A method and device for identifying illegal construction time of illegal buildings

Abstract

The present invention relates to the field of remote sensing technology, and discloses a method and device for identifying the time of illegal construction of illegal buildings. The method comprises: taking the illegal house POI point as the center point, cropping each scene image; segmenting all the house roofs in each cropped scene image, and identifying the roof masks of all houses; extracting the center point of each roof mask, and taking the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask; drawing a time series graph of the average spectral reflectance; calculating the mutation point of the time series in the time series graph of the average spectral reflectance; finding the horizontal coordinate corresponding to the mutation point in the time series graph of the average spectral reflectance, and determining the illegal construction time of the illegal house. The present invention realizes the high-precision extraction of the house roof mask by using a large model image segmentation algorithm and a post-processing method, and infers the time point of the illegal construction by calculating the spectral reflectance and the time series analysis method.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing technology, and in particular to a method and a device for identifying the time of illegal construction of illegal buildings. Background Art

[0002] In the context of my country's accelerated urbanization and rapid growth of urban population, many self-built houses where migrant workers live and self-built houses with lower costs for commercial purposes generally have safety hazards. Illegal construction of self-built houses is emerging in an endless stream. This not only has a negative impact on the city's environment, but also reduces the quality of life of residents, and even has the risk of causing serious urban safety accidents.

[0003] In the process of carrying out special work on the inspection and rectification of hidden dangers in self-built houses, local governments and relevant departments have adopted the manual method of inspecting illegal buildings, which not only consumes a lot of resources and funds, but also fails to track the history of the entire construction process of illegal buildings. There is a lack of timely grasp and dynamic monitoring of illegal information, which makes it difficult to assess the durability of illegal buildings and potential structural safety risks.

[0004] Building codes and standards may change over time. Identifying the construction time of illegal buildings helps assess whether the building meets the specifications of the construction period, which is crucial for assessing structural integrity and safety, especially when disasters occur. In addition, building materials will age over time and their performance will deteriorate. By determining the time of illegal construction, it is possible to better judge the current durability of the building and the need for reinforcement, demolition and other measures. Finally, based on the construction time, regulatory authorities can formulate effective intervention priorities and strategies to form a more orderly urban governance system. Summary of the invention

[0005] In view of this, the present invention provides a method and device for identifying the time of illegal construction of illegal buildings, so as to solve the problem that manual investigation cannot trace the history of the entire process from the appearance to the end of illegal houses.

[0006] In a first aspect, the present invention provides a method for identifying illegal construction time of illegal buildings, comprising:

[0007] Get the POI points of illegal houses;

[0008] Taking the illegal house POI point as the center point, each image in the historical multi-source optical remote sensing image data is cropped according to a preset range;

[0009] Using the automatic segmentation mode of the Segment Anything model, all the house roofs in each cropped image are segmented and the roof masks of all the houses are identified;

[0010] Extract the center point of each roof mask, and take the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask;

[0011] Calculate the average spectral reflectance within the mask boundary of the target roof, and draw a time series graph of the average spectral reflectance;

[0012] Calculate the mutation point of the time series in the time series graph of the average spectral reflectance;

[0013] The horizontal coordinate corresponding to the mutation point is searched in the time series diagram of the average spectral reflectance value to determine the illegal construction time of the illegal house.

[0014] In an optional embodiment, the target roof mask c * The mathematical formula is as follows:

[0015]

[0016] Among them, P is the illegal house POI point, c i is the i-th roof mask in the roof mask set C, p i is the center point of the i-th roof mask, A i is the area of ​​the i-th roof mask, D i is the distance from the center point of the i-th roof mask to the POI point of the illegal house, d(p i ,P) is the calculation of p i and P, j is the index of each element in the roof mask set C, j∈{1,2,...,n}.

