lines, including: superimposing and comparing line maps from different years, marking newly added line sections over the years, and analyzing the spatial distribution of new lines to determine whether they are concentrated in certain areas; calculating the statistical characteristics of the directional distribution of new lines; fitting the distribution function of the direction of new lines to determine the main development direction; correcting the directional distribution function based on urban development plans and population distribution forecasts; and sampling and generating possible new lines based on the corrected directional distribution to predict future development trends.

Furthermore, calculating the directional distribution statistical characteristics of the newly added lines includes the following steps:

The formula for calculating the direction angle is as follows:

θ _i =arctan2(Δy _i , Δxi ₎

Where θ _i is the direction angle of the i-th line segment; Δy _i and _Δxi are the coordinate differences of the line segment on the vertical axis and the horizontal axis respectively; calculate the main direction and variance:

Main direction formula:

S＝1-C

Where N is the total number of line segments and C is the length of the result vector used to calculate the variance.

The steps to fit the distribution function of the newly added route directions and determine the main development direction are as follows: The kernel density estimation (KDE) method can better fit and explain the distribution of route directions. The formula is as follows:

Among them, the kernel function K _h usually selects a Gaussian kernel, and h is the bandwidth.

The correction of the directional distribution function includes the following steps: obtaining the city's long-term development plan and the population distribution forecast data for the next 10 years, adjusting f(θ), and the correction factor:

H(θ)＝1-α.I(θ∈θ _restricted )

Adjusted density function:

f'(θ)＝H(θ).f(θ)

Among them, α is the correction strength parameter, which is between 0 and 1; I is the indicator function, which is 1 if the direction θ falls within the restricted area, otherwise it is 0.

The formula for calculating population weight is:

W(θ)＝β.P(θ)

Adjusted density function:

f”(θ)＝W(θ).f'(θ)

Among them, β is the population influence parameter, which is used to adjust the intensity of the influence of population distribution on the line direction distribution; P(θ) is the population distribution density in direction θ; combined with the adjustment of restricted areas in urban development planning and the influence of population distribution, a comprehensive optimized line direction distribution function is obtained:

G(θ)＝f”(θ)

It should be noted that the final optimized density function will comprehensively consider urban planning restrictions, future population distribution forecasts, and original route direction data to provide a more comprehensive and realistic route direction distribution forecast.

The decision support module includes the following contents: collecting various drafts of urban development plans and rail transit construction plans; evaluating the demand coverage of each planning scheme based on traffic forecast results; evaluating the comprehensive effects of each planning scheme in combination with rail transit network effect analysis; and predicting the impact of each planning scheme through a dynamic causal model of rail transit and urban development.

The user interface module is used to provide an interface for users (such as urban planners and traffic managers) to view analysis results and reports, or enter new query requests.

The details are as follows: a web interface is provided to present data analysis results in the form of maps, charts, etc. Users can choose to view different analysis reports; a query input box is provided, where users can enter new planning schemes or routes to conduct impact assessments; the back end receives new queries, performs corresponding analysis, and returns results to the front end. Users can export analysis reports and data tables, etc.

The data storage and management module is responsible for storing all collected raw data, processed data and analysis results.

The details are as follows: store various original image data and pre-processed data; use relational database to store extracted feature data and establish indexes; use columnar database to store intermediate result data of various spatial analyses; establish metadata directory to record data source, processing flow and other information.

This embodiment also provides a computer device, which is suitable for the case of a processing system for urban rail transit remote sensing image data, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the processing system for urban rail transit remote sensing image data proposed in the above embodiment.

