WO2023116359A1 - 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质 - Google Patents

绿色、蓝色和灰色基础设施分类方法、装置、系统与介质 Download PDF

Info

Publication number
WO2023116359A1
WO2023116359A1 PCT/CN2022/134944 CN2022134944W WO2023116359A1 WO 2023116359 A1 WO2023116359 A1 WO 2023116359A1 CN 2022134944 W CN2022134944 W CN 2022134944W WO 2023116359 A1 WO2023116359 A1 WO 2023116359A1
Authority
WO
WIPO (PCT)
Prior art keywords
green
gray
blue
infrastructure
grid
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.)
Ceased
Application number
PCT/CN2022/134944
Other languages
English (en)
French (fr)
Inventor
刘俊国
贾金霖
崔文惠
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.)
Southern University of Science and Technology
Original Assignee
Southern University of Science and Technology
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 Southern University of Science and Technology filed Critical Southern University of Science and Technology
Priority to US18/556,730 priority Critical patent/US12608913B2/en
Publication of WO2023116359A1 publication Critical patent/WO2023116359A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Definitions

  • the present invention relates to the technical field of image processing, in particular to a green, blue and gray infrastructure classification method, device, system and medium.
  • the infrastructure in the city usually includes water bodies, trees, grasslands, bare land, buildings, roads, etc., and there are great differences in the utilization performance of rainwater by different infrastructures. Therefore, relevant urban planners need to assist the city in planning and construction according to the rainwater utilization performance of different types of infrastructure, but the existing methods for classifying urban infrastructure generally have problems of low accuracy and efficiency. How to improve the accuracy and efficiency of green, blue and gray infrastructure classification is an urgent problem to be solved.
  • the main purpose of the present invention is to propose a green, blue and gray infrastructure classification method, device, system and medium, aiming at solving the problem of how to improve the accuracy and efficiency of green, blue and gray infrastructure classification.
  • the present invention provides a green, blue and gray infrastructure classification method
  • the green, blue and gray infrastructure classification method includes the following steps:
  • a sample file is obtained based on the color orthophoto, and green, blue, and gray infrastructure classification results corresponding to the target area are obtained according to the target light band image set and the sample file.
  • the step of obtaining the target light band image set and the color orthomap includes:
  • the sample file includes a training sample and a verification sample
  • the step of obtaining the sample file based on the color orthomap includes:
  • the grid image in the color grid orthomap is offset to obtain the verification sample.
  • the step of obtaining the green, blue and gray infrastructure classification results corresponding to the target area includes:
  • the step of determining green, blue and gray infrastructure classification results includes:
  • the green, blue, and gray infrastructure pre-classification results are determined as the green, blue, and gray infrastructure classification results
  • preset processing is performed on the grid image and the target light band image set to obtain an optimal grid image and an optimal target light Band images are collected, and a step is performed: overlapping the grid image and the color orthomap to obtain a color grid orthomap.
  • the step of performing preset processing on the grid image and the target light band image set to obtain the optimal grid image and the optimal target light band image set includes:
  • a sample file is obtained based on the color grid orthomap, and according to the target light band image set and the sample file, the green, blue and gray infrastructure classification results corresponding to the target area are obtained After the step, the green, blue and gray infrastructure classification method also includes:
  • a classification map corresponding to the target area is generated, and according to the classification map, rainwater utilization analysis data corresponding to the target area is provided.
  • the present invention also provides a green, blue and gray infrastructure classification device, the green, blue and gray infrastructure classification device includes:
  • An acquisition module configured to acquire a multispectral photo corresponding to the target area, and obtain a set of target light band images and a color orthographic map based on the multispectral photo;
  • the classification module is configured to obtain a sample file based on the color orthophoto, and obtain green, blue and gray infrastructure classification results corresponding to the target area according to the target light band image set and the sample file.
  • the acquisition module also includes a two-dimensional reconstruction module, and the two-dimensional reconstruction module is used for:
  • the classification module also includes a generation module, and the generation module is used for:
  • the grid image in the color grid orthomap is offset to obtain the verification sample.
  • classification module is also used for:
  • classification module is also used for:
  • the green, blue, and gray infrastructure pre-classification results are determined as the green, blue, and gray infrastructure classification results
  • preset processing is performed on the grid image and the target light band image set to obtain an optimal grid image and an optimal target light Band images are collected, and a step is performed: overlapping the grid image and the color orthomap to obtain a color grid orthomap.
  • classification module also includes an optimization module, and the optimization module is used for:
  • classification module also includes an analysis module, and the analysis module is used for:
  • a classification map corresponding to the target area is generated, and according to the classification map, rainwater utilization analysis data corresponding to the target area is provided.
  • the present invention also provides a green, blue and gray infrastructure classification system
  • the green, blue and gray infrastructure classification system includes: a memory, a processor and stored in the memory and a green, blue and gray infrastructure classification program operable on said processor, said green, blue and gray infrastructure classification program being executed by said processor to implement green, blue and gray as described above Steps in an infrastructure taxonomy approach.
  • the present invention also provides a medium, the medium is a computer-readable storage medium, and the computer-readable storage medium stores green, blue and gray infrastructure classification programs, and the green, blue and gray infrastructure classification programs are stored on the computer-readable storage medium.
  • the blue and gray infrastructure classification program is executed by the processor, the steps of the above green, blue and gray infrastructure classification method are implemented.
  • the green, blue and gray infrastructure classification method proposed by the present invention obtains the multi-spectral photos corresponding to the target area, and based on the multi-spectral photos, obtains a target light band image set and a color orthomap; based on the color ortho , to obtain a sample file, and according to the target light band image set and the sample file, obtain the green, blue, and gray infrastructure classification results corresponding to the target area.
  • the present invention obtains a set of target light band images and a color orthomap, and combines the sample files obtained based on the color orthomap and the set of target light band images to obtain the green and blue colors corresponding to the target area. and gray infrastructure classification results, improving the accuracy and efficiency of green, blue and gray infrastructure classification.
  • Fig. 1 is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present invention
  • Fig. 2 is a schematic flow chart of the first embodiment of the green, blue and gray infrastructure classification method of the present invention
  • FIG. 1 is a schematic diagram of the equipment structure of the hardware operating environment involved in the solution of the embodiment of the present invention.
  • the device in this embodiment of the present invention may be a PC or a server device.
  • the device may include: a processor 1001 , such as a CPU, a network interface 1004 , a user interface 1003 , a memory 1005 , and a communication bus 1002 .
  • the communication bus 1002 is used to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory.
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
  • FIG. 1 does not constitute a limitation to the device, and may include more or less components than shown in the figure, or combine some components, or arrange different components.
  • the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and green, blue, and gray infrastructure classification programs.
  • the operating system is a program that manages and controls portable green, blue and gray infrastructure classification equipment and software resources, supports network communication modules, user interface modules, green, blue and gray infrastructure classification programs, and other programs or software Running; the network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.
  • the green, blue and gray infrastructure classification device calls the green, blue and gray infrastructure classification program stored in the memory 1005 through the processor 1001 , and perform operations in each embodiment of the following green, blue and gray infrastructure classification methods.
  • FIG. 2 is a schematic flowchart of the first embodiment of the green, blue and gray infrastructure classification method of the present invention, and the method includes:
  • Step S10 obtaining the multispectral photo corresponding to the target area, and based on the multispectral photo, obtaining a target light band image set and a color orthographic map;
  • step S20 a sample file is obtained based on the color orthophoto, and green, blue, and gray infrastructure classification results corresponding to the target area are obtained according to the target light band image set and the sample file.
  • the green, blue and gray infrastructure classification method of this embodiment is applied to the green, blue and gray infrastructure classification equipment of urban planning agencies, and the green, blue and gray infrastructure classification equipment can be terminals or PC equipment, for description
  • the green, blue, and gray infrastructure classification equipment is used as an example to describe; the green, blue, and gray infrastructure classification equipment obtains the multispectral photos corresponding to the target area, and performs two-dimensional reconstruction operations on the multispectral photos, and according to After two-dimensional reconstruction of multi-spectral photos and preset resolutions, a collection of target light band images and color orthomaps are obtained; green, blue and gray infrastructure classification equipment generates grid images according to preset grid spacing, and Overlay the grid image and the color orthomap to obtain the color grid orthomap; the green, blue and gray infrastructure classification equipment recognizes the grid point attributes corresponding to each grid point in the color grid orthomap, and according to The grid point attribute obtains the training sample, and then offsets the grid image in the color grid orthophoto map to obtain the verification sample; the green, blue and gray infrastructure classification equipment classifies
  • sample files include training samples and verification samples; the types of infrastructure have been set by relevant R&D personnel into seven categories, including water bodies, trees and shrubs, grasslands, green roofs, bare land, buildings, and roads, among which water bodies are blue Trees and shrubs, grasslands, green roofs, and bare land are green infrastructure, and buildings and roads are gray infrastructure.
