CN113095223A - Newly-added illegal building identification method and system based on aerial orthographic image - Google Patents
Newly-added illegal building identification method and system based on aerial orthographic image Download PDFInfo
- Publication number
- CN113095223A CN113095223A CN202110392840.7A CN202110392840A CN113095223A CN 113095223 A CN113095223 A CN 113095223A CN 202110392840 A CN202110392840 A CN 202110392840A CN 113095223 A CN113095223 A CN 113095223A
- Authority
- CN
- China
- Prior art keywords
- image
- researched
- difference value
- region
- area
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 53
- 230000000877 morphologic effect Effects 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/32—Determination of transform parameters for the alignment of images, i.e. image registration using correlation-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention provides a newly-added illegal building identification method and a system based on aerial orthographic images, which comprise the following steps: respectively collecting a first image of a region to be researched at a first moment and a second image of the region to be researched at a second moment after a preset time length at the first moment; respectively carrying out orthoscopic processing and splicing operation on the first image and the second image to obtain a first orthoscopic image of the area to be researched at a first moment and a second orthoscopic image of the area to be researched at a second moment; performing an image registration operation on the first and second orthoimages to align the first and second orthoimages; subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the area to be researched; carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference value image of the area to be researched; vectorizing the image spots of the binary difference image of the region to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of the newly added illegal building.
Description
Technical Field
The embodiment of the invention relates to the field of illegal building identification, in particular to a newly added illegal building identification method and system based on aerial orthographic images.
Background
Along with the increasing of the living standard of people at present, the income per capita increases year by year, the urbanization construction process is continuously accelerated, and a large amount of illegal buildings are gradually derived in the process. Illegal buildings have certain potential safety hazards, disturb the urban and rural planning order and are not beneficial to the sustainable development of cities. At present, the management of urban illegal buildings is mainly based on site reconnaissance of management personnel, the management means is single in a traditional mode, the full coverage of the scope of the jurisdiction cannot be achieved due to the view field, and particularly, the urban illegal buildings on the top layer are used as urban high-rise buildings. In order to improve the efficiency, a method for monitoring illegal buildings by adopting satellite remote sensing images is available, and the work of managers is reduced to a certain extent.
However, by adopting the existing method for monitoring illegal buildings by using the satellite remote sensing image, a certain difficulty exists in timely acquiring the satellite image, a certain time interval exists between the acquisition and the transmission of the satellite acquired image and the acquisition, and the completion of the illegal buildings under construction may exist in the time interval, so that the illegal buildings under construction and new illegal buildings are not easily discovered in time. In addition, the resolution of the satellite images is not high enough, the spatial resolution of the current satellite images can reach the sub-meter level, but the current illegal buildings tend to be small gradually, such as a small sentry box for illegal construction and the like, the illegal buildings only occupy a plurality of pixels on the satellite images, and are easy to remove as noise points in the algorithm processing process.
Disclosure of Invention
The invention provides a newly-added illegal building identification method and system based on aerial orthographic images, which are beneficial for managers to timely and accurately discover newly-added illegal buildings, so that the identification efficiency of the newly-added illegal buildings is improved.
In a first aspect of the present invention, an embodiment of the present invention provides a method for identifying a newly added illegal building based on an aerial orthographic image, including:
respectively collecting a first image of a region to be researched at a first moment and a second image of the region to be researched at a second moment after a preset time length at the first moment;
respectively carrying out orthoscopic processing and splicing operation on the first image and the second image so as to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment;
performing an image registration operation on the first and second orthoimages to align the first and second orthoimages;
subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched;
carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference image of the area to be researched;
vectorizing the image spots of the binarization difference image of the region to be researched to obtain a vector file; and
and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building.
In another embodiment of the present invention, the subtracting the first ortho image from the second ortho image to obtain the image difference of the region to be studied includes:
respectively extracting R, G and B wave bands of the first orthoscopic image and R, G and B wave bands of the second orthoscopic image by using wave band operation, and respectively subtracting R, G and B wave bands of the first orthoscopic image from R, G and B wave bands of the second orthoscopic image to obtain an R wave band image difference value, a G wave band image difference value and a B wave band image difference value of the first orthoscopic image and the second orthoscopic image.
In another embodiment of the present invention, the binarizing the image difference value of the region to be studied to obtain a binarized difference image of the region to be studied includes:
respectively carrying out binarization processing on the R waveband image difference value, the G waveband image difference value and the B waveband image difference value to obtain an R waveband binarization difference value, a G waveband binarization difference value and a B waveband binarization difference value; and
and taking a union set of the R waveband binarization difference value, the G waveband binarization difference value and the B waveband binarization difference value to obtain a binarization difference image of the area to be researched.
In another embodiment of the present invention, the performing an image registration operation on the first and second orthoimages to align the first and second orthoimages comprises:
selecting a plurality of control points on the first orthoimage;
selecting a plurality of control points on the second ortho image, wherein the plurality of control points selected on the second ortho image correspond to the plurality of control points selected on the first ortho image one to one; and
aligning each of the plurality of control points on the first ortho image with a corresponding control point on the second ortho image, respectively.
In another embodiment of the present invention, the plurality of control points on the first ortho image include at least one of corner points of a house and inflection points of a road.
