CN118115866A - Processing system of urban rail transit remote sensing image data - Google Patents

Processing system of urban rail transit remote sensing image data Download PDF

Info

Publication number
CN118115866A
CN118115866A CN202410141960.3A CN202410141960A CN118115866A CN 118115866 A CN118115866 A CN 118115866A CN 202410141960 A CN202410141960 A CN 202410141960A CN 118115866 A CN118115866 A CN 118115866A
Authority
CN
China
Prior art keywords
data
module
line
rail transit
distribution
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202410141960.3A
Other languages
Chinese (zh)
Inventor
成遥遥
冯清倩
苗娇娇
华明
卜晗
关健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Newahua Technology Co ltd
Nanjing Shazhi Platinum Technology Co ltd
Original Assignee
Nanjing Newahua Technology Co ltd
Nanjing Shazhi Platinum Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Newahua Technology Co ltd, Nanjing Shazhi Platinum Technology Co ltd filed Critical Nanjing Newahua Technology Co ltd
Priority to CN202410141960.3A priority Critical patent/CN118115866A/en
Publication of CN118115866A publication Critical patent/CN118115866A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/182—Network patterns, e.g. roads or rivers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Astronomy & Astrophysics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a processing system of 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 method greatly improves the acquisition efficiency of urban rail transit system data, and fine space information can be rapidly acquired through remote sensing images; the digital degree of urban rail transit is greatly enriched, and the extraction of various key features provides a data base for planning analysis.

Description

Processing system of urban rail transit remote sensing image data
Technical Field
The invention relates to the technical field of image data processing, in particular to a processing system of urban rail transit remote sensing image data.
Background
The urban rail transit remote sensing image processing system starts late and starts to develop gradually after about 2000 years. Early systems were mainly applied to line security and used simple video surveillance systems to identify and extract security targets in images. After about 2010, as image processing technology, particularly deep learning, advances, rail transit image processing systems began to implement more complex functions.
After 2020, a design of integrating multiple image processing tasks into one system appears to realize richer monitoring and analysis functions in a carriage, but the following defects still exist at present: in the prior art, the data of the rail transit system is mainly acquired by means of ground investigation, the cost is high, the efficiency is low, and the space information covering the wide area cannot be acquired rapidly; the prior art cannot effectively extract key features of rail transit, such as a rail line, a station, a surrounding environment and the like, and has insufficient data support; the traffic prediction depends on a static allocation model, cannot consider dynamic factors, and has limited prediction precision; the interactive relation between rail transit and urban development is difficult to study in a three-dimensional way, and planning analysis is not scientific enough; decision support relies on manual experience, different schemes are difficult to evaluate, quantitative analysis is absent, and the like.
Disclosure of Invention
The present invention has been made in view of the above-mentioned problems occurring in the conventional urban rail transit remote sensing image processing.
Therefore, the problem to be solved by the invention is how to provide a system for improving the intelligent level of urban rail transit planning.
In order to solve the technical problems, the invention provides the following technical scheme:
In a first aspect, an embodiment of the present invention provides a processing system for 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 used for collecting remote sensing images of urban rail transit; the data preprocessing module is used for preprocessing an original remote sensing image; the feature extraction module is used for extracting features, and outputting structured feature labeling results according to final key features; the data analysis module is used for processing the image data; the decision support module is used for carrying out decision support; the user interface module is used for providing an interface for a user to check analysis results and report or input a new query request; the data storage and management module is used for storing all collected original data, processed data and analysis results; the data acquisition module transmits acquired data to the data preprocessing module; the data preprocessing module sends preprocessed data to the feature extraction module; the feature extraction module transmits the extracted feature data to the data analysis module; the analysis result of the data analysis module is used for generating a report or transmitting the report to the decision support module; the output of the decision support module is used for providing reports to relevant decision makers; the user interface module directly interacts with a user, obtains user input and displays results processed by other modules; the data storage and management module provides data access and storage services for other modules.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the data acquisition module comprises: collecting track traffic route diagram data, wherein M= { M 1,m2,...,mn }, M represents a set of all track traffic routes, and M i represents an ith route; marking a path range P (m i) of each line m i, and marking a station position if the line mi is an underground line; if the line is an overground line, marking the whole line; analyzing the turning and intersection point of each line m i, and if a planned but unopened line m j exists, marking P (m j); using a minimum bounding box algorithm, a minimum rectangular or polygonal area B is calculated that contains all paths P (m i), as follows:
Wherein, when calculating B, it is necessary to ensure that the path ranges overlap.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the data preprocessing module comprises the following contents: checking whether the image data has distortion condition or not, and performing geometric correction; analyzing the noise distribution condition of the image, and designing a filtering method to remove noise; adjusting the color balance of the image, carrying out histogram equalization and reducing the brightness influence; cutting, scaling and rotating the image, and adjusting the image to a uniform size; ordering and normalization are applied to map the image values to a fixed numerical range.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the steps for performing geometric correction are as follows: collecting a dataset containing various tilted and warped images, labeling the images, indicating the correct geometry or corrected image; designing a CNN model, wherein the input of the CNN model is an original distorted image, and the output is a correction parameter of the image; a loss function MSE is defined, the formula is as follows:
wherein Y i is the real parameter, Is the prediction parameter and n is the number of samples.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the data analysis module comprises the following contents: according to the track line characteristics, the distribution information of each line is statistically analyzed; establishing a flow prediction model by utilizing station distribution information and combining population distribution data to predict the passenger flow of each station in the future; analyzing characteristic changes of different years, judging the direction of a newly added line, and predicting the future development trend; research on the mutual influence relationship between rail transit and urban development; and (3) evaluating the influence of the newly added line on the whole track traffic network by applying a traffic assignments prediction model.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the characteristic changes of different years are analyzed, the direction of the newly added line is judged, and the future development trend is predicted, which comprises the following steps: collecting rail transit route map data of the city for the past 10 years; comparing the change of the line structure, analyzing the position distribution characteristics of the newly added line, comprising: overlapping and comparing the circuit diagrams in different years, marking the newly added circuit sections in the past year, analyzing the spatial distribution condition of the newly added circuit, and judging whether the circuit diagrams are concentrated in certain areas or not; calculating the direction distribution statistical characteristics of the newly added line; fitting a distribution function of the newly added line direction, and judging the main development direction; correcting a direction distribution function according to city development planning and population distribution prediction; based on the corrected direction distribution, sampling to generate possible newly added lines, and predicting future development trend.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the step of calculating the direction distribution statistical characteristics of the newly added line comprises the following steps: calculating a direction angle:
θi＝arctan2(Δyi,Δxi)
Wherein θ i is the direction angle of the i-th line segment; Δy i,Δxi is the coordinate difference of the line segment on the vertical and horizontal axes, respectively; calculating a main direction and variance:
S＝1-C
where N is the total number of line segments and C is the length of the resulting vector.
As a preferable scheme of the processing system of the urban rail transit remote sensing image data, the invention comprises the following steps: the step of fitting the distribution function of the new line direction and judging the main development direction is as follows: using the kernel density estimation formula:
Wherein, the kernel function K h generally selects Gaussian kernel, h is bandwidth; the correction direction distribution function includes: obtaining long-term development planning of cities and population distribution prediction data of the next 10 years, and adjusting f (theta), wherein correction factors are as follows:
H(θ)＝1-α.I(θ∈θrestricted)
adjusted density function:
f'(θ)＝H(θ).f(θ)
wherein alpha is a correction intensity parameter, between 0 and 1; i is an indication function, if the direction theta falls in the limiting area, the direction theta is 1, otherwise, the direction theta is 0; the calculation formula of population weight is:
W(θ)＝β.P(θ)
adjusted density function:
f”(θ)＝W(θ).f'(θ)
Wherein, beta is a population distribution density in the direction theta, and P (theta) is a population distribution density in the direction theta; combining the influence of the adjustment of the limited area of the urban development planning and population distribution to obtain a final line direction distribution function:
G(θ)＝f”(θ)
Wherein G (θ) is the final line direction distribution function.
The method has the beneficial effects that the method greatly improves the acquisition efficiency of urban rail transit system data, and fine space information can be rapidly acquired through remote sensing images; the digital degree of urban rail transit is greatly enriched, and the extraction of various key features provides a data basis for planning analysis; comprehensive and quantitative traffic prediction is provided, and support is provided for future demand assessment and route planning; the dynamic interrelation of the track traffic and the urban development can be studied in depth, so that the planning is more scientific; the method provides more intelligent decision support for track traffic construction, evaluates the advantages and disadvantages of different planning schemes, and promotes the effective utilization and deep mining analysis of multi-source heterogeneous data in the track traffic field.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a block diagram of a processing system for urban rail transit remote sensing image data in embodiment 1.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a processing system for urban rail transit remote sensing image data, which includes the following steps:
The system 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 data acquisition module transmits the acquired data to the data preprocessing module; the data preprocessing module sends the preprocessed data to the feature extraction module; the feature extraction module transmits the extracted feature data to the data analysis module; the data analysis module analysis results may be used for report generation or passed to a decision support module; the output of the decision support module is used for providing reports to relevant decision makers; the user interface module directly interacts with a user to acquire user input and display results processed 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, and the remote sensing images are usually from satellites, unmanned aerial vehicles or aerial photographs.
Specifically, judging an urban rail transit path, determining a range area in which images need to be collected, contacting a commercial satellite company, acquiring a high-resolution satellite image covering the area, performing detailed shooting in a key area by using an unmanned aerial vehicle, acquiring an unmanned aerial vehicle overlooking image, performing aerial shooting on the rail transit area, and acquiring an image of a bird's eye view; and uniformly cutting and splicing the multisource remote sensing images to construct an image dataset of the urban rail transit, and sending the image dataset to a data preprocessing module after processing.
Further, the process of determining the range area where the image needs to be collected is as follows:
Collecting track traffic route diagram data, wherein M= { M 1,m2,...,mn }, M represents a set of all track traffic routes, and M i represents an ith route; for each line m i, labeling its path range P (m i), these paths may be represented by a set of line segments, curves, or points; if the line m i is an underground line, marking the station position; if the line is an overground line, marking the whole line; for each line m i, analyze its turn and junction and adjust P (m i) to ensure integrity; if there is a planned but unopened route m j, then P is noted (m j).
Using a minimum bounding box algorithm, a minimum rectangular or polygonal area B is calculated that contains all paths P (m i), as follows:
And when calculating B, ensuring that the path ranges overlap so as to facilitate subsequent image stitching, wherein the finally determined spatial range B is the data area needing to collect the remote sensing image.
The data preprocessing module is used for preprocessing an original remote sensing image, including image correction, denoising, standardization and the like, so as to facilitate subsequent analysis.
Specifically, the data preprocessing module includes the following contents: checking whether the image data has distortion conditions such as inclination, local distortion and the like, and performing geometric correction; analyzing the noise distribution condition of the image, and designing a filtering method to remove noise; adjusting the color balance of the image, carrying out histogram equalization and reducing the brightness influence; cutting, scaling and rotating the image, and adjusting the image to a uniform size; applying ordering and normalization to map the image values to a fixed numerical range; the preprocessed image data is sent to a feature extraction module for subsequent analysis.
Further, the steps for performing the geometric correction are as follows:
Collecting a dataset containing various tilted and warped images, labeling the images, indicating the correct geometry or corrected image; designing a CNN model, wherein the input of the CNN model is an original distorted image, and the output is correction parameters of the image, such as a rotation angle, a distortion degree and the like; defining a loss function MSE:
wherein Y i is the real parameter, Is the prediction parameter and n is the number of samples.
The correction algorithm corrects the image using parameters of CNN prediction, for example, if the predicted output is a tilt angle, using affine transformation; model performance is evaluated on a separate test dataset, and model structure and training process are iteratively optimized according to performance results.
The steps of cropping, scaling and rotation transformation of the image are as follows: identifying key points in the image that represent salient features in the image, such as corner points, edges, or unique textures; generating a saliency map using the key points, wherein the saliency map can be generated by evaluating the density and distribution of the feature points, for example, enhancing the area around the feature points using a method such as Gaussian blur; analyzing the saliency map to determine key areas in the image, wherein the formula is as follows:
R＝argmaxx,yS(x,y)
Wherein S (x, y) is a saliency value of point (x, y) in the saliency map, and R is a determined key region; the cropping window is determined using a bounding box or a minimum closed area algorithm.
The feature extraction module comprises the following contents: detecting a line profile in an image by using a Canny edge detection algorithm; extracting a track line in the image by line combination analysis through Hough transformation; using a template matching technology and a preset station template to identify the station position in the image; the ground targets of different categories such as roads, buildings and the like are distinguished through a segmentation and classification algorithm; by means of deep learning technology such as convolutional neural network, intelligent recognition of various ground targets is achieved; and finally summarizing key features of the track, the station, the building and the like, and outputting a structured feature labeling result.
Preferably, using a template matching technique and a preset station template, identifying the station position in the image includes the following steps: selecting standard templates of stations, wherein the templates are selected to cover different station types and viewing angles so as to improve the identification universality and accuracy; preprocessing a template and an image to be analyzed; sliding a template on an image to be analyzed, and calculating the matching degree of the template and each position of the image, wherein the specific formula is as follows:
Wherein T is a template and F is an image; when the matching score exceeds a set threshold e, a station is considered found at that location, and once a match is found, the location of the matching area is recorded, which may be used for further analysis, such as the geographic location of the station, the relationship with other urban facilities, etc.
The data analysis module comprises the following contents: according to the track line characteristics, the length, intersection condition, coverage range and other distribution information of each line are statistically analyzed; establishing a flow prediction model by utilizing station distribution information and combining population distribution data to predict the passenger flow of each station in the future; analyzing characteristic changes of different years, judging the direction of a newly added line, and predicting the future development trend; research on the mutual influence relationship between rail transit and urban development; and (3) evaluating the influence of the newly added line on the whole track traffic network by applying a traffic assignments prediction model.
Specifically, by using station distribution information and combining population distribution data, a flow prediction model is established, and the prediction of the passenger flow of each station in the future comprises the following steps: collecting rail transit line graph data, and marking position coordinates of each station and adjacent stations; collecting thermodynamic diagram data of population distribution of the city, which represents population distribution densities of different areas; mapping the station position to a population distribution thermodynamic diagram, and counting population numbers in a service range as potential passenger flow of the station; taking historical passenger flow data as training samples, taking station positions, surrounding population and the like as characteristics, and establishing a regression model; for future newly built stations, the coordinate locations and service coverage population are input, and the model predicts the future passenger flow of the station.
Analyzing the characteristic changes of different years, judging the direction of the newly added line, and predicting the future development trend comprises the following steps: collecting rail transit route map data of the city for the past 10 years; comparing the change of the line structure, analyzing the position distribution characteristics of the newly added line, comprising: overlapping and comparing the circuit diagrams in different years, marking the newly added circuit sections in the past year, and analyzing whether the spatial distribution condition of the newly added circuit is concentrated in certain areas or not; calculating the direction distribution statistical characteristics of the newly added line; fitting a distribution function of the newly added line direction, and judging the main development direction; correcting a direction distribution function according to city development planning and population distribution prediction; based on the corrected direction distribution, sampling to generate possible newly added lines, and predicting future development trend.
Further, calculating the direction distribution statistical feature of the newly added line includes the following steps:
The formula for calculating the direction angle is as follows:
θi＝arctan2(Δyi,Δxi)
Wherein θ i is the direction angle of the i-th line segment; Δy i,Δxi is the coordinate difference of the line segment on the vertical and horizontal axes, respectively; calculating a main direction and variance:
The main direction formula:
S＝1-C
where N is the total number of line segments and C is the length of the resulting vector, used to calculate the variance.
Fitting a distribution function of the new line direction, and judging the main development direction as follows: the distribution of line directions can be better fitted and explained using the Kernel Density Estimation (KDE) method, with the following formula:
where kernel function K h typically selects a gaussian kernel, h is the bandwidth.
The correction of the direction distribution function comprises the following steps: acquiring long-term development planning of a city and population distribution prediction data of the next 10 years, adjusting f (theta), and correcting factors:
H(θ)＝1-α.I(θ∈θrestricted)
adjusted density function:
f'(θ)＝H(θ).f(θ)
Wherein alpha is a correction intensity parameter, between 0 and 1; i is an indication function, which is 1 if the direction θ falls within the limit region, and 0 otherwise.
The calculation formula of population weight is:
W(θ)＝β.P(θ)
adjusted density function:
f”(θ)＝W(θ).f'(θ)
Wherein, beta is a human mouth influence parameter used for adjusting the intensity of influence of population distribution on line direction distribution; p (θ) is population density in direction θ; combining the influence of the adjustment of the limited area of the urban development planning and population distribution, obtaining a comprehensively optimized line direction distribution function:
G(θ)＝f”(θ)
It should be noted that the final optimized density function will comprehensively consider city planning constraints, future population distribution predictions, and original route direction data to provide a more comprehensive and practical route direction distribution prediction.
The decision support module comprises the following contents: collecting various draft of urban development planning and rail transit construction planning; based on the flow prediction result, the demand coverage condition of each planning scheme is evaluated; the comprehensive effect of each planning scheme is evaluated by combining with the analysis of the rail transit network effect; and predicting the influence of each planning scheme through a dynamic causal model of rail transit and urban development.
The user interface module is used for providing an interface for users (such as city planners and traffic managers) to check analysis results and reports or input new inquiry requests.
The method comprises the following steps: providing a webpage interface, presenting data analysis results in the form of a map, a chart and the like, and enabling a user to select to view different analysis reports; providing a query input box, and enabling a user to input a new planning scheme or line to perform influence evaluation; the back end receives the new inquiry, carries out corresponding analysis, returns the result to the front end, and the user can derive an analysis report, a data table and the like.
The data storage and management module is used for storing all the collected original data, processed data and analysis results.
The method comprises the following steps: storing original various image data and preprocessed data; storing the extracted characteristic data by using a relational database, and establishing an index; storing intermediate result data of various spatial analyses by adopting a column database; and establishing a metadata catalog, and recording information such as data sources, processing flows and the like.
The embodiment also provides a computer device, which is suitable for the situation of a processing system of urban rail transit remote sensing image data, and comprises: a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the processing system of the urban rail transit remote sensing image data according to the embodiment.
The computer device may be a terminal comprising a processor, a memory, a communication interface, a display screen and input means connected by a system bus. Wherein the processor of the computer device is configured 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 computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The embodiment also provides a storage medium, on which a computer program is stored, which when executed implements a processing system for implementing urban rail transit remote sensing image data as proposed in the above embodiment; the storage medium may be implemented by any type or combination of volatile or nonvolatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
In conclusion, the method greatly improves the acquisition efficiency of urban rail transit system data, and fine space information can be rapidly acquired through remote sensing images; the digital degree of urban rail transit is greatly enriched, and the extraction of various key features provides a data basis for planning analysis; comprehensive and quantitative traffic prediction is provided, and support is provided for future demand assessment and route planning; the dynamic interrelation of the track traffic and the urban development can be studied in depth, so that the planning is more scientific; the method provides more intelligent decision support for track traffic construction, evaluates the advantages and disadvantages of different planning schemes, and promotes the effective utilization and deep mining analysis of multi-source heterogeneous data in the track traffic field.
Example 2
Referring to table 1, for the second embodiment of the present invention, experimental simulation data of a processing system of urban rail transit remote sensing image data is provided for further verifying the advancement of the present invention.
A city, 300 ten thousand population, 3 existing subway lines and 1 light rail line, 2 newly built subway lines are planned in the future 5 years.
And carrying out detailed flight shooting on the existing urban rail transit of the A city by using an unmanned aerial vehicle to obtain 5 ten thousand aerial images, obtaining an optical image with 1 meter resolution of the urban area of the A city from a commercial satellite, and collecting the data of the rail transit route map of the planning department in the past 10 years.
Processing unmanned aerial vehicle images by using Pix4D and other software to obtain point clouds, digital surface models and orthographic images; performing geometric correction and registration on the satellite images, and splicing the satellite images with the unmanned aerial vehicle images to construct a data set; identifying past and existing rail transit lines in the satellite image by using a convolutional neural network; and identifying station position information in the unmanned aerial vehicle image by using template matching.
And counting the length, intersection distribution and coverage information of the existing 4 track traffic lines, predicting the trend of the future newly-increased lines by utilizing the direction distribution characteristics of the newly-increased lines in the past 10 years, establishing a track traffic and urban development relation model, and analyzing an interaction mechanism.
Extracting path information of two new planning lines and predicting network flow change caused by the newly added lines; optimizing the positions and the number of the new line stations based on the flow prediction; and constructing a virtual digital twin city of the city A, and performing simulation test on the construction of a new line.
TABLE 1 comparison of the invention with the prior art
System index Prior Art The invention is that
Data acquisition mode Manual investigation Multisource remote sensing
Analytical techniques Static analysis Deep learning
Decision support mode Experience judgment Digital twin simulation
Results display Statistical report Three-dimensional visualization
Compared with the prior art, the table highlights the technical advantages of the invention in the aspects of acquiring multi-source heterogeneous data, adopting a front edge analysis technology, constructing digital twin, providing a three-dimensional interactive interface and the like, comprehensively improves the efficiency and quality of urban rail transit planning decisions, and shows remarkable technical progress.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.

Claims (8)

1. A processing system of urban rail transit remote sensing image data is characterized in that: comprising the following steps:
The system 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 data acquisition module is used for collecting remote sensing images of urban rail transit; the data preprocessing module is used for preprocessing an original remote sensing image; the feature extraction module is used for extracting features, and outputting structured feature labeling results according to final key features; the data analysis module is used for processing the image data; the decision support module is used for carrying out decision support; the user interface module is used for providing an interface for a user to check analysis results and report or input a new query request; the data storage and management module is used for storing all collected original data, processed data and analysis results;
The data acquisition module transmits acquired data to the data preprocessing module; the data preprocessing module sends preprocessed data to the feature extraction module; the feature extraction module transmits the extracted feature data to the data analysis module; the analysis result of the data analysis module is used for generating a report or transmitting the report to the decision support module; the output of the decision support module is used for providing reports to relevant decision makers; the user interface module directly interacts with a user, obtains user input and displays results processed by other modules; the data storage and management module provides data access and storage services for other modules.
2. The urban rail transit remote sensing image data processing system according to claim 1, wherein: the data acquisition module comprises:
Collecting track traffic route diagram data, wherein M= { M 1,m2,...,mn }, M represents a set of all track traffic routes, and mi represents an ith route; marking a path range P (m i) of each line mi, and marking a station position if the line m i is an underground line; if the line is an overground line, marking the whole line; analyzing the turning and intersection point of each line m i, and if a planned but unopened line m j exists, marking P (m j);
using a minimum bounding box algorithm, a minimum rectangular or polygonal area B is calculated that contains all paths P (m i), as follows:
Wherein, when calculating B, it is necessary to ensure that the path ranges overlap.
3. The processing system of urban rail transit remote sensing image data according to claim 2, wherein: the data preprocessing module comprises the following contents:
checking whether the image data has distortion condition or not, and performing geometric correction;
analyzing the noise distribution condition of the image, and designing a filtering method to remove noise;
Adjusting the color balance of the image, carrying out histogram equalization and reducing the brightness influence;
cutting, scaling and rotating the image, and adjusting the image to a uniform size;
Ordering and normalization are applied to map the image values to a fixed numerical range.
4. The urban rail transit remote sensing image data processing system according to claim 3, wherein: the steps for performing geometric correction are as follows:
collecting a dataset containing various tilted and warped images, labeling the images, indicating the correct geometry or corrected image;
designing a CNN model, wherein the input of the CNN model is an original distorted image, and the output is a correction parameter of the image; a loss function MSE is defined, the formula is as follows:
wherein Y i is the real parameter, Is the prediction parameter and n is the number of samples.
5. The urban rail transit remote sensing image data processing system according to claim 4, wherein: the data analysis module comprises the following contents:
According to the track line characteristics, the distribution information of each line is statistically analyzed;
Establishing a flow prediction model by utilizing station distribution information and combining population distribution data to predict the passenger flow of each station in the future;
Analyzing characteristic changes of different years, judging the direction of a newly added line, and predicting the future development trend;
research on the mutual influence relationship between rail transit and urban development;
and (3) evaluating the influence of the newly added line on the whole track traffic network by applying a traffic assignments prediction model.
6. The urban rail transit remote sensing image data processing system according to claim 5, wherein: the characteristic changes of different years are analyzed, the direction of the newly added line is judged, and the future development trend is predicted, which comprises the following steps:
collecting rail transit route map data of the city for the past 10 years;
Comparing the change of the line structure, analyzing the position distribution characteristics of the newly added line, comprising: overlapping and comparing the circuit diagrams in different years, marking the newly added circuit sections in the past year, analyzing the spatial distribution condition of the newly added circuit, and judging whether the circuit diagrams are concentrated in certain areas or not;
Calculating the direction distribution statistical characteristics of the newly added line;
fitting a distribution function of the newly added line direction, and judging the development direction;
Correcting a direction distribution function according to city development planning and population distribution prediction;
based on the corrected direction distribution, sampling to generate possible newly added lines, and predicting future development trend.
7. The urban rail transit remote sensing image data processing system according to claim 6, wherein: the step of calculating the direction distribution statistical characteristics of the newly added line comprises the following steps:
Calculating a direction angle:
θi＝arctan2(Δyi,Δxi)
wherein θ i is the direction angle of the i-th line segment; Δy i,Δxi is the coordinate difference of the line segment on the vertical and horizontal axes, respectively;
calculating a main direction and variance:
S＝1-C
where N is the total number of line segments and C is the length of the resulting vector.
8. The urban rail transit remote sensing image data processing system according to claim 7, wherein: the step of fitting the distribution function of the new line direction and judging the development direction is as follows:
Using the kernel density estimation formula:
Wherein, the kernel function K h generally selects Gaussian kernel, h is bandwidth;
the correction direction distribution function includes: obtaining long-term development planning of cities and population distribution prediction data of the next 10 years, and adjusting f (theta), wherein correction factors are as follows:
H(θ)＝1-α.I(θ∈θrestricted)
adjusted density function:
f'(θ)＝H(θ).f(θ)
wherein alpha is a correction intensity parameter, between 0 and 1; i is an indication function, if the direction theta falls in the limiting area, the direction theta is 1, otherwise, the direction theta is 0;
The calculation formula of population weight is:
W(θ)＝β.P(θ)
adjusted density function:
f”(θ)＝W(θ).f'(θ)
Wherein, beta is a population distribution density in the direction theta, and P (theta) is a population distribution density in the direction theta;
combining the influence of the adjustment of the limited area of the urban development planning and population distribution to obtain a final line direction distribution function:
G(θ)＝f”(θ)
Wherein G (θ) is the final line direction distribution function.
CN202410141960.3A 2024-01-31 2024-01-31 Processing system of urban rail transit remote sensing image data Withdrawn CN118115866A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410141960.3A CN118115866A (en) 2024-01-31 2024-01-31 Processing system of urban rail transit remote sensing image data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410141960.3A CN118115866A (en) 2024-01-31 2024-01-31 Processing system of urban rail transit remote sensing image data

Publications (1)

Publication Number Publication Date
CN118115866A true CN118115866A (en) 2024-05-31

Family

ID=91219013

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410141960.3A Withdrawn CN118115866A (en) 2024-01-31 2024-01-31 Processing system of urban rail transit remote sensing image data

Country Status (1)

Country Link
CN (1) CN118115866A (en)

Similar Documents

Publication Publication Date Title
US11797725B2 (en) Intelligent imagery
US11144795B2 (en) System and method for detecting features in aerial images using disparity mapping and segmentation techniques
US8878865B2 (en) Three-dimensional map system
US11392897B1 (en) Intelligent system and method for assessing structural damage using aerial imagery
US10964201B1 (en) Wildfire defender
Fathi et al. A videogrammetric as-built data collection method for digital fabrication of sheet metal roof panels
US20130051661A1 (en) Using Human Intelligence Tasks for Precise Image Analysis
CN113780270B (en) Target detection method and device
US20200334901A1 (en) Thresholds for change identification when comparing imagery
CN111476084A (en) Deep learning-based parking lot dynamic parking space condition identification method
CN118196671B (en) Hydraulic loop mapping data acquisition method and system based on geospatial information
Chen et al. UVLens: Urban village boundary identification and population estimation leveraging open government data
CN113420109B (en) Method for measuring permeability of street interface, computer and storage medium
CN114238541A (en) Sensitive target information acquisition method and device and computer equipment
CN117541594A (en) Double-non-maximum-suppression transverse wind ridging small target detection method and system
CN118115866A (en) Processing system of urban rail transit remote sensing image data
CN114114457B (en) Fracture characterization method, device and equipment based on multi-modal logging data
CN113033314A (en) Mobile scenic spot intelligent service system and service method for travel peak deployment
Touzani et al. Machine Learning for Automated Extraction of Building Geometry
Adi et al. iRodd (intelligent-road damage detection) for real-time infrastructure preservation in detection, classification, calculation, and visualization
Salama Neural Network Guided Variability Detection in Geospatial Data
Deng et al. Automatic Vision-Based Dump Truck Productivity Measurement Based on Deep-Learning Illumination Enhancement for Low-Visibility Harsh Construction Environment
Zhou et al. Development of the Database for Domestic System Interchanges
CN114022772A (en) Method, system, device and storage medium for predicting spatial distribution of mobile vendor
CN118691236A (en) Digital intelligent integrated system and management and control platform based on BIM technology

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20240531