Illegal building detection method and system based on superpixel and morphology using oblique photography

Abstract

The present invention discloses a method and system for detecting illegal buildings by oblique photography based on superpixels and morphology, and the method comprises: obtaining first surface height image data, first surface orthophoto image data of a target area in a first time period, and second surface height image data and second surface orthophoto image data of a second time period; calculating height change image data of the target area; performing superpixel segmentation processing on the height change image data to obtain superpixel units; performing object clustering and filtering analysis on the superpixel units using architectural morphology indexes to obtain vector data of the target area. The present invention obtains height change image data based on surface height image data of different time periods, and performs post-processing on the height change image data through superpixel segmentation and architectural morphology analysis, thereby solving the problems of recognition accuracy and algorithm efficiency, and thus realizing accurate detection of urban building changes.

Description

Technical Field

[0001] The present invention relates to the field of building detection, and in particular to a method and system for detecting illegal buildings using oblique photography based on superpixels and morphology. Background Art

[0002] At present, my country's urbanization is developing rapidly, and various types of buildings are being built in a short period of time. Along with this, a large number of illegal buildings have been formed by self-built and illegal construction, which has seriously affected the building census and urban planning. The traditional building change detection and extraction methods are mainly achieved through manual investigation and interpretation of remote sensing images; however, both methods have their own disadvantages. For example, manual investigation requires law enforcement personnel to carry out on-site investigation, with a long investigation cycle and high manpower consumption, involving local or regional protection, and it is also very difficult to collect data on illegal buildings in the later stage; and the interpretation of remote sensing images is limited by the shortcomings of remote sensing images themselves, such as low timeliness, low spatial resolution, and susceptibility to weather, which makes it difficult to meet monitoring requirements.

[0003] As a high-tech technology that can obtain real surface information in real time, oblique photography by drones has attracted much attention from urban planners in recent years and has been initially applied to urban building change monitoring. By carrying a variety of sensors on the flight platform, oblique photography technology can quickly collect rich ground real information from multiple angles, and further process and transform it into DSM (surface orthophoto data) and DOM (surface orthophoto data), which meet the current needs of urban building change monitoring in terms of time resolution, spatial resolution, and height resolution. The existing methods are oriented towards real-life three-dimensional modeling, judging illegal buildings by changes in the map, but they can only present intuitive and effective representations in small-area applications; there are also methods that directly analyze the difference in DSM height changes before and after to detect building changes, but this analysis method also has the disadvantage that the morphological accuracy of the extracted building change area is not high. Summary of the invention

[0004] In order to solve at least one of the technical problems existing in the prior art, the purpose of the present invention is to provide a method and system for detecting illegal buildings by oblique photography based on superpixels and morphology.

[0005] According to a first aspect of an embodiment of the present invention, a method for detecting illegal buildings by oblique photography based on superpixels and morphology comprises the following steps:

[0006] Acquire first surface height image data and first surface orthophoto image data of the target area in the first time period and second surface height image data and second surface orthophoto image data of the target area in the second time period;

[0007] Calculate the height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data and the second surface orthophoto image data;

[0008] Performing super-pixel segmentation processing on the height-change image data to obtain super-pixel units;

[0009] The architectural morphology index is used to perform object clustering and filtering analysis on the superpixel unit to obtain vector data of the target area.

[0010] Further, the step of obtaining first surface height image data and first surface orthophoto image data of the target area in the first time period and second surface height image data and second surface orthophoto image data of the second time period includes:

[0011] Acquire first oblique image data of the target area in a first time period and second oblique image data in a second time period;

[0012] Generate the first surface height image data and the first surface orthophoto image data according to the first oblique image data;

[0013] The second surface height image data and the second surface orthophoto image data are generated according to the second oblique image data.

[0014] Further, the step of calculating the height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data and the second surface orthophoto image data includes:

[0015] Acquire the first surface height image data, the first surface orthophoto image data, the second surface height image data, and the second surface orthophoto image data;

[0016] Performing geographic location registration on the first surface orthophoto image data and the second surface orthophoto image data to obtain registration adjustment parameters;

[0017] Registering the first ground surface height image data and the second ground surface height image data according to the registration adjustment parameter;

[0018] The height change image data of the target area is calculated based on the first surface height image data and the second surface height image data after registration.

