A building model generation system for design

Abstract

The present invention belongs to the field of three-dimensional modeling, and discloses a building model generation system for design, including a point cloud data acquisition device and a modeling device; the point cloud data acquisition device is used to perform three-dimensional scanning on a room to be designed to obtain point cloud data for modeling; the modeling device is used to generate a three-dimensional model of the room to be designed based on the point cloud data for modeling. The present invention sets a shooting device, a computing device and a mobile device, so that when moving on a scanning section of a long straight line segment and acquiring point cloud data, the position of the next shooting point is calculated according to the position of the previous scanning point, and the position of the next scanning point is calculated based on the shooting image obtained from the next shooting point, so that when performing three-dimensional scanning in an area with a relatively complex structure, the overlap between the point cloud data obtained by two adjacent scanning points is higher, providing more detailed information for the area with a relatively complex structure, and improving the modeling accuracy.

Description

Technical Field

[0001] The invention relates to the field of three-dimensional modeling, and in particular to a building model generation system for design. Background Art

[0002] When decorating an interior, it is usually necessary to first build a three-dimensional model of the room, and then carry out decoration design based on the three-dimensional model. In the prior art, the house is usually scanned in an equidistant scanning manner to obtain point cloud data for modeling. That is, the distance between two adjacent scanning points is the same. This scanning method has the following disadvantages: for areas with more complex structures, such as areas where doors and windows are located, due to the rapid shape changes in complex areas, the number of point clouds containing detailed information may be insufficient, which ultimately leads to inaccurate dimensions after modeling, resulting in the designed decoration plan being unable to be applied to the actual decoration process. Summary of the invention

[0003] The purpose of the present invention is to disclose a building model generation system for design, which solves the problem of how to improve the accuracy of modeling when modeling a room before decoration design, so that the size after modeling is more accurate.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The present invention provides a building model generation system for design, comprising a point cloud data acquisition device and a modeling device;

[0006] The point cloud data acquisition device is used to perform three-dimensional scanning on the room to be designed to obtain point cloud data for modeling;

[0007] The modeling device is used to generate a three-dimensional model of the room to be designed based on the point cloud data for modeling;

[0008] The point cloud data acquisition device includes a path planning device, a mobile device, a scanning device, a photographing device and a computing device;

[0009] The path planning device is used to construct a scanning path according to the floor plan of the room to be designed, so that the scanning device can maintain a preset distance from the wall of the room to be designed when moving on the scanning path;

[0010] The mobile device is used to drive the scanning device and the photographing device to move on the scanning path;

[0011] The computing device is used to segment the scanning path to obtain a plurality of scanning sections and determine the types of the scanning sections, where the types of the scanning sections include straight sections and curved sections;

[0012] The computing device is also used to determine the shooting points and scanning points of the scanning road section, including:

[0013] When the mobile device moves on a straight road segment whose length is greater than a preset length threshold, the computing device is used to calculate the position of the next shooting point according to the position of the previous scanning point;

[0014] The shooting device is used to shoot the room to be designed at the next shooting point to obtain a shooting image;

[0015] The computing device is also used to calculate the regional complexity according to the captured image, and calculate the position of the next scanning point based on the regional complexity;

[0016] When the mobile device moves on a straight road segment whose length is less than or equal to a preset length threshold, the computing device uses the midpoint of the straight road segment as the position of the scanning point;

[0017] When the mobile device moves on a curved road section, if the length of the curved road section is less than or equal to a preset length threshold, the computing device uses the midpoint of the curved road section as the position of the scanning point;

[0018] If the length of the curved road section is greater than a preset length threshold, the computing device evenly divides the curved road section into a plurality of local road sections whose lengths are less than or equal to the length threshold, and uses the midpoint of each local road section as the position of a scanning point;

[0019] The scanning device is used to scan the room to be designed at the scanning point to obtain the point cloud data of each scanning point;

[0020] The mobile device is used to move the scanning device to the scanning point and to move the shooting device to the shooting point.

