CN111798415A - Method and device for monitoring buildings in expressway control area and storage medium - Google Patents
Method and device for monitoring buildings in expressway control area and storage medium Download PDFInfo
- Publication number
- CN111798415A CN111798415A CN202010545784.1A CN202010545784A CN111798415A CN 111798415 A CN111798415 A CN 111798415A CN 202010545784 A CN202010545784 A CN 202010545784A CN 111798415 A CN111798415 A CN 111798415A
- Authority
- CN
- China
- Prior art keywords
- control area
- remote sensing
- resolution remote
- sensing image
- expressway
- 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 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 49
- 238000001514 detection method Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012806 monitoring device Methods 0.000 claims description 10
- 238000005192 partition Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 241001464837 Viridiplantae Species 0.000 abstract description 2
- 238000009413 insulation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000007619 statistical method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000033228 biological regulation Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 101150073669 NCAN gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a device and a storage medium for monitoring buildings in a highway control area, wherein the method comprises the following steps: acquiring a high-resolution remote sensing image within a control area of the expressway; performing superpixel segmentation on the high-resolution remote sensing image to obtain a superpixel block; detecting a straight line segment in each superpixel block; counting the number of straight line segments in each super pixel block, determining a segmentation threshold, and if the number of the straight line segments is greater than the segmentation threshold, marking all pixels in the super pixel block as a building; otherwise, all pixels in the superpixel block are marked as non-buildings. According to the invention, the remote sensing image is used for detecting the buildings in the control area of the expressway, even if a large number of sound insulation screens and green plants are arranged on two sides of the expressway, the covering range of the expressway is wide, the spatial resolution can reach the sub-meter level, and the revisiting period is short, so that the buildings in the control area of the expressway can be accurately monitored, and the manual on-site inspection cost is effectively reduced.
Description
Technical Field
The invention relates to a method and a device for monitoring buildings in a highway control area and a storage medium, belonging to the technical field of remote sensing digital image processing.
Background
With the rapid development of national social economy construction, particularly the rapid increase of economy along the highway, a plurality of challenges are brought to the administration of the highway control area by the administration related management departments. In order to reduce contradiction between human and land and guarantee the safety of highway operation, a lot of provinces have clear regulations on buildings in the range of highway control areas, such as the regulations of highway regulations in Jiangsu province: the range of 30 meters from the outer edge of the highway barrier and 50 meters from the outer edge of the interchange and extra-large bridge barrier is a highway building control area; "the vertical projection of the buildings and structures on both sides of the highway can not be in the control area range of the highway buildings"; the advertisement facilities are forbidden to be arranged in the ranges of expressways, road sites and building control areas, and the like.
However, in recent years, in order to solve environmental problems such as noise and exhaust gas, a large number of sound insulation screens and green plants are added on two sides of a highway, the illegal conditions are difficult to find in time during highway patrol, the control area management difficulty is increased, and the means for supervising buildings in the highway range by purely depending on a manual patrol mode cannot be completely adapted.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a method, a device and a storage medium for monitoring buildings in an expressway control area.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a method for monitoring buildings in a highway control area, comprising the steps of:
acquiring a high-resolution remote sensing image within a control area of the expressway;
performing superpixel segmentation on the high-resolution remote sensing image to obtain a superpixel block;
detecting a straight line segment in each superpixel block;
counting the number of straight line segments in each super pixel block, determining a segmentation threshold, and if the number of the straight line segments is greater than the segmentation threshold, marking all pixels in the super pixel block as a building; otherwise, all pixels in the superpixel block are marked as non-buildings.
With reference to the first aspect, further, the method for obtaining high-resolution remote sensing images in the control area of the highway includes the following steps:
collecting multi-time-phase high-resolution remote sensing images and calibration data of the range of the highway control area, wherein the multi-time-phase high-resolution remote sensing images comprise the same highway control area;
and matching and fusing the multi-time high-resolution remote sensing image with the calibration data of the expressway control area range, thereby obtaining the high-resolution remote sensing image in the expressway control area range.
With reference to the first aspect, further, the super-pixel segmentation is performed by using a SLIC algorithm.
With reference to the first aspect, further, in the SLIC algorithm, 200 pixels are selected as an orientation degree division scale, the size of each super-pixel block is N/200, and the step length S = sqrt (N/200) of adjacent seed points;
wherein N is the total number of pixels of the high-resolution remote sensing image, and N = L × W; l is the length of the high-resolution remote sensing image, and W is the width of the high-resolution remote sensing image.