The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a microprocessor, a processing system for urban rail transit remote sensing image data as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

In summary, the present invention greatly improves the efficiency of acquiring data from urban rail transit systems, and can quickly collect detailed spatial information through remote sensing images; it greatly enriches the degree of digitization of urban rail transit, and the extraction of various key features provides a data basis for planning and analysis; it provides a comprehensive and quantitative traffic volume forecast to provide support for future demand assessment and line planning; it can conduct in-depth research on the dynamic relationship between rail transit and urban development to make planning more scientific; it provides more intelligent decision-making support for rail transit construction, evaluates the advantages and disadvantages of different planning schemes, and promotes the effective use and in-depth mining and analysis of multi-source heterogeneous data in the field of rail transit.

Example 2

Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of a processing system for urban rail transit remote sensing image data are provided.

City A, with a population of 3 million, currently has 3 subway lines and 1 light rail line, and plans to build 2 new subway lines in the next 5 years.

Use drones to conduct detailed flight photography of City A’s existing rail transit, obtain 50,000 aerial images, acquire 1-meter resolution optical images of City A’s entire area from commercial satellites, and collect rail transit route map data from the planning department for the past 10 years.

Use software such as Pix4D to process drone images to obtain point clouds, digital surface models, and orthophotos; perform geometric correction and registration on satellite images, and stitch them with drone images to construct a data set; use convolutional neural networks to identify past and existing rail transit lines in satellite images; and use template matching to identify station location information in drone images.

Statistics are collected on the length, intersection distribution, and coverage of the four existing rail transit lines. The directional distribution characteristics of new lines added in the past 10 years are used to predict the trend of new lines in the future, establish a relationship model between rail transit and urban development, and analyze the interactive mechanism.

Extract the path information of the two newly planned lines and predict the changes in network traffic brought about by the new lines. Based on the traffic prediction, optimize the location and number of new line stations. Build a virtual digital twin city of City A and conduct simulation tests on the construction of new lines.

Table 1 Comparison between the present invention and the prior art

System indicators current technology this invention Data acquisition method Manual investigation Multi-source remote sensing analytical skills Static Analysis Deep Learning Decision support methods Experience Digital Twin Simulation Results Statistical Reports 3D Visualization

By comparing with the existing technology, this table highlights the technical advantages of the present invention in acquiring multi-source heterogeneous data, adopting cutting-edge analysis technology, building digital twins and providing three-dimensional interactive interfaces, which comprehensively improves the efficiency and quality of urban rail transit planning decisions and demonstrates significant technological progress.

It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims (8)