[0019] Furthermore, the step of performing super-pixel segmentation processing on the height-change image data to obtain super-pixel units includes:

[0020] Acquire the height change image data and category data;

[0021] Calculating a segmentation interval, and segmenting the height-varying image data according to the segmentation interval to form superpixel seed points;

[0022] Analyze surrounding pixels with the superpixel seed point as the center, and assign the pixels to the superpixel seed point;

[0023] The superpixel seed points are allocated according to the category data to form the superpixel units.

[0024] Furthermore, the segmentation interval is calculated by the following formula:

[0025]

[0026] Wherein, S represents the segmentation spacing, N represents the total number of pixels of the highly variable image data, and K represents the size of the superpixel seed point.

[0027] Furthermore, the step of performing object clustering and filtering analysis on the superpixel unit using the architectural morphology index to obtain vector data of the target area includes:

[0028] Acquire the superpixel unit;

[0029] Calculating basic properties of a single superpixel unit;

[0030] Calculate the merged attributes between different superpixel units according to the basic attributes, and then calculate the measurement parameter according to the merged attributes;

[0031] Performing a threshold determination on the measurement parameter, and performing a merging operation according to the determination result to obtain a clustering unit;

[0032] The vector data of the target area is obtained according to the clustering unit.

[0033] Furthermore, the basic attributes include the average value of height change, area, morphological index, and the number of superpixel unit mergers.

[0034] According to a second aspect of an embodiment of the present invention, a superpixel and morphology-based oblique photography illegal building detection system includes the following modules:

[0035] A data acquisition module, used to acquire first surface height image data and first surface orthophoto image data of a target area in a first time period and second surface height image data and second surface orthophoto image data of a second time period;

[0036] an altitude change analysis module, configured to calculate altitude change image data of the target area according to the first surface altitude image data, the first surface orthophoto image data, the second surface altitude image data and the second surface orthophoto image data;

[0037] A superpixel segmentation analysis module is used to perform superpixel segmentation processing on the height change image data to obtain superpixel units;

[0038] The architectural morphology analysis module is used to perform object clustering and filtering analysis on the superpixel unit using the architectural morphology index to obtain vector data of the target area.

[0039] According to a third aspect of an embodiment of the present invention, a superpixel and morphology-based oblique photography illegal building detection system includes:

[0040] at least one processor;

[0041] at least one memory for storing at least one program;

[0042] When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in the first aspect.

[0043] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium stores a program executable by a processor, wherein the program executable by the processor is used to implement the method described in the first aspect when executed by the processor.

[0044] The beneficial effects of the present invention are: obtaining height change image data based on surface height image data of different time periods, clustering pixels through superpixel segmentation, and then filtering and analyzing attributes with superpixel units, which can greatly reduce processing time and improve algorithm efficiency compared to direct clustering analysis. In the later stage, architectural morphology clustering analysis is used to solve the recognition accuracy problem, thereby realizing accurate detection of urban building changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present invention or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 is a flowchart of steps provided by an embodiment of the present invention;

[0047] Figure 2is a module connection diagram provided by an embodiment of the present invention;

[0048] Figure 3 It is a device connection diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The concept, specific structure and technical effects of the present invention will be clearly and completely described below in combination with the embodiments and drawings to fully understand the purpose, scheme and effect of the present invention.

[0050] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0052] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] An embodiment of the present invention provides a method for detecting illegal buildings using oblique photography based on superpixels and morphology. The method can be applied to a terminal or a server, and can also be software running in a terminal or a server, such as an application with an image color constancy processing function. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms. Reference Figure 1 The method comprises the following steps S100 to S400:

[0054] S100, acquiring first surface height image data and first surface orthophoto image data of a target area in a first time period and second surface height image data and second surface orthophoto image data of a second time period;

[0055] Optionally, S100 may be implemented by the following steps:

[0056] S101, acquiring first oblique image data of a target area in a first time period and second oblique image data in a second time period;

[0057] S102, generating first surface height image data and first surface orthophoto image data according to the first oblique image data;

[0058] S103, generating second surface height image data and second surface orthophoto image data according to the second oblique image data;

[0059] S200, calculating height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data, and the second surface orthophoto image data;

[0060] Optionally, S200 can be implemented by the following steps:

[0061] S201, acquiring first surface height image data, first surface orthophoto image data, second surface height image data, and second surface orthophoto image data;