  • the green, blue and gray infrastructure classification method of this embodiment obtains the multispectral photos corresponding to the target area, and based on the multispectral photos, obtains the target light band image set and the color orthomap; based on the color orthomap, the sample files, and according to the target light band image collection and sample files, the green, blue and gray infrastructure classification results corresponding to the target area are obtained.
  • the present invention obtains a target light band image set and a color orthomap, and combines the sample files obtained based on the color orthomap and the target light band image set to obtain the green and blue colors corresponding to the target area. and gray infrastructure classification results, improving the accuracy and efficiency of green, blue and gray infrastructure classification.
  • Step S10 obtaining the multispectral photo corresponding to the target area, and based on the multispectral photo, obtaining a target light band image set and a color orthographic map;
  • the green, blue and gray infrastructure classification equipment uses a drone with the function of taking multi-spectral photos to shoot the target area under suitable weather conditions to obtain multi-spectral photos corresponding to the target area, And based on the multi-spectral photos, a collection of target light band images and color orthographs are obtained; for example, relevant researchers determine the target area to be studied according to the actual situation, and fly to the distance target by a drone with the function of taking multi-spectral photos.
  • the ground of the area is above the preset height, and the target area is photographed, and the multispectral photos corresponding to the target area taken by the drone are sent to the green, blue, and gray infrastructure classification equipment, and the green, blue, and gray bases
  • the facility classification equipment obtains the multispectral photos corresponding to the target area, based on the multispectral photos, the target light band image set and the color orthomap corresponding to the target area are obtained.
  • the multispectral photos refer to the Photographs, sometimes with only 3 bands (such as a color image), but sometimes contain many more bands, even hundreds, each band being a grayscale image that represents the The brightness of the scene obtained by the sensitivity, in the multispectral photo, each pixel is related to a numerical string of pixels in different bands, that is, a vector;
  • the target light band image collection includes: blue light band images, green light band images, Red light band images, red edge light band images, near-infrared light band images, NDVI images and DSM images, among which, NDVI images are images for detecting vegetation growth status, vegetation coverage and eliminating some radiation errors, etc.
  • DSM Digital Surface Model , Digital Surface Model
  • DSM image refers to the digital surface model image;
  • the color orthophoto map refers to the color image of the target area taken by the drone from above top view.
  • step S10 includes:
  • Step a performing a two-dimensional reconstruction operation on the multi-spectral photo, and obtaining a target light band image set and a color orthographic map based on the multi-spectral photo after the two-dimensional reconstruction operation and a preset resolution.
  • the green, blue, and gray infrastructure classification devices perform two-dimensional reconstruction operations on the obtained multispectral photos corresponding to the target area, and obtain the target A collection of light band images and color orthographic maps, where the preset resolution can be 6cm, 6.5cm, 8cm or 10cm, etc.
  • relevant researchers set the preset resolution to 6cm, green, blue and gray infrastructure
  • the classification equipment inputs the multi-spectral photos corresponding to the target area into DJI Terra or similar image stitching software, performs two-dimensional reconstruction operations on the multi-spectral photos, and obtains blue-light band images, green-light band images, and red-light band images with a resolution of 6cm. images, red-edge light band images, near-infrared light band images, NDVI images, DSM images and color orthomaps.
  • step S20 a sample file is obtained based on the color orthophoto, and green, blue, and gray infrastructure classification results corresponding to the target area are obtained according to the target light band image set and the sample file.
  • the green, blue and gray infrastructure classification equipment is based on the color orthomap
  • the sample file is obtained through eCognition software and Arc GIS software, and the blue light band image and the green light band image are selected from the target light band image collection.
  • Image, red band image, red edge band image, near-infrared band image, NDVI image, DSM image, one or more images are combined, and combined with the sample file, the green, blue and gray corresponding to the target area are obtained Infrastructure classification results.
  • eCognition is an intelligent image analysis software, which adopts an object-oriented information extraction method and can make full use of object information (color tone, shape, texture, level) and inter-class information (comparison with adjacent objects, child objects, and parent objects). relevant features) for analysis
  • Arc GIS software is a software that can be used to collect, organize, manage, analyze, communicate and publish geographic information
  • sample files include training samples and verification samples.
  • step S20 also includes:
  • Step b generating a grid image according to a preset grid spacing, and overlapping the grid image with the colored orthomap to obtain a colored grid orthomap;
  • the green, blue and gray infrastructure classification equipment generates a grid image through the eCognition software according to the preset grid spacing, and overlaps the grid image with the color orthomap corresponding to the target area to obtain a color grid grid orthophoto; for example, relevant researchers set the sampling interval to 11.6 meters based on experience, and based on the corresponding size of the grid image to be generated, the sampling interval is proportionally reduced to obtain the preset grid spacing, green, blue and
  • the gray infrastructure classification equipment generates a grid image through the eCognition software according to the preset grid spacing, and overlays the grid image on the surface of the color orthomap, so that the grid image and the color orthomap overlap to obtain a color grid orthophoto It can be understood that the grid image is overlaid on the surface of the color orthomap to obtain the color grid orthomap, the surface of the color grid orthomap has a grid, and each grid point on the grid will correspond to the color Different infrastructure on grid orthomaps.
  • Step c identifying the grid point attribute corresponding to each grid point in the color grid orthophoto, and obtaining the training sample according to the grid point attribute;
  • the grid point corresponding to each grid point corresponding to the grid in the color grid orthomap is analyzed by Arc GIS software. Attributes are identified, and training samples are obtained according to the grid point attributes corresponding to each grid point; it can be understood that a grid point refers to the intersection point formed by the intersection of two line segments in the grid, and each grid point in the color grid orthograph The points will correspond to different infrastructures on the color grid orthophoto map.
  • the grid point attribute is the type of infrastructure corresponding to the grid point. There are seven types of green roofs, bare land, buildings, and roads, among which water bodies are blue infrastructures, trees and shrubs, grasslands, green roofs, and bare lands are green infrastructures, and buildings and roads are gray infrastructures.
  • Step d offsetting the grid image in the color grid orthophoto map to obtain the verification sample.
  • the green, blue, and gray infrastructure classification devices offset the grids in the color grid orthophoto, specifically, the overall grid can be moved up, down, left, right, Offset in the upper left, upper right, etc., so that the grid point attribute corresponding to each grid point in the grid is different from the grid point attribute corresponding to each grid point in the training sample, and then the verification sample is obtained, for example: green, blue
  • the colored and gray infrastructure classification equipment shifts the grid in the color grid orthophoto downward by a preset grid spacing, and identifies the grid attribute corresponding to each grid point after the offset, and then obtains the corresponding verification
  • the sample optionally, can offset the entire grid in the color grid orthophoto map in multiple directions, so as to obtain multiple verification samples.
  • Step e performing segmentation operation on the set of target optical band images according to spectral similarity to obtain shape objects, and calculating green , blue and gray infrastructure pre-classification results;
  • the green, blue and gray infrastructure classification equipment performs segmentation operations on the target light band image set through eCognition software, according to the blue light band image, green light band image, red light band image, Based on the numerical similarity of the red-edge light band images, near-infrared light band images, NDVI images, and DSM images, the shape objects are segmented, and the grid point attributes in the training samples in the sample file are assigned to each shape object, and then randomly Algorithms such as forest, fuzzy classification and Bayesian algorithm, calculate the attribute value of other shape objects without attributes, and obtain the green, blue and gray infrastructure pre-classification results;
  • Algorithms such as forest, fuzzy classification and Bayesian algorithm
  • Step f Perform accuracy evaluation on the green, blue and gray infrastructure pre-classification results based on the verification sample in the sample file, obtain the accuracy evaluation result, and determine the green and blue infrastructure based on the accuracy evaluation result. and gray infrastructure classification results.
  • the green, blue and gray infrastructure classification equipment evaluates the accuracy of the green, blue and gray infrastructure pre-classification results based on the grid point attributes corresponding to each grid point in the verification sample in the sample file, and obtains Accuracy evaluation results, and based on the accuracy evaluation results, determine green, blue and gray infrastructure classification results.
  • the step of determining green, blue and gray infrastructure classification results includes:
  • Step f1 comparing the accuracy evaluation result with the preset accuracy to obtain the comparison result
  • the green, blue and gray infrastructure classification equipment compares the accuracy evaluation results with the preset accuracy to obtain the comparison results.
  • the relevant researchers set the preset accuracy to 0.8 according to the actual situation.
  • the accuracy evaluation result of the green, blue, and gray infrastructure pre-classification results obtained by the green and gray infrastructure classification equipment is 0.7, and the comparison result obtained by comparing the accuracy evaluation result with the preset accuracy is that the accuracy evaluation result is less than the preset accuracy. If the accuracy evaluation result of the green, blue, and gray infrastructure pre-classification results obtained by the green, blue, and gray infrastructure classification equipment is 0.85, the comparison result obtained by comparing the accuracy evaluation result with the preset accuracy is that the accuracy evaluation result is not good. Less than the preset precision.
  • Step f2 if the comparison result is that the accuracy evaluation result is not less than the preset accuracy, then determine the green, blue and gray infrastructure pre-classification result as the green, blue and gray infrastructure classification result;
  • the green, blue and gray infrastructure pre-classification results are determined as green, blue and gray Infrastructure classification results, and use the green, blue and gray infrastructure classification results to provide stormwater utilization analysis data corresponding to the target area.
  • Step f3 if the comparison result is that the accuracy evaluation result is less than the preset accuracy, perform preset processing on the grid image and the target optical band image set to obtain the optimal grid image and the optimal