In another embodiment of the present invention, after the binarizing processing is performed on the image difference value of the region to be studied to obtain the binarized difference image of the region to be studied, and before the vectorizing is performed on the image spots of the binarized difference image of the region to be studied to obtain the vector file, the method further includes:
and carrying out morphological processing on the binarization difference image of the region to be researched.
In another embodiment of the present invention, the preset time period is greater than or equal to the first time period threshold.
In another embodiment of the present invention, the first image and the second image have a course overlap and a side overlap each greater than or equal to a first overlap threshold when acquired.
In another embodiment of the present invention, the first image and the second image have a ground resolution of 5-10 cm/pixel at the time of acquisition.
In a second aspect of the present invention, an embodiment of the present invention provides a new illegal building identification system based on aerial orthophoto images, including:
the image acquisition module is used for respectively acquiring a first image of an area to be researched at a first moment and a second image of the area to be researched at a second moment after a preset time length at the first moment;
the orthoimage production module is used for respectively carrying out orthoimage processing and splicing operation on the first image and the second image so as to obtain a first orthoimage of the area to be researched at the first moment and a second orthoimage of the area to be researched at the second moment;
a geographic registration module for performing an image registration operation on the first and second orthoimages to align the first and second orthoimages;
an image difference acquisition module, configured to subtract the first ortho image from the second ortho image to obtain an image difference of the region to be studied; carrying out binarization processing on the image difference value of the region to be researched to obtain a binarization difference value image of the region to be researched; and
a newly added illegal building position acquisition module used for vectorizing the image spots of the binarization difference image of the area to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building.
The newly-added illegal building identification method and system based on the aerial orthographic images, provided by the embodiment of the invention, respectively collect a first image of a to-be-researched area at a first moment and a second image of the to-be-researched area at a second moment after a preset time duration at the first moment; respectively carrying out orthoscopic processing and splicing operation on the first image and the second image so as to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment; performing an image registration operation on the first and second orthoimages to align the first and second orthoimages; subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched; carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference image of the area to be researched; vectorizing the image spots of the binarization difference image of the region to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building. According to the embodiment of the invention, the unmanned aerial vehicle is adopted to acquire the data of different time phases of the area to be researched, the acquired data is processed to obtain the orthophoto map, the two orthophotos are subjected to geographic registration, image difference, morphological processing, vectorization and the like, and finally the position of the newly-added illegal building is extracted and obtained, so that the image of the area to be researched can be issued in time, and managers can find the newly-added illegal building in time. In addition, as the unmanned aerial vehicle is adopted to acquire data of different time phases of the area to be researched, the resolution of the acquired image of the area to be researched is higher, and the method and the device are beneficial to accurately identifying the newly added illegal buildings by managers, so that the identification efficiency of the newly added illegal buildings is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for describing the embodiments or the prior art, and it is apparent that the drawings in the following description are some embodiments of the present invention, but not all embodiments. For a person skilled in the art, other figures can also be obtained from these figures without inventive exercise.
Fig. 1 is a schematic flow chart of a new illegal building identification method based on an aerial orthographic image according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a newly added illegal building identification system based on an aerial orthographic image according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Based on the problems in the prior art, the embodiment of the invention provides a method for identifying newly-added illegal buildings based on aerial orthophoto images.
Fig. 1 is a schematic flow chart of a new illegal building identification method based on an aerial orthographic image according to an embodiment of the present invention. The embodiment of the invention provides an execution main body of a newly-added illegal building identification method based on aerial orthographic images, which can be a newly-added illegal building identification system based on aerial orthographic images. The newly-added illegal building identification system based on the aerial orthographic images comprises an unmanned aerial vehicle, a digital camera and a newly-added illegal building identification device based on the aerial orthographic images. The newly added illegal building identification device based on the aerial orthographic images can be realized in a software and/or hardware mode, wherein the hardware is a processor or an electronic device, and the software is a computer program instruction or an application program and the like. The newly added illegal building identification device based on the aerial orthographic image can be an independent electronic device, or the newly added illegal building identification device based on the aerial orthographic image can be integrated in the electronic device. The electronic device is, for example, a computer.
As shown in fig. 1, the newly added illegal building identification method based on aerial orthographic images includes:
s101, respectively collecting a first image of a region to be researched at a first moment and a second image of the region to be researched at a second moment after a preset time length at the first moment.
In one embodiment of the invention, in the newly added illegal building identification system based on aerial orthographic images, an unmanned aerial vehicle carrying a digital camera can be used to periodically collect images of an area to be researched. The drone may be, for example, a multi-rotor drone or a vertical take-off and landing fixed wing drone, or the like. This unmanned aerial vehicle gathers the first image in the region of waiting to study at the first moment, gathers the second image in the region of waiting to study at the second moment after the first moment is predetermine for a long time, gathers the third image in the region of waiting to study at the third moment after the second moment is predetermine for a long time, analogizes with this to obtain the image of waiting to study regional different time phases.