[0062] S202, performing geographic location registration on the first surface orthophoto image data and the second surface orthophoto image data to obtain registration adjustment parameters;

[0063] S203, registering the first ground surface height image data and the second ground surface height image data according to the registration adjustment parameter;

[0064] S204, calculating the height change image data of the target area according to the registered first surface height image data and the second surface height image data;

[0065] In some preferred embodiments, control points are marked on the RGB bands of two surface orthophotos of different time periods to make the control points as evenly distributed and effective as possible; according to the specific conditions of the control points and the two images, a polynomial correction method is used for spatial registration, and two surface height images corresponding to different time periods are registered according to the registration modification parameters and a registered image of cubic convolution interpolation is output; and the height change image data is calculated according to the following formula:

[0066] DSMChange = DSM2 - DSM1,

[0067] DSM2 represents the latest collected surface height image, and DSM1 represents the previously collected surface height image, and the height change image DSMChange of the same location is obtained; when the pixel value is positive, it means the height increases, otherwise it means the height decreases;

[0068] S300, performing super-pixel segmentation processing on the height change image data to obtain super-pixel units;

[0069] Optionally, S300 can be implemented by the following steps:

[0070] S301, obtaining height change image data and category data;

[0071] S302, calculating the segmentation interval, and segmenting the height-varying image data according to the segmentation interval to form super-pixel seed points;

[0072] S303, analyzing surrounding pixels with the superpixel seed point as the center, and assigning the pixels to the superpixel seed point;

[0073] S304, allocating superpixel seed points according to the category data, thereby forming superpixel units;

[0074] In some preferred embodiments, the segmentation spacing is calculated by the following formula:

[0075]

[0076] Among them, S represents the segmentation spacing, N represents the total number of pixels of the highly variable image data, and K represents the size of the superpixel seed point;

[0077] Initialize the superpixel seed point in the row and column direction S; move the superpixel seed point to the lowest gradient point within the 3*3 range, and initialize the label and distance (D) of the superpixel seed point respectively; take the superpixel seed point as the center, and calculate all the pixel points p within the accessible range 2S*2S in all directions. j To the superpixel seed point p i The distance D j , D j Calculated by the following formula:

[0078]

[0079] Among them, d c Represents the pixel distance, the formula is d c =(v j -v i )V;d s Represents the spatial distance, and the formula is m represents a fixed constant, and its value range is generally [1,40], which is used to weigh the relative importance of pixel similarity and spatial proximity. j Whether it belongs to the superpixel seed point p i , D j If the distance is less than the maximum distance of the superpixel seed point class, it can be assigned to this seed point class. If it is visited by multiple seed points, it belongs to the superpixel seed point class with the smallest distance. Update all category data and move the superpixel seed point to the morphological center of the category to which it belongs. Repeat the above steps 10 times to get a relatively ideal result.

[0080] S400, performing object clustering and filtering analysis on superpixel units using architectural morphology index to obtain vector data of the target area;

[0081] Optionally, S400 can be implemented by the following steps:

[0082] S401, obtaining a super pixel unit;

[0083] S402, calculating the basic attributes of a single superpixel unit; the basic attributes include the average height change, area, morphological index, and number of superpixel unit mergers; filtering out superpixel units that have not undergone height changes.

[0084] S403, calculating the merged attributes between different superpixel units according to the basic attributes, and then calculating the measurement parameters according to the merged attributes;

[0085] S404, performing a threshold determination on the measurement parameter, and performing a merging operation according to the determination result to obtain a clustering unit;

[0086] S405. Obtain vector data of the target area according to the clustering units.

[0087] In some embodiments, we calculate their respective attributes based on superpixel units, including: the average value of height change mean, the total area of the superpixel area, the shape index shaperatio, the number of times the superpixels are merged n. Removing superpixels with mean < 2.5 can eliminate the influence of vehicle changes because the height of illegal construction is generally above about 3m, and the adjacent superpixel sets of the superpixel SP are counted. i of the adjacent superpixel set Calculate the superpixel SP i respectively with all its adjacent superpixels SP j The merged attribute mean ij , area ij , shaperatio ij , n ij ; and further calculate the measurement parameter measure ij ; The superpixel SP i Select the adjacent superpixel SP with the largest merging index value as measure1. If the maximum merging index measure2 of SP j is also SP j , or measure1 > measure2, then the merging requirement is met, and continue to execute the next step. If they are inconsistent and measure1 < measure2, then SP i stops merging, consider the next superpixel unit, that is, re - execute the previous step; for the superpixel units that meet the merging requirements, further perform a threshold threshold judgment. Those greater than the threshold are merged. After merging, update the merged attributes and their adjacent superpixel sets, and continue to execute the previous step; those less than the threshold stop the merging judgment and consider the next superpixel unit; after traversing all the superpixel units, update the threshold, and count the total number of merges merge_times this time; if merge_times == 0 appears continuously 3 times, then stop the iteration; the clustering unit filters out the building change area according to the number of merges, area, and shape index; It should be noted that the calculation formula for the measurement parameter measure is as follows: i