  • the optimal target light band images are collected, and a step is performed: overlapping the grid image and the color orthomap to obtain a color grid orthomap.
  • this step if the comparison result of the green, blue and gray infrastructure classification equipment is that the accuracy evaluation result is less than the preset accuracy, preset processing is performed on the grid image and the target light band image set to obtain the optimal grid
  • the image and the optimal target light band image are collected, and the grid image is overlapped with the color orthomap to obtain the color grid orthomap and subsequent steps, until the obtained green, blue and gray infrastructure pre-classification results correspond to The precision is no less than the preset precision.
  • step of performing preset processing on the grid image and the target light band image set to obtain the optimal grid image and the optimal target light band image set includes:
  • the green, blue and gray infrastructure classification devices perform scaling operations on the grid spacing corresponding to the grid image to obtain a first preset number of grid images, and respectively Perform the first preset operation on each grid image to obtain the optimal grid image, such as: green, blue and gray infrastructure classification equipment can perform grid spacing corresponding to the grid image according to the preset grid spacing Scaling operation to obtain the first preset number of grid images, optionally, green, blue and gray infrastructure classification devices correspond to the grid images on the basis of the preset grid spacing according to the instructions of relevant researchers The grid spacing is increased or decreased, and the grid spacing is increased or decreased once, and the corresponding grid image is obtained, and finally the first preset number of grid images is obtained and then stopped.
  • green, blue and gray infrastructure classification devices perform scaling operations on the grid spacing corresponding to the grid image to obtain a first preset number of grid images, and respectively Perform the first preset operation on each grid image to obtain the optimal grid image, such as: green, blue and gray infrastructure classification equipment can perform grid spacing corresponding to the grid image according to the preset grid spacing Scaling
  • the green, blue and gray infrastructure classification equipment can intelligently set the first preset number, and intelligently increase or decrease the grid spacing corresponding to the grid image on the basis of the preset grid spacing. Zoom out to end up with a grid image of the first preset amount.
  • the green, blue and gray infrastructure classification devices After obtaining the first preset number of grid images, the green, blue and gray infrastructure classification devices perform a first preset operation on each grid image, that is, perform a combination of grid images and The color orthomaps are overlapped to obtain the color grid orthomaps and the subsequent steps, and the accuracy evaluation results corresponding to the green, blue and gray infrastructure pre-classification results corresponding to each grid image are obtained, and then each The accuracy evaluation result corresponding to the grid image is compared with the preset accuracy, and the grid image corresponding to the accuracy evaluation result not less than the preset accuracy is selected, and the grid image corresponding to the accuracy evaluation result not less than the preset accuracy is selected.
  • the grid image with the largest grid spacing is selected as the optimal grid image.
  • the green, blue, and gray infrastructure classification devices perform addition and subtraction operations on the target light band images in the target light band image set to obtain a second preset number of target light band image sets, based on the optimal network
  • the second preset operation is performed on each target light band image set for each grid image, so as to obtain the optimal target light band image set.
  • green, blue and gray infrastructure classification equipment performs increase and decrease operations on target light band images in the target light band image set to obtain a second preset number of target light band image sets, optionally, green, blue
  • the color and gray infrastructure classification equipment increases or decreases the target light band images in the target light band image set according to the instructions of the relevant researchers, and finally obtains the second preset number of target light band image sets and then stops.
  • the green, blue and gray infrastructure classification equipment can intelligently set the second preset number, and intelligently increase or decrease the target light band images in the target light band image collection, and finally obtain the second preset number.
  • the target light band image collection may include: blue light band images, green light band images, NDVI images, and DSM images, may include blue light band images, green light band images, red light band images, NDVI images, and DSM images. It may include blue-light band images, green-light band images, red-light band images, near-infrared light band images, NDVI images, DSM images, etc.
  • the green, blue and gray infrastructure classification equipment obtains training samples and verification samples based on the optimal grid image and the color orthomap corresponding to the target area, and respectively performs The second preset operation, that is, to perform a segmentation operation on each target light band image set in the second preset number of target light band image sets to obtain a shape object, and according to the training samples and shape objects in the sample file , calculate the green, blue and gray infrastructure pre-classification results and the subsequent steps to obtain the accuracy evaluation results corresponding to the green, blue and gray infrastructure pre-classification results corresponding to each target light band image set, and in the accuracy
  • the target light band image set with the highest accuracy evaluation is selected from each target light band image set whose evaluation result is not less than the preset precision, and is used as the optimal target light band image set.
  • the green, blue and gray infrastructure classification equipment obtains the multispectral photos corresponding to the target area, and performs two-dimensional reconstruction operations on the multispectral photos, and according to the two-dimensional Reconstruct the multi-spectral photos and preset resolutions to obtain the target light band image collection and color orthomap; the green, blue and gray infrastructure classification equipment generates grid images according to the preset grid spacing, and the grid The image is overlaid with the color orthomap to obtain the color grid orthomap; the green, blue and gray infrastructure classification equipment recognizes the grid point attribute corresponding to each grid point in the color grid orthomap, and according to the grid point attribute Obtain the training sample, and then offset the grid image in the color grid orthophoto to obtain the verification sample; the green, blue and gray infrastructure classification equipment performs segmentation operation on the target light band image set to obtain the shape object, And according to the grid point attributes and shape objects in the training samples in the sample file, the green, blue and gray infrastructure pre-classification results are calculated, and then based on the
  • the difference between the second embodiment of the green, blue and gray infrastructure classification method and the first embodiment of the green, blue and gray infrastructure classification method is that after step S20, the green, blue and gray infrastructure classification method also includes:
  • Step g Generate a classification map corresponding to the target area according to the green, blue and gray infrastructure classification results, and provide rainwater utilization analysis data corresponding to the target area according to the classification map.
  • the green, blue and gray infrastructure classification equipment is based on the grid images corresponding to the preset grid spacing and the blue light band image, the green light band image, the red light band image, the red edge light band image, the near
  • the green, blue and gray infrastructure classification results obtained from the target light band image set composed of infrared light band images, NDVI images, and DSM images or the green, blue and gray infrastructure classification results to generate a classification map corresponding to the target area.
  • the classification map includes: water bodies, trees and shrubs, grasslands, green roofs, bare land, buildings, roads, these seven types of infrastructure types in target areas, and according to The classification map provides the rainwater utilization analysis data corresponding to the target area.
  • the green, blue and gray infrastructure classification device in this embodiment generates a classification map corresponding to the target region according to the finally obtained green, blue and gray infrastructure classification results of the target region, and the classification map includes: water bodies, trees and According to the classification map, provide the rainwater utilization analysis data corresponding to the target area, so that the green, blue and gray infrastructure classification results can be Provide data for stormwater utilization analysis in the target area.
  • Green, blue and gray infrastructure classification devices of the present invention include:
  • An acquisition module configured to acquire a multispectral photo corresponding to the target area, and obtain a set of target light band images and a color orthographic map based on the multispectral photo;
  • the classification module is configured to obtain a sample file based on the color orthophoto, and obtain green, blue and gray infrastructure classification results corresponding to the target area according to the target light band image set and the sample file. Further, the acquisition module also includes a two-dimensional reconstruction module, and the two-dimensional reconstruction module is used for:
  • the classification module also includes a generation module, and the generation module is used for:
  • the grid image in the color grid orthomap is offset to obtain the verification sample.
  • classification module is also used for:
  • classification module is also used for:
  • the green, blue, and gray infrastructure pre-classification results are determined as the green, blue, and gray infrastructure classification results
  • preset processing is performed on the grid image and the target light band image set to obtain an optimal grid image and an optimal target light Band images are collected, and a step is performed: overlapping the grid image and the color orthomap to obtain a color grid orthomap.
  • classification module also includes an optimization module, and the optimization module is used for:
  • classification module also includes an analysis module, and the analysis module is used for:
  • a classification map corresponding to the target area is generated, and according to the classification map, rainwater utilization analysis data corresponding to the target area is provided.
  • the invention also provides a medium.
  • the medium of the present invention is a computer-readable storage medium, and green, blue and gray infrastructure classification programs are stored on the computer-readable storage medium.
  • green, blue and gray infrastructure classification programs are executed by a processor, the above-mentioned steps in the green, blue and gray infrastructure taxonomy.
  • the method implemented when the green, blue and gray infrastructure classification program running on the processor is executed can refer to the various embodiments of the green, blue and gray infrastructure classification method of the present invention, which will not be repeated here. .
  • the term “comprises”, “comprises” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present invention can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM) , magnetic disk, optical disk), including several instructions to enable a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