In one embodiment of the present invention, the preset time period may be greater than the first time period threshold. In order to better determine the data acquisition period, the value of the first duration threshold may be set according to the actual situation of the area to be studied, for example, may be set to be half a month, one month, six months, or one year. Specifically, the value of the first time length threshold may be set according to the frequency of newly-increased illegal buildings in the area to be studied, and the frequency may have a certain seasonality. In addition, the value of the first time length threshold value can be set according to the speed of illegal construction of newly-increased illegal buildings in the area to be researched. For example, if the construction period of a general illegal building is half a month, the value of the first time length threshold may be set to be half a month. The value of the first time period threshold may also be determined according to other factors, which is not limited in the present invention.
In one embodiment of the present invention, in order to ensure the data availability of the acquired image of the area to be studied, it should be ensured that the course overlap and the side overlap of the acquired image of the area to be studied are both greater than or equal to a first overlap threshold, and the value of the first overlap threshold may be 70%. The first threshold value of the degree of overlap may take other values as long as the data availability of the acquired image of the region to be studied is ensured, which is not a limitation of the present invention.
In one embodiment of the invention, the ground resolution of the acquired images of the area to be studied is 5-10 cm/pixel in order to ensure data availability of the acquired images of the area to be studied.
S102, respectively carrying out orthoscopic processing and splicing operation on the first image and the second image to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment.
In an embodiment of the invention, after the newly added illegal building identification system based on the aerial orthographic images collects the images of the area to be researched, the images of two adjacent time phases of the area to be researched can be selected for orthographic production. The two adjacent time phases may be any two adjacent time phases separated by a preset time length, and for example, the two adjacent time phases may be a first time and a second time, a second time and a third time, or a third time and a fourth time, and the like. For convenience of explanation, how to realize the identification of the newly added illegal buildings based on the aerial orthographic images by the invention is described below by taking the first time and the second time as examples.
In an embodiment of the invention, the Pix4DMapper software can efficiently and quickly acquire the spliced orthoimages, and the automation degree of the production process is high, so that the Pix4DMapper software can be installed in the newly added illegal building identification system based on the aerial orthoimages, and the Pix4DMapper software can be adopted to respectively perform the orthographic processing and splicing operation on the first image and the second image, so as to obtain the first orthographic image of the area to be researched at the first moment and the second orthographic image at the second moment. Specifically, the first image and the second image are imported into Pix4d mapper software installed in a newly added illegal building identification system based on aerial orthographic images, an output coordinate system is set, for example, a CGCS2000 coordinate system is adopted, and a good band number is selected. For example, in Qingdao, CGCS2000/3-degree Gauss-Kruger CM 120E may be selected as the band number, where CGCS2000/3-degree Gauss-Kruger CM 120E indicates that three degrees of banding are projected using the Gaussian-gram, and the central meridian is 120 ° east meridian. Then selecting and generating a raster Digital Surface Model (DSM) and an ortho-image map, selecting and merging tile options, and automatically and respectively carrying out ortho-processing and splicing operation on the first image and the second image by the Pix4 DMDoper software so as to obtain a spliced first ortho-image and a spliced second ortho-image covering the whole range, wherein the first ortho-image corresponds to the first image and the second ortho-image corresponds to the second image.
When the Pix4DMapper software is used for orthophoto production, other options such as ground resolution options may also be set. In order to perform the subsequent image registration operation normally, the ortho-image resolution of each phase needs to be unified.
In one embodiment of the present invention, the ground resolution of the first and second images at the time of acquisition is typically set to 5-10 cm/pixel. The ground resolution of the level can better screen ground buildings, small buildings cannot be omitted, and the influence of noise can be reduced while image registration is facilitated.
It should be understood that in addition to the Pix4DMapper software, other ways of obtaining the first and second orthoimages may be used in other embodiments of the invention.
S103, carrying out image registration operation on the first orthoimage and the second orthoimage so as to align the first orthoimage and the second orthoimage.
In an embodiment of the present invention, after the newly added illegal building identification system based on the aerial ortho-images obtains the first ortho-image of the area to be studied at the first time and the second ortho-image at the second time, the image registration operation may be further performed on the first ortho-image and the second ortho-image to align the first ortho-image and the second ortho-image.
In one embodiment of the present invention, the performing an image registration operation on the first and second orthoimages to align the first and second orthoimages comprises:
selecting a plurality of control points on the first orthoimage;
selecting a plurality of control points on the second ortho image, wherein the plurality of control points selected on the second ortho image correspond to the plurality of control points selected on the first ortho image one to one; and
aligning each of the plurality of control points on the first ortho image with a corresponding control point on the second ortho image, respectively.
Specifically, in an embodiment of the present invention, the newly added illegal building identification system based on the aerial ortho image may select a plurality of control points on the first ortho image, and then select a plurality of control points on the second ortho image, where the plurality of control points selected on the second ortho image correspond to the plurality of control points selected on the first ortho image one-to-one, and then align each of the plurality of control points on the first ortho image with a corresponding control point on the second ortho image. In this embodiment of the present invention, the ground objects corresponding to the corresponding pixels on the first and second ortho-images can be made consistent by completely aligning the plurality of control points selected on the first ortho-image and the plurality of control points selected on the second ortho-image through the image registration operation.
