JP5636966B2 - Error detection apparatus and error detection program - Google Patents

Description

  The present invention relates to an error detection apparatus and an error detection program.

  A technique for comparing a captured image of an object with three-dimensional design information of the object has been proposed.

  As a technique related to this, Patent Document 1 discloses an input means for inputting an image obtained by photographing a marker and an object having a known three-dimensional positional relationship using a camera, and a position of the marker on the input image. Position and orientation detection means for determining the position and orientation relationship between the object and the camera using the image, and superimposed display for displaying the three-dimensional design information superimposed on the captured image based on the position and orientation relationship obtained by the position and orientation detection means There is disclosed an error detection device having means and means for extracting an error from a difference between a photographed image and three-dimensional design information displayed superimposed thereon.

JP 2002-92647 A

  An object of the present invention is to provide an error for detecting an error of a target object with respect to design information of the target object in consideration of an allowable amount of error on a two-dimensional display based on at least a shooting direction and a shooting distance of a captured image of the target object. The object is to provide a detection device and an error detection program.

[1] An operator is applied to viewpoint coordinates indicating a viewpoint for displaying three-dimensional design information indicating the design contents of the target object as a two-dimensional display image, and an object formed based on the design information is displayed. Alignment means for aligning the captured image and the display image of the design information;
At least the distance between the viewpoint coordinates of the design information aligned with the captured image by the alignment means and the plane of the design information constituting the object, the viewpoint coordinates of the design information, and the object of the design information The tolerance of the error on the two-dimensional display calculated based on the angle formed by the straight line passing through the coordinates of the surface constituting the object and the normal of the surface is used as the coordinate of the two-dimensional display image of the design information. Generating means for generating an error tolerance distribution image indicating the distribution of the error tolerance in association with each other;
Extraction means for extracting coordinates that are the contours of the object from the display image of the design information and the captured image;
The distance between the coordinates of the contour of the object of the display image of the design information extracted by the extraction means and the coordinates of the contour of the object of the captured image corresponding to the coordinates of the contour of the object is the error tolerance generated by the generation means. When the coordinates of the corresponding coordinates of the capacity distribution image exceed an allowable amount of error on the two-dimensional display, the coordinates of the display image of the design information and the contour of the object of the photographed image are determined as error points having errors. Error point determination means;
An error detection apparatus having

[2] The error detection device according to claim 1, further comprising an error point display unit that displays the error point determined by the error point determination unit to have an error in the display image of the design information.

[3] The extraction unit extracts coordinates that are contours of the object from a plurality of captured images,
The error point determination unit is configured to detect an error point when coordinates serving as an outline of the target object extracted from the plurality of captured images exceed an error tolerance on a two-dimensional display of an error tolerance distribution image corresponding to the coordinates. It is determined that
Among the error points of the plurality of photographed images determined by the error point determination means, those having a large tolerance on the two-dimensional display of the error tolerance distribution image corresponding to the error point The error detection apparatus according to claim 2, further comprising an error point selecting unit that selects the error points as representative error points.

[4] The error point display means, when an error point displayed on the display image of the design information is selected, the viewpoint of the photographed image associated with the representative error point selected by the error point selection means. The error detection apparatus according to claim 3, wherein a display image of the design information and the error point are displayed from coordinates.

[5] The generating means defines and expands each coordinate range of the error tolerance distribution image based on an error tolerance on the two-dimensional display of the coordinates,
The error point determination unit is configured such that a distance between a coordinate serving as the contour of the target object of the display image of the design information extracted by the extracting unit and a coordinate serving as the contour of the target object of the captured image corresponds to the generation. An error having an error in the coordinates of the display image of the design information and the contour of the object of the captured image when included in the expanded range of the corresponding coordinates of the error tolerance distribution image generated by the means The error detection device according to claim 1, wherein the error detection device determines a point.