本发明公开了一种绿色、蓝色和灰色基础设施分类方法、装置、系统和介质，该方法包括：获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。本发明根据目标区域对应的多光谱照片，得到目标光波段图像集合以及彩色正射图，并结合基于彩色正射图得到的样本文件以及目标光波段图像集合，得到目标区域对应的绿色、蓝色和灰色基础设施分类结果，提高了绿色、蓝色和灰色基础设施分类的准确度和效率。

Description

绿色、蓝色和灰色基础设施分类方法、装置、系统与介质 技术领域
本发明涉及影像处理技术领域，尤其涉及绿色、蓝色和灰色基础设施分类方法、装置、系统与介质。
背景技术
目前，随着城市的不断发展，城市中的基础设施通常包含有水体、树木、草地、裸地、建筑、道路等，不同的基础设施对雨水的利用性能存在较大差异。因此，相关城市规划人员需要根据不同类型的基础设施的雨水利用性能，辅助城市进行规划建设，而现有的对城市中的基础设施进行分类的方法普遍存在准确度和效率较低的问题。如何提高绿色、蓝色和灰色基础设施分类的准确度和效率，是急需解决的问题。
发明内容
本发明的主要目的在于提出一种绿色、蓝色和灰色基础设施分类方法、装置、系统与介质，旨在解决如何提高绿色、蓝色和灰色基础设施分类的准确度和效率的问题。
为实现上述目的，本发明提供一种绿色、蓝色和灰色基础设施分类方法，所述绿色、蓝色和灰色基础设施分类方法包括如下步骤：
获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
优选地，基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图的步骤包括：
对所述多光谱照片进行二维重建操作，并根据经过所述二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图。
优选地，样本文件包括训练样本和验证样本，所述基于所述彩色正射图，得到样本文件的步骤包括：
根据预设网格间距，生成网格图像，并将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图；
识别所述彩色网格正射图中每个格点对应的格点属性，并根据所述格点属性得到所述 训练样本；
将所述彩色网格正射图中的网格图像进行偏移，以得到所述验证样本。
优选地，根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果的步骤包括：
依据光谱相似性对所述目标光波段图像集合进行分割操作，得到形状对象，并根据所述样本文件中的所述训练样本和对应的所述形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果；
基于所述样本文件中的所述验证样本对所述绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
优选地，基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果的步骤包括：
将所述精度评价结果与预设精度进行对比，得到对比结果；
若所述对比结果为所述精度评价结果不小于所述预设精度，则将所述绿色、蓝色和灰色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果；
若所述对比结果为所述精度评价结果小于所述预设精度，则对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行步骤：将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图。
优选地，对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合的步骤包括：
对所述网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对每个网格图像进行第一预设操作，以得到最优网格图像；
对所述目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于所述最优网格图像分别对每个目标光波段图像集合进行第二预设操作，以得到最优目标光波段图像集合。
优选地，基于所述彩色网格正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果的步骤之后，所述绿色、蓝色和灰色基础设施分类方法还包括：
根据所述绿色、蓝色和灰色基础设施分类结果，生成所述目标区域对应的分类地图，并根据所述分类地图，提供所述目标区域对应的雨水利用分析数据。
此外，为实现上述目的，本发明还提供一种绿色、蓝色和灰色基础设施分类装置，所述绿色、蓝色和灰色基础设施分类装置包括：
获取模块，用于获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
分类模块，用于基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
进一步地，所述获取模块还包括二维重建模块，所述二维重建模块用于：
对所述多光谱照片进行二维重建操作，并根据经过所述二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图。进一步地，所述分类模块还包括生成模块，所述生成模块用于：
根据预设网格间距，生成网格图像，并将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图；
识别所述彩色网格正射图中每个格点对应的格点属性，并根据所述格点属性得到所述训练样本；
将所述彩色网格正射图中的网格图像进行偏移，以得到所述验证样本。
进一步地，所述分类模块还用于：
依据光谱相似性对所述目标光波段图像集合进行分割操作，得到形状对象，并根据所述样本文件中的所述训练样本和对应的所述形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果；
基于所述样本文件中的所述验证样本对所述绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
进一步地，所述分类模块还用于：
将所述精度评价结果与预设精度进行对比，得到对比结果；
若所述对比结果为所述精度评价结果不小于所述预设精度，则将所述绿色、蓝色和灰色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果；
若所述对比结果为所述精度评价结果小于所述预设精度，则对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行步骤：将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图。
进一步地，所述分类模块还包括优化模块，所述优化模块用于：
对所述网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对每个网格图像进行第一预设操作，以得到最优网格图像；
对所述目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于所述最优网格图像分别对每个目标光波段图像集合进行第二预设操作，以得到最优目标光波段图像集合。
进一步地，所述分类模块还包括分析模块，所述分析模块用于：
根据所述绿色、蓝色和灰色基础设施分类结果，生成所述目标区域对应的分类地图，并根据所述分类地图，提供所述目标区域对应的雨水利用分析数据。
此外，为实现上述目的，本发明还提供一种绿色、蓝色和灰色基础设施分类系统，所述绿色、蓝色和灰色基础设施分类系统包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的绿色、蓝色和灰色基础设施分类程序，所述绿色、蓝色和灰色基础设施分类程序被所述处理器执行时实现如上所述的绿色、蓝色和灰色基础设施分类方法的步骤。
此外，为实现上述目的，本发明还提供一种介质，所述介质为计算机可读存储介质，所述计算机可读存储介质上存储有绿色、蓝色和灰色基础设施分类程序，所述绿色、蓝色和灰色基础设施分类程序被处理器执行时实现如上所述的绿色、蓝色和灰色基础设施分类方法的步骤。
本发明提出的绿色、蓝色和灰色基础设施分类方法，获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。本发明根据目标区域对应的多光谱照片，得到目标光波段图像集合以及彩色正射图，并结合基于彩色正射图得到的样本文件以及目标光波段图像集合，得到目标区域对应的绿色、蓝色和灰色基础设施分类结果，提高了绿色、蓝色和灰色基础设施分类的准确度和效率。
附图说明
图1是本发明实施例方案涉及的硬件运行环境的设备结构示意图；
图2为本发明绿色、蓝色和灰色基础设施分类方法第一实施例的流程示意图；
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
如图1所示，图1是本发明实施例方案涉及的硬件运行环境的设备结构示意图。
本发明实施例设备可以是PC机或服务器设备。
如图1所示，该设备可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器，也可以是稳定的存储器(non-volatile memory)，例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的设备结构并不构成对设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及绿色、蓝色和灰色基础设施分类程序。
其中，操作系统是管理和控制便携绿色、蓝色和灰色基础设施分类设备与软件资源的程序，支持网络通信模块、用户接口模块、绿色、蓝色和灰色基础设施分类程序以及其他程序或软件的运行；网络通信模块用于管理和控制网络接口1004；用户接口模块用于管理和控制用户接口1003。
在图1所示的绿色、蓝色和灰色基础设施分类设备中，所述绿色、蓝色和灰色基础设施分类设备通过处理器1001调用存储器1005中存储的绿色、蓝色和灰色基础设施分类程序，并执行下述绿色、蓝色和灰色基础设施分类方法各个实施例中的操作。
基于上述硬件结构，提出本发明绿色、蓝色和灰色基础设施分类方法实施例。
参照图2，图2为本发明绿色、蓝色和灰色基础设施分类方法第一实施例的流程示意图，所述方法包括：
步骤S10，获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