It should be noted that the plurality of control points selected on the first ortho image are reasonably distributed on the first ortho image and cover the entire frame range of the first ortho image. Similarly, the plurality of control points selected on the second ortho image are reasonably distributed on the second ortho image and cover the whole image range of the second ortho image. For example, the selected control points may be selected from corner points of a house, road corners or other distinctive, easily located ground points, etc.
For example, the newly added illegal building identification system based on the aerial ortho image may select 10 control points, i.e., control point 1, control point 2, control point 3, control point 4, control point 5, control point 6, control point 7, control point 8, control point 9, and control point 10, on the first ortho image, select 10 control points, i.e., control point 11, control point 12, control point 13, control point 14, control point 15, control point 16, control point 17, control point 18, control point 19, and control point 20, on the second ortho image, sequentially align the control point 1 of the first ortho image with the control point 11 of the second ortho image, align the control point 2 of the first ortho image with the control point 12 of the second ortho image, and so on until the control point 10 of the first ortho image is aligned with the control point 20 of the second ortho image. It should be understood that the number of the control points respectively selected on the first ortho-image and the second ortho-image in the present invention is not limited to 10, and less than 10 control points may be selected, or more than 10 control points may be selected, as long as the control points cover the entire image range of the ortho-image, which is not limited by the present invention.
In an embodiment of the invention, the newly added illegal building identification system based on the aerial orthographic image can be installed with ArcGis software. In step S103, the first and second ortho images may be input into the ArcGis software, and the geographic registration function of the ArcGis software is utilized to align the first and second ortho images.
It should be understood that in addition to the ArcGis software, in other embodiments of the present invention, other ways may be used to perform the image registration operation on the first and second ortho images to align the first and second ortho images.
And S104, subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched.
In an embodiment of the present invention, the first ortho-image and the second ortho-image are visible light true color images, and after the first ortho-image and the second ortho-image are aligned, the first ortho-image may be subtracted from the second ortho-image by the newly added illegal building identification system based on aerial ortho-images to obtain the image difference of the area to be researched.
Specifically, subtracting the first ortho image from the second ortho image to obtain an image difference value of the region to be studied, including:
respectively extracting R, G and B wave bands of the first orthoscopic image and R, G and B wave bands of the second orthoscopic image by using wave band operation, and respectively subtracting R, G and B wave bands of the first orthoscopic image from R, G and B wave bands of the second orthoscopic image to obtain an R wave band image difference value, a G wave band image difference value and a B wave band image difference value of the first orthoscopic image and the second orthoscopic image.
In an embodiment of the present invention, the new illegal building identification system based on the aerial ortho-image may be installed with an ENVI software, and the image difference of the area to be studied is obtained by inputting the first ortho-image and the second ortho-image into the ENVI software.
It should be appreciated that in addition to the ENVI software, in other embodiments of the invention, other ways of subtracting the first ortho image from the second ortho image may be used to obtain the image difference for the region under investigation.
And S105, carrying out binarization processing on the image difference value of the region to be researched to obtain a binarization difference image of the region to be researched.
In an embodiment of the present invention, after obtaining an image difference value of a region to be researched, a newly added illegal building identification system based on an aerial orthophoto image performs binarization processing on the image difference value of the region to be researched to obtain a binarization difference image of the region to be researched.
In one embodiment of the invention, the threshold value used for the binarization process is determined on the basis of the actual pixel value of the image difference of the region to be investigated. The selection of the threshold is influenced by various factors, such as shooting time, shooting angle and the like. Also, the threshold values selected at different times may be different.
In the process of binarization processing, multiple binarization processing can be performed, and a proper threshold value is selected to perform binarization processing on the image difference value of the region to be researched so as to obtain a binarization difference image of the region to be researched. The binarization difference image obtained by the proper threshold value can delete most noise influences, such as Gaussian noise and the like, and can ensure that small illegal buildings are not lost.
In an embodiment of the present invention, the binarizing processing the image difference value of the region to be studied to obtain a binarized difference value image of the region to be studied includes:
respectively carrying out binarization processing on the R waveband image difference value, the G waveband image difference value and the B waveband image difference value to obtain an R waveband binarization difference value, a G waveband binarization difference value and a B waveband binarization difference value; and
and taking a union set of the R waveband binarization difference value, the G waveband binarization difference value and the B waveband binarization difference value to obtain a binarization difference image of the area to be researched.
In an embodiment of the present invention, the newly added illegal building identification system based on the aerial orthophoto image may use the ENVI software installed therein to perform binarization processing on the image difference value of the region to be researched to obtain a binarized difference value image of the region to be researched.
It should be understood that, in addition to the ENVI software, in other embodiments of the present invention, other manners may be used to binarize the image difference of the region under study to obtain a binarized difference image of the region under study.
And S106, carrying out vectorization on the image spots of the binarization difference image of the region to be researched to obtain a vector file.
In an embodiment of the invention, after the newly added illegal building identification system based on the aerial orthophoto image performs binarization processing on the image difference value of the area to be researched to obtain the binarization difference value image of the area to be researched, vectorizing the image spots of the binarization difference value image of the area to be researched to obtain the vector file.
In an embodiment of the present invention, the newly added illegal building identification system based on the aerial ortho-image may use the ENVI software installed therein to perform vectorization on the image spots of the binarized difference image of the region to be studied, so as to obtain a vector file in shp format.