With reference to the first aspect, further, the LSD algorithm is used to detect straight line segments in each super-pixel block.
With reference to the first aspect, further, the method for determining the segmentation threshold includes the following steps:
sequencing the number of the line segments of the straight line segments of all the superpixel blocks;
determining the segmentation threshold using an automatic threshold segmentation algorithm.
With reference to the first aspect, further, the method further includes:
counting the pixel number of the high-resolution remote sensing image within the range of the control area of the expressway;
counting the number of pixels of the marked buildings;
and calculating the ratio of the pixel number of the building to the pixel number of the high-resolution remote sensing image in the control area range of the expressway, and drawing a ratio curve.
In a second aspect, the invention provides a building monitoring device for a highway control area, which comprises the following modules:
an acquisition module: the system is used for acquiring high-resolution remote sensing images in the range of the highway control area;
a segmentation module: the super-pixel segmentation module is used for carrying out super-pixel segmentation on the high-resolution remote sensing image to obtain super-pixel blocks;
a detection module: for detecting straight line segments in each superpixel block;
a marking module: the system comprises a super pixel block, a partition threshold value and a building, wherein the super pixel block is used for counting the number of straight line segments in each super pixel block, and if the number of the straight line segments is larger than the partition threshold value, all pixels in the super pixel block are marked as the building; otherwise, all pixels in the superpixel block are marked as non-buildings.
In a third aspect, the present invention provides a building monitoring device for a highway control area, comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method of any of the first aspects.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any one of the first aspect.
Compared with the prior art, the monitoring method, the monitoring device and the storage medium for the buildings in the expressway control area provided by the embodiment of the invention have the following beneficial effects:
by utilizing the characteristics that the coverage range of the high-resolution remote sensing image is wide, the spatial resolution can reach the sub-meter level, and the revisit period can be in units of days, the buildings in the range of the control area of the expressway are monitored, the manual on-site inspection cost can be effectively reduced, the working efficiency of the administrative related management departments in the management work of the buildings in the control area of the expressway is effectively improved, and the area of the land along the expressway is fully ensured not to be illegally occupied.
Drawings
Fig. 1 is a flow chart of a method for monitoring buildings in a highway control area according to an embodiment of the invention;
FIG. 2 is a schematic block diagram of a method for monitoring buildings in a highway controlled area according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of a building monitoring device for a highway control area according to an embodiment of the invention;
FIG. 4 is a high-resolution remote sensing image within the control area of a highway obtained from Beijing satellite II;
FIG. 5 is a diagram of the effect of superpixel segmentation on FIG. 4 using the SLIC algorithm;
FIG. 6 is a graph of the effect of using the LSD algorithm to perform line segment detection on FIG. 5;
FIG. 7 is an effect diagram of superimposing the superpixel segmentation result of FIG. 5 with the straight line segment detection result of FIG. 6;
fig. 8 is a graph of the building monitoring results of fig. 4 obtained by the monitoring method provided by the embodiment of the invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1 and fig. 2, an embodiment of the present invention provides a method for monitoring a building in a highway control area, where the method includes the following steps:
acquiring a high-resolution remote sensing image within a control area of the expressway;
performing superpixel segmentation on the high-resolution remote sensing image to obtain a superpixel block;
detecting a straight line segment in each superpixel block;
counting the number of straight line segments in each super pixel block, determining a segmentation threshold, and if the number of the straight line segments is greater than the segmentation threshold, marking all pixels in the super pixel block as a building; otherwise, all pixels in the superpixel block are marked as non-buildings.
Specifically, the method for acquiring the high-resolution remote sensing image in the range of the highway control area comprises the following steps: collecting multi-time-phase high-resolution remote sensing images and calibration data of the range of the highway control area, wherein the multi-time-phase high-resolution remote sensing images comprise the same highway control area; and matching and fusing the multi-time high-resolution remote sensing image with the calibration data of the expressway control area range, thereby obtaining the high-resolution remote sensing image in the expressway control area range.