[0021] Optionally, the scanning device, the photographing device and the computing device can all be moved driven by a mobile device.

[0022] Optionally, the scanning path is segmented to obtain multiple scanning sections, including:

[0023] Get the vertices on the scan path and use the path between two vertices as a scan segment.

[0024] Optionally, determine the type of the scanned section, including:

[0025] Connect the two vertices of the scanned segment to obtain a straight line segment;

[0026] It is determined whether the scanned section completely coincides with the straight line segment. If so, the scanned section is a straight line segment; if not, the scanned section is a curved section.

[0027] Optionally, the position of the next shooting point is calculated based on the position of the previous scanning point, including:

[0028] Denote the viewing angle of the scanning device as θ;

[0029] Let d represent the preset distance; let wid represent the scanning width of the scanning device.

[0030] The position of the next shooting point is to move along the scanning direction from the previous scanning point on the scanning path, passing the distance location.

[0031] Optionally, the regional complexity is calculated based on the captured image, including:

[0032] Cropping the captured image to obtain a cropped image;

[0033] Compute regional complexity based on cropped images.

[0034] Optionally, cropping the captured image to obtain a cropped image includes:

[0035] N represents the number of columns of the captured image, then Column to The pixels of compose the cropped image.

[0036] Optionally, calculate regional complexity based on the cropped image, including:

[0037] The regional complexity is calculated using the following formula:

[0038]

[0039] cplex represents the regional complexity, α represents the image gradient coefficient, pixsht represents the set of pixels in the cropped image, numpix represents the total number of pixels in pixsht, gradmx represents the maximum value of the image gradient of all pixels in pixsht, and grad i represents the image gradient of pixel i, numfea represents the number of structural feature points in pixsht, and β represents the structural feature coefficient.

[0040] Optionally, the viewing angle of the photographing device is the same as that of the scanning device.

[0041] Optionally, the room to be designed is photographed to obtain photographic images, including:

[0042] The wall of the room to be designed is photographed to obtain a photographed image.

[0043] The advancements of the present invention include:

[0044] The present invention does not directly use a simple equidistant scanning method to scan the house to obtain modeling data, but sets up a shooting device, a computing device and a mobile device, so that when moving on a long scanning section that is a straight line segment and acquiring point cloud data, the position of the next shooting point can be calculated according to the position of the previous scanning point, and the position of the next scanning point can be calculated based on the shooting image obtained by the next shooting point. Therefore, when performing three-dimensional scanning in an area with a more complex structure, the overlap between the point cloud data obtained by two adjacent scanning points is higher, so that when the subsequent point cloud data is fused, more detailed information can be provided for the area with a more complex structure, thereby improving the accuracy after modeling, and then improving the accuracy of the decoration design plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 A schematic diagram of a system for generating a building model for design according to the present invention.

[0047] Figure 2 A schematic diagram of the floor plan of the present invention.

[0048] Figure 3 A schematic diagram of the scanning path of the present invention.

[0049] Figure 4 A schematic diagram of the apex of the present invention.

[0050] Figure 5 A schematic diagram of the relationship between the scanning width, viewing angle, and preset distance of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope parameters of the protection of the present invention.

[0052] like Figure 1 In one embodiment shown, the present invention provides a building model generation system for design, including a point cloud data acquisition device and a modeling device;

[0053] The point cloud data acquisition device is used to perform three-dimensional scanning on the room to be designed to obtain point cloud data for modeling;

[0054] The modeling device is used to generate a three-dimensional model of the room to be designed based on the point cloud data for modeling;

[0055] The point cloud data acquisition device includes a path planning device, a mobile device, a scanning device, a photographing device and a computing device;

[0056] The path planning device is used to construct a scanning path according to the floor plan of the room to be designed, so that the scanning device can maintain a preset distance from the wall of the room to be designed when moving on the scanning path;

[0057] The mobile device is used to drive the scanning device and the photographing device to move on the scanning path;

[0058] The computing device is used to segment the scanning path to obtain a plurality of scanning sections and determine the types of the scanning sections, where the types of the scanning sections include straight sections and curved sections;