[0088]

[0089] Among them, m1, m2, m3 take positive values, representing the importance degree between each parameter;

[0090] mean ij , of the calculation formula is,

[0091]

[0092] ​The exponential function is selected so that when the areas of superpixels i and j are close, the parameter changes little and is close to 1, and as the area ratio difference increases, the parameter decreases exponentially. ij The calculation formula is,

[0093]

[0094] shaperatio ij The calculation formula is,

[0095]

[0096] This value ranges from [0,1], describing whether the shape is close to the minimum enclosing matrix. ij =area ij / length ij , and rectshape ij It refers to the shaperatio of the minimum bounding matrix after the superpixel ij is merged.

[0097] n ij The calculation formula is,

[0098]

[0099] n j It stands for Super Pixel SP i The number of merges of neighbors j, so Stands for Super Pixel SP i The number of times all neighbors are merged.

[0100] As for the update of the threshold, we implement it through the following formula:

[0101] threshold=max(0.65,threshold-0.02*Iterate / step),

[0102] Iterate represents the total number of algorithm loops, and step represents updating the threshold once after step loops.

[0103] By acquiring height change image data based on surface height image data of different time periods and post-processing the height change image data through superpixel segmentation and architectural morphology analysis, we can solve the recognition accuracy problem in the existing solutions and thus achieve accurate detection of urban building changes.

[0104] Reference Figure 2 The present invention provides a superpixel and morphology-based oblique photography illegal building detection system, comprising the following modules:

[0105] The data acquisition module 201 is used to acquire first surface height image data and first surface orthophoto image data of a target area in a first time period and second surface height image data and second surface orthophoto image data of a second time period;

[0106] The height change analysis module 202 is connected to the data acquisition module 201 to realize interaction, and is used to calculate the height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data and the second surface orthophoto image data;

[0107] The super pixel segmentation analysis module 203 is connected to the height change analysis module 202 to realize interaction, and is used to perform super pixel segmentation processing on the height change image data to obtain super pixel units;

[0108] The architectural morphology analysis module 204 is connected to the superpixel segmentation analysis module 203 to realize interaction, and is used to perform object clustering and filtering analysis on the superpixel units using the architectural morphology index to obtain vector data of the target area.

[0109] Reference Figure 3 The present invention provides a superpixel and morphology-based oblique photography illegal building detection system, comprising:

[0110] at least one processor 301;

[0111] At least one memory 302, used to store at least one program;

[0112] When at least one program is executed by at least one processor 301, at least one processor 301 implements the following Figure 1 The method shown.

[0113] Figure 1 The contents of the method embodiment shown are all applicable to the system embodiment, and the functions specifically implemented by the system embodiment are the same as those in the embodiment of the present invention. Figure 1 The method embodiment shown is the same as that of Figure 1 The beneficial effects achieved by the method embodiments shown are also the same.

[0114] The present invention also provides a computer-readable storage medium, wherein a program executable by a processor is stored, and when the program executable by the processor is executed by the processor, it is used to implement the following Figure 1 The method shown.

[0115] Figure 1 The contents of the method embodiment shown in the figure are applicable to the storage medium embodiment. The functions specifically implemented by the storage medium embodiment are the same as those in the method embodiment shown in the figure. Figure 1 The method embodiment shown is the same as that of Figure 1The beneficial effects achieved by the method embodiments shown are also the same.