Compared with the medium-low resolution remote sensing image, the high-resolution remote sensing image has higher spatial resolution. The higher spatial resolution means that the image expresses the ground feature more fully and specifically, and has abundant information quantity. Compared with the image shot by a common camera, the high-resolution remote sensing image has the characteristic of wider coverage range, the whole control area can be shot in one scene, and a user can conveniently sense the full view of the highway control area. And matching and fusing the acquired high-resolution remote sensing image with a pre-calibrated expressway control area range to obtain image data in the control area range, and preparing for subsequent processing. The resolution ratio of the high-resolution second satellite image or the Beijing second image which can be adopted in the embodiment of the invention can reach 0.8 meter, and the size of a common artificial building is more than 0.8 meter, so the image with the resolution ratio can meet the requirement of building detection.
The embodiment of the invention provides a detection process of a building in a high-resolution remote sensing image highway control area, and as shown in figure 2, the building detection method mainly comprises image superpixel segmentation, straight line detection and building judgment. Specifically, when the super-pixel segmentation is performed on the image to obtain a super-pixel block, based on the high-resolution remote sensing image used in this embodiment, a Simple Linear Iterative Clustering (SLIC) super-pixel segmentation algorithm is specifically implemented as follows:
step 1-a, determining the number of segmented super pixel blocks and initial seed points:
reading the size of the high-resolution remote sensing image, and assuming the length of the image to beLWide isWThen the total number of image pixels isN=L*W(ii) a In this embodiment, the resolution of the high-resolution remote sensing images is greater than 0.8 m, and the length of a building is generally 10m, so that it is appropriate to take 200 pixels in the orientation degree segmentation scale in this embodiment, the size of each super-pixel block is N/200, and the step length of the adjacent seed points isSThe calculation formula is as follows:
to be provided withSAnd uniformly distributing initial seed points in the image according to the calculated number (N/200) of the superpixel blocks as step sizes.
Step 1-b, re-optimizing the seed points:
initial selection of seed points in step 1-an*nThe adjustment is made in the neighborhood of (c),ncan take any integer value, in this embodimentnAnd taking 3. The specific implementation method comprises the following steps:
stepb-01: calculating gradient values of all pixel points in 3 × 3 neighborhood, specifically as follows:
for a certain pixel point(i,j)Gradient thereofG(x,y)Calculated according to the following formula:
G(x,y)=dx(i,j)+dy(i,j)
dx(i,j)=I(i+1,j)-I(i,j)
dy(i,j)=I(i,j+1)-I(i,j)
in the formula (I), the compound is shown in the specification,dx(i,j)representing pixel points(i,j)The value of the horizontal-direction gradient of (a),dy(i,j)representing pixel points(i,j)The gradient value in the vertical direction is set,I(i,j)representing pixel points(i,j)The pixel value of (2), adopted in this embodimentR、G、BThe average of the values is taken as the pixel value.
Stepb-02: and comparing the calculation results, and taking the point with the minimum gradient value as the optimized seed point, thereby avoiding the influence of the initially selected seed point on the boundary line with larger gradient on the subsequent segmentation effect.
Step 1-c, labeling pixel classification labels:
at each seed point2S*2S(where S is the foregoing step sizeS) And performing K-means clustering in the neighborhood range, and distributing the clustered labels for each pixel point.
Step 1-d, distance measurement:
and respectively calculating the distance between the classified pixel point and the seed point. The distance calculation formula is as follows:
in the formula (I), the compound is shown in the specification,r i ,r j ,g i ,g j ,b i ,b j are respectively a pointiAnd pointjThe value over the RGB band of (a),d c is the color distance;x i ,y i is a pointiThe coordinates of the image of (a) are,x j ,y j is a pointjThe coordinates of the image of (a) are,d s represents a spatial distance;N s is the maximum color distance within the class,N s =S；N c taking a fixed constant as the maximum color distance in the classmIn this embodimentmThe value was taken to be 30.
Step 1-e, iterative optimization:
in order to make the above step errors converge, an iterative calculation is required. In order to accelerate the iterative convergence speed and avoid overlong running time caused by excessive iterative computation, the iteration times can be manually set. Practice shows that the high-resolution remote sensing image in the embodiment can achieve a better effect when the iteration number is set to be 12.
Step 1-f, connectivity enhancement:
in order to avoid the situations of multiple connectivity, over-pixel block size and undersize after iteration, connectivity enhancement operation needs to be performed after iteration. The method comprises the following specific steps:
firstly, a marking table is newly built, all elements in the table are marked as-1, discontinuous superpixel blocks, superpixel blocks with small sizes and the nearest superpixel blocks are combined from left to right and from top to bottom, and the traversed pixel points are marked as 0 until all the pixel points are traversed.