It should be understood that, in addition to the ENVI software, in other embodiments of the present invention, other manners may be used to vectorize the patches of the binarized difference image of the region under study to obtain a vector file.
In addition, it should be noted that, because the construction of a newly developed building in the urban construction process may cause erroneous judgment and identification, before step S106 is executed, simple manual operation is also required to perform the screening and warehousing of the image patches of the binarized difference image of the area to be researched, so as to improve the accuracy of identifying the newly added illegal buildings by using the newly added illegal building identification method based on the aerial orthophoto image provided by the invention.
Specifically, the binarization difference image of the area to be researched is loaded into a newly added illegal building identification system based on an aerial orthophoto image, and the pattern spot of the binarization difference image of the area to be researched is set to be a pattern which only displays the outline and has no filling. Then, a rolling operation is performed on the patches of the binarized difference image of the region to be studied, for example, the rolling operation by the ArcGis software, and a manager visually performs screening and identification of illegal building patches. Then, the determined illegal building pattern is given with its attribute, and the attribute information of the illegal building can be performed according to the requirements of local departments, for example, the pattern mark, the position information, the area, etc. can be included. In addition, the attribute table of the illegal buildings can be derived for deep analysis, such as analysis of the monthly increment of the illegal buildings.
And S107, superposing the vector file on the second ortho-image to obtain the position of the newly-added illegal building.
In an embodiment of the present invention, after vectorizing a pattern spot of a binarized difference image of a region to be studied by an aerial ortho-image-based newly-added illegal building recognition system to obtain a vector file, the vector file is superimposed on the second ortho-image to obtain a position of a newly-added illegal building.
Specifically, since the second ortho-image and the vector file both have the geographic coordinate system, the position of the newly added illegal building can be displayed by superimposing the vector file on the second ortho-image.
In one embodiment of the present invention, the newly added illegal building identification system based on aerial ortho images can use the ArcGis software installed therein to superimpose a vector file on the second ortho image to obtain the location of the newly added illegal building.
It should be understood that in addition to the ArcGis software, in other embodiments of the present invention, the vector file may be superimposed on the second ortho image in other ways to obtain the location of the newly added illegal building.
In an embodiment of the present invention, after the binarizing processing is performed on the image difference value of the region to be studied to obtain the binarized difference image of the region to be studied, and before the vectorizing is performed on the image spots of the binarized difference image of the region to be studied to obtain the vector file, the method further includes: and carrying out morphological processing on the binarization difference image of the region to be researched. Because the binarized difference image of the region to be researched is easily affected by noise and can have the incompleteness of image spots, the newly added illegal building identification system based on the aerial orthophoto carries out binarization processing on the image difference value of the region to be researched so as to obtain the binarized difference image of the region to be researched, and then carries out morphological processing, such as morphological expansion processing, on the binarized difference image of the region to be researched, so that the image spots of illegal buildings included in the binarized difference image of the region to be researched are more complete. And then, vectorizing the morphologically processed binary difference image by using a newly added illegal building identification system based on the aerial ortho-image to obtain a vector file. According to the newly-added illegal building identification method based on aerial orthophoto images, provided by the embodiment of the invention, after the image difference value of the to-be-researched area is subjected to binarization processing to obtain the binarization difference image of the to-be-researched area, the binarization difference image of the to-be-researched area is subjected to morphological processing, and then the image spots of the binarization difference image of the to-be-researched area are subjected to vectorization to obtain a vector file, so that more complete image spots of illegal buildings can be obtained, the newly-added illegal buildings can be accurately identified by managers, and the identification efficiency of the newly-added illegal buildings is improved.
The embodiment of the invention provides a newly-added illegal building identification method based on aerial orthographic images, which comprises the steps of respectively collecting a first image of a to-be-researched area at a first moment and a second image of the to-be-researched area at a second moment after a preset time length at the first moment; respectively carrying out orthoscopic processing and splicing operation on the first image and the second image so as to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment; performing an image registration operation on the first and second orthoimages to align the first and second orthoimages; subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched; carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference image of the area to be researched; vectorizing the image spots of the binarization difference image of the region to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building. According to the embodiment of the invention, the unmanned aerial vehicle is adopted to acquire the data of different time phases of the area to be researched, the acquired data is processed to obtain the orthophoto map, the two orthophotos are subjected to geographic registration, image difference, morphological processing, vectorization and the like, and finally the position of the newly-added illegal building is extracted and obtained, so that the image of the area to be researched can be issued in time, and managers can find the newly-added illegal building in time. In addition, as the unmanned aerial vehicle is adopted to acquire data of different time phases of the area to be researched, the resolution of the acquired image of the area to be researched is higher, and the method and the device are beneficial to accurately identifying the newly added illegal buildings by managers, so that the identification efficiency of the newly added illegal buildings is improved.