1. A system for processing urban rail transit remote sensing image data, characterized in that it includes: Data acquisition module, data preprocessing module, feature extraction module, data analysis module, decision support module, user interface module and data storage and management module; The data acquisition module is responsible for collecting remote sensing images of urban rail transit; the data preprocessing module is used to preprocess the original remote sensing images; the feature extraction module is used to extract features, and finally the key features, and output structured feature annotation results; the data analysis module is used to process image data; the decision support module is used to provide decision support; the user interface module is used to provide an interface for users to view analysis results and reports or input new query requests; the data storage and management module is responsible for storing all collected original data, processed data and analysis results; The data acquisition module transmits the collected data to the data preprocessing module; the data preprocessing module sends the preprocessed data to the feature extraction module; the feature extraction module passes the extracted feature data to the data analysis module; the analysis results of the data analysis module are used for report generation or passed to the decision support module; the output of the decision support module is used to provide reports to relevant decision makers; the user interface module directly interacts with the user, obtains user input, and displays the results of processing by other modules; the data storage and management module provides data access and storage services for other modules. 2. The system for processing urban rail transit remote sensing image data according to claim 1, wherein the data acquisition module comprises: Collect rail transit line map data, M = {m ₁ ,m ₂ ,...,m _n }, where M represents the set of all rail transit lines, and mi represents the i-th line; for each line mi, mark its path range P(m _i ), if the line _mi is an underground line, mark the station location; if it is an above-ground line, mark the entire line; for each line _mi , analyze its turning points and intersections, if there is a line m _j that is planned but not opened, then, and mark P(m _j ); Use the minimum bounding box algorithm to calculate the minimum rectangular or polygonal area B that contains all paths P(m _i ). The formula is as follows: When calculating B, it is necessary to ensure that the ranges of the paths overlap. 3. The system for processing urban rail transit remote sensing image data according to claim 2, wherein the data preprocessing module comprises the following contents: Check whether the image data is distorted and perform geometric correction; Analyze the noise distribution of the image and design filtering methods to remove noise; Adjust the image color balance, perform histogram equalization, and reduce the impact of brightness; Crop, scale, and rotate images to adjust them to a uniform size; Applies sorting and normalization to map image values to a fixed numerical range. 4. The system for processing urban rail transit remote sensing image data as claimed in claim 3 is characterized in that the steps of performing geometric correction are as follows: Collect a dataset containing various tilted and distorted images and annotate them to indicate the correct geometry or the corrected image. Design a CNN model. The input of the CNN model is the original distorted image, and the output is the correction parameter of the image. Define a loss function MSE, the formula is as follows: Among them, _Yi is the real parameter, is the prediction parameter and n is the number of samples. 5. The system for processing urban rail transit remote sensing image data according to claim 4, wherein the data analysis module comprises the following contents: According to the characteristics of the track lines, statistically analyze the distribution information of each line; Using station distribution information and population distribution data, a traffic forecasting model is established to predict the passenger flow of each station in the future; Analyze the changes in characteristics of different years, determine the direction of new lines, and predict future development trends; Study the mutual influence between rail transit and urban development; Apply the traffic assignments prediction model to evaluate the impact of new lines on the overall rail transit network. 6. The processing system of urban rail transit remote sensing image data according to claim 5, characterized in that: the analysis of characteristic changes in different years, determination of the direction of new lines, and prediction of future development trends comprises the following steps: Collect the city's rail transit route map data for the past 10 years; Compare changes in line structure and analyze the location distribution characteristics of new lines, including: superimposing and comparing line maps from different years, marking newly added line sections over the years, analyzing the spatial distribution of new lines, and determining whether they are concentrated in certain areas; Calculate the directional distribution statistical characteristics of the newly added lines; Fit the distribution function of the newly added line direction to determine the development direction; Modify the directional distribution function according to the urban development plan and population distribution forecast; Based on the revised directional distribution, possible new routes are generated by sampling and future development trends are predicted. 7. The system for processing urban rail transit remote sensing image data according to claim 6, wherein the step of calculating the directional distribution statistical characteristics of the newly added lines comprises the following steps: Calculate the direction angle: θ _i =arctan2(Δy _i , Δxi ₎ Wherein, θ _i is the direction angle of the i-th line segment; Δy _i , _Δxi are the coordinate differences of the line segment on the vertical axis and the horizontal axis respectively; Compute the principal directions and variances: S＝1-C Where N is the total number of line segments and C is the length of the result vector. 8. The processing system of urban rail transit remote sensing image data according to claim 7, characterized in that: the step of fitting the distribution function of the newly added line direction and determining the development direction is as follows: Use the kernel density estimation formula: Among them, the kernel function K _h usually selects the Gaussian kernel, and h is the bandwidth; The correction direction distribution function includes: obtaining the city's long-term development plan and the population distribution forecast data for the next 10 years, and adjusting f(θ). The correction factor is as follows: H(θ)＝1-α.I(θ∈θ _restricted ) Adjusted density function: f'(θ)＝H(θ).f(θ) Among them, α is the correction intensity parameter, between 0 and 1; I is the indicator function, which is 1 if the direction θ falls within the restricted area, otherwise it is 0; The formula for calculating population weight is: W(θ)＝β.P(θ) Adjusted density function: f”(θ)＝W(θ).f'(θ) Among them, β is the population influence parameter, P(θ) is the population distribution density in direction θ; Combining the restricted area adjustment of urban development planning and the impact of population distribution, the final line direction distribution function is obtained: G(θ)＝f”(θ) Among them, G(θ) is the final line direction distribution function.