As shown in fig. 4, the resolution of the high-resolution remote sensing image in the control area range of the expressway is as high as 0.8 m, and the green space and buildings are clearly visible in the image, which is obtained by a beijing second satellite. Selecting 200 pixels as the orientation degree segmentation scale, and performing superpixel segmentation on the image according to the aforementioned steps 1-a to 1-f of this embodiment can obtain a superpixel segmentation effect map as shown in fig. 5, and as can be seen from fig. 5, the greenbelt and the building have been segmented into different superpixel blocks.
Specifically, in detecting a straight Line segment in each super-pixel block, a Line Segment Detector (LSD) algorithm is used to detect a straight Line segment in each super-pixel block. Based on the high-resolution remote sensing image used in the embodiment, the LSD line detection algorithm is specifically implemented by the following steps:
step 2-a, image scale down-sampling:
to reduce the aliasing effect in the image, the original high-resolution remote sensing image is down-sampled in the x and y directions at a scale of 0.8.
Step 2-b, gradient calculation:
and calculating gradient values of each pixel point in the x direction and the y direction.
Step 2-c, gradient pseudo-ordering:
the larger the gradient value is, the more prominent the edge point is, and the seed point is more suitable for use. However, it is time consuming to completely sort the gradient values, so the gradient values are divided into 1024 levels, and the 1024 levels cover the range of the gradient from 0 to 255. And establishing a state list, and setting all pixel points as unused. Traversing the whole gradient map, putting pixel coordinates with the same gradient value into the same linked list according to the gradient strength, and integrating 1024 linked lists from large to small.
Step 2-d, gradient threshold suppression:
and setting the corresponding position in the pixel point state table with the gradient value smaller than rho as used. In this embodiment, according to experience, when ρ is 0.2, a good detection result can be obtained.
Step 2-e, region growing:
and taking out the coordinate position of the image stored at the head of the linked list table as a seed point, taking the seed point as a starting point, similarly performing region diffusion according to the gradient angle direction, deleting the pixel coordinate from the linked list when one pixel is diffused, and changing the marking state into used until the diffusion can not be continued any more.
Step 2-f, rectangle estimation:
and performing rectangle fitting on the diffusion area, judging whether the density of points in the same rectangle meets a threshold value D, if not, truncating the rectangle into a plurality of rectangle frames until the density of the points in all the rectangles meets the threshold value. In this embodiment, 20 out of D is preferable.
Step 2-g, detecting linear output:
and calculating the density of the midpoint of each fitted rectangle, introducing an adjusting model according to the density ratio, and constraining whether the current rectangle can be output as a straight line according to the adjusting model. Thereby obtaining all the detected straight line segments of the image. The calculation formula of whether the fitted rectangle can be output as a straight line is as follows:
where N and M are the columns and rows of the sampled image and B (N, k, p) is a binomial distribution. N is the number of all pixels in the current rectangle, k is the largest number of pixels in the uniform direction, and p is the probability density. When NFA is less than 1, then the current rectangle is considered to be the most straight line output.
As shown in fig. 6, which is an effect diagram of performing the linear segment detection on fig. 5 by using the LSD algorithm, where the gradient threshold parameter is 0.2 and the density threshold parameter is 20, it can be seen from fig. 6 that the detected linear segments are mainly concentrated in the area where the building is located, and there are almost no linear segments in the green space and other parts, so that it is feasible to determine the building by linear segment detection. Specifically, when building determination is performed, the number of straight line segments in each superpixel block needs to be counted, a reasonable threshold is set, when the number of line segments is greater than the threshold, all pixels in the superpixel block are marked as a building, and when the number of line segments is less than the threshold, all pixels in the superpixel block are marked as a non-building. In this embodiment, the threshold determination step is as follows:
step 3-a, counting the number of straight line segments of each super pixel block;
step 3-b, sequencing the number of each linear line segment;
and 3-c, obtaining a segmentation threshold by adopting an automatic threshold segmentation algorithm (ostu).
Specifically, the number of the straight line segments in the step 3-b is used as a gray level, and a total of L levels are set; counting the number of superpixel blocks appearing in each gray level, wherein the superpixel blocks can be used as a histogram; the histogram is normalized to stretch the gray scale from 0-L to 0-255. Is provided withiRepresenting the segmentation threshold, i.e. one gray level, iterates from 0 to 255. Statistics 0-iNumber of super-pixel blocks of gray scaleRatio of total number of image super pixel blocksw 0And count 0-iAverage value of gray levelsu 0(ii) a Statistics ofi-255 gray level superpixel blocks in total to the total superpixel blocksw 1And the mean value of gray scaleu 1. Calculation of the variance G =w 0*w 1*（u 0-u 1）*（u 0-u 1) (ii) a Then when G is the maximum value, outputiI.e. the segmentation threshold.