[6]
Applying an operator to viewpoint coordinates indicating a viewpoint for displaying three-dimensional design information indicating the design of the target object as a two-dimensional display image, and a captured image of the target formed based on the design information; Alignment means for aligning the display image of the design information;
At least the distance between the viewpoint coordinates of the design information aligned with the captured image by the alignment means and the plane of the design information constituting the object, the viewpoint coordinates of the design information, and the object of the design information The tolerance of the error on the two-dimensional display calculated based on the angle formed by the straight line passing through the coordinates of the surface constituting the object and the normal of the surface is used as the coordinate of the two-dimensional display image of the design information. Generating means for generating an error tolerance distribution image indicating the distribution of the error tolerance in association with each other;
Extraction means for extracting coordinates that are the contours of the object from the display image of the design information and the captured image;
The distance between the coordinates of the contour of the object of the display image of the design information extracted by the extraction means and the coordinates of the contour of the object of the captured image corresponding to the coordinates of the contour of the object is the error tolerance generated by the generation means. When the coordinates of the corresponding coordinates of the capacity distribution image exceed an allowable amount of error on the two-dimensional display, the coordinates of the display image of the design information and the contour of the object of the photographed image are determined as error points having errors. An error detection program that functions as error point determination means.

  According to the invention according to claim 1 or 6, the design information of the target object of the target object in consideration of the allowable amount of error on the two-dimensional display based on at least the shooting direction and the shooting distance of the shot image of the target object. The error with respect to can be detected.

  According to the invention which concerns on Claim 2, an error point can be displayed with the display image of design information.

  According to the third aspect of the present invention, it is possible to select an error point having a large error tolerance on two-dimensional display from a plurality of captured images.

  According to the invention which concerns on Claim 4, the display image of design information can be displayed from the viewpoint coordinate corresponding to the error point with a large tolerance | permissible_error of a two-dimensional display.

  According to the fifth aspect of the present invention, it is determined whether or not the coordinates serving as the contour of the target object are error points according to the error tolerance distribution image expanded according to the error tolerance on the two-dimensional display. can do.

FIG. 1 is a schematic diagram illustrating a configuration example of an error detection system according to the present embodiment. FIG. 2 is a block diagram illustrating a configuration example of the error detection apparatus according to the present embodiment. FIGS. 3A and 3B are schematic diagrams showing an example of the contents of the photographed image information, FIG. 3C is a schematic diagram showing an example of the contents of the photographed information, and FIG. 3D is the object three-dimensional information. It is the schematic which shows an example of the display image of 113. FIG. FIGS. 4A and 4B are schematic diagrams for explaining parameters for calculating an error associated with two-dimensional display. FIGS. 5A and 5B are schematic diagrams illustrating an example of the configuration of the error map. FIGS. 6A to 6C are schematic diagrams for explaining an example of an error map expansion processing method. FIGS. 7A and 7B are schematic diagrams for explaining an operation example of the edge extracting means. 8A (a) and 8 (b) are edge information generated from the edge point set extracted by the edge extraction means. 8B (a) and 8 (b) are edge information including an error distance calculated by the edge extraction unit. 9A to 9D are schematic diagrams for explaining an example of the operation of the error point determination unit. FIG. 10A is a schematic diagram showing an example of the content of error information in which the edge label is added to the edge information 115 by the error point determination means, and FIG. 10B is a diagram for explaining the operation of the error point selection means. FIG. FIG. 11 is a schematic diagram showing an example of a display image of error three-dimensional information generated by the error point display means 106. 12A and 12B are schematic views showing another example of the display image of the error three-dimensional information generated by the error point display means. FIG. 13 is a flowchart illustrating an example of the operation of the error detection apparatus 1. FIGS. 14A to 14C are schematic diagrams for explaining an example of a method for determining whether or not there is an error in an edge point without performing expansion processing in the error map.

(Error detection system configuration)
FIG. 1 is a schematic diagram illustrating a configuration example of an error detection system according to the present embodiment.

  The error detection system 5 is configured by connecting an error detection device 1 and a camera 2 that captures an object 3 with a USB (Universal Serial Bus) cable or the like.

  The error detection apparatus 1 includes a CPU (Central Processing Unit) having a function for processing information and an electronic component such as a storage unit inside the main body, and processes image information generated as a result of photographing with the camera 2. The information processing apparatus includes a display unit 12 such as a liquid crystal display that displays an image, and an operation unit 13 such as a keyboard and a mouse that output an operation signal corresponding to the operation content. Note that the error detection device 1 is, for example, a personal computer, and a PDA (Personal Digital Assistant), a mobile phone, or the like can also be used.

  The camera 2 shoots the object 3 from a plurality of other shooting directions in addition to the shooting direction 20a, and records the shooting direction 20a and the other shooting directions together with the shot image information corresponding to the shot direction. Is transmitted to the error detection apparatus 1.

  The object 3 is a three-dimensional object composed of a plurality of surfaces. Note that the surface of the object 3 may have a pattern, and the type of material or the like is not particularly limited.

(Configuration of error detection device)
FIG. 2 is a block diagram illustrating a configuration example of the error detection apparatus 1 according to the present embodiment.

  The error detection apparatus 1 includes a CPU and the like. The control unit 10 controls each unit and executes various programs. The storage unit 11 is a storage medium such as an HDD (Hard Disk Drive) or a flash memory and stores information. A display unit 12 for displaying characters and images, such as a liquid crystal display, an operation unit 13 for outputting an operation signal corresponding to the operation content, such as a keyboard and a mouse, and a communication unit for communicating information with the camera 2 14.

  The error detection device 1 is, for example, an electronic device such as a personal computer, a PDA, or a mobile phone. However, the error detection device 1 may be a server device that does not include the display unit 12 and the operation unit 13, and in that case, the network is used. The operation unit and display unit of the connected terminal device replace these functions.

  The control unit 10 executes an error detection program 110, which will be described later, so that the captured image information receiving unit 100, the alignment unit 101, the error map generation unit 102, the edge extraction unit 103, the error point determination unit 104, and the error point selection unit. 105 and error point display means 106 and the like.

  The photographed image information accepting unit 100 accepts photographed image information 111 photographed by the camera 2 via the communication unit 14 and photographing information 112 including contents such as a photographing direction, a photographing position, and lens characteristics, and stores them in the storage unit 11. To do.

  The alignment means 101 calculates and obtains a transformation matrix of three-dimensional coordinates for matching a display image, which is an image obtained by displaying the object three-dimensional information 113 in two dimensions, with the photographed image information 111, and shoots with the transformation matrix. The image information 111 and the object three-dimensional information 113 are aligned. Note that the transformation matrix is a matrix that translates, rotates, and scales a three-dimensional position. The alignment is not limited to a matrix, and any operator that translates, rotates, and enlarges / reduces a three-dimensional position may be used.

  The error map generation means 102 calculates the allowable amount of error on the two-dimensional display from the imaging information 112 corresponding to the object 3D information 113 and the imaging image information 111 to be aligned by a method described later. An error map 114 is generated in which the allowable amount of error is associated with the coordinates of the display image 120 described later.

  The edge extraction means 103 is a coordinate (hereinafter referred to as an “edge point”) corresponding to an edge (contour) of the target object 3 from the captured image information 111 and the target object three-dimensional information 113 aligned with the captured image information 111. .) Is extracted to generate edge information 115.

  The error point determination unit 104 compares the edge point extracted by the edge extraction unit 103 with the error map 114 generated by the error map generation unit 102 to determine whether the edge point is an error point having an error. The determination result is reflected in the edge information 115 and generated as error information 116.

  The error point selection unit 105 selects a more probable error point when there are two or more error points having a high probability of being the same point in the error information 116.

  The error point display means 106 plots and displays the error points of the error information 116 on the display image of the target object three-dimensional information 113.

  The storage unit 11 includes an error detection program 110 that causes the control unit 10 to operate as the above-described units 100 to 106, captured image information 111 that is image information of the object 3 captured by the camera 2, and a camera at the time of shooting. 2 includes shooting information 112 including information such as shooting direction, shooting position, and lens characteristics, object three-dimensional information 113 that is design information written in three dimensions to manufacture the object 3, and error map generation means 102. The generated error map 114, the edge information 115 extracted by the edge extraction unit 103, the error information 116 generated by the error point determination unit 104, and the like are stored.

  FIGS. 3A and 3B are schematic diagrams showing an example of the contents of the photographed image information, FIG. 3C is a schematic diagram showing an example of the contents of the photographed information, and FIG. 3D is the object three-dimensional information. It is the schematic which shows an example of the display image of 113. FIG.

  The photographed image information 111a shown in FIG. 3A is information obtained by photographing the object 3 from the photographing direction 20a by the camera 2, as shown in the photographing information 112 shown in FIG. .

  Also, the photographed image information 111b shown in FIG. 3B is information obtained by photographing the object 3 from the photographing direction 20b by the camera 2 as shown in the photographing information 112 shown in FIG.

  An object three-dimensional display image 113A shown in FIG. 3C is a display image 120 displayed on the display unit 12 by reproducing the object three-dimensional information 113. The target object three-dimensional display image 113 </ b> A may be an image whose display content is enlarged / reduced or rotated according to the user's operation content on the operation unit 13.

  The shooting information 112 shown in FIG. 3D includes a shooting image information column in which an identifier of shooting image information generated by the camera 2 is recorded, a shooting direction column in which the shooting direction of the shooting image information is recorded, and the like.

(Operation of error detection device)
Hereinafter, with reference to FIGS. 1 to 8, an example of the operation of the error detection device 1 will be described. (1) Basic operation, (2) Error map generation operation, (3) Error point detection operation, (4) Error point display operation This will be explained separately.

(1) Basic operation First, the user photographs the object 3 from a plurality of photographing directions with the camera 2. The camera 2 stores shooting information 112 obtained from the shooting direction, shooting position, lens characteristics, and the like in the storage unit of the camera 2 together with the shot image information 111 taken.

  The user operates the operation unit 13 of the error detection device 1 to instruct communication with the camera 2. The operation unit 13 outputs an operation signal according to the operation.

  When receiving the operation signal from the operation unit 13, the error detection device 1 starts communication with the camera 2 via the communication unit 14. Next, the photographed image information accepting unit 100 accepts the photographed image information 111 and the photographed information 112 from the storage unit of the camera 2 and stores them in the storage unit 11. Note that the photographed image information accepting unit 100 may accept photographed image information 111 and photographed information 112 previously photographed from an external device other than the camera 2.

  Next, when the user requests alignment of the captured image information 111 and the object three-dimensional information 113 stored in the storage unit via the operation unit 13, the alignment unit 101 of the error detection apparatus 1 firstly The display image of the object three-dimensional information 113 is aligned with, for example, the captured image information 111a.

  For example, the alignment method is performed by selecting a characteristic point for matching the coordinates from the captured image information 111 and the target object three-dimensional information 113 by a user's operation, and the position of these characteristic points. Is calculated and obtained, and the coordinates of the object three-dimensional information 113 are converted by the conversion matrix to match the position with the captured image information 111. Note that the transformation matrix is a matrix that translates, rotates, and scales a three-dimensional position.

(2) Error Map Generation Operation FIG. 13 is a flowchart showing an example of the operation of the error detection device 1.

  Next, the error map generation means 102 generates an error map 114a from the object three-dimensional information 113 aligned with the captured image information 111a by a method described below (S1).

  First, the error map generation unit 102 forms an object with the viewpoint coordinates corresponding to the viewpoint of the object 3D information 113 aligned with the captured image information 111a, that is, the viewpoint coordinates corresponding to the imaging direction 20a of the camera 2. M, which is an allowable amount of error on the two-dimensional display determined from the relationship with the plurality of surfaces to be calculated.

  FIGS. 4A and 4B are schematic diagrams for explaining each parameter for calculating the allowable amount of error on the two-dimensional display.

なお、（ｘ、ｙ）は、対象物三次元情報１１３の表示画像１２０上の座標を示し、画像の解像度（ｐｉｘｅｌ）分存在するものである。 The surface constituting the object 3 is the object surface S, the normal of the object surface S is n, the viewpoint coordinates for the object 3 are the camera position P, and the virtual plane corresponding to the display screen of the display unit 12 is the image plane I and When the allowable error in design is the allowable error e, the allowable amount of error on the two-dimensional display using the angle a between the shooting direction and the normal n, the distance d between the viewpoint coordinates and the object surface S, and the focal distance f. Where m is expressed as in the following formula (1).

Here, (x, y) indicates the coordinates on the display image 120 of the object three-dimensional information 113, and exists for the resolution (pixel) of the image.

  Next, the error map generation means 102 sets the value of m to m = 0 when the value of m is smaller than a predetermined threshold and when the normal n changes continuously (when it is not a plane), and the display image An error map 114a described below is generated in association with the 120 coordinates.

  FIGS. 5A and 5B are schematic diagrams illustrating an example of the configuration of the error map.

Error map shown in FIG. 5 (a) 114a is, m = 0 point and a set of points with the m = 0 by the above-described method as a region 114a _1, The region 114a of the set of points a m ≠ 0 ₂ is displayed.

Next, the error map generation means 102 expands the range of each coordinate of the error map 114a in proportion to the value of m (S2), and generates an error map 114b. The area 114b ₁ is a set of points where m = 0 similarly to the area 114a ₁ , and the area 114b ₂ is an area obtained by expanding the area 114a ₂ .

  It should be noted that adjustment between adjacent regions having different values of m in the expansion processing is handled by the method described below.

  FIGS. 6A to 6C are schematic diagrams for explaining an example of an error map expansion processing method.

As shown in FIG. 6 (a), regions A ₁ before expansion processing an m = 2, when the area A ₂ is assumed to be m = 6, if there is no adjacent region, FIG. 6 (b ), The regions A ₁ and A ₂ are expanded by ₂ pixels and 6 pixels on the outside by the expansion process. In this case, the error detection result to be described later varies depending on which region is prioritized.

For example, as shown in FIG. 6 (c1), a large region of the value of m, i.e. when the area A ₂ is preferentially expand the region to the boundary l ₂ and reduces erroneous detection of a point within tolerance.

Further, for example, as shown in FIG. 6 (c2), a small region of the value of m, i.e. when extending the area give priority to the area A ₁ to the boundary l _1, undetected points with error is reduced.

Further, for example, as shown in FIG. 6 (c3), when m is generates area _{A 3,} defined by a m = 4, which is an intermediate value by the boundary _{l 1} and _{l 2,} FIG. 6 (c1) and ( A point having an error with an intermediate property in the case shown in c2) is detected.

(3) Error Point Detection Operation FIGS. 7A and 7B are schematic diagrams for explaining an operation example of the edge extraction unit 103. FIG.

  Next, the edge extraction unit 103 uses the information defining the normal of the surface of the object three-dimensional information or the boundary of the plane for the display image 120, and uses the gray value of the photograph from the photographed image information 111a. Then, a coordinate point corresponding to the edge of the object 3 is extracted using an edge extraction method represented by a Sobel filter. As a result, as shown in FIG. 7A, an edge point set 115A is extracted based on the display image 120 (S3). Further, as shown in FIG. 7B, an edge point set 115B is extracted based on the captured image information 111a. In the edge point set 115A, coordinates are extracted in pixel units (pixels) of the object three-dimensional information 113, and in the edge point set 115B, coordinates are extracted in pixel units (pixels) of the captured image information 111a. Note that the edge extraction unit 103 may perform noise removal such as isolated point removal so that noise is not included in the extraction of edge points.

  8A (a) and 8 (b) are edge information generated from the edge point set extracted by the edge extraction means 103. FIG.

  As shown in FIG. 8A (a), the edge information 115a corresponds to the edge two-dimensional coordinate field indicating the two-dimensional coordinates of the edge in the display image 120 of the object three-dimensional information 113 and the photographing direction of the display image 120. And a photo number column indicating the photo number of the photographed image information.

  As shown in FIG. 8A (b), the edge information 115b includes a coordinate field on the edge image indicating the coordinates of the edge in the coordinates of the captured image information 111a and a photo number field indicating the photo number of the captured image information 111a. Have.

  8B (a) and 8 (b) are edge information including the error distance calculated by the edge extraction unit 103. FIG.

である。エッジ点集合１１５ｂについても同様に、各エッジの画像上の座標点に最も近いエッジ点集合１１５ａ内のエッジの二次元座標との距離を計算し、誤差距離として記録する。以上より、図８Ｂ（ａ）に示すエッジ情報１１５ａ’及び図８Ｂ（ｂ）に示すエッジ情報１１５ｂ’が得られる。 First, the edge extraction unit 103 calculates the distance between the edge point set 115a and a point in the edge point set 115b closest to each edge point, and records it as an error distance. For example, as shown in FIG. 8B, the coordinates on the image of the edge of the edge point set 115b closest to the two-dimensional coordinates (202, 325) of the edge of the edge point set 115a are (203, 324), and the error distance thereof. Is

It is. Similarly, for the edge point set 115b, the distance from the two-dimensional coordinates of the edge in the edge point set 115a closest to the coordinate point on the image of each edge is calculated and recorded as an error distance. As described above, the edge information 115a ′ shown in FIG. 8B (a) and the edge information 115b ′ shown in FIG. 8B (b) are obtained.

  FIGS. 9A to 9D are schematic diagrams for explaining an example of the operation of the error point determination unit 104.

  Next, the error point determination unit 104 includes edge point sets 115A and 115B extracted by the edge extraction unit 103 shown in FIG. 9A (FIGS. 7A and 7B), and FIG. 9B. The error map 114b generated by the error map generation means 102 and subjected to the expansion process is synthesized (S4) to generate an error image 116A shown in FIG. 9C.

Next, when the error point determination unit 104 is an edge point included in the region 114b ₂ and its error distance (FIG. 8B (a) and (b)) is larger than the allowable amount m of the error map 114b, It is determined that the edge has an error (S5), and an edge label I indicating that is given. Set 116 b ₁ of edge points edge labeled I is assigned is indicated by a thick solid line in FIG. 9 (d).

Further, if the error distance (FIG. 8B (a) and (b) in FIG. 8B) is an edge point included in the region 114b ₂ and is smaller than the allowable amount m of the error map 114b, it is determined that the edge has no error. Then, the edge label II indicating that is given. Set 116 b ₂ of edge points edge labeled III was granted is indicated by a thin solid line in FIG. 9 (d).

The edge points contained in the region 114b ₁ is determined as an edge of the outside inspection, imparting an edge label III indicating that. Edge label III is a set of granted edge points 116 b ₃ are shown by broken lines in FIG. 9 (d).

  FIG. 10A is a schematic diagram showing a content example of error information in which an edge label is added to the edge information 115 by the error point determination means 104.

  The error information 116b includes a three-dimensional coordinate column of edges of the edge information 115a and 115b, a coordinate column on the edge image, a photo number column, and further includes an edge label column. The three-dimensional coordinates of the edge are obtained from the coordinates (x, y) on the image of the edge, the camera angle (shooting direction and shooting distance), and the position of the object 3.

  FIG. 10B is a schematic diagram for explaining the operation of the error point selection unit 105.

  The error point selection unit 105 performs the above-described step S5 for a plurality of photographed image information, merges the error information in the plurality of photographed image information 111 (S6), and in the generated error information 116c, the three-dimensional coordinates of the edge point The most reliable data is selected on the basis of criteria such as those having edge labels other than III, those having a small angle a with the normal n, and those having a large m value (S7).

(4) Error Point Display Operation FIG. 11 is a schematic diagram showing an example of a display image of error three-dimensional information generated by the error point display means 106.

Next, the error point display means 106 is provided with the edge point set 116c ₁ and the edge label II to which the error information 116c and the edge label I are assigned for each edge label on the display image 120 of the object three-dimensional information 113. The edge point set 116c ₂ and the edge point set 116c ₃ to which the edge label III is assigned are plotted (S8), and error three-dimensional information 116C is generated.

  12A and 12B are schematic views showing another example of the display image of the error three-dimensional information generated by the error point display means 106. FIG.

  Further, as shown in FIG. 12A, the error point display means 106 is selected when an arbitrary edge point of the display image 120 of the error three-dimensional information 116C is selected by the cursor 120a according to the operation of the user. The values of m in a plurality of photographed image information of the edge points thus obtained are compared, and as shown in FIG. 12B, error three-dimensional information in the photographing direction of the photographed image information corresponding to the edge point having the largest value of m The display image 120 of 116B ′ is displayed.

[Other embodiments]
The present invention is not limited to the above embodiment, and various modifications can be made without departing from the gist of the present invention.

  FIGS. 14A to 14C are schematic diagrams for explaining an example of a method for determining whether or not there is an error in an edge point without performing expansion processing in the error map.

As shown in FIG. 14 (a), in the area _{A 1} is an m = 2, when the area _{A 2} is assumed to be m = 6, as shown in FIG. 14 (b), the captured image information 111 A case where a photographed image line l _photo composed of a set of edge points and a three-dimensional image line l _3D composed of a set of edge points of the target object three-dimensional information 113 exist as described below. It is determined whether there is an error for each of l _photo and line l _3D of the three-dimensional image.

For example, as shown in FIG. _14C1, for the line l _photo of the captured image, the value of the vector d _photo up to the line l _3D of the three-dimensional image has a value m = 6 or more of the previous error map indicated by the vector. If so, the error point determination means 104 determines that there is an error.

Further, as shown in FIG. 14C2, for the line l _3D of the three-dimensional image, the value of the vector d _3D up to the line l _photo of the three-dimensional image is the error map value m = 2 indicated by the vector. If so, the error point determination means 104 determines that there is an error.

  The error detection program 110 can also be provided by being stored in a storage medium such as a CD-ROM, and can be downloaded from a server device connected to a network such as the Internet to a storage unit in the device. Good. In addition, a part or all of the photographed image information receiving unit 100, the alignment unit 101, the error map generation unit 102, the edge extraction unit 103, the error point determination unit 104, the error point selection unit 105, and the error point display unit 106 may be ASIC or the like. You may implement | achieve by the hardware of. Note that each step shown in the operation description of the above embodiment can be changed in order, omitted or added.

DESCRIPTION OF SYMBOLS 1 Error detection apparatus 2 Camera 3 Object 5 Error detection system 10 Control part 11 Memory | storage part 12 Display part 13 Operation part 14 Communication part 100 Captured image information reception means 101 Positioning means 102 Error map generation means 103 Edge extraction means 104 Error point Determination means 105 Error point selection means 106 Error point display means 110 Error detection program 111 Shooting image information 112 Shooting information 113 Object three-dimensional information 114 Error map 115 Edge information 115A Edge point set 115B Edge point set 115a Edge information 115b Edge information 116 Error information 116A Error image 116B Error three-dimensional information 116C Error three-dimensional information 120 Display image

Claims (6)