[0059] The computing device is also used to determine the shooting points and scanning points of the scanning road section, including:

[0060] When the mobile device moves on a straight road segment whose length is greater than a preset length threshold, the computing device is used to calculate the position of the next shooting point according to the position of the previous scanning point;

[0061] The shooting device is used to shoot the room to be designed at the next shooting point to obtain a shooting image;

[0062] The computing device is also used to calculate the regional complexity according to the captured image, and calculate the position of the next scanning point based on the regional complexity;

[0063] When the mobile device moves on a straight road segment whose length is less than or equal to a preset length threshold, the computing device uses the midpoint of the straight road segment as the position of the scanning point;

[0064] When the mobile device moves on a curved road section, if the length of the curved road section is less than or equal to a preset length threshold, the computing device uses the midpoint of the curved road section as the position of the scanning point;

[0065] If the length of the curved road section is greater than a preset length threshold, the computing device evenly divides the curved road section into a plurality of local road sections whose lengths are less than or equal to the length threshold, and uses the midpoint of each local road section as the position of a scanning point;

[0066] The scanning device is used to scan the room to be designed at the scanning point to obtain the point cloud data of each scanning point;

[0067] The mobile device is used to move the scanning device to the scanning point and to move the shooting device to the shooting point.

[0068] The present invention does not directly use a simple equidistant scanning method to scan the house to obtain modeling data, but sets up a shooting device, a computing device and a mobile device, so that when moving on a long scanning section that is a straight line segment and acquiring point cloud data, the position of the next shooting point can be calculated according to the position of the previous scanning point, and the position of the next scanning point can be calculated based on the shooting image obtained by the next shooting point. Therefore, when performing three-dimensional scanning in an area with a more complex structure, the overlap between the point cloud data obtained by two adjacent scanning points is higher, so that when the subsequent point cloud data is fused, more detailed information can be provided for the area with a more complex structure, thereby improving the accuracy after modeling, and then improving the accuracy of the decoration design plan.

[0069] Specifically, in one embodiment, the floor plan is as follows: Figure 2 As shown, Figure 2 When performing 3D modeling of the master bedroom in the figure, the scanning path of the component is as follows Figure 3 As shown, in Figure 3 In the example, the distance between the scanning path and the wall is the preset distance.

[0070] In the present invention, the scanning path is a path extending along the interior of the floor plan and in a direction close to the wall.

[0071] Specifically, the preset distance is a working distance when the scanning device can reach the maximum scanning range while maintaining scanning accuracy, for example, 2 meters. The better the performance of the scanning device, the larger the corresponding preset distance.

[0072] Optionally, the point cloud data acquisition device further includes a point cloud data fusion module, which is used to fuse the point cloud data obtained from all scanning points to obtain point cloud data for modeling.

[0073] Specifically, when the room to be designed is relatively large, it is difficult to establish a complete three-dimensional model of the room in one scan. At this time, it is necessary to obtain multiple copies of point cloud data through multiple scans. In the present invention, there are overlapping areas between some point cloud data, so that more point cloud data carrying effective information can be provided for areas with complex structures. After fusion, the detailed information carried by the point cloud in the area with complex structure can meet the needs of high-precision modeling.

[0074] Optionally, the scanning device, the photographing device and the computing device can all be moved driven by a mobile device.

[0075] Specifically, the scanning device, the photographing device and the computing device can all be placed above the mobile device, thereby avoiding the mobile device running back and forth to switch the carried devices, thereby improving the scanning efficiency.

[0076] Optionally, the scanning path is segmented to obtain multiple scanning sections, including:

[0077] Get the vertices on the scan path and use the path between two vertices as a scan segment.

[0078] Specifically, the vertices are shown in 4. Figure 4 A scanning path is shown, which includes a straight section and a curved section. In the present invention, the place where the slope changes becomes a vertex. For a straight section, the vertex is the starting point and the end point of the straight section, and for a curved section, the vertex includes the point connected to the straight section. Figure 4 Only two of the vertices are indicated.

[0079] Optionally, determine the type of the scanned section, including:

[0080] Connect the two vertices of the scanned segment to obtain a straight line segment;

[0081] It is determined whether the scanned section completely coincides with the straight line segment. If so, the scanned section is a straight line segment; if not, the scanned section is a curved section.

[0082] Specifically, on a straight line segment, the slope of each point is the same.

[0083] Optionally, the position of the next shooting point is calculated based on the position of the previous scanning point, including:

[0084] Denote the viewing angle of the scanning device as θ;

[0085] Let d represent the preset distance; let wid represent the scanning width of the scanning device.

[0086] The position of the next shooting point is to move along the scanning direction from the previous scanning point on the scanning path, passing the distance location.

[0087] The relationship between the scan width, viewing angle, and preset distance is as follows: Figure 5 As shown, in Figure 5 In the figure, AB represents the scanning width, the angle between AC and BC is the viewing angle θ of the scanning device, point C is the location of the scanning device, the length of CD is d, and the direction of CD is the scanning direction of the scanning device.

[0088] When scanning in the room to be designed, the locations of AB are where the walls or other house structures are located.

[0089] Specifically, the above-mentioned viewing angle refers to the viewing angle in the horizontal direction.

[0090] Optionally, the preset length threshold is wid.

[0091] Specifically, the preset length threshold is the same as the scanning width of the scanning device. Therefore, when the length of the straight section is less than the scanning width, it means that a complete scanning result can be obtained by shooting at the midpoint of the straight section.

[0092] For a curved road section, when its length is less than a preset length threshold, it means that a complete scanning result can be obtained by scanning only the midpoint of the curved road section.

[0093] Specifically, the curved road section is evenly divided into a plurality of local sections whose lengths are less than or equal to the length threshold, including:

[0094] The number of local segments is calculated using the following formula:

[0095]

[0096] numway indicates the number of local sections, and length indicates the length of the curve section;

[0097] Divide the curved road segment into numway local sections of equal length.

[0098] Specifically, when calculating the number of local sections, the method of rounding up is adopted, so that the final local section is equal to or less than the length threshold, so that the scanning device can also obtain a complete scanning result when shooting at the midpoint of the local section.

[0099] Specifically, when designing existing houses, the walls are generally designed to be in the form of straight lines, so curved sections are relatively rare in actual application scenarios.

[0100] However, the present invention still sets corresponding scanning point determination schemes for different scenarios, thereby increasing the application scope of the present invention.

[0101] Optionally, the regional complexity is calculated based on the captured image, including:

[0102] Cropping the captured image to obtain a cropped image;

[0103] Compute regional complexity based on cropped images.

[0104] Specifically, in the scanned image, a part of the area overlaps with the area scanned by the scanning device at the previous scanning point, while the other part is the area that the scanning device failed to scan at the previous scanning point. Therefore, by cropping the captured image, most of the areas that failed to scan can be removed, as well as areas far from the edge of the area scanned by the previous scanning point, leaving areas close to the edge, thereby improving the representativeness of the calculated regional complexity and making the calculation results of subsequent scanning points more accurate.

[0105] Optionally, cropping the captured image to obtain a cropped image includes:

[0106] N represents the number of columns of the captured image, then Column to The pixels of compose the cropped image.

[0107] Optionally, calculate regional complexity based on the cropped image, including:

[0108] The regional complexity is calculated using the following formula:

[0109]

[0110] cplex represents the regional complexity, α represents the image gradient coefficient, pixsht represents the set of pixels in the cropped image, numpix represents the total number of pixels in pixsht, gradmx represents the maximum value of the image gradient of all pixels in pixsht, and grad i represents the image gradient of pixel i, numfea represents the number of structural feature points in pixsht, and β represents the structural feature coefficient.

[0111] Specifically, in the present invention, when the image gradient of the pixel points in the cropped image changes more dramatically and the number of structural feature points increases, it means that the degree of structural change of the area of ​​the room to be designed contained in the cropped image is greater. Since it is at the edge of the viewing angle of the scanning device, it is necessary to increase the amount of point cloud data of this area in the subsequent scanning process, so as to achieve higher modeling accuracy in the subsequent modeling process.