As shown in fig. 7, the result of super-pixel division in fig. 5 and the result of straight line segment detection in fig. 6 are superimposed. Fig. 8 is a graph of the building monitoring results of fig. 4 obtained by the monitoring method provided by the embodiment of the invention, wherein the building is clearly divided.
In conclusion, the invention can improve the monitoring capability and effect of buildings in the highway control area, and plays a positive role in reducing the manual inspection cost and ensuring that the area along the highway is not illegally occupied.
As shown in fig. 1, the method for obtaining a high-resolution remote sensing image in a control area of a highway further includes performing statistical analysis on the building detection result. Based on the detection result of this embodiment, the specific statistical analysis implementation steps are as follows:
step 4-a, counting the number of pixels in the range of the highway control area;
step 4-b, counting the number of pixels marked as buildings;
step 4-c, the ratio of the number of the building pixels to the total number of the pixels in the range of the control area;
and 4-d, drawing a multi-temporal remote sensing image building pixel number ratio curve.
By carrying out statistical analysis on the change of the proportion of the buildings in the range of the highway control area, law enforcement officers can be helped to judge the increase or decrease of the buildings in the range of the highway control area. If the new increase is gradually made, the law enforcement strength is not enough, and the investigation is not strict; if the number is reduced, the management is effective.
As shown in fig. 3, an embodiment of the present invention further provides a highway control area building monitoring device, which can be used in the foregoing monitoring method, and the device includes the following modules:
an acquisition module: the system is used for acquiring high-resolution remote sensing images in the range of the highway control area;
a segmentation module: the super-pixel segmentation module is used for carrying out super-pixel segmentation on the high-resolution remote sensing image to obtain super-pixel blocks;
a detection module: for detecting straight line segments in each superpixel block;
a marking module: the system comprises a super pixel block, a partition threshold value and a building, wherein the super pixel block is used for counting the number of straight line segments in each super pixel block, and if the number of the straight line segments is larger than the partition threshold value, all pixels in the super pixel block are marked as the building; otherwise, all pixels in the superpixel block are marked as non-buildings.
Wherein, the acquisition module specifically includes:
the high-resolution remote sensing image acquisition unit is used for storing and calling a high-resolution remote sensing image shot by a satellite;
and the expressway control area range defining unit is used for marking the control area range needing to be detected on the acquired high-resolution image and defining a boundary line.
Wherein, the segmentation module specifically includes:
the segmentation scale input unit supports a user to manually input an initial segmentation scale for the high-resolution remote sensing images with different resolutions;
and the segmentation processing unit is used for performing super-pixel segmentation processing on the image.
Wherein, detection module specifically includes:
the line detection unit is used for detecting the line segments in each super pixel block and counting the number of the line segments in each super pixel block;
a detection threshold calculation unit for calculating a classification threshold for determining whether the super pixel block is a building area;
and a detection result calculation unit for marking the pixels determined as the building.
The embodiment of the invention provides a monitoring device for buildings in an expressway control area, which further comprises a statistical analysis module, wherein the statistical analysis module is used for counting the area of the buildings in the expressway control area and analyzing the change trend, and the monitoring device specifically comprises the following components:
a. calculating the area and the area ratio of a single remote sensing image high-speed road control area;
b. and analyzing the change trend of the buildings in the control area range of the expressway through the multi-temporal remote sensing image in the same area.
The embodiment of the invention also provides a monitoring device for the buildings in the expressway control area, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of any of the preceding methods.
An embodiment of the invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of any of the methods described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for monitoring a building in a highway control area, comprising the steps of:
acquiring a high-resolution remote sensing image within a control area of the expressway;
performing superpixel segmentation on the high-resolution remote sensing image to obtain a superpixel block;
detecting a straight line segment in each superpixel block;
counting the number of straight line segments in each super pixel block, determining a segmentation threshold, and if the number of the straight line segments is greater than the segmentation threshold, marking all pixels in the super pixel block as a building; otherwise, all pixels in the superpixel block are marked as non-buildings.