Fig. 2 is a schematic structural diagram of a newly added illegal building identification system based on an aerial orthographic image according to an embodiment of the present invention. As shown in fig. 2, the newly added illegal building identification system based on aerial orthographic images according to the embodiment of the present invention includes:
the image acquisition module 201 is configured to acquire a first image of an area to be studied at a first time and a second image of the area to be studied at a second time after a preset time duration at the first time, respectively;
an orthoimage production module 202, configured to perform orthoimage processing and stitching on the first image and the second image respectively to obtain a first orthoimage of the region to be studied at the first time and a second orthoimage of the region to be studied at the second time;
a geographic registration module 203, configured to perform an image registration operation on the first ortho image and the second ortho image to align the first ortho image and the second ortho image;
an image difference obtaining module 204, configured to subtract the first orthoimage from the second orthoimage to obtain an image difference of the region to be studied; carrying out binarization processing on the image difference value of the region to be researched to obtain a binarization difference value image of the region to be researched; and
a newly added illegal building position acquisition module 205, configured to perform vectorization on the image spot of the binarized difference image of the region to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building.
In an embodiment of the present invention, the image difference obtaining module 204 is specifically configured to:
respectively extracting R, G and B wave bands of the first orthoscopic image and R, G and B wave bands of the second orthoscopic image by using wave band operation, and respectively subtracting R, G and B wave bands of the first orthoscopic image from R, G and B wave bands of the second orthoscopic image to obtain an R wave band image difference value, a G wave band image difference value and a B wave band image difference value of the first orthoscopic image and the second orthoscopic image.
In an embodiment of the present invention, the image difference obtaining module 204 is further configured to:
respectively carrying out binarization processing on the R waveband image difference value, the G waveband image difference value and the B waveband image difference value to obtain an R waveband binarization difference value, a G waveband binarization difference value and a B waveband binarization difference value; and
and taking a union set of the R waveband binarization difference value, the G waveband binarization difference value and the B waveband binarization difference value to obtain a binarization difference image of the area to be researched.
In an embodiment of the present invention, the geographic registration module 203 is specifically configured to:
selecting a plurality of control points on the first orthoimage;
selecting a plurality of control points on the second ortho image, wherein the plurality of control points selected on the second ortho image correspond to the plurality of control points selected on the first ortho image one to one; and
aligning each of the plurality of control points on the first ortho image with a corresponding control point on the second ortho image, respectively.
In one embodiment of the present invention, the plurality of control points on the first ortho image include at least one of corner points of a house and inflection points of a road.
In one embodiment of the present invention, the preset time period is greater than or equal to a first time period threshold.
In one embodiment of the present invention, the course overlap and the side-by-side overlap of the first image and the second image during the acquisition are both greater than or equal to a first overlap threshold.
In one embodiment of the invention, the first image and the second image have a ground resolution of 5-10 cm/pixel at the time of acquisition.
Another embodiment of the present invention provides a new illegal building identification system based on aerial orthographic images, further comprising: and the morphology processing module is used for carrying out morphology processing on the binary difference image of the region to be researched. In the newly added illegal building identification system based on aerial ortho-images provided by the embodiment of the invention, after the image difference value acquisition module 204 performs binarization processing on the image difference value of the area to be researched to obtain the binarized difference image of the area to be researched, the morphological processing module is used for performing morphological processing on the binarized difference image of the area to be researched, and then the newly added illegal building position acquisition module 205 performs vectorization on the image spot of the binarized difference image of the area to be researched to obtain the vector file, so that a more complete image spot of an illegal building can be obtained, managers can accurately identify the newly added illegal building, and the identification efficiency of the newly added illegal building is improved.
The newly-added illegal building identification system based on the aerial orthographic images, provided by the embodiment of the invention, respectively collects a first image of a region to be researched at a first moment and a second image of the region to be researched at a second moment after a preset time duration at the first moment; respectively carrying out orthoscopic processing and splicing operation on the first image and the second image so as to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment; performing an image registration operation on the first and second orthoimages to align the first and second orthoimages; subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched; carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference image of the area to be researched; vectorizing the image spots of the binarization difference image of the region to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building. According to the embodiment of the invention, the unmanned aerial vehicle is adopted to acquire the data of different time phases of the area to be researched, the acquired data is processed to obtain the orthophoto map, the two orthophotos are subjected to geographic registration, image difference, morphological processing, vectorization and the like, and finally the position of the newly-added illegal building is extracted and obtained, so that the image of the area to be researched can be issued in time, and managers can find the newly-added illegal building in time. In addition, as the unmanned aerial vehicle is adopted to acquire data of different time phases of the area to be researched, the resolution of the acquired image of the area to be researched is higher, and the method and the device are beneficial to accurately identifying the newly added illegal buildings by managers, so that the identification efficiency of the newly added illegal buildings is improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A newly-added illegal building identification method based on aerial orthographic images is characterized by comprising the following steps:
respectively collecting a first image of a region to be researched at a first moment and a second image of the region to be researched at a second moment after a preset time length at the first moment;
respectively carrying out orthoscopic processing and splicing operation on the first image and the second image so as to obtain a first orthoscopic image of the area to be researched at the first moment and a second orthoscopic image of the area to be researched at the second moment;
performing an image registration operation on the first and second orthoimages to align the first and second orthoimages;
subtracting the first orthoimage from the second orthoimage to obtain an image difference value of the region to be researched;
carrying out binarization processing on the image difference value of the area to be researched to obtain a binarization difference image of the area to be researched;
vectorizing the image spots of the binarization difference image of the region to be researched to obtain a vector file; and
and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building.
