JP5752631B2 - Image generation method, image generation apparatus, and operation support system - Google Patents

Description

  The present invention relates to an image generation method for generating an output image based on a plurality of input images captured by a plurality of cameras attached to an object to be operated, an image generation apparatus, and an operation support system using the apparatus.

  Conventionally, there is known a driving support system that converts each of images captured by a plurality of in-vehicle cameras that capture the periphery of a vehicle into a bird's-eye view image and presents an output image obtained by connecting the bird's-eye view images to the driver (for example, , See Patent Document 1).

  When generating an overlapping area image corresponding to the overlapping area of the imaging ranges of two cameras, this driving support system sets one comb-like boundary line that divides the overlapping area image into two, The two bird's-eye view images are connected so that the partial regions of the two bird's-eye view images captured by the two cameras are alternately arranged in a comb shape.

  Normally, an object with a height existing in an overlapping area is displayed in a bird's eye view image by extending in two directions in the extension direction of a line connecting each of the two cameras and the object. Therefore, if the overlap area image is bisected by one straight line, one area corresponds to the bird's eye view image by one camera, and the other area corresponds to the bird's eye view image by the other camera, it disappears from the overlap area image. May end up.

  In this respect, this driving support system can prevent the object with the height from disappearing from the overlapping region image by comb-like joining, and the object can be easily recognized by the driver. You can do that.

JP 2007-109166 A

  However, the driving support system described in Patent Document 1 generates overlapping region images by alternately arranging the partial regions of the two bird's-eye view images in a comb-tooth shape. It will divide | segment and will reduce the visibility of the object.

  In view of the above, the present invention prevents the disappearance of an object in an area where the imaging ranges of a plurality of cameras overlap in an output image generated based on a plurality of input images captured by a plurality of cameras. An object of the present invention is to provide an image generation method, an image generation apparatus, and an operation support system using the apparatus that can improve the visibility of the object.

  In order to achieve the above-described object, an image generation method according to an embodiment of the present invention is an image generation method that generates an output image based on a plurality of input images captured by a plurality of cameras attached to an object to be operated. And the input image portions of the two cameras corresponding to overlapping regions where the imaging ranges of the two cameras of the plurality of cameras overlap each other form a striped pattern in the output image. Each of the image portions is arranged, an edge is detected in the image portion corresponding to the overlapping region in the output image, and it is determined whether the edge belongs to the image of the three-dimensional object based on the arrangement of the edges; A solid object image area is detected based on an arrangement of edges determined to belong to an object image, and a display mode of the solid object image area is controlled.

  An image generation apparatus according to an embodiment of the present invention is an image generation apparatus including a control unit that generates an output image based on a plurality of input images captured by a plurality of cameras attached to an object to be operated. The control unit is configured such that each input image portion of the two cameras corresponding to an overlapping region where the imaging ranges of two cameras of the plurality of cameras overlap each other forms a striped pattern in the output image. Each of the input image portions is arranged, an edge is detected in an image portion corresponding to the overlapping region in the output image, and it is determined whether the edge belongs to a three-dimensional object image based on the arrangement of the edges. The solid object image region is detected based on the arrangement of the edges determined to belong to the solid object image, and the display mode of the solid object image region is controlled.

  An operation support system according to an embodiment of the present invention is an operation support system that supports movement or operation of an object to be operated, for moving or operating the above-described image generation device and the object to be operated. And a display unit that is installed in an operation room and displays an output image generated by the image generation apparatus.

  By the above-described means, the present invention prevents the disappearance of an object in an area where the imaging ranges of a plurality of cameras overlap in an output image generated based on a plurality of input images captured by a plurality of cameras. It is possible to provide an image generation method, an image generation apparatus, and an operation support system using the apparatus that can improve the visibility of the object.

It is a block diagram which shows roughly the structural example of the image generation apparatus which concerns on this invention. It is a figure which shows the structural example of the shovel mounted with an image generation apparatus. It is a figure which shows an example of the space model on which an input image is projected. It is a figure which shows an example of the relationship between a space model and a process target image plane. It is a figure for demonstrating matching with the coordinate on an input image plane, and the coordinate on a space model. It is a figure for demonstrating the matching between the coordinates by a coordinate matching means. It is a figure for demonstrating the effect | action of a parallel line group. It is a figure for demonstrating the effect | action of an auxiliary line group. It is a flowchart which shows the flow of a process target image generation process and an output image generation process. It is a display example (the 1) of an output image. It is a display example (the 2) of an output image. It is a figure for demonstrating the loss | disappearance prevention process which prevents the loss | disappearance of the object in the overlapping area | region of each imaging range of two cameras. FIG. 12 is a comparison diagram showing a difference between the output image shown in FIG. 11 and an output image obtained by applying a loss prevention process to the output image of FIG. 11. It is a figure for demonstrating the process for improving the visibility of the solid object of the output image part corresponding to an overlap area | region. It is a figure which shows the example of the output image obtained by controlling the display mode of a solid object image area. It is a flowchart which shows the flow of an output image correction process.

  Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings.

  FIG. 1 is a block diagram schematically showing a configuration example 100 of an image generation apparatus according to the present invention.

  The image generation apparatus 100 is an apparatus that generates an output image based on an input image captured by a camera 2 mounted on a construction machine and presents the output image to a driver, for example, a control unit 1, a camera 2, An input unit 3, a storage unit 4, and a display unit 5 are included.

  FIG. 2 is a diagram illustrating a configuration example of the excavator 60 on which the image generating apparatus 100 is mounted. The excavator 60 is configured such that the upper swing body 63 is placed on the crawler-type lower traveling body 61 via the swing mechanism 62. It is mounted so as to be pivotable around the pivot axis PV.

  The upper swing body 63 includes a cab (operator's cab) 64 on the front left side, a drilling attachment E on the front center, and the camera 2 (right camera 2R, rear camera 2B) on the right and rear surfaces. ). In addition, the display part 5 shall be installed in the position in the cab 64 where the driver | operator is easy to visually recognize.

  Next, each component of the image generation apparatus 100 will be described.

  The control unit 1 is a computer including a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), an NVRAM (Non-Volatile Random Access Memory), etc. A program corresponding to each of the attaching means 10 and the output image generating means 11 is stored in the ROM or NVRAM, and the CPU executes processing corresponding to each means while using the RAM as a temporary storage area.

  The camera 2 is a device for acquiring an input image that reflects the periphery of the excavator 60. For example, the camera 2 is attached to the right side surface and the rear surface of the upper swing body 63 so as to be able to capture an area that is a blind spot of the driver in the cab 64. (See FIG. 2), a right side camera 2R and a rear camera 2B provided with an image sensor such as a CCD (Charge Coupled Device) and a CMOS (Complementary Metal Oxide Semiconductor). The camera 2 may be attached to a position other than the right side and the rear side of the upper swing body 63 (for example, the front side and the left side), and a wide-angle lens or a fisheye lens is attached so as to capture a wide range. It may be.

  In addition, the camera 2 acquires an input image according to a control signal from the control unit 1 and outputs the acquired input image to the control unit 1. In addition, when the camera 2 acquires an input image using a fisheye lens or a wide-angle lens, the corrected input image obtained by correcting apparent distortion and tilt caused by using these lenses is transmitted to the control unit 1. Although it is output, an input image in which the apparent distortion or tilt is not corrected may be output to the control unit 1 as it is. In that case, the control unit 1 corrects the apparent distortion and tilt.

  The input unit 3 is a device that allows an operator to input various types of information to the image generation device 100, and is, for example, a touch panel, a button switch, a pointing device, a keyboard, or the like.

  The storage unit 4 is a device for storing various types of information, and is, for example, a hard disk, an optical disk, or a semiconductor memory.

  The display unit 5 is a device for displaying image information. For example, the display unit 5 is a liquid crystal display, a projector, or the like installed in a cab 64 (see FIG. 2) of a construction machine. Display an image.

  Further, the image generating apparatus 100 generates a processing target image based on the input image, and performs an image conversion process on the processing target image so that the positional relationship with the surrounding obstacles and a sense of distance can be intuitively grasped. After generating the output image to be performed, the output image may be presented to the driver.

  The “processing target image” is an image that is generated based on an input image and that is a target of image conversion processing (for example, scale conversion, affine conversion, distortion conversion, viewpoint conversion processing, etc.). When an input image including a horizontal image (for example, an empty portion) is used in an image conversion process with an image captured from above by a camera that captures the image from above, the horizontal image is The input image is projected onto a predetermined spatial model so that it is not unnaturally displayed (for example, the sky part is not treated as being on the ground surface), and then the projected image projected onto the spatial model is changed to another two. It is an image suitable for image conversion processing, which is obtained by reprojecting onto a dimensional plane. The processing target image may be used as an output image as it is without performing an image conversion process.

  The “spatial model” is a plane or curved surface other than the processing target image plane that is the plane on which the processing target image is located (for example, a plane parallel to the processing target image plane or an angle with the processing target image plane). A plane or a curved surface to be formed), and a projection target of an input image composed of one or a plurality of planes or curved surfaces.

  Note that the image generation apparatus 100 may generate an output image by performing image conversion processing on the projection image projected on the space model without generating a processing target image. Further, the projection image may be used as an output image as it is without being subjected to image conversion processing.

  FIG. 3 is a diagram illustrating an example of a spatial model MD onto which an input image is projected. FIG. 3A illustrates a relationship between the excavator 60 and the spatial model MD when the excavator 60 is viewed from the side. FIG. 3B shows the relationship between the excavator 60 and the space model MD when the excavator 60 is viewed from above.

  As shown in FIG. 3, the space model MD has a semi-cylindrical shape, and includes a planar region R1 inside the bottom surface and a curved region R2 inside the side surface.

  FIG. 4 is a diagram illustrating an example of a relationship between the space model MD and the processing target image plane, and the processing target image plane R3 is a plane including the plane area R1 of the space model MD, for example. 4 shows the space model MD not in a semi-cylindrical shape as shown in FIG. 3 but in a cylindrical shape for the sake of clarity, the space model MD may be either a semi-cylindrical shape