2. The method for monitoring the buildings in the expressway control area according to claim 1, wherein the method for acquiring the high-resolution remote sensing image within the expressway control area comprises the following steps:
collecting multi-time-phase high-resolution remote sensing images and calibration data of the range of the highway control area, wherein the multi-time-phase high-resolution remote sensing images comprise the same highway control area;
and matching and fusing the multi-time high-resolution remote sensing image with the calibration data of the expressway control area range, thereby obtaining the high-resolution remote sensing image in the expressway control area range.
3. The highway controlled-area building monitoring method of claim 1, wherein a SLIC algorithm is used for superpixel segmentation.
4. The highway controlled-area building monitoring method according to claim 3, wherein 200 pixels are selected as an orientation degree segmentation scale in the SLIC algorithm, the size of each super-pixel block is N/200, and the step length S = sqrt (N/200) of the adjacent seed points;
wherein N is the total number of pixels of the high-resolution remote sensing image, and N = L × W; l is the length of the high-resolution remote sensing image, and W is the width of the high-resolution remote sensing image.
5. The highway controlled-area building monitoring method of claim 1, wherein the line segments in each superpixel block are detected using an LSD algorithm.
6. The highway controlled-zone building monitoring method according to claim 1, wherein the method for determining the segmentation threshold comprises the following steps:
sequencing the number of the line segments of the straight line segments of all the superpixel blocks;
determining the segmentation threshold using an automatic threshold segmentation algorithm.
7. The highway controlled area building monitoring method of claim 1, further comprising:
counting the pixel number of the high-resolution remote sensing image within the range of the control area of the expressway;
counting the number of pixels of the marked buildings;
and calculating the ratio of the pixel number of the building to the pixel number of the high-resolution remote sensing image in the control area range of the expressway, and drawing a ratio curve.
8. A highway controlled area building monitoring device, comprising:
an acquisition module: the system is used for acquiring high-resolution remote sensing images in the range of the highway control area;
a segmentation module: the super-pixel segmentation module is used for carrying out super-pixel segmentation on the high-resolution remote sensing image to obtain super-pixel blocks;
a detection module: for detecting straight line segments in each superpixel block;
a marking module: the system comprises a super pixel block, a partition threshold value and a building, wherein the super pixel block is used for counting the number of straight line segments in each super pixel block, and if the number of the straight line segments is larger than the partition threshold value, all pixels in the super pixel block are marked as the building; otherwise, all pixels in the superpixel block are marked as non-buildings.
9. A monitoring device for buildings in a highway control area is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
10. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545784.1A CN111798415A (en) | 2020-06-16 | 2020-06-16 | Method and device for monitoring buildings in expressway control area and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545784.1A CN111798415A (en) | 2020-06-16 | 2020-06-16 | Method and device for monitoring buildings in expressway control area and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111798415A true CN111798415A (en) | 2020-10-20 |
Family
ID=72804734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010545784.1A Pending CN111798415A (en) | 2020-06-16 | 2020-06-16 | Method and device for monitoring buildings in expressway control area and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111798415A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022413A (en) * | 2021-10-14 | 2022-02-08 | 中山大学 | High-frequency full-automatic remote sensing monitoring method for production and construction land |
| CN115641327A (en) * | 2022-11-09 | 2023-01-24 | 浙江天律工程管理有限公司 | Building engineering quality supervision and early warning system based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077515A (en) * | 2012-12-29 | 2013-05-01 | 北方工业大学 | Multi-spectral image building change detection method |
| CN103927743A (en) * | 2014-03-27 | 2014-07-16 | 中国科学院长春光学精密机械与物理研究所 | Method for detecting man-made targets in remotely-sensed images |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| CN107092877A (en) * | 2017-04-12 | 2017-08-25 | 武汉大学 | Remote sensing image roof contour extracting method based on basement bottom of the building vector |
| CN107730496A (en) * | 2017-10-26 | 2018-02-23 | 武汉大学 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