2. The method of claim 1, wherein subtracting the first ortho image from the second ortho image to obtain an image difference for the region under study comprises:
respectively extracting R, G and B wave bands of the first orthoscopic image and R, G and B wave bands of the second orthoscopic image by using wave band operation, and respectively subtracting R, G and B wave bands of the first orthoscopic image from R, G and B wave bands of the second orthoscopic image to obtain an R wave band image difference value, a G wave band image difference value and a B wave band image difference value of the first orthoscopic image and the second orthoscopic image.
3. The method according to claim 2, wherein the binarizing the image difference value of the region to be studied to obtain a binarized difference image of the region to be studied comprises:
respectively carrying out binarization processing on the R waveband image difference value, the G waveband image difference value and the B waveband image difference value to obtain an R waveband binarization difference value, a G waveband binarization difference value and a B waveband binarization difference value; and
and taking a union set of the R waveband binarization difference value, the G waveband binarization difference value and the B waveband binarization difference value to obtain a binarization difference image of the area to be researched.
4. The method of any one of claims 1 to 3, wherein said performing an image registration operation on said first and second orthoimages to align said first and second orthoimages comprises:
selecting a plurality of control points on the first orthoimage;
selecting a plurality of control points on the second ortho image, wherein the plurality of control points selected on the second ortho image correspond to the plurality of control points selected on the first ortho image one to one; and
aligning each of the plurality of control points on the first ortho image with a corresponding control point on the second ortho image, respectively.
5. The method of claim 4, wherein the plurality of control points on the first orthophoto image comprise at least one of corner points of a house and corner points of a road.
6. The method according to any one of claims 1 to 3, wherein after the binarizing processing the image difference value of the region to be studied to obtain the binarized difference image of the region to be studied, and before the vectorizing the image patches of the binarized difference image of the region to be studied to obtain the vector file, the method further comprises:
and carrying out morphological processing on the binarization difference image of the region to be researched.
7. The method according to any one of claims 1 to 3, wherein the preset time period is greater than or equal to a first time period threshold.
8. The method of any of claims 1 to 3, wherein the first and second images, when acquired, each have a heading overlap and a side-by-side overlap greater than or equal to a first overlap threshold.
9. The method of any one of claims 1 to 3, wherein the first image and the second image have a ground resolution of 5-10 cm/pixel at the time of acquisition.
10. The utility model provides a newly-increased illegal building identification system based on orthophoto that takes photo by plane, its characterized in that includes:
the image acquisition module is used for respectively acquiring a first image of an area to be researched at a first moment and a second image of the area to be researched at a second moment after a preset time length at the first moment;
the orthoimage production module is used for respectively carrying out orthoimage processing and splicing operation on the first image and the second image so as to obtain a first orthoimage of the area to be researched at the first moment and a second orthoimage of the area to be researched at the second moment;
a geographic registration module for performing an image registration operation on the first and second orthoimages to align the first and second orthoimages;
an image difference acquisition module, configured to subtract the first ortho image from the second ortho image to obtain an image difference of the region to be studied; carrying out binarization processing on the image difference value of the region to be researched to obtain a binarization difference value image of the region to be researched; and
a newly added illegal building position acquisition module used for vectorizing the image spots of the binarization difference image of the area to be researched to obtain a vector file; and superposing the vector file on the second orthographic image to obtain the position of a newly added illegal building.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110392840.7A CN113095223A (en) | 2021-04-13 | 2021-04-13 | Newly-added illegal building identification method and system based on aerial orthographic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110392840.7A CN113095223A (en) | 2021-04-13 | 2021-04-13 | Newly-added illegal building identification method and system based on aerial orthographic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113095223A true CN113095223A (en) | 2021-07-09 |
Family
ID=76676563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110392840.7A Pending CN113095223A (en) | 2021-04-13 | 2021-04-13 | Newly-added illegal building identification method and system based on aerial orthographic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095223A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762931A (en) * | 2021-09-10 | 2021-12-07 | 广州建通测绘地理信息技术股份有限公司 | Method for monitoring illegal building based on DSM and DOM |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101281649A (en) * | 2008-05-30 | 2008-10-08 | 武汉大学 | Method for detecting surroundings variation movably |
| TW200840993A (en) * | 2007-04-04 | 2008-10-16 | Univ Nat Central | Ortho-rectification method of photogrammetry with high-spatial resolution |