[0017] In an optional implementation, the calculating the average spectral reflectance within the mask boundary of the target roof and drawing a time series graph of the average spectral reflectance includes:

[0018] Calculate the spectral reflectance of each Red / Green / Blue band of each pixel within the mask boundary of the target roof respectively;

[0019] The spectral reflectance of the Red / Green / Blue bands of all pixels is averaged to obtain the average spectral reflectance of the Red / Green / Blue bands;

[0020] A time series graph of the average spectral reflectance is drawn based on the changing trend of the average spectral reflectance of the Red / Green / Blue bands over time.

[0021] In an optional implementation, before executing the step of calculating the mutation point of the time series in the spectral reflectance average value time series graph, the method further includes:

[0022] The sliding window averaging method is used to smooth the time series graph of the spectral reflectance average value.

[0023] In an optional implementation, the step of calculating the mutation point of the time series in the time series graph of the average spectral reflectance value includes:

[0024] The first order difference of the time series points in the time series graph of the average spectral reflectance;

[0025] The point with the largest first-order difference is taken as the mutation point of the time series.

[0026] In an optional implementation, the obtaining of the illegal house POI point includes:

[0027] Obtain a manual inspection list of illegal houses and house geographic information data;

[0028] The manual illegal house inspection list is combined with the house geographic information data to extract the illegal house POI points.

[0029] In an optional implementation, taking the illegal house POI point as the center point, cropping each image in the historical multi-source optical remote sensing image data according to a preset range includes:

[0030] Acquire historical multi-source optical remote sensing image data;

[0031] Preprocessing the historical multi-source optical remote sensing image data so that all images are in the same geographic coordinate system;

[0032] Taking the illegal house POI point as the center point, each image is cropped according to a preset range.

[0033] In a second aspect, the present invention provides a device for identifying illegal construction time, comprising:

[0034] Acquisition module, used to obtain the POI points of illegal houses;

[0035] A cropping module, for cropping each image in the historical multi-source optical remote sensing image data according to a preset range with the illegal house POI point as the center point;

[0036] The segmentation module is used to segment all the house roofs in each cropped image using the automatic segmentation mode of the Segment Anything model, and identify the roof masks of all the houses;

[0037] An extraction module is used to extract the center point of each roof mask, and take the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask;

[0038] A drawing module, used for calculating the average spectral reflectance within the mask boundary of the target roof, and drawing a time series graph of the average spectral reflectance;

[0039] A calculation module, used for calculating the mutation point of the time series in the time series graph of the average spectral reflectance;

[0040] The identification module is used to find the horizontal coordinate corresponding to the mutation point in the time series diagram of the average spectral reflectance value, and determine the illegal construction time of the illegal house.

[0041] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for identifying the time of illegal construction of illegal buildings according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for identifying the time of illegal construction of illegal buildings according to the first aspect or any corresponding embodiment thereof.

[0043] The invention provides a method for identifying the illegal construction time of illegal buildings, comprising: obtaining illegal house POI points; taking the illegal house POI points as the center points, cropping each scene image in historical multi-source optical remote sensing image data according to a preset range; using the automatic segmentation mode of the Segment Anything model to segment all house roofs in each cropped scene image, and identifying the roof masks of all houses; extracting the center point of each roof mask, and taking the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask; calculating the average spectral reflectance within the boundary of the target roof mask, and drawing a time series graph of the average spectral reflectance; calculating the mutation point of the time series in the time series graph of the average spectral reflectance; searching for the horizontal coordinate corresponding to the mutation point in the time series graph of the average spectral reflectance, and determining the illegal construction time of the illegal house. The present invention realizes high-precision extraction of house roof masks based on existing historical optical remote sensing image data, combined with image segmentation large models and post-processing methods, and then monitors the changes in long-term roof spectral characteristics by calculating spectral reflectance and time series analysis methods, detects the construction time of illegal houses, successfully infers the time point of illegal construction, and realizes the retrospective and dynamic monitoring of historical changes of illegal houses in cities. The information on the construction time of illegal buildings reveals the evolution of construction standards and materials used over time, which helps regulatory authorities take more targeted inspection, reinforcement, demolition and other measures, and provides important legal and regulatory enforcement for urban management departments.

[0044] The invention provides a device for identifying the illegal construction time of illegal buildings, comprising: an acquisition module, used for acquiring illegal house POI points; a clipping module, used for taking the illegal house POI points as the center points, and clipping each scene image in the historical multi-source optical remote sensing image data according to a preset range; a segmentation module, used for using the automatic segmentation mode of the Segment Anything model to segment all house roofs in each clipped scene image, and identify the roof masks of all houses; an extraction module, used for extracting the center point of each roof mask, and taking the roof mask with the largest area and the nearest center point to the illegal house POI points as the target roof mask; a drawing module, used for calculating the average spectral reflectance within the boundary of the target roof mask, and drawing a time series graph of the average spectral reflectance; a calculation module, used for calculating the mutation point of the time series in the time series graph of the average spectral reflectance; and an identification module, used for finding the horizontal coordinate corresponding to the mutation point in the time series graph of the average spectral reflectance, and determining the illegal construction time of the illegal house. The present invention realizes high-precision extraction of house roof masks based on existing historical optical remote sensing image data, combined with image segmentation large models and post-processing methods, and then monitors changes in long-term roof spectral characteristics by calculating spectral reflectance and time series analysis methods, detects the construction time of illegal houses, and successfully infers the time point of illegal construction, thereby realizing dynamic monitoring of illegal houses in cities, helping to evaluate the durability of buildings and possible risks, and providing important legal and regulatory enforcement for urban management departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a flow chart of a method for identifying illegal construction time of illegal buildings according to an embodiment of the present invention;

[0047] Figure 2 is a structural block diagram of a device for identifying illegal construction time of illegal buildings according to an embodiment of the present invention;

[0048] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0050] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0051] The present invention provides a method for identifying illegal construction time of illegal buildings, such as Figure 1 As shown, the following steps are included:

[0052] Step S11, obtaining illegal house POI points.

[0053] Specifically, the illegal house POI points are obtained through the following process:

[0054] Step S111, obtaining a manual illegal house inspection list and house geographic information data;

[0055] Step S112, merging the manual illegal house inspection list with the house geographic information data to extract the illegal house POI points.

[0056] In the embodiment of the present invention, the manual illegal house inspection list includes house number, house address, etc. House geographic information data includes house number, house type, geographic location and its coordinates, etc.

[0057] Step S12, taking the illegal house POI point as the center point, cropping each image in the historical multi-source optical remote sensing image data according to a preset range.

[0058] Specifically, step S12 includes the following process:

[0059] Step S121, acquiring historical multi-source optical remote sensing image data.

[0060] In the embodiment of the present invention, the historical multi-source optical remote sensing image data covers the building status of the study area at different periods.

[0061] Step S122, pre-processing the historical multi-source optical remote sensing image data to make all images in the same geographic coordinate system.

[0062] In an embodiment of the present invention, historical multi-source optical remote sensing image data preprocessing, including radiation calibration, atmospheric correction, geographic registration, terrain correction, projection transformation, etc., makes all images in the same geographic coordinate system to ensure the accuracy and consistency of the data.

[0063] Step S123, taking the illegal house POI point as the center point, cropping each image according to a preset range.

[0064] In the embodiment of the present invention, the preset range is 200*200 (pixels). Taking the illegal house POI point as the center point, each image is cropped within a range of 200*200.

[0065] Step S13, using the automatic segmentation mode of the Segment Anything model, segment all the house roofs in each cropped image and identify the roof masks of all the houses.

[0066] Specifically, the automatic segmentation mode of the Segment Anything model is used to segment all the house roofs in each cropped image. Based on the image segmentation algorithm of the large model, the model can identify all the house roof masks in the optical remote sensing data taken by different sensors, and use them as target roof masks to provide reliable and accurate basic data for the subsequent calculation of roof spectral reflectance.

[0067] Step S14, extracting the center point of each roof mask, and taking the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask.

[0068] Specifically, the roof masks are post-processed to extract the center point of each roof mask, and the roof mask with the closest center point to the illegal house POI point and the largest area is used as the target roof mask.

[0069] Assume there is a roof mask set C = {c 1 ,c 2 ,...,c n}, where each element c i Represents a roof mask. Each element c i There is a central point p i and an area A i .

[0070] Let P be the illegal house POI point. Calculate a target roof mask c * , satisfying the following conditions: c * The center point p * The distance to P is the shortest and c * Area A * Maximum. Expressed in mathematical formula, it is divided into two steps:

[0071] Step 1: Find the nearest center point. For each c i , calculate p i Distance D to Pi ,Right now:

[0072] D i =d(p i ,P)

[0073] Find D i The minimum value D min .

[0074] Step 2: Select the target roof mask with the largest area and select it from all D i =D min c i Among them, select A with the largest area i , that is: find c * , so that:

[0075]

[0076] Target roof mask c * It can be determined by the following mathematical formula:

[0077]

[0078] Among them, d(p i ,P) is the calculation of p i and P, j is the index of each element in the roof mask set C, j∈{1,2,...,n}.

[0079] Step S15, calculating the average spectral reflectance within the mask boundary of the target roof, and drawing a time series graph of the average spectral reflectance.

[0080] Specifically, step S15 includes the following process:

[0081] Step S151, respectively calculating the spectral reflectance of each Red / Green / Blue band of each pixel within the target roof mask boundary.

[0082] Step S152, averaging the spectral reflectances of the Red / Green / Blue bands of all pixels to obtain an average spectral reflectance of the Red / Green / Blue bands.

[0083] Step S153 , plotting a time series graph of the average spectral reflectance according to the variation trend of the average spectral reflectance of the Red / Green / Blue bands over time.

[0084] In the embodiment of the present invention, after extracting the target roof mask in each scene image, the spectral reflectance of each Red / Green / Blue band of each pixel within the mask boundary is calculated respectively. The spectral reflectance of the Red / Green / Blue band of all pixels is averaged to obtain the average spectral reflectance of the Red / Green / Blue band. i .

[0085] Among them, Average i The calculation formula is as follows:

[0086] Assuming that there are N pixels in the 2D plane frame of the i-th building roof, then Average i The calculation formula is as follows:

[0087]

[0088] Where N is the total number of pixels in the two-dimensional plane box of the i-th building roof, R ij is the spectral reflectance of the Red / Green / Blue bands of the j-th pixel of the ith building.

[0089] Step S16, smoothing the spectral reflectance average value time series graph using a sliding window averaging method.

[0090] Specifically, in order to improve the robustness of the change detection method against accidental errors such as sensor error and observation angle offset, the sliding window averaging method is used to smooth the time series graph of the average spectral reflectance to eliminate the influence of isolated mutation points on the results.

[0091] Among them, the calculation formula of the sliding window average method is as follows:

[0092]

[0093] Among them, SMA t is the sliding average at time t, P t is the original value at time t, and n is the time window.

[0094] Step S17, calculating the mutation point of the time series in the spectral reflectance average value time series graph.

[0095] Specifically, step S17 includes the following process:

[0096] Step S171, first-order difference of the time series points in the spectral reflectance average value time series graph.

[0097] Step S172, taking the point with the largest first-order difference as the mutation point of the time series.

[0098] In the embodiment of the present invention, based on the time series points after sliding window averaging, the first-order difference ΔDiff of the sequence points is calculated, and the point with the largest first-order difference ΔDiff is taken as the mutation point of the time series.

[0099] Among them, the calculation formula of the first-order difference of the value after sliding average is as follows:

[0100] ΔDiff=SMA t -SMA t-1

[0101] Among them, SMA t is the sliding average at time t, SMA t-1 is the sliding average at time t-1.

[0102] Step S18, searching the horizontal coordinate corresponding to the mutation point in the time series diagram of the average value of the spectral reflectance to determine the illegal construction time of the illegal house.

[0103] Specifically, in the smoothed time series curve, after finding the mutation point with obvious changes, the horizontal axis corresponding to the point is the date when the illegal construction occurred, and the corresponding high-resolution remote sensing image is obtained. Thus, the time when the illegal construction of the house occurred within the time range of the available remote sensing image is confirmed. According to the above steps, all illegal houses in the existing illegal investigation database are automatically detected for roof changes and construction time, thereby supplementing the historical information of the illegal construction database.

[0104] The invention provides a method for identifying the illegal construction time of illegal buildings, comprising: obtaining illegal house POI points; taking the illegal house POI points as the center points, cropping each scene image in historical multi-source optical remote sensing image data according to a preset range; using the automatic segmentation mode of the Segment Anything model to segment all house roofs in each cropped scene image, and identifying the roof masks of all houses; extracting the center point of each roof mask, and taking the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask; calculating the average spectral reflectance within the boundary of the target roof mask, and drawing a time series graph of the average spectral reflectance; calculating the mutation point of the time series in the time series graph of the average spectral reflectance; searching for the horizontal coordinate corresponding to the mutation point in the time series graph of the average spectral reflectance, and determining the illegal construction time of the illegal house. The present invention realizes high-precision extraction of house roof masks based on existing historical optical remote sensing image data, combined with image segmentation large models and post-processing methods, and then monitors changes in long-term roof spectral characteristics by calculating spectral reflectance and time series analysis methods, detects the construction time of illegal houses, and successfully infers the time point of illegal construction, thereby realizing dynamic monitoring of illegal houses in cities, helping to evaluate the durability of buildings and possible risks, and providing important legal and regulatory enforcement for urban management departments.

[0105] The present invention provides a device for identifying illegal construction time. Figure 2 As shown, including:

[0106] The acquisition module 21 is used to obtain the POI points of the illegal houses.

[0107] The cropping module 22 is used to crop each image in the historical multi-source optical remote sensing image data according to a preset range, taking the illegal house POI point as the center point.

[0108] The segmentation module 23 is used to segment all the house roofs in each cropped image by using the automatic segmentation mode of the Segment Anything model, and identify the roof masks of all the houses.

[0109] The extraction module 24 is used to extract the center point of each roof mask, and take the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask.

[0110] The drawing module 25 is used to calculate the average spectral reflectance within the mask boundary of the target roof and draw a time series graph of the average spectral reflectance.

[0111] The calculation module 26 is used to calculate the mutation point of the time series in the spectral reflectance average value time series graph.

[0112] The identification module 27 is used to find the horizontal coordinate corresponding to the mutation point in the time series diagram of the average value of the spectral reflectance, and determine the illegal construction time of the illegal house.

[0113] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0114] The invention provides a device for identifying the illegal construction time of illegal buildings, comprising: an acquisition module, used for acquiring illegal house POI points; a clipping module, used for taking the illegal house POI points as the center points, and clipping each scene image in the historical multi-source optical remote sensing image data according to a preset range; a segmentation module, used for using the automatic segmentation mode of the Segment Anything model to segment all house roofs in each clipped scene image, and identify the roof masks of all houses; an extraction module, used for extracting the center point of each roof mask, and taking the roof mask with the largest area and the nearest center point to the illegal house POI points as the target roof mask; a drawing module, used for calculating the average spectral reflectance within the boundary of the target roof mask, and drawing a time series graph of the average spectral reflectance; a calculation module, used for calculating the mutation point of the time series in the time series graph of the average spectral reflectance; and an identification module, used for finding the horizontal coordinate corresponding to the mutation point in the time series graph of the average spectral reflectance, and determining the illegal construction time of the illegal house. The present invention realizes high-precision extraction of house roof masks based on existing historical optical remote sensing image data, combined with image segmentation large models and post-processing methods, and then monitors changes in long-term roof spectral characteristics by calculating spectral reflectance and time series analysis methods, detects the construction time of illegal houses, and successfully infers the time point of illegal construction, thereby realizing dynamic monitoring of illegal houses in cities, helping to evaluate the durability of buildings and possible risks, and providing important legal and regulatory enforcement for urban management departments.

[0115] The embodiment of the present invention also provides a computer device having the above Figure 2 The illegal building illegal construction time identification device shown.

[0116] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0117] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0118] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0119] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0120] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0121] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0122] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0123] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for identifying illegal construction time, characterized in that: include: Get the POI points of illegal houses; Taking the illegal house POI point as the center point, each image in the historical multi-source optical remote sensing image data is cropped according to a preset range; Using the automatic segmentation mode of the Segment Anything model, all the house roofs in each cropped image are segmented and the roof masks of all the houses are identified; Extract the center point of each roof mask, and take the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask; Calculate the average spectral reflectance within the mask boundary of the target roof, and draw a time series graph of the average spectral reflectance; Calculate the mutation point of the time series in the time series graph of the average spectral reflectance; The horizontal coordinate corresponding to the mutation point is found in the time series diagram of the average spectral reflectance value to determine the illegal construction time of the illegal house.

2. The method for identifying illegal construction time according to claim 1 is characterized in that: The target roof mask c * The mathematical formula is as follows: Among them, P is the illegal house POI point, c i is the i-th roof mask in the roof mask set C, p i is the center point of the i-th roof mask, A i is the area of ​​the i-th roof mask, D i is the distance from the center point of the i-th roof mask to the POI point of the illegal house, d(p i ,P) is the calculation of p i and P, j is the index of each element in the roof mask set C, j∈{1,2,...,n}.

3. The method for identifying illegal construction time according to claim 1 is characterized in that: The calculating the average spectral reflectance within the mask boundary of the target roof and drawing a time series graph of the average spectral reflectance includes: Calculate the spectral reflectance of each Red / Green / Blue band of each pixel within the mask boundary of the target roof respectively; The spectral reflectance of the Red / Green / Blue bands of all pixels is averaged to obtain the average spectral reflectance of the Red / Green / Blue bands; A time series graph of the average spectral reflectance is drawn based on the changing trend of the average spectral reflectance of the Red / Green / Blue bands over time.

4. The method for identifying illegal construction time according to claim 1 is characterized in that: Before executing the step of calculating the mutation point of the time series in the spectral reflectance average value time series graph, the method further includes: The sliding window averaging method is used to smooth the time series graph of the spectral reflectance average value.

5. The method for identifying illegal construction time according to claim 1 is characterized in that: The step of calculating the mutation point of the time series in the time series graph of the average spectral reflectance comprises: The first order difference of the time series points in the time series graph of the average spectral reflectance; The point with the largest first-order difference is taken as the mutation point of the time series.

6. The method for identifying illegal construction time according to claim 1 is characterized in that: The obtaining of illegal house POI points includes: Obtain a manual inspection list of illegal houses and house geographic information data; The manual illegal house inspection list is combined with the house geographic information data to extract the illegal house POI points.

7. The method for identifying illegal construction time according to claim 1 is characterized in that: The method of taking the illegal house POI point as the center point and cropping each image in the historical multi-source optical remote sensing image data according to a preset range includes: Acquire historical multi-source optical remote sensing image data; Preprocessing the historical multi-source optical remote sensing image data so that all images are in the same geographic coordinate system; Taking the illegal house POI point as the center point, each image is cropped according to a preset range.

8. A device for identifying illegal construction time, characterized in that: include: Acquisition module, used to obtain the POI points of illegal houses; A cropping module is used to crop each image in the historical multi-source optical remote sensing image data according to a preset range with the illegal house POI point as the center point; The segmentation module is used to segment all the house roofs in each cropped image using the automatic segmentation mode of the Segment Anything model, and identify the roof masks of all the houses; An extraction module is used to extract the center point of each roof mask, and take the roof mask with the largest area and the closest center point to the illegal house POI point as the target roof mask; A drawing module, used for calculating the average spectral reflectance within the mask boundary of the target roof, and drawing a time series graph of the average spectral reflectance; A calculation module, used for calculating the mutation point of the time series in the time series graph of the average spectral reflectance; The identification module is used to find the horizontal coordinate corresponding to the mutation point in the time series diagram of the average spectral reflectance value, and determine the illegal construction time of the illegal house.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the illegal building illegal construction time identification method described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for identifying the illegal construction time of any one of claims 1 to 7.

Images