KR-20260065737-A - Image analysis device, image analysis method, and computer program

Abstract

The image analysis device includes a pose calculation unit that calculates a plurality of pose information representing the respective poses of a plurality of faces constituting the surface of a three-dimensional model that is placed in a virtual space and represents an object in real space, a reference calculation unit that calculates reference plane information representing a reference plane based on three or more surface position information representing the respective positions of three or more specific locations on the three-dimensional model, and a relative pose calculation unit that calculates relative pose information representing the pose of a face relative to a reference plane based on the pose information and reference plane information.

Inventors

• 다카미자와 다쿠야
• 이구치 시게노부
• 마츠모토 히로키

Assignees

• 칼타 가부시키가이샤

Dates

Publication Date

20260511

Application Date

20241028

Claims (12)

1. As an image analysis device, A pose calculation unit that calculates multiple pose information representing the respective poses of multiple faces constituting the surface of a 3D model placed in a virtual space and representing an object in real space, and A reference calculation unit that calculates reference plane information representing a reference plane based on three or more surface position information representing the respective locations of three or more specific points on the above three-dimensional model, and A relative posture calculation unit that calculates relative posture information representing the posture of the surface with respect to the reference plane based on the above posture information and the above reference plane information. Image analysis device including
2. In paragraph 1, An image analysis device in which the above-mentioned detail information is normal information representing the normal of the above-mentioned surface.
3. In paragraph 2, The above normal information includes information on the normal vector of the surface, and An image analysis device wherein the above relative attitude information includes information indicating the slope of the normal vector with respect to the reference plane.
4. In paragraph 3, The above reference plane information includes information on a reference vector parallel to the above reference plane, and An image analysis device wherein the relative attitude information includes information representing the inner product of the normal vector and the reference vector.
5. In paragraph 1, An image analysis device further comprising a coloring unit that colors the three-dimensional model based on a plurality of relative pose information.
6. In paragraph 5, The above posture information includes information on the normal vector of the surface, and An image analysis device in which the coloring part is capable of coloring the three-dimensional model in such a way that the normal vector is directed vertically upward and vertically downward with respect to the horizontal direction.
7. In paragraph 5, The above posture information includes information on the normal vector of the surface, and An image analysis device in which the coloring part is capable of coloring the three-dimensional model in a way that distinguishes between cases where the normal vector is directed toward the vertical direction and cases where it is directed toward the horizontal direction.
8. In paragraph 1 or 2, An image analysis device further comprising a receiving unit that receives the designation of three or more specific locations through an input device operated by a user.
9. In paragraph 1 or 2, An image analysis device in which the above reference calculation unit calculates the reference surface information by the least squares method based on the above three or more surface position information.
10. In paragraph 1 or 2, An image analysis device in which the above-mentioned object is a reinforced concrete structure.
11. As an image analysis method, A step of calculating multiple attitude information representing the respective attitudes of multiple faces constituting the surface of a 3D model that is placed in a virtual space and represents an object in real space, and A step of calculating reference plane information representing a reference plane based on three or more surface position information representing the respective locations of three or more specific points on the above three-dimensional model, and A step of calculating relative posture information representing the posture of the surface relative to the reference plane based on the posture information and the reference plane information. Image analysis method including
12. As a computer program, on the computer, A step of calculating multiple attitude information representing the respective attitudes of multiple faces constituting the surface of a 3D model that is placed in a virtual space and represents an object in real space, and A step of calculating reference plane information representing a reference plane based on three or more surface position information representing the respective locations of three or more specific points on the above three-dimensional model, and A step of calculating relative posture information representing the posture of the surface relative to the reference plane based on the posture information and the reference plane information. A computer program that executes.

Description

Image analysis device, image analysis method, and computer program The present disclosure relates to an image analysis device, an image analysis method, and a computer program. In the point cloud data utilization system described in Patent Document 1, an operator uses an operating unit to specify a predetermined number of points (e.g., 3 points) among the projected coordinate points in an image of an area where an object to be inspected is displayed. Next, a control unit creates a plane containing each coordinate point corresponding to the specified projected coordinate points as a virtual reference plane. The virtual reference plane virtually represents a surface in an ideal state free from damage, etc. Next, the control unit extracts each coordinate point whose normal distance from the virtual reference plane is greater than or equal to a predetermined value as a feature point. Next, a display unit displays the projected coordinate point corresponding to the feature point by changing its color to distinguish it from other projected coordinate points. As a result, a location that protrudes or is sunken beyond a predetermined amount from the virtual reference plane is characterized. FIG. 1 is a block diagram showing an example of the configuration of an image analysis system according to one embodiment of the present invention. Figures 2 (a) and 2 (b) are schematic cross-sectional views showing the phenomenon of lifting occurring in the concrete of a reinforced concrete structure, which is the subject. FIG. 3 is a block diagram showing an example of a server configuration according to the same embodiment. FIG. 4 is a perspective view showing an example of a three-dimensional model according to the same embodiment. FIG. 5 is a perspective view showing an example of a surface constituting the surface of a three-dimensional model according to the same embodiment. FIG. 6 is a perspective view showing an example of a point group and a reference plane according to the same embodiment. FIG. 7 is a drawing showing the cross-section of an object superimposed on a point group and a reference plane of a three-dimensional model according to the same embodiment. FIG. 8 is a perspective view showing a reference plane, a reference plane vector, a plane, a normal vector, and a reference vector according to the same embodiment. FIG. 9 is a perspective view showing an example of multiple surfaces sharing one point of a point group according to the same embodiment. FIG. 10 is a drawing showing a color table according to the same embodiment. FIG. 11 is a schematic drawing showing a colored three-dimensional model according to the same embodiment. FIG. 12 is a flowchart illustrating an image analysis method according to the same embodiment. Suitable embodiments of the present disclosure will be described in detail below with reference to the attached drawings. Additionally, in this specification and drawings, components having substantially the same functional configuration are given the same reference numerals to avoid redundant descriptions. FIG. 1 is a diagram showing an example of the configuration of an image analysis system (SYS) according to an embodiment of the present invention. As shown in FIG. 1, the image analysis system (SYS) includes a server (1). The server (1) corresponds to an example of an "image analysis device" of the present disclosure. The server (1) supports, for example, the detection of an abnormality in an object existing in actual space (hereinafter referred to as "object (100)"). That is, the server (1) supports the inspection of the object (100). The object (100) is, for example, a reinforced concrete structure. In this case, for example, the reinforced concrete structure has a wall surface (surface) that is approximately parallel to the vertical direction. Also, for example, an abnormality of the object (100) is lifting of the concrete. FIGS. 2(a) and FIGS. 2(b) are schematic cross-sectional views illustrating the phenomenon of lifting occurring in the concrete (101) of the object (100), which is a reinforced concrete structure. As shown in FIG. 2(a), the object (100), which is a reinforced concrete structure, includes concrete (101) and reinforcing bars (103). The surface (104) of the concrete (101) is exposed. The direction (D) indicates a vertical upward direction. The reinforcing bars (103) are, for example, deformed reinforcing bars. The reinforcing bar (103) may corrode and expand due to water or the like penetrating the concrete (101). As a result, cracks (104) may occur in the concrete (101) starting from the reinforcing bar (103). Also, as shown in FIG. 2 (b), a portion of the concrete (101) is extruded, causing a lifted portion (102). The server (1) supports the detection of a lifted portion (102) of concrete (101) based on a three-dimensional model of the object (100). In particular, in this embodiment, the server (1) can suppress the omission of detection of the lifted portion (102) bas