| CN105893972A (en) * | 2016-04-08 | 2016-08-24 | 深圳市智绘科技有限公司 | Automatic illegal building monitoring method based on image and realization system thereof |
| CN106971402A (en) * | 2017-04-21 | 2017-07-21 | 西安电子科技大学 | A kind of SAR image change detection aided in based on optics |
| CN108052917A (en) * | 2017-12-25 | 2018-05-18 | 东南大学 | A kind of method of the architecture against regulations automatic identification found based on new and old Temporal variation |
| US20190194666A1 (en) * | 2016-06-17 | 2019-06-27 | Ionis Pharmaceuticals, Inc. | Modulation of gys1 expression |
| CN110189355A (en) * | 2019-05-05 | 2019-08-30 | 暨南大学 | Safe escape channel occupies detection method, device, electronic equipment and storage medium |
| CN110689563A (en) * | 2019-09-27 | 2020-01-14 | 佛山科学技术学院 | Data processing method for extracting illegal building information in remote sensing image |
| CN112085778A (en) * | 2020-08-04 | 2020-12-15 | 广东国地规划科技股份有限公司 | Oblique photography illegal building detection method and system based on superpixels and morphology |
-
2021
- 2021-04-13 CN CN202110392840.7A patent/CN113095223A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200840993A (en) * | 2007-04-04 | 2008-10-16 | Univ Nat Central | Ortho-rectification method of photogrammetry with high-spatial resolution |
| CN101281649A (en) * | 2008-05-30 | 2008-10-08 | 武汉大学 | Method for detecting surroundings variation movably |
| CN105893972A (en) * | 2016-04-08 | 2016-08-24 | 深圳市智绘科技有限公司 | Automatic illegal building monitoring method based on image and realization system thereof |
| US20190194666A1 (en) * | 2016-06-17 | 2019-06-27 | Ionis Pharmaceuticals, Inc. | Modulation of gys1 expression |
| CN106971402A (en) * | 2017-04-21 | 2017-07-21 | 西安电子科技大学 | A kind of SAR image change detection aided in based on optics |
| CN108052917A (en) * | 2017-12-25 | 2018-05-18 | 东南大学 | A kind of method of the architecture against regulations automatic identification found based on new and old Temporal variation |
| CN110189355A (en) * | 2019-05-05 | 2019-08-30 | 暨南大学 | Safe escape channel occupies detection method, device, electronic equipment and storage medium |
| CN110689563A (en) * | 2019-09-27 | 2020-01-14 | 佛山科学技术学院 | Data processing method for extracting illegal building information in remote sensing image |
| CN112085778A (en) * | 2020-08-04 | 2020-12-15 | 广东国地规划科技股份有限公司 | Oblique photography illegal building detection method and system based on superpixels and morphology |
Non-Patent Citations (3)
| Title |
|---|
| 宫鹏 等: "利用数字摄影测量探测橡树草原变化", 《遥感学报》 * |
| 张晓东: "基于遥感影像与GIS数据的变化检测理论和方法研究", 《中国优秀博硕士学位论文全文数据库(博士)基础科学辑》 * |
| 郝中豫 等: "低空遥感在违法建筑快速监测中的应用", 《测绘信息与工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762931A (en) * | 2021-09-10 | 2021-12-07 | 广州建通测绘地理信息技术股份有限公司 | Method for monitoring illegal building based on DSM and DOM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kakooei et al. | Fusion of satellite, aircraft, and UAV data for automatic disaster damage assessment | |
| Ghanea et al. | Building extraction from high-resolution satellite images in urban areas: Recent methods and strategies against significant challenges | |
| US8503761B2 (en) | Geospatial modeling system for classifying building and vegetation in a DSM and related methods | |
| CN110889327B (en) | Intelligent detection method for sewage outlet around water area based on thermal infrared image | |
| Grigillo et al. | Automated building extraction from IKONOS images in suburban areas | |
| CN107818303A (en) | Unmanned plane oil-gas pipeline image automatic comparative analysis method, system and software memory | |
| Mozgovoy et al. | Automated recognition of vegetation and water bodies on the territory of megacities in satellite images of visible and IR bands | |
| CN112990086A (en) | Remote sensing image building detection method and device and computer readable storage medium | |
| JP7418281B2 (en) | Feature classification system, classification method and its program | |
| CN110986889A (en) | High-voltage substation panoramic monitoring method based on remote sensing image technology | |
| CN103700063B (en) | Topography integration quick mapping method based on high definition satellite image | |
| Uzar | Automatic building extraction with multi-sensor data using rule-based classification | |
| CN114463623A (en) | Method and device for detecting farmland change based on multi-scale remote sensing image | |
| CN112085778A (en) | Oblique photography illegal building detection method and system based on superpixels and morphology | |
| CN113286081A (en) | Target identification method, device, equipment and medium for airport panoramic video | |
| CN113095223A (en) | Newly-added illegal building identification method and system based on aerial orthographic image | |
| CN111753645A (en) | Inspection method and inspection device for photovoltaic power station and storage medium | |
| Shokri et al. | Utility poles extraction from mobile LiDAR data in urban area based on density information | |
| CN115760885B (en) | High-closure-degree wetland forest parameter extraction method based on consumer-level unmanned aerial vehicle image | |
| CN116468869A (en) | Live-action three-dimensional modeling method, equipment and medium based on remote sensing satellite image | |
| Cömert et al. | Detection of collapsed building from unmanned aerial vehicle data with object based image classification | |
| Poznanska et al. | Derivation of urban objects and their attributes for large-scale urban areas based on very high resolution UltraCam true orthophotos and nDSM: a case study Berlin, Germany | |
| Grigillo et al. | Classification based building detection from GeoEye-1 images | |
| Liu et al. | Framework for Runway's True Heading Extraction in Remote Sensing Images Based on Deep Learning and Semantic Constraints | |
| Wang et al. | Building extraction from LiDAR and aerial images and its accuracy evaluation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |