JP7126316B2 - House change estimation device and program - Google Patents

Description

The present invention relates to a house change estimation device and program.

Techniques exist for estimating changes in fixed assets such as houses in two periods.

As an example of such a technique, Patent Literature 1 describes a technique for discriminating a change based on comparison results in mesh units using DSM (Digital Surface Model) image data or orthophoto image data.

Further, Patent Literature 2 describes a technique for judging a house change by comparing house objects specified based on DSM data for two different periods.

JP 2016-99316 A WO2009/51258

However, in the technique described in Patent Document 1, DSM image data and orthophoto image data are compared with respect to the entire image in units of meshes. Therefore, it has been difficult to accurately estimate house changes due to the effects of noise in DSM data, misalignment in registration, topography, features such as trees, and moving objects.

Further, in the technique described in Patent Literature 2, a house change is determined by comparing house objects. For this reason, there are types of house changes such as rebuilding or extension/renovation in which the height change of the house is small, for which house change estimation cannot be performed well.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and one of its objects is to provide a house change estimating device and a program capable of accurately estimating many kinds of house changes.

(1) A house change estimation apparatus according to the present invention includes extraction means for extracting a house area in which a house is represented in a house change estimation area based on elevation data of a ground surface layer including features; the elevation indicated by the elevation data in the second period, the elevation data between the first period and the second period, for the house area extracted based on the elevation data in the period or a comparison result of the color information represented in the images taken in the first period and the second period; and the identified at least a house change estimating means for estimating a house change for said house between said first period and said second period based on one.

(2) In the house change estimating device according to (1) above, the house change estimating means compares the altitude indicated by the altitude data between the first period and the second period based on Then, the presence or absence of reconstruction of the house can be estimated.

(3) In the house change estimating device according to (1) above, the house change estimating means compares the altitude indicated by the altitude data between the first period and the second period, and and the presence or absence of reconstruction of the house can be estimated based on the comparison result of the color information.

(4) In the house change estimating device described in (1) to (3) above, the house change estimating means, based on a comparison result of hue components in the color information expressed by the HSI color system, It can be configured to estimate the house change of about.

(5) In the house change estimation device according to (1) to (4) above, color adjustment is performed on at least one of the image taken in the first period and the image taken in the second period. color adjustment means for performing color adjustment, wherein the house change estimation means estimates a house change for the house based on a comparison result of color information represented in the image on which the color adjustment has been performed be able to.

(6) A program according to the present invention includes a procedure for extracting a house area in which a house is represented within a house movement estimation area based on elevation data of a ground surface layer including features, the elevation in the first period comparison of the elevation indicated by the elevation data in the second period and the elevation indicated by the elevation data between the first period and the second period for the house area extracted based on the data of A procedure for identifying at least one of a result or a comparison result of color information represented in images taken at said first time period and said second time period, based on said at least one identified, said causing a computer to execute a procedure for estimating a house change for the house between the first period and the second period;

According to the present invention, it is possible to accurately estimate many types of house changes.

1 is a configuration diagram of a house change estimation device according to an embodiment of the present invention; FIG. It is a figure which shows an example of a ground typical vertical cross-sectional view. It is a figure which shows an example of NDSM. FIG. 10 is a diagram showing an example of NDSM unevenness in a target area after vegetation removal processing generated based on DSM data at time t1, binarized for convenience. FIG. 10 is a diagram showing an example of NDSM unevenness in a target area after vegetation removal processing generated based on DSM data at time t2, binarized for convenience. FIG. 4 is a diagram showing an example of a plurality of convex regions as a result of region division processing for the NDSM shown in FIG. 3; FIG. 5 is a diagram showing an example of a plurality of convex regions as a result of region division processing for the NDSM shown in FIG. 4; FIG. 10 is a diagram showing an example of a house object within the target area at time t1; FIG. 10 is a diagram showing an example of a house object within the target area at time t2; FIG. 4 is a diagram schematically showing an example of an orthoimage obtained by photographing a target area at time t1; FIG. 10 is a diagram schematically showing an example of an orthoimage obtained by photographing a target area at time t2; 1 is a functional block diagram showing an example of functions of a house change estimation device according to an embodiment of the present invention; FIG. It is a figure which shows an example of the screen showing the estimation result of house change. It is a flowchart which shows an example of the flow of the process performed with the house change estimation apparatus which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the flow of the process performed with the house change estimation apparatus which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the flow of the process performed with the house change estimation apparatus which concerns on one Embodiment of this invention.

An embodiment of the present invention will be described in detail below with reference to the drawings.

FIG. 1 is a configuration diagram of a house change estimation device 10 according to one embodiment of the present invention. The house change estimation device 10 according to this embodiment is a computer such as a personal computer. As shown in FIG. 1, the house change estimation device 10 includes a processor 12, a storage unit 14, a display unit 16, and an operation unit 18, for example.

The processor 12 is a program control device such as a CPU that operates according to a program installed in the house change estimation device 10, for example.

The storage unit 14 is a storage element such as ROM or RAM, a hard disk drive, or the like. The storage unit 14 stores programs and the like executed by the processor 12 .

The display unit 16 is a display device such as a liquid crystal display, and displays various images according to instructions from the processor 12 .

The operation unit 18 is a user interface such as a keyboard and a mouse, and receives user operation input and outputs a signal indicating the content of the input to the processor 12 .

The house change estimation device 10 may include a communication interface such as a network board, an optical disk drive for reading optical disks such as DVD-ROMs and Blu-ray (registered trademark) disks, a USB (Universal Serial Bus) port, and the like. .

The house change estimation device 10 according to the present embodiment estimates the house change between time t1 and time t2 for a predetermined target area as described below. In the following description, it is assumed that timing t2 is later than timing t1.

In this embodiment, for example, first, as shown in FIGS. 2A and 2B, DTM (Digital Terrain Model) 22 included in DSM 20 represented by DSM (Digital Surface Model) data at time t1 and time t2 A normalization process is performed to remove the effects of

FIG. 2A shows an example of a schematic vertical sectional view of the ground. The DSM 20 represents the horizontal coordinates/elevation of the surface of features such as houses 24 and trees 26, and the horizontal coordinates/elevation of the ground surface 28 exposed between the features. Here, the elevation of the house in the DSM 20 is the sum of the elevation of the ground surface below it and the height of the house.

In the normalization process, the NDSM (Normalized Digital Surface Model) 30 shown in FIG. 2B is generated by subtracting the value of the DTM 22 from the value of the DSM 20 . FIG. 2B schematically shows the resulting NDSM 30 corresponding to the ground in FIG. 2A. In the NDSM 30, features (houses 32, trees 34) have height information from the ground surface, while the ground surface 36 basically has a height corresponding to a height of zero. For example, the DTM 22 can be estimated from the DSM 20 by various filtering processes such as morphological filtering. Alternatively, an existing DTM related to the target area may be used as the DTM22.

In the NDSM 30 , features other than the house 32 also have significant heights, and in particular, vegetation such as trees 34 can have a height corresponding to the house 32 , and thus becomes a noise factor when determining the house 32 . Therefore, in the present embodiment, for example, a vegetation removal process is performed to remove a portion related to vegetation from the NDSM 30 . In the vegetation removal process, a vegetation area is determined, and masking such as rewriting to 0 is performed on the NDSM data of the area.

The roof or roof of a house has a smooth surface over a relatively large horizontal distance, whereas the vegetation area has height variations with a relatively small spatial period. For example, this difference can be used to determine vegetation areas and remove them from NDSM 30 . Specifically, an area in which the variance of gradients between adjacent points of NDSM data exceeds a predetermined threshold value can be determined as a vegetation area.

It is also possible to determine the vegetation area based on the texture that appears in the image taken from an aircraft or the like due to height fluctuations, and it is also possible to determine the vegetation area from image analysis using AI technology.

In addition, multispectral images can be used to detect vegetation areas based on the strong reflection of near-infrared light by tree leaves. For example, the NDVI (Normalized Difference Vegetation Index) calculated using the pixel value D (R) of the red (R) component and the pixel value D (IR) of the near-infrared (IR) component is a predetermined An area equal to or greater than the threshold can be determined as a vegetation area. NDVI is calculated by, for example, the formula NDVI=(D(IR)-D(R))/(D(IR)+D(R)).

Then, as shown in FIGS. 3 to 6, a region dividing process of dividing the target region represented by the NDSM on which the vegetation removal processing has been performed into convex regions 42 each including one convex portion 40 appearing in the NDSM. is executed. The conversion process from DSM to NDSM described above basically removes unevenness on the ground surface that appears on a scale larger than the spread of the house, leaving a convex part with a size corresponding to the house. Therefore, a convex region 42 can be generated for each house.

FIG. 3 is a diagram showing an example of NDSM unevenness in a target area after vegetation removal processing generated based on the DSM data at time t1, binarized for convenience. FIG. 4 is a diagram that conveniently binarizes NDSM unevenness in a target area after vegetation removal processing that is generated based on DSM data at time t2. In FIGS. 3 and 4, the positions of the protrusions 40 are indicated by oblique lines.

In the region dividing process, as shown in FIGS. 5 and 6, the target region is divided into a plurality of convex regions 42 such that the plurality of convex regions 40 are separated from each other. FIG. 5 shows an example of a plurality of convex regions 42 that are the result of region division processing for the NDSM shown in FIG. FIG. 6 shows a plurality of convex areas 42 that are the result of the area segmentation process for the NDSM shown in FIG. A watershed method, for example, can be used as a technique for this area division.

Then, as described above, contour extraction processing for extracting the contour of the house is performed on the convex region 42 extracted by the normalization processing, the vegetation removal processing, and the region division processing. In the contour extraction process, for example, point groups forming edges are extracted based on changes in elevation of the ground surface layer (eg, gradient data) acquired from an aircraft or the like.

In addition, contour extraction can be performed using an image of the surface layer of the ground taken from an aircraft or the like, in combination with a multispectral image.

Specifically, for example, a point group forming an edge is extracted based on changes in an image displayed in terms of brightness and color. Edge extraction can be performed using various edge filters.

Then, a process of extracting a line segment and generating a line segment image is performed on the point group forming the edge. For example, by performing filtering that performs tracking and segmentation processing, the point cloud is segmented into a set of points that can be regarded as a unit, and it is recognized as noise without forming a unit of sufficient size. Eliminate possible points. Then, line segments are extracted by, for example, Hough transform. Then, a process of extracting the outline of the house from the line segment image is executed. For example, the outline of a house is extracted by applying the Perceptual Grouping technique to the line segment image.

Then, in this embodiment, for example, a polygon surrounded by the extracted outline is specified as the house object 44 . In this embodiment, the area occupied by the house object 44 in the target area is the area representing the house associated with the house object 44 . Hereinafter, the area occupied by the house object 44 will be called a house area.

FIG. 7 shows an example of a house object 44 within the target area at time t1 identified based on the convex area 42 shown in FIG. FIG. 8 shows an example of a house object 44 within the target area at time t2 identified based on the convex area 42 shown in FIG.

In this embodiment, for each house object 44 in the target area at time t1, the house change of the house associated with the house object 44 between time t1 and time t2 is estimated. Also, in this embodiment, for each house object 44 in the target area at time t2, the house change of the house associated with the house object 44 between time t1 and time t2 is estimated.

Focusing on one house object 44 in the target area at time t1, an example of estimating the house change of the house associated with the house object 44 will be described below.

First, the altitude at time t1 of the house area associated with the one house object 44 is specified. Here, for example, an average value of altitudes at each of a plurality of positions in the house area indicated by the DSM at time t1 may be specified as the altitude of the house area at time t1.

Then, the altitude of the house area at time t2 is specified. Here, for example, an average value of altitudes at each of a plurality of positions in the house area indicated by the DSM at time t2 may be specified as the altitude of the house area at time t2.

Then, for example, the altitude of the house area at time t1 and the altitude of the house area at time t2 are compared.

Here, for example, the altitude information of each pixel in the house area at time t1 may be compared with the altitude information of each pixel in the house area at time t2. An example of the comparison result of the altitude information is an altitude difference value indicating the difference between the altitude of each pixel in the house area at time t1 and the altitude of each pixel in the house area at time t2.

Further, in the present embodiment, for example, color information represented in the image captured at time t1 is specified for the house area. FIG. 9 is a diagram schematically showing an example of an orthoimage obtained by photographing the target area at time t1. For example, in the orthorectified image illustrated in FIG. 9, the color information of each pixel in the house area is specified. A plurality of houses 46 are represented in the orthoimage shown in FIG.

Further, in this embodiment, for example, the color information represented in the image captured at time t2 is specified for the house area. FIG. 10 is a diagram schematically showing an example of an orthoimage obtained by photographing the target area at time t2. For example, in the orthoimage illustrated in FIG. 10, the color information of each pixel in the house area is specified. The orthoimage shown in FIG. 10 also shows a plurality of houses 46 .

In this embodiment, for example, the color information of each pixel in the house area at time t1 is compared with the color information of each pixel in the house area at time t2. An example of the comparison result of the color information is a color difference value indicating the difference between the color of each pixel in the house area at time t1 and the color of each pixel in the house area at time t2.

Here, for example, for all pixels in the house region, the square of the difference in R value, the square of the difference in G value, and the square of the difference in B value between the pixel at time t1 and the pixel at time t2 An average change vector, which is the average of the square roots of the sums of , may be specified as the color difference value. Here, the R value, G value, and B value indicate the pixel value of the red component, the pixel value of the green component, and the pixel value of the blue component, respectively.

Further, for example, the average values of the R, G, and B values of the pixels in the house region at time t1 and the averages of the R, G, and B values of the pixels in the house region at time t2 A value and may be specified. Then, the square root of the sum of the square of the difference between the average values of the R values, the square of the difference between the average values of the G values, and the square of the difference between the average values of the B values may be specified as the color difference value.

Further, for example, pixel value representation using RGB values may be converted to pixel value representation using HSI values (pixel value representation based on the HSI color system). Then, an average value of differences in hue components (H components) or an average value of absolute values of differences in hue components (H components) calculated for all pixels in the house region may be specified as the color difference value.

Edge extraction may also be performed for regions in the orthorectified image corresponding to, for example, house regions. Then, the difference in the ratio of the number of pixels specified as edges to the total number of pixels included in the house area may be specified as the color difference value.

Then, for example, for the house area corresponding to the house object 44, based on at least one of the NDSM at time t2, the altitude comparison result, and the color information comparison result, it is associated with the house object 44. It is presumed that there will be house changes in the house.

Here, for example, if the value indicating the altitude at time t2 is smaller than a predetermined threshold (approximately 0), it may be estimated that the house has been destroyed.

Also, for example, if the difference between the value indicating the altitude at time t1 and the value indicating the altitude at time t2 is equal to or greater than a predetermined threshold value (for example, 2 meters or more), it is estimated that the house has been rebuilt. good.

Further, for example, when the difference between the value indicating the altitude at time t1 and the value indicating the altitude at time t2 is less than a predetermined threshold value (for example, less than 2 meters) and the value indicating the difference in color information is equal to or greater than a predetermined value , it may be presumed that the house was rebuilt.

In addition, in the present embodiment, based on the comparison result of NDSM, elevation, and color information at time t2 for the house area corresponding to the house object 44, the area of the house associated with the house object 44 is calculated. A change may be estimated.

If the value indicating the area at time t2 is larger than the value indicating the area at time t1 by a predetermined threshold or more (for example, 10 square meters or more), it may be estimated that the house has undergone a major extension or reconstruction.

If the value indicating the area at time t2 is larger than the value indicating the area at time t1, but the difference is less than a predetermined threshold value (for example, less than 10 square meters), the house has undergone a small extension or renovation. may be estimated.

Further, when the value indicating the area at time t2 is smaller than the value indicating the area at time t1, it may be estimated that the house has been reduced.

Further, in the present embodiment, the number of houses arranged in the house area corresponding to the house object 44 is calculated based on the comparison result of the NDSM, the altitude, and the color information at time t2. may be estimated. For example, if it is estimated that a plurality of house objects 44 are arranged at time t2 in the house area corresponding to the house object 44 at time t1, the house associated with the house object 44 will be rebuilt. It may be presumed that

In this embodiment, for all house objects 44 in the target area at time t1, the house change of the house associated with the house object 44 between time t1 and time t2 is estimated as described above. be.

Similarly, for all house objects 44 within the target area at time t2, the house change of the house associated with the house object 44 between time t1 and time t2 is estimated.

In this case, for example, if the value indicating the altitude at time t1 is smaller than a predetermined threshold value (approximately 0), it may be estimated that the house has been newly constructed.

Further, for example, when it is estimated that a plurality of house objects 44 are arranged at time t1 in the house area corresponding to the house object 44 at time t2, even if it is estimated that the house has been rebuilt, good.

Also in this embodiment, color adjustment of the orthorectified image may be performed. For example, histograms may be generated for each of the R, G, and B values of the orthoimage. Then, for example, color adjustment is performed on the orthoimage at time t1 so that the average value and standard deviation represented by the histogram of the orthoimage at time t1 match or approach the average value and standard deviation represented by the histogram of the orthoimage at time t2. may be Further, for example, color adjustment is performed on the orthoimage at time t2 to make the average value and standard deviation represented by the histogram of the orthoimage at time t2 match or approximate the average value and standard deviation represented by the histogram of the orthoimage at time t1. may be Also, color adjustment may be performed on both the orthorectified image at time t1 and the orthorectified image at time t2.

Then, based on the comparison result of the color information represented in the orthorectified images for which color adjustment has been performed, the house change of the house associated with the house object 44 may be estimated.

For example, if there are a large number of existing house change interpretation results, the threshold value described above may be determined using Otsu's automatic discrimination method. Alternatively, the thresholds described above may be set manually by visual interpretation using samples.

As described above, according to the present embodiment, it is possible to accurately estimate many types of house changes.

The functions of the house change estimating device 10 according to this embodiment and the processing executed by the house change estimating device 10 according to this embodiment will be further described below.

FIG. 11 is a functional block diagram showing an example of functions implemented in the house change estimation device 10 according to this embodiment. Note that the house change estimation device 10 according to the present embodiment does not need to implement all the functions shown in FIG. 11, and functions other than the functions shown in FIG. 11 may be installed.

As shown in FIG. 11, the house change estimation device 10 according to the present embodiment includes functionally, for example, a DSM data storage unit 50, an image storage unit 52, a house object extraction unit 54, an identification unit 56, a house change estimation A portion 58 is included. The specifying unit 56 includes an altitude specifying unit 56a and a color information specifying unit 56b. The DSM data storage unit 50 and the image storage unit 52 are mainly implemented by the storage unit 14 . The house object extraction unit 54 , the identification unit 56 , and the house change estimation unit 58 are mainly implemented by the processor 12 .

The functions described above may be implemented by causing the processor 12 to execute a program including instructions corresponding to the functions described above, which is installed in the house change estimation device 10, which is a computer. This program may be supplied to the house change estimation device 10 via a computer-readable information storage medium such as an optical disk, a magnetic disk, a magnetic tape, a magneto-optical disk, or a flash memory, or via the Internet or the like. good.

In this embodiment, the DSM data storage unit 50 stores DSM data of the target area at a plurality of times including time t1 and time t2, for example.

In this embodiment, the image storage unit 52 stores images of target regions at a plurality of times including time t1 and time t2, for example. The image stored in the image storage unit 52 may be, for example, a photographed image of the target area, such as an aerial photograph image or a high-resolution satellite image. Also, the images stored in the image storage unit 52 may be, for example, orthorectified images.

In this embodiment, the house object extraction unit 54, for example, based on the elevation data of the surface layer of the ground including the features in the estimated house change area for which the house change is to be estimated, extracts a house within the estimated house change area. Extract the house area represented by . In the above example, the house object extraction unit 54 extracts the house area associated with the house object 44 in the target area at times t1 and t2, for example.

In the present embodiment, for example, the identifying unit 56 uses the altitude, the comparison result of the altitude, or the , at least one of the comparison results of the color information.

In the present embodiment, for example, the altitude specifying unit 56a determines the altitude indicated by the altitude data in the first period and the altitude data in the second period for the house area extracted based on the altitude data in the first period. Identify the altitude indicated by . The altitude specifying unit 56a may specify a comparison result between the altitude indicated by the altitude data in the first period and the altitude indicated by the altitude data in the second period. In the above example, when timing t1 corresponds to the first timing, timing t2 corresponds to the second timing. Also, when the timing t2 corresponds to the first timing, the timing t1 corresponds to the second timing.

In the present embodiment, for example, the color information specifying unit 56b, for the house area extracted based on the altitude data of the first period, the color information represented in the image photographed in the first period and the second and color information expressed in the image taken at the time. Again, as described above, if time t1 corresponds to the first time in the above example, time t2 corresponds to the second time. Also, when the timing t2 corresponds to the first timing, the timing t1 corresponds to the second timing.

The color information specifying unit 56b may perform color adjustment on at least one of the image captured during the first period and the image captured during the second period. In this case, the color information specifying unit 56b may specify the color information represented in the color-adjusted image.

In this embodiment, the house change estimating unit 58 estimates, for example, the house change of the house represented in the house area between the first period and the second period.

Here, as described above, the house change estimation unit 58 determines the house area extracted based on the altitude data in the first period based on the altitude indicated by the altitude data in the second period. You may estimate the house change of the house matched. In addition, as described above, the house movement estimation unit 58 estimates the house movement of the house associated with the house region extracted based on the altitude data in the first period between the first period and the second period. You may estimate based on the comparison result of the altitude which the data of the altitude in .

In addition, as described above, the house change estimating unit 58 captures the house change of the house associated with the house region extracted based on the altitude data of the first time period and the second time period. It may be estimated based on the comparison result of the color information represented in the image. Here, as described above, the color difference values described above may be used as the comparison result of the color information.

Also, even if a house change is estimated based on multiple combinations of the elevation indicated by the elevation data, the comparison result of the elevation indicated by the elevation data, and the comparison result of the color information represented in the photographed image. good.

In addition, the house change estimation unit 58 determines whether or not the house represented in the house area will be rebuilt based on the comparison result of the altitude indicated by the altitude data between the first period and the second period. can be estimated.

In addition, the house change estimation unit 58 performs a comparison of the elevation indicated by the elevation data between the first period and the second period and the comparison result of the color information for the house represented in the house area. Presence or absence of rebuilding may be estimated.

Also, the house change estimation unit 58 may estimate the house change of the house represented in the house area based on the comparison result of the hue components in the color information represented by the HSI color system.

Further, the house change estimation unit 58 may estimate the house change of the house represented in the house area based on the comparison result of the color information represented in the color-adjusted image.

Further, the house change estimation unit 58 may output the house change estimation result for the house represented in the house area. FIG. 12 shows an example of a screen showing the estimation result of house change. In the example of FIG. 12, an image representing the estimation result of the house change of the house in the target area between time t1 and time t2 is superimposed on the orthoimage illustrated in FIG.

An example of the flow of processing performed by the house change estimation device 10 according to the present embodiment will be described below with reference to the flow charts illustrated in FIGS. 13A to 13C.

First, the house object extraction unit 54 acquires DSM data representing the DSM of the target area at time t1 and the DSM of the target area at time t2 from the DSM data storage unit 50 (S101).

Then, the color information specifying unit 56b acquires the image of the target region at time t1 and the image of the target region at time t2 from the image storage unit 52 (S102). Here, as described above, the color information specifying unit 56b may perform color adjustment on at least one of the image of the target region at time t1 and the image of the target region at time t2.

Then, the house object extraction unit 54 executes the normalization process described above on each of the DSM of the target area at time t1 and the DSM of the target area at time t2 (S103). By the processing shown in S103, the NDSM of the target region at time t1 and the NDSM of the target region at time t2 are generated.

Then, the house object extraction unit 54 executes vegetation removal processing on the NDSM generated by the processing shown in S103 (S104).

Then, the house object extracting unit 54 executes region dividing processing on the NDSM for which the processing shown in S104 has been executed (S105). The target region at time t1 and the target region at time t2 are divided into a plurality of convex regions 42 by the process shown in S105.

Then, the house object extraction unit 54 executes contour extraction processing on each of the plurality of convex regions 42 at time t1 and the plurality of convex regions 42 at time t2 (S106). By the process shown in S106, the house object 44 within the target area at time t1 and the house object 44 within the target area at time t2 are specified. Hereinafter, the house object 44 identified for the target area at time t1 will be referred to as the first house object, and the house object 44 identified for the target area at time t2 will be referred to as the second house object.

Then, the house change estimation unit 58 assigns an order number starting from 1 to each of the first house objects identified in the process shown in S106, and assigns an order number starting from 1 to each of the second house objects identified in the process shown in S106. A starting sequence number is set (S107). Hereinafter, it is assumed that the number of identified first house objects is M and the number of identified second house objects is N. An order number of 1 to M or less is set to each of the identified first house objects, and an order number of 1 to N or less is set to each of the identified second house objects.

Then, the house change estimation unit 58 sets 1 as the value of the variable i (S108).

Then, the altitude specifying unit 56a determines, based on the altitudes at time t1 for a plurality of positions included in the house area corresponding to the first house object whose order number is i, indicated by the DSM at time t1, the height of the house area. The altitude at time t1 is identified (S109). Here, for example, an average value of altitudes at time t1 for a plurality of positions included in the house region may be specified as the altitude of the house region at time t1.

Then, the altitude specifying unit 56a determines, based on the altitudes at time t2 of a plurality of positions included in the house area corresponding to the first house object having the sequence number i, indicated by the DSM at time t2, the height of the house area. The altitude at time t2 is identified (S110). Here, for example, an average value of altitudes at time t2 for a plurality of positions included in the house region may be specified as the altitude of the house region at time t2.

Then, the color information specifying unit 56b determines, at time t1 is specified (S111). Here, color information in the image on which color adjustment has been performed may be specified.

Then, the color information specifying unit 56b determines, at time t2, each pixel included in the house area corresponding to the first house object whose order number is i in the image of the target area at time t2 acquired in the process shown in S102. is specified (S112). Here, color information in the image on which color adjustment has been performed may be specified.

Then, the house change estimating unit 58 determines time t1 and time t2 for the house corresponding to the first house object whose order number is i, based on the altitude and color information specified in the processing shown in S109 to S112. A house change in between is estimated (S113). Here, house change may be estimated based on part of the altitude and color information specified in the processing shown in S109 to S112.

Then, the house change estimation unit 58 confirms whether or not the value of the variable i is M (S114).

When it is confirmed that the value of the variable i is not M (S114: N), the house change estimation unit 58 increases the value of the variable i by 1 (S115), and returns to the processing shown in S109.

When it is confirmed that the value of the variable i is M (S114: Y), the house change estimation unit 58 changes the value of the variable i to 1 (S116).

Then, the altitude specifying unit 56a determines, based on the altitudes at time t2 of a plurality of positions included in the house region corresponding to the second house object having the order number i indicated by the DSM at time t2, the height of the house region. The altitude at time t2 is identified (S117). Here, for example, an average value of altitudes at time t2 for a plurality of positions included in the house region may be specified as the altitude of the house region at time t2.

Then, the altitude specifying unit 56a determines, based on the altitudes at time t1 for a plurality of positions included in the house area corresponding to the second house object having the order number i, indicated by the DSM at time t1, the height of the house area. The altitude at time t1 is identified (S118). Here, for example, an average value of altitudes at time t1 for a plurality of positions included in the house region may be specified as the altitude of the house region at time t1.

Then, the color information specifying unit 56b determines, at time t2, each pixel included in the house area corresponding to the second house object whose order number is i in the image of the target area at time t2 acquired in the process shown in S102. is specified (S119). Here, color information in the image on which color adjustment has been performed may be specified.

Then, the color information specifying unit 56b determines, at time t1 (S120). Here, color information in the image on which color adjustment has been performed may be specified.

Then, the house change estimating unit 58 determines time t1 and time t2 for the house corresponding to the second house object whose order number is i, based on the altitude and color information specified in the processing shown in S117 to S120. A house change in between is estimated (S121). Here, the house change may be estimated based on part of the altitude and color information specified in the processing shown in S117 to S120.

Then, the house change estimation unit 58 confirms whether or not the value of the variable i is N (S122).

When it is confirmed that the value of the variable i is not N (S122: N), the house change estimation unit 58 increases the value of the variable i by 1 (S123), and returns to the processing shown in S117.

If it is confirmed that the value of the variable i is N (S122: Y), the processing shown in this processing example ends.

It should be noted that the present invention is not limited to the above-described embodiments.

Moreover, the specific character strings and numerical values described above and the specific character strings in the drawings are examples, and the character strings and numerical values are not limited.

10 house change estimation device, 12 processor, 14 storage unit, 16 display unit, 18 operation unit, 20 DSM, 22 DTM, 24 house, 26 tree, 28 ground surface, 30 NDSM, 32 house, 34 tree, 36 ground surface, 40 Projection 42 Projection region 44 House object 46 House 50 DSM data storage unit 52 Image storage unit 54 House object extraction unit 56 Identification unit 56a Altitude identification unit 56b Color information identification unit 58 House change estimation part.

Claims (2)

an extracting means for extracting a house area in which a house is represented within the estimated house change area based on the elevation data of the ground surface layer including the feature;
Edge extraction executing means for executing edge extraction for the area in the image captured at the first time and the second time corresponding to the house area extracted based on the altitude data at the first time. When,
a pixel number specifying means for specifying the number of pixels specified as an edge by the edge extraction for each of the regions in the images captured at the first time period and the second time period;
The house between the first time period and the second time period based on the number of pixels specified for each of the regions in the images captured at the first time period and the second time period. a house change estimation means for estimating a house change for
A house change estimation device comprising: A procedure for extracting a house area in which a house is represented within the estimated house change area based on the elevation data of the ground surface layer including the features;
a step of performing edge extraction for regions in the images captured during the first and second periods corresponding to the house regions extracted based on the elevation data for the first period;
a step of identifying the number of pixels identified as edges by the edge extraction for each of the regions in the images captured at the first time period and the second time period;
The house between the first time period and the second time period based on the number of pixels specified for each of the regions in the images captured at the first time period and the second time period. A procedure for estimating house changes for
A program characterized by causing a computer to execute

Images