[0112] Optionally, the process of obtaining structural feature points includes:

[0113] For pixel point q in the cropped image, the feature judgment value of pixel point q is calculated using the following formula:

[0114]

[0115] judfea q represents the feature judgment value of pixel q, δ represents the preset weight, graydiscq represents the grayscale difference value of pixel q, graymx represents the maximum grayscale value of the pixels in the 8-neighborhood of pixel q, graybg q Indicates that the absolute value of the grayscale difference between pixel q and pixel q in the 8-neighborhood is greater than graydisc q The number of pixels;

[0116]

[0117] gray q represents the gray value of pixel q, nebq represents the set of pixels in the 8-neighborhood of pixel q, distc q,j represents the distance between pixel q and pixel j, distcf represents the variance of the distance between pixel nebq and pixel j, gray j represents the gray value of pixel j, grayf represents the variance of the difference between the gray values ​​of pixel j in nebq;

[0118] The pixel points whose feature judgment values ​​are greater than a preset feature judgment value threshold are regarded as structural feature points.

[0119] Specifically, in the present invention, the feature judgment value comprehensively represents the pixel point from two different angles. The larger the gray value difference between the pixel point and the pixel points in the 8-neighborhood (i.e., graybg q The larger the value of , the greater the difference between the weighted value of the grayscale value of the pixel in the 8-neighborhood, that is, graydisc q The larger the value of , the larger the feature judgment value finally calculated; and when calculating the grayscale difference value, in addition to considering the grayscale value, the distance between the pixels is also considered, thereby introducing structural features to the feature judgment value of the present invention, so that the present invention can more accurately identify the structural feature points in the cropped image.

[0120] Optionally, the preset feature judgment value threshold may be 0.8.

[0121] Optional, the default weight is 0.5.

[0122] Optionally, the value of the image gradient coefficient is 0.6, and the value of the structural feature coefficient is 0.4.

[0123] Optionally, the position of the next scan point is calculated based on the area complexity, including:

[0124] Use the following formula to calculate the moving distance of the scanning device:

[0125]

[0126] Among them, movdist represents the moving distance, and cplexmx represents the maximum value of regional complexity;

[0127] The position of the next scanning point is the position reached after moving a distance of movdist along the scanning path from the previous scanning point.

[0128] Specifically, in the present invention, the greater the complexity of the area, the smaller the moving distance, so that the degree of overlap of the point cloud data obtained by two adjacent scanning points is higher, thereby being able to provide more point clouds carrying valid information for areas with complex structures, so that when the point cloud data are fused, the valid information carried by the point clouds in areas with complex structures is effectively guaranteed.

[0129] Optionally, the maximum value of the regional complexity can be obtained by taking the limit of the calculation formula of the regional complexity.

[0130] Optionally, the viewing angle of the photographing device is the same as that of the scanning device.

[0131] Specifically, maintaining the same viewing angle can avoid obtaining too many pixels that are not within the scanning range of the previous scanning point when processing the captured image, thereby improving the efficiency of calculating regional complexity.

[0132] Optionally, the room to be designed is photographed to obtain photographic images, including:

[0133] The wall of the room to be designed is photographed to obtain a photographed image.

[0134] Specifically, the direction of the nearest wall of the designed room is photographed to obtain a photographed image.

[0135] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0136] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0138] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope parameters of the technical solutions of the embodiments of the present invention.

Claims

1. A building model generation system for design, characterized in that: It includes a point cloud data acquisition device and a modeling device; The point cloud data acquisition device is used to perform three-dimensional scanning on the room to be designed to obtain point cloud data for modeling; The modeling device is used to generate a three-dimensional model of the room to be designed based on the point cloud data for modeling; The point cloud data acquisition device includes a path planning device, a mobile device, a scanning device, a photographing device and a computing device; The path planning device is used to construct a scanning path according to the floor plan of the room to be designed, so that the scanning device can maintain a preset distance from the wall of the room to be designed when moving on the scanning path; The mobile device is used to drive the scanning device and the photographing device to move on the scanning path; The computing device is used to segment the scanning path to obtain a plurality of scanning sections and determine the types of the scanning sections, where the types of the scanning sections include straight sections and curved sections; The computing device is also used to determine the shooting points and scanning points of the scanned road section, including: When the mobile device moves on a straight road segment whose length is greater than a preset length threshold, the computing device is used to calculate the position of the next shooting point according to the position of the previous scanning point; The shooting device is used to shoot the room to be designed at the next shooting point to obtain a shooting image; The computing device is also used to calculate the regional complexity according to the captured image, and calculate the position of the next scanning point based on the regional complexity; When the mobile device moves on a straight road segment whose length is less than or equal to a preset length threshold, the computing device uses the midpoint of the straight road segment as the position of the scanning point; When the mobile device moves on a curved road section, if the length of the curved road section is less than or equal to a preset length threshold, the computing device uses the midpoint of the curved road section as the position of the scanning point; If the length of the curved road section is greater than a preset length threshold, the computing device evenly divides the curved road section into a plurality of local road sections whose lengths are less than or equal to the length threshold, and uses the midpoint of each local road section as the position of a scanning point; The scanning device is used to scan the room to be designed at the scanning point to obtain the point cloud data of each scanning point; The mobile device is used to move the scanning device to the scanning point and move the shooting device to the shooting point; The position of the next shooting point is calculated based on the position of the previous scanning point, including: Denote the viewing angle of the scanning device as θ; Let d represent the preset distance; let wid represent the scanning width of the scanning device. The position of the next shooting point is to move along the scanning direction from the previous scanning point on the scanning path, passing the distance location; The position of the next scan point is calculated based on the regional complexity, including: Use the following formula to calculate the moving distance of the scanning device: Among them, movdist represents the moving distance, cplexmx represents the maximum value of regional complexity; cplex represents regional complexity; The position of the next scanning point is the position reached after moving a distance of movdist along the scanning path from the previous scanning point.

2. The architectural model generation system for design according to claim 1, characterized in that: The scanning device, the photographing device and the computing device can all be moved driven by the mobile device.

3. The architectural model generation system for design according to claim 1, characterized in that: The scanning path is segmented to obtain multiple scanning sections, including: Get the vertices on the scan path and use the path between two vertices as a scan segment.

4. The architectural model generation system for design according to claim 3, characterized in that: Determine the type of road segment to scan, including: Connect the two vertices of the scanned segment to obtain a straight line segment; It is determined whether the scanned section completely coincides with the straight line segment. If so, the scanned section is a straight line segment; if not, the scanned section is a curved section.

5. The architectural model generation system for design according to claim 1, characterized in that: Calculate the regional complexity based on the captured image, including: Cropping the captured image to obtain a cropped image; Compute regional complexity based on cropped images.

6. The architectural model generation system for design according to claim 5, characterized in that: Crop the captured image to obtain a cropped image, including: N represents the number of columns of the captured image, then Column to The pixels in the columns make up the cropped image.

7. The architectural model generation system for design according to claim 6, characterized in that: Calculates regional complexity based on cropped images, including: The regional complexity is calculated using the following formula: cplex represents the regional complexity, α represents the image gradient coefficient, pixsht represents the set of pixels in the cropped image, numpix represents the total number of pixels in pixsht, gradmx represents the maximum value of the image gradient of all pixels in pixsht, and grad i represents the image gradient of pixel i, numfea represents the number of structural feature points in pixsht, and β represents the structural feature coefficient.

8. The architectural model generation system for design according to claim 1, characterized in that: The viewing angle of the photographing device is the same as that of the scanning device.

9. The architectural model generation system for design according to claim 1, characterized in that: Photograph the room to be designed and obtain photographic images, including: The wall of the room to be designed is photographed to obtain a photographed image.

Images