| CN108629286A (en) * | 2018-04-03 | 2018-10-09 | 北京航空航天大学 | A kind of remote sensing airport target detection method based on the notable model of subjective perception |
| CN108761451A (en) * | 2018-05-21 | 2018-11-06 | 中南大学 | A kind of land use change survey intelligent Understanding method based on multi-temporal remote sensing image |
| CN109598729A (en) * | 2018-11-28 | 2019-04-09 | 江苏科技大学 | A kind of ship target detection method divided based on SRM and be layered line segment feature |
-
2020
- 2020-06-16 CN CN202010545784.1A patent/CN111798415A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077515A (en) * | 2012-12-29 | 2013-05-01 | 北方工业大学 | Multi-spectral image building change detection method |
| CN103927743A (en) * | 2014-03-27 | 2014-07-16 | 中国科学院长春光学精密机械与物理研究所 | Method for detecting man-made targets in remotely-sensed images |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| CN107092877A (en) * | 2017-04-12 | 2017-08-25 | 武汉大学 | Remote sensing image roof contour extracting method based on basement bottom of the building vector |
| CN107730496A (en) * | 2017-10-26 | 2018-02-23 | 武汉大学 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
| CN108629286A (en) * | 2018-04-03 | 2018-10-09 | 北京航空航天大学 | A kind of remote sensing airport target detection method based on the notable model of subjective perception |
| CN108761451A (en) * | 2018-05-21 | 2018-11-06 | 中南大学 | A kind of land use change survey intelligent Understanding method based on multi-temporal remote sensing image |
| CN109598729A (en) * | 2018-11-28 | 2019-04-09 | 江苏科技大学 | A kind of ship target detection method divided based on SRM and be layered line segment feature |
Non-Patent Citations (1)
| Title |
|---|
| 魏旭 等: "一种结合MBI和SLIC算法的遥感影像建筑物提取方法", 《测绘与空间地理信息》, vol. 42, no. 10, pages 100 - 103 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022413A (en) * | 2021-10-14 | 2022-02-08 | 中山大学 | High-frequency full-automatic remote sensing monitoring method for production and construction land |
| CN114022413B (en) * | 2021-10-14 | 2023-03-24 | 中山大学 | High-frequency full-automatic remote sensing monitoring method for production and construction land |
| CN115641327A (en) * | 2022-11-09 | 2023-01-24 | 浙江天律工程管理有限公司 | Building engineering quality supervision and early warning system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN110889328B (en) | Method, device, electronic equipment and storage medium for detecting road traffic condition | |
| CN103268470B (en) | Object video real-time statistical method based on any scene | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN107038416A (en) | A kind of pedestrian detection method based on bianry image modified HOG features | |
| CN104599511B (en) | Traffic flow detection method based on background modeling | |
| CN115797775B (en) | Intelligent illegal building identification method and system based on near-to-ground video image | |
| CN105632170A (en) | Mean shift tracking algorithm-based traffic flow detection method | |
| CN110633678B (en) | Quick and efficient vehicle flow calculation method based on video image | |
| CN111798415A (en) | Method and device for monitoring buildings in expressway control area and storage medium | |
| Xiang et al. | Lightweight fully convolutional network for license plate detection | |
| CN111369495A (en) | Video-based panoramic image change detection method | |
| CN111680704B (en) | Automatic and rapid extraction method and device for newly-increased human active plaque of ocean red line | |
| CN108804992A (en) | A kind of Demographics' method based on deep learning | |
| CN115937673B (en) | Geographic element rapid change discovery method based on mobile terminal photo | |
| CN107992856A (en) | High score remote sensing building effects detection method under City scenarios | |
| CN109993134A (en) | A kind of intersection vehicle checking method based on HOG and SVM classifier | |
| Bu et al. | A UAV photography–based detection method for defective road marking | |
| CN109271904A (en) | A kind of black smoke vehicle detection method based on pixel adaptivenon-uniform sampling and Bayesian model | |
| CN112085778A (en) | Oblique photography illegal building detection method and system based on superpixels and morphology | |
| CN113610873B (en) | Noctilucent remote sensing image data processing method and device | |
| CN108830882A (en) | Video abnormal behaviour real-time detection method | |
| CN110807406A (en) | Foggy day detection method and device | |
| CN111126303A (en) | Multi-parking-space detection method for intelligent parking | |
| CN114187523A (en) | High-resolution remote sensing image mangrove forest monitoring method and system |
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 | ||
| CB02 | Change of applicant information |
Address after: 210014 No. 9, Ziyun Avenue, Qinhuai District, Jiangsu, Nanjing Applicant after: China Design Group Co.,Ltd. Address before: 210014 No. 9, Ziyun Avenue, Qinhuai District, Jiangsu, Nanjing Applicant before: CHINA DESIGN GROUP Co.,Ltd. |
|
| CB02 | Change of applicant information |