步骤S20，基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
本实施例绿色、蓝色和灰色基础设施分类方法运用于城市规划机构的绿色、蓝色和灰色基础设施分类设备中，绿色、蓝色和灰色基础设施分类设备可以为终端或PC设备，为 描述方便，以绿色、蓝色和灰色基础设施分类设备为例进行描述；绿色、蓝色和灰色基础设施分类设备获取目标区域对应的多光谱照片，并对多光谱照片进行二维重建操作，并根据经过二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图；绿色、蓝色和灰色基础设施分类设备根据预设网格间距，生成网格图像，并将网格图像与彩色正射图进行重叠，得到彩色网格正射图；绿色、蓝色和灰色基础设施分类设备识别彩色网格正射图中每个格点对应的格点属性，并根据格点属性得到训练样本，再将彩色网格正射图中的网格图像进行偏移，以得到所述验证样本；绿色、蓝色和灰色基础设施分类设备根据光谱相似性对目标光波段图像集合进行分割操作，得到形状对象，并根据样本文件中的训练样本中的格点属性和对应的形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果，再基于绿色、蓝色和灰色基础设施预分类结果与样本文件中的验证样本进行精度评价，得到精度评价结果，并基于精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。需要说明的是，样本文件包括训练样本以及验证样本；基础设施的类型有相关研发人员设定为水体、树木及灌木、草地、绿色屋顶、裸地、建筑、道路等七类，其中水体为蓝色基础设施，树木及灌木、草地、绿色屋顶、裸地为绿色基础设施，建筑、道路为灰色基础设施。
本实施例的绿色、蓝色和灰色基础设施分类方法，获取目标区域对应的多光谱照片，并基于多光谱照片，得到目标光波段图像集合以及彩色正射图；基于彩色正射图，得到样本文件，并根据目标光波段图像集合和样本文件，得到目标区域对应的绿色、蓝色和灰色基础设施分类结果。本发明根据目标区域对应的多光谱照片，得到目标光波段图像集合以及彩色正射图，并结合基于彩色正射图得到的样本文件以及目标光波段图像集合，得到目标区域对应的绿色、蓝色和灰色基础设施分类结果，提高了绿色、蓝色和灰色基础设施分类的准确度和效率。
以下将对各个步骤进行详细说明：
步骤S10，获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
在本实施例中，绿色、蓝色和灰色基础设施分类设备通过具有拍摄多光谱照片功能的无人机，在适合的天气条件下对目标区域进行拍摄，以获取目标区域对应的多光谱照片，并基于多光谱照片，得到目标光波段图像集合以及彩色正射图；如：相关研究人员根据实际情况，确定待研究的目标区域，并通过具有拍摄多光谱照片功能的无人机飞行到距离目标区域地面为预设高度的上空，对目标区域进行拍摄，并将无人机拍摄的目标区域对应的 多光谱照片发送到绿色、蓝色和灰色基础设施分类设备中，绿色、蓝色和灰色基础设施分类设备在获取到目标区域对应的多光谱照片时，基于多光谱照片，得到目标区域对应的目标光波段图像集合以及彩色正射图，需要说明的是，多光谱照片是指包含很多带的照片，有时只有3个带(例如彩色图像)，但有时包含的带要多得多，甚至有上百个，每个带是一幅灰度图像，它表示根据用来产生该带的传感器的敏感度得到的场景亮度，在多光谱照片中，每个像素都与一个由像素在不同带的数值串，即一个矢量相关；目标光波段图像集合中包括：蓝光波段图像、绿光波段图像、红光波段图像、红边光波段图像、近红外光波段图像、NDVI图像和DSM图像，其中，NDVI图像是检测植被生长状态、植被覆盖度和消除部分辐射误差等的图像，DSM(数字地表模型，Digital Surface Model)是指包含了地表建筑物、桥梁和树木等高度的地面高程模型，即DSM图像是指数字地表模型图像；彩色正射图是指无人机从上空拍摄的目标区域的彩色俯视图。
具体地，步骤S10包括：
步骤a，对所述多光谱照片进行二维重建操作，并根据经过所述二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图。
在该步骤中，绿色、蓝色和灰色基础设施分类设备对获得到目标区域对应的多光谱照片进行二维重建操作，并根据经过二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图，其中，预设分辨率可以是6cm、6.5cm、8cm或10cm等，如：相关研究人员设定预设分辨率为6cm，绿色、蓝色和灰色基础设施分类设备将目标区域对应的多光谱照片输入DJI Terra或类似的图像拼接软件中，对多光谱照片进行二维重建操作，分别得到分辨率为6cm的蓝光波段图像、绿光波段图像、红光波段图像、红边光波段图像、近红外光波段图像、NDVI图像、DSM图像和彩色正射图。
步骤S20，基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
在本实施例中，绿色、蓝色和灰色基础设施分类设备基于彩色正射图，并通过eCognition软件和Arc GIS软件得到样本文件，并从目标光波段图像集合中选择蓝光波段图像、绿光波段图像、红光波段图像、红边光波段图像、近红外光波段图像、NDVI图像、DSM图像中的一个或多个图像进行组合，再结合样本文件，得到目标区域对应的绿色、蓝色和灰色基础设施分类结果。需要说明的是，eCognition是智能化影像分析软件，采用面向对象的信息提取方法，能够充分利用对象信息(色调、形状、纹理、层次)和类间信息(与邻近对象、子对象、父对象的相关特征)进行分析；Arc GIS软件是一个可用于收集、 组织、管理、分析、交流和发布地理信息的软件；样本文件包括训练样本和验证样本。
具体地，步骤S20还包括：
步骤b，根据预设网格间距，生成网格图像，并将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图；
在该步骤中，绿色、蓝色和灰色基础设施分类设备根据预设网格间距，通过eCognition软件生成网格图像，并将网格图像与目标区域对应的彩色正射图进行重叠，得到彩色网格正射图；如：相关研究人员根据经验将取样间隔设置为11.6米，并基于需要生成的网格图像对应的尺寸，等比例缩小取样间隔，得到预设网格间距，绿色、蓝色和灰色基础设施分类设备根据预设网格间距，通过eCognition软件生成网格图像，并将网格图像覆盖在彩色正射图表面，使得网格图像与彩色正射图重叠，得到彩色网格正射图，可以理解的是，将网格图像覆盖在彩色正射图表面得到彩色网格正射图，彩色网格正射图表面具有网格，其中网格上的每个格点会分别对应彩色网格正射图上的不同的基础设施。
步骤c，识别所述彩色网格正射图中每个格点对应的格点属性，并根据所述格点属性得到所述训练样本；
在该步骤中，绿色、蓝色和灰色基础设施分类设备在得到彩色网格正射图后，通过Arc GIS软件对彩色网格正射图中的网格对应的每个格点对应的格点属性进行识别，并根据每个格点对应的格点属性得到训练样本；可以理解的是，格点是指网格中两条线段相交形成的交点，彩色网格正射图中的每个格点会分别对应彩色网格正射图上的不同的基础设施，格点属性即为格点对应的基础设施的类型，基础设施的类型有相关研发人员设定为水体、树木及灌木、草地、绿色屋顶、裸地、建筑、道路等七类，其中水体为蓝色基础设施，树木及灌木、草地、绿色屋顶、裸地为绿色基础设施，建筑、道路为灰色基础设施。
步骤d，将所述彩色网格正射图中的网格图像进行偏移，以得到所述验证样本。
在该步骤中，绿色、蓝色和灰色基础设施分类设备在得到训练样本后，将彩色网格正射图中的网格进行偏移，具体可将网格整体向上、下、左、右、左上、右上等方向进行偏移，使得网格中每个格点对应的格点属性与训练样本中的每个格点对应的格点属性不同即可，进而得到验证样本，例如：绿色、蓝色和灰色基础设施分类设备将彩色网格正射图中的网格整体向下偏移一个预设网格间距，并识别偏移后每个格点对应的网格属性，进而得到对应的验证样本，可选地，可对彩色网格正射图中的网格整体向多个方向偏移，进而得到多个验证样本。
步骤e，依据光谱相似性对所述目标光波段图像集合进行分割操作，得到形状对象， 并根据所述样本文件中的所述训练样本和对应的所述形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果；
在该步骤中，绿色、蓝色和灰色基础设施分类设备通过eCognition软件对目标光波段图像集合进行分割操作，依据目标光波段图像集合中的蓝光波段图像、绿光波段图像、红光波段图像、红边光波段图像、近红外光波段图像、NDVI图像、DSM图像的波段数值相似性，分割出形状对象，并把样本文件中的训练样本中的格点属性赋予每个形状对象，再通过随机森林、模糊分类和贝叶斯算法等算法，计算其他无属性的形状对象的属性值，得到绿色、蓝色和灰色基础设施预分类结果；
步骤f，基于所述样本文件中的所述验证样本对所述绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
在该步骤中，绿色、蓝色和灰色基础设施分类设备基于样本文件中的验证样本中的每个格点对应的格点属性对绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
进一步地，基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果的步骤包括：
步骤f1，将所述精度评价结果与预设精度进行对比，得到对比结果；
在该步骤中，绿色、蓝色和灰色基础设施分类设备将精度评价结果与预设精度进行对比，得到对比结果，如：相关研究人员根据实际情况设定预设精度为0.8，若绿色、蓝色和灰色基础设施分类设备得到的绿色、蓝色和灰色基础设施预分类结果的精度评价结果为0.7，则精度评价结果与预设精度进行对比得到的对比结果为精度评价结果小于预设精度，若绿色、蓝色和灰色基础设施分类设备得到的绿色、蓝色和灰色基础设施预分类结果的精度评价结果为0.85，则精度评价结果与预设精度进行对比得到的对比结果为精度评价结果不小于预设精度。
步骤f2，若所述对比结果为所述精度评价结果不小于所述预设精度，则将所述绿色、蓝色和灰色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果；
在该步骤中，绿色、蓝色和灰色基础设施分类设备若得到对比结果为精度评价结果不小于预设精度，则将绿色、蓝色和灰色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果，并利用绿色、蓝色和灰色基础设施分类结果提供目标区域对应的雨水利用分析数据。
步骤f3，若所述对比结果为所述精度评价结果小于所述预设精度，则对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行步骤：将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图。
在该步骤中，绿色、蓝色和灰色基础设施分类设备若得到对比结果为精度评价结果小于预设精度，则对网格图像以及目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行将网格图像与彩色正射图进行重叠，得到彩色网格正射图以及后续步骤，直到得到的绿色、蓝色和灰色基础设施预分类结果对应的精度不小于预设精度为止。
进一步地，对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合的步骤包括：
对所述网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对每个网格图像进行第一预设操作，以得到最优网格图像；
在该步骤中，绿色、蓝色和灰色基础设施分类设备对网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对第一预设数量中的每个网格图像进行第一预设操作，以得到最优网格图像，如：绿色、蓝色和灰色基础设施分类设备可根据预设网格间距，对网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，可选地，绿色、蓝色和灰色基础设施分类设备根据相关研究人员的指令，在预设网格间距的基础上对网格图像对应的网格间距进行增大或缩小，每对网格间距进行增大或缩小进行一次增大或缩小，便得到对应的网格图像，最终得到第一预设数量的网格图像即停止。可选地，绿色、蓝色和灰色基础设施分类设备可智能地设定第一预设数量，并智能地在预设网格间距的基础上对网格图像对应的网格间距进行增大或缩小，最终得到第一预设数量的网格图像。绿色、蓝色和灰色基础设施分类设备在得到第一预设数量的网格图像后，对每个网格图像进行第一预设操作，即，对每个网格图像执行将网格图像与彩色正射图进行重叠，得到彩色网格正射图以及后续步骤，以得到的每个网格图像对应的绿色、蓝色和灰色基础设施预分类结果对应的精度评价结果，再将每个的网格图像对应的精度评价结果与预设精度进行对比，筛选出不小于预设精度的精度评价结果对应的网格图像，并在不小于预设精度的精度评价结果对应的网格图像中筛选出网格间距最大的网格图像，作为最优网格图像。
对所述目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于所述最优网格图像分别对每个目标光波段图像集合进行第二 预设操作，以得到最优目标光波段图像集合。
在该步骤中，绿色、蓝色和灰色基础设施分类设备对目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于最优网格图像分别对每个目标光波段图像集合进行第二预设操作，以得到最优目标光波段图像集合。如：绿色、蓝色和灰色基础设施分类设备对目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，可选地，绿色、蓝色和灰色基础设施分类设备根据相关研究人员的指令，对目标光波段图像集合中的目标光波段图像进行增加或减少，最终得到第二预设数量的目标光波段图像集合即停止。可选地，绿色、蓝色和灰色基础设施分类设备可智能地设定第二预设数量，并智能地对目标光波段图像集合中的目标光波段图像进行增加或减少，最终得到第二预设数量的目标光波段图像集合。具体地，目标光波段图像集合中可能包括：蓝光波段图像、绿光波段图像、NDVI图像、DSM图像，可能包括蓝光波段图像、绿光波段图像、红光波段图像、NDVI图像、DSM图像，也可能包括蓝光波段图像、绿光波段图像、红光波段图像、近红外光波段图像、NDVI图像、DSM图像等。绿色、蓝色和灰色基础设施分类设备基于最优网格图像与目标区域对应的彩色正射图得到训练样本和验证样本，并分别对第二预设数量中的每个目标光波段图像集合进行第二预设操作，即，分别对第二预设数量中的每个目标光波段图像集合执行对目标光波段图像集合进行分割操作，得到形状对象，并根据样本文件中的训练样本和形状对象，计算得到绿色、蓝色和灰色基础设施预分类结果以及后续步骤，以得到的每个目标光波段图像集合对应的绿色、蓝色和灰色基础设施预分类结果对应的精度评价结果，并在精度评价结果不小于预设精度的每个目标光波段图像集合中筛选出精度评价最高的目标光波段图像集合，作为最优目标光波段图像集合。
本实施例的绿色、蓝色和灰色基础设施分类方法，绿色、蓝色和灰色基础设施分类设备获取目标区域对应的多光谱照片，并对多光谱照片进行二维重建操作，并根据经过二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图；绿色、蓝色和灰色基础设施分类设备根据预设网格间距，生成网格图像，并将网格图像与彩色正射图进行重叠，得到彩色网格正射图；绿色、蓝色和灰色基础设施分类设备识别彩色网格正射图中每个格点对应的格点属性，并根据格点属性得到训练样本，再将彩色网格正射图中的网格图像进行偏移，以得到验证样本；绿色、蓝色和灰色基础设施分类设备对目标光波段图像集合进行分割操作，得到形状对象，并根据样本文件中的训练样本中的格点属性和形状对象，计算得到绿色、蓝色和灰色基础设施预分类结果，再基于绿色、蓝色和灰色 基础设施预分类结果与样本文件中的验证样本进行精度评价，得到精度评价结果，并基于精度评价结果，确定绿色、蓝色和灰色基础设施分类结果，提高了绿色、蓝色和灰色基础设施分类的准确度和效率。
进一步地，基于本发明绿色、蓝色和灰色基础设施分类方法第一实施例，提出本发明绿色、蓝色和灰色基础设施分类方法第二实施例。
绿色、蓝色和灰色基础设施分类方法的第二实施例与绿色、蓝色和灰色基础设施分类方法的第一实施例的区别在于，在步骤S20之后，绿色、蓝色和灰色基础设施分类方法还包括：
步骤g，根据所述绿色、蓝色和灰色基础设施分类结果，生成所述目标区域对应的分类地图，并根据所述分类地图，提供所述目标区域对应的雨水利用分析数据。
在本实施例中，绿色、蓝色和灰色基础设施分类设备根据通过预设网格间距对应的网格图像和蓝光波段图像、绿光波段图像、红光波段图像、红边光波段图像、近红外光波段图像、NDVI图像、DSM图像组成的目标光波段图像集合得到的绿色、蓝色和灰色基础设施分类结果或通过最优网格图像和最优目标光波段图像集合得到的绿色、蓝色和灰色基础设施分类结果，生成目标区域对应的分类地图，该分类地图中包括：水体、树木及灌木、草地、绿色屋顶、裸地、建筑、道路这七类目标区域的基础设施类型，并根据分类地图，提供目标区域对应的雨水利用分析数据。
本实施例的绿色、蓝色和灰色基础设施分类设备根据最终得到的目标区域的绿色、蓝色和灰色基础设施分类结果，生成目标区域对应的分类地图，该分类地图中包括：水体、树木及灌木、草地、绿色屋顶、裸地、建筑、道路这七类目标区域的基础设施类型，并根据分类地图，提供目标区域对应的雨水利用分析数据，使得绿色、蓝色和灰色基础设施分类结果能为目标区域的雨水利用分析提供数据。
本发明还提供一种绿色、蓝色和灰色基础设施分类装置。本发明绿色、蓝色和灰色基础设施分类装置包括：
获取模块，用于获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
分类模块，用于基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。进一步地，所述获取模块还包括二维重建模块，所述二维重建模块用于：
对所述多光谱照片进行二维重建操作，并根据经过所述二维重建操作的多光谱照片以 及预设分辨率，得到目标光波段图像集合以及彩色正射图。进一步地，所述分类模块还包括生成模块，所述生成模块用于：
根据预设网格间距，生成网格图像，并将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图；
识别所述彩色网格正射图中每个格点对应的格点属性，并根据所述格点属性得到所述训练样本；
将所述彩色网格正射图中的网格图像进行偏移，以得到所述验证样本。
进一步地，所述分类模块还用于：
依据光谱相似性对所述目标光波段图像集合进行分割操作，得到形状对象，并根据所述样本文件中的所述训练样本和对应的所述形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果；
基于所述样本文件中的所述验证样本对所述绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
进一步地，所述分类模块还用于：
将所述精度评价结果与预设精度进行对比，得到对比结果；
若所述对比结果为所述精度评价结果不小于所述预设精度，则将所述绿色、蓝色和灰色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果；
若所述对比结果为所述精度评价结果小于所述预设精度，则对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行步骤：将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图。
进一步地，所述分类模块还包括优化模块，所述优化模块用于：
对所述网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对每个网格图像进行第一预设操作，以得到最优网格图像；
对所述目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于所述最优网格图像分别对每个目标光波段图像集合进行第二预设操作，以得到最优目标光波段图像集合。
进一步地，所述分类模块还包括分析模块，所述分析模块用于：
根据所述绿色、蓝色和灰色基础设施分类结果，生成所述目标区域对应的分类地图，并根据所述分类地图，提供所述目标区域对应的雨水利用分析数据。
本发明还提供一种介质。
本发明介质为计算机可读存储介质，计算机可读存储介质上存储有绿色、蓝色和灰色基础设施分类程序，所述绿色、蓝色和灰色基础设施分类程序被处理器执行时实现如上所述的绿色、蓝色和灰色基础设施分类方法的步骤。
其中，在所述处理器上运行的绿色、蓝色和灰色基础设施分类程序被执行时所实现的方法可参照本发明绿色、蓝色和灰色基础设施分类方法各个实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书与附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (10)