Applying an operator to viewpoint coordinates indicating a viewpoint for displaying three-dimensional design information indicating the design of the target object as a two-dimensional display image, and a captured image of the target formed based on the design information; Alignment means for aligning the display image of the design information;
At least the distance between the viewpoint coordinates of the design information aligned with the captured image by the alignment means and the plane of the design information constituting the object, the viewpoint coordinates of the design information, and the object of the design information The tolerance of the error on the two-dimensional display calculated based on the angle formed by the straight line passing through the coordinates of the surface constituting the object and the normal of the surface is used as the coordinate of the two-dimensional display image of the design information. Generating means for generating an error tolerance distribution image indicating the distribution of the error tolerance in association with each other;
Extraction means for extracting coordinates that are the contours of the object from the display image of the design information and the captured image;
The distance between the coordinates of the contour of the object of the display image of the design information extracted by the extraction means and the coordinates of the contour of the object of the captured image corresponding to the coordinates of the contour of the object is the error tolerance generated by the generation means. When the coordinates of the corresponding coordinates of the capacity distribution image exceed an allowable amount of error on the two-dimensional display, the coordinates of the display image of the design information and the contour of the object of the photographed image are determined as error points having errors. Error point determination means;
An error detection apparatus having   The error detection apparatus according to claim 1, further comprising an error point display unit that displays the error point determined by the error point determination unit to have an error in the display image of the design information. The extraction means extracts coordinates that are the contours of the object from a plurality of captured images,
The error point determination unit is configured to detect an error point when coordinates serving as an outline of the target object extracted from the plurality of captured images exceed an error tolerance on a two-dimensional display of an error tolerance distribution image corresponding to the coordinates. It is determined that
Among the error points of the plurality of photographed images determined by the error point determination means, those having a large tolerance on the two-dimensional display of the error tolerance distribution image corresponding to the error point The error detection apparatus according to claim 2, further comprising an error point selecting unit that selects the error points as representative error points.   The error point display means, when an error point displayed in the display image of the design information is selected, from the viewpoint coordinates of the captured image associated with the representative error point selected by the error point selection means. The error detection apparatus according to claim 3, wherein a display image of design information and the error point are displayed. The generating means expands the range of each coordinate of the error tolerance distribution image based on an error tolerance on the two-dimensional display of the coordinate,
The error point determination unit is configured such that a distance between a coordinate serving as the contour of the target object of the display image of the design information extracted by the extracting unit and a coordinate serving as the contour of the target object of the captured image corresponds to the generation. An error having an error in the coordinates of the display image of the design information and the contour of the object of the captured image when included in the expanded range of the corresponding coordinates of the error tolerance distribution image generated by the means The error detection device according to claim 1, wherein the error detection device determines a point. Computer
Applying an operator to viewpoint coordinates indicating a viewpoint for displaying three-dimensional design information indicating the design of the target object as a two-dimensional display image, and a captured image of the target formed based on the design information; Alignment means for aligning the display image of the design information;
At least the distance between the viewpoint coordinates of the design information aligned with the captured image by the alignment means and the plane of the design information constituting the object, the viewpoint coordinates of the design information, and the object of the design information The tolerance of the error on the two-dimensional display calculated based on the angle formed by the straight line passing through the coordinates of the surface constituting the object and the normal of the surface is used as the coordinate of the two-dimensional display image of the design information. Generating means for generating an error tolerance distribution image indicating the distribution of the error tolerance in association with each other;
Extraction means for extracting coordinates that are the contours of the object from the display image of the design information and the captured image;
The distance between the coordinates of the contour of the object of the display image of the design information extracted by the extraction means and the coordinates of the contour of the object of the captured image corresponding to the coordinates of the contour of the object is the error tolerance generated by the generation means. When the coordinates of the corresponding coordinates of the capacity distribution image exceed an allowable amount of error on the two-dimensional display, the coordinates of the display image of the design information and the contour of the object of the photographed image are determined as error points having errors. An error detection program that functions as error point determination means.

Images