[0116] It is understood that all or some steps and systems in the disclosed method above can be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0117] The embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A superpixel and morphology-based oblique photography illegal building detection method, characterized in that: The following steps are involved: Acquire first surface height image data and first surface orthophoto image data of the target area in the first time period and second surface height image data and second surface orthophoto image data of the target area in the second time period; Calculate the height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data and the second surface orthophoto image data; Performing super-pixel segmentation processing on the height-change image data to obtain super-pixel units; Using architectural morphology index to perform object clustering and filtering analysis on the superpixel unit to obtain vector data of the target area; The step of performing super-pixel segmentation processing on the height-change image data to obtain super-pixel units includes: Acquire the height change image data and category data; Calculating a segmentation interval, and segmenting the height-varying image data according to the segmentation interval to form superpixel seed points; Analyze surrounding pixels with the superpixel seed point as the center, and assign the pixels to the superpixel seed point; Allocate the superpixel seed points according to the category data to form the superpixel unit; The step of performing object clustering and filtering analysis on the superpixel unit using the architectural morphology index to obtain vector data of the target area includes: Acquire the superpixel unit; Calculate basic attributes of a single superpixel unit, wherein the basic attributes include average height variation, area, morphological index, and number of superpixel unit merging times; Calculate the merged attributes between different superpixel units according to the basic attributes, and then calculate the measurement parameter according to the merged attributes; Performing a threshold determination on the measurement parameter, and performing a merging operation according to the determination result to obtain a clustering unit; The vector data of the target area is obtained according to the clustering unit.

2. The method for detecting illegal buildings by oblique photography based on superpixel and morphology according to claim 1 is characterized in that: The step of acquiring first surface height image data and first surface orthophoto image data of the target area in the first time period and second surface height image data and second surface orthophoto image data of the second time period comprises: Acquire first oblique image data of the target area in a first time period and second oblique image data in a second time period; Generate the first surface height image data and the first surface orthophoto image data according to the first oblique image data; The second surface height image data and the second surface orthophoto image data are generated according to the second oblique image data.

3. The method for detecting illegal buildings by oblique photography based on superpixel and morphology according to claim 1, characterized in that: The step of calculating the height change image data of the target area according to the first surface height image data, the first surface orthophoto image data, the second surface height image data and the second surface orthophoto image data comprises: Acquire the first surface height image data, the first surface orthophoto image data, the second surface height image data, and the second surface orthophoto image data; Performing geographic location registration on the first surface orthophoto image data and the second surface orthophoto image data to obtain registration adjustment parameters; Registering the first ground surface height image data and the second ground surface height image data according to the registration adjustment parameter; The height change image data of the target area is calculated based on the first surface height image data and the second surface height image data after registration.

4. The method for detecting illegal buildings by oblique photography based on superpixel and morphology according to claim 1, characterized in that: The segmentation spacing is calculated by the following formula: Wherein, S represents the segmentation spacing, N represents the total number of pixels of the highly variable image data, and K represents the size of the superpixel seed point.

5. The oblique photography illegal building detection system based on superpixel and morphology is characterized by: Includes the following modules: A data acquisition module, used to acquire first surface height image data and first surface orthophoto image data of a target area in a first time period and second surface height image data and second surface orthophoto image data of a second time period; an altitude change analysis module, configured to calculate altitude change image data of the target area according to the first surface altitude image data, the first surface orthophoto image data, the second surface altitude image data and the second surface orthophoto image data; A superpixel segmentation analysis module is used to perform superpixel segmentation processing on the height change image data to obtain superpixel units; An architectural morphology analysis module is used to perform object clustering and filtering analysis on the superpixel unit using an architectural morphology index to obtain vector data of the target area; The superpixel segmentation analysis module is specifically used for: Acquire the height change image data and category data; Calculating a segmentation interval, and segmenting the height-varying image data according to the segmentation interval to form superpixel seed points; Analyze surrounding pixels with the superpixel seed point as the center, and assign the pixels to the superpixel seed point; Allocate the superpixel seed points according to the category data to form the superpixel unit; The architectural morphology analysis module is specifically used for: Acquire the superpixel unit; Calculate basic attributes of a single superpixel unit, wherein the basic attributes include average height variation, area, morphological index, and number of superpixel unit merging times; Calculate the merged attributes between different superpixel units according to the basic attributes, and then calculate the measurement parameter according to the merged attributes; Performing a threshold determination on the measurement parameter, and performing a merging operation according to the determination result to obtain a clustering unit; The vector data of the target area is obtained according to the clustering unit.

6. The oblique photography illegal building detection system based on superpixel and morphology is characterized by: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement the method according to any one of claims 1 to 4 when executed by the processor.

Images