  1. 一种绿色、蓝色和灰色基础设施分类方法，其特征在于，所述绿色、蓝色和灰色基础设施分类方法包括如下步骤：
    获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
    基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
  2. 如权利要求1所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图的步骤包括：
    对所述多光谱照片进行二维重建操作，并根据经过所述二维重建操作的多光谱照片以及预设分辨率，得到目标光波段图像集合以及彩色正射图。
  3. 如权利要求1所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述样本文件包括训练样本和验证样本，所述基于所述彩色正射图，得到样本文件的步骤包括：
    根据预设网格间距，生成网格图像，并将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图；
    识别所述彩色网格正射图中每个格点对应的格点属性，并根据所述格点属性得到所述训练样本；
    将所述彩色网格正射图中的网格图像进行偏移，以得到所述验证样本。
  4. 如权利要求3所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果的步骤包括：
    依据光谱相似性对所述目标光波段图像集合进行分割操作，得到形状对象，并根据所述样本文件中的所述训练样本和对应的所述形状对象光波段图像数值，计算得到绿色、蓝色和灰色基础设施预分类结果；
    基于所述样本文件中的所述验证样本对所述绿色、蓝色和灰色基础设施预分类结果进行精度评价，得到精度评价结果，并基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果。
  5. 如权利要求4中所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述基于所述精度评价结果，确定绿色、蓝色和灰色基础设施分类结果的步骤包括：
    将所述精度评价结果与预设精度进行对比，得到对比结果；
    若所述对比结果为所述精度评价结果不小于所述预设精度，则将所述绿色、蓝色和灰 色基础设施预分类结果确定为绿色、蓝色和灰色基础设施分类结果；
    若所述对比结果为所述精度评价结果小于所述预设精度，则对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合，并执行步骤：将所述网格图像与所述彩色正射图进行重叠，得到彩色网格正射图。
  6. 如权利要求5所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述对所述网格图像以及所述目标光波段图像集合进行预设处理，以得到最优网格图像和最优目标光波段图像集合的步骤包括：
    对所述网格图像对应的网格间距进行缩放操作，以得到第一预设数量的网格图像，并分别对每个网格图像进行第一预设操作，以得到最优网格图像；
    对所述目标光波段图像集合中的目标光波段图像进行增减操作，以得到第二预设数量的目标光波段图像集合，基于所述最优网格图像分别对每个目标光波段图像集合进行第二预设操作，以得到最优目标光波段图像集合。
  7. 如权利要求1所述的绿色、蓝色和灰色基础设施分类方法，其特征在于，所述基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果的步骤之后，所述绿色、蓝色和灰色基础设施分类方法还包括：
    根据所述绿色、蓝色和灰色基础设施分类结果，生成所述目标区域对应的分类地图，并根据所述分类地图，提供所述目标区域对应的雨水利用分析数据。
  8. 一种绿色、蓝色和灰色基础设施分类装置，其特征在于，所述绿色、蓝色和灰色基础设施分类装置包括：
    获取模块，用于获取目标区域对应的多光谱照片，并基于所述多光谱照片，得到目标光波段图像集合以及彩色正射图；
    分类模块，用于基于所述彩色正射图，得到样本文件，并根据所述目标光波段图像集合和所述样本文件，得到所述目标区域对应的绿色、蓝色和灰色基础设施分类结果。
  9. 一种绿色、蓝色和灰色基础设施分类系统，其特征在于，所述绿色、蓝色和灰色基础设施分类系统包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的绿色、蓝色和灰色基础设施分类程序，所述绿色、蓝色和灰色基础设施分类程序被所述处理器执行时实现如权利要求1至7中任一项所述的绿色、蓝色和灰色基础设施分类方法的步骤。
  10. 一种介质，其特征在于，所述介质为计算机可读存储介质，所述计算机可读存储 介质上存储有绿色、蓝色和灰色基础设施分类程序，所述绿色、蓝色和灰色基础设施分类程序被处理器执行时实现如权利要求1至7中任一项所述的绿色、蓝色和灰色基础设施分类方法的步骤。
PCT/CN2022/134944 2021-12-20 2022-11-29 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质 Ceased WO2023116359A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/556,730 US12608913B2 (en) 2021-12-20 2022-11-29 Method, device, system and medium for classifying green-blue-gray infrastructure

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111565957.7 2021-12-20
CN202111565957.7A CN114359630B (zh) 2021-12-20 2021-12-20 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质

Publications (1)

Publication Number Publication Date
WO2023116359A1 true WO2023116359A1 (zh) 2023-06-29

Family

ID=81102284

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/134944 Ceased WO2023116359A1 (zh) 2021-12-20 2022-11-29 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质

Country Status (3)

Country Link
US (1) US12608913B2 (zh)
CN (1) CN114359630B (zh)
WO (1) WO2023116359A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114359630B (zh) * 2021-12-20 2025-09-16 南方科技大学 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210061817A (ko) * 2019-11-20 2021-05-28 한국해양과학기술원 식생현황분석장치 및 그 동작 방법
CN114359630A (zh) * 2021-12-20 2022-04-15 南方科技大学 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8503761B2 (en) * 2009-11-12 2013-08-06 Harris Corporation Geospatial modeling system for classifying building and vegetation in a DSM and related methods
US9147132B2 (en) * 2013-09-11 2015-09-29 Digitalglobe, Inc. Classification of land based on analysis of remotely-sensed earth images
KR101965235B1 (ko) * 2018-12-10 2019-04-03 주식회사 지오스토리 무인기 원격탐사를 통한 잘피군락지 분포조사방법
CN109740562B (zh) * 2019-01-14 2020-12-08 中国科学院地理科学与资源研究所 一种生态海绵型城市建设适宜区的系统及方法
CN109977901A (zh) * 2019-04-03 2019-07-05 山东理工大学 一种基于无人机遥感的玉米田间杂草识别方法
CN110672550B (zh) * 2019-09-10 2021-11-19 中国科学院上海技术物理研究所 一种微区重要生物资源像谱分析仪
CN112513874A (zh) * 2019-12-06 2021-03-16 深圳市大疆创新科技有限公司 作物生长状况评估方法和装置
CN111426637A (zh) * 2020-04-16 2020-07-17 江苏省环境监测中心 一种利用无人机获取城市黑臭河流水质参数的方法
DE102020122052B3 (de) * 2020-08-24 2021-08-26 Bareways GmbH Verfahren und system zur kodierung von bilddaten, die eine geografische linie repräsentieren
CN112883987A (zh) * 2021-03-11 2021-06-01 成都数之联科技有限公司 基于遥感光谱特征的目标提取方法及系统及装置及介质

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210061817A (ko) * 2019-11-20 2021-05-28 한국해양과학기술원 식생현황분석장치 및 그 동작 방법
CN114359630A (zh) * 2021-12-20 2022-04-15 南方科技大学 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
YANG SHUQIN, SONG ZHISHUANG, YIN HANPING, ZHANG ZHITAO, NING JIFENG: "Crop Classification Method of UVA Multispectral Remote Sensing Based on Deep Semantic Segmentation", TRANSACTIONS OF THE CHINESE SOCIETY FOR AGRICULTURAL MACHINERY., vol. 52, no. 3, 1 March 2021 (2021-03-01), pages 185 - 192, XP093073379, DOI: 10.6441/j.issu.1000-1298.2021.03.020 *

Also Published As

Publication number Publication date
US12608913B2 (en) 2026-04-21
CN114359630A (zh) 2022-04-15
US20240371133A1 (en) 2024-11-07
CN114359630B (zh) 2025-09-16

Similar Documents

Publication Publication Date Title
Choi et al. An automatic approach for tree species detection and profile estimation of urban street trees using deep learning and Google street view images
CN110263717B (zh) 一种融入街景影像的土地利用类别确定方法
Ghanea et al. Building extraction from high-resolution satellite images in urban areas: Recent methods and strategies against significant challenges
Yu et al. Automated derivation of urban building density information using airborne LiDAR data and object-based method
US9070018B1 (en) Automated roof identification systems and methods
Herrault et al. Automatic extraction of forests from historical maps based on unsupervised classification in the CIELab color space
CN113033386A (zh) 一种基于高分辨率遥感影像的输电线路通道隐患识别方法及系统
CN113033516A (zh) 对象识别统计方法及装置、电子设备、存储介质
US12437498B2 (en) System and method for home Façade features in a geographic region
CN118298317B (zh) 一种基于在线地图训练集的自动标注方法及系统
CN117612038B (zh) 基于无人机影像的矿区植被碳汇精细演算方法
JP3380457B2 (ja) 地理画像上の影成分の除去方法及び地理画像処理装置、記録媒体
WO2023116359A1 (zh) 绿色、蓝色和灰色基础设施分类方法、装置、系统与介质
Liu et al. A framework of road extraction from airborne lidar data and aerial imagery
CN116108122A (zh) 一种基于空间熵的城市用地功能自动识别方法
JPH10269354A (ja) ノイズ画素の除去方法及び地理画像処理装置、記録媒体
Zambrano et al. Comparing methodologies for mapping the afforestation of public streets in Chapada Neighbourhood, using pléiades images
Talebi et al. Detection of tree crowns based on reclassification using aerial images and lidar data
Nizamuddin et al. Utilization of GIS Machine Learning for Mapping of Building Shapes in Tibang Village, Banda Aceh City, Aceh, Indonesia
Holland et al. Automating the photogrammetric workflow in a national mapping agency
KR20230063245A (ko) Rs gis 기반 친수시설 정보맵 작성 및 유역조사를 위한 시스템 및 방법
Shorter Unsupervised building detection from irregularly spaced LiDAR and aerial imagery
Ejikeme et al. Object-Based Approach for Landuse/Landcover Mapping of Makurdi Area of Benue State, Nigeria using High Resolution Satellite Imagery
El-Naggar Data capture using vectorization of satellite images and maps to serve change detection
LAWRENCE EARLY DETECTION OF HERACLEUM MANTEGAZZIANUM (GIANT HOGWEED) BASED ON LEAF SPECTRAL CHARACTERISTICS FROM UAV

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22909674

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22909674

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12.02.2025)

122 Ep: pct application non-entry in european phase

Ref document number: 22909674

Country of ref document: EP

Kind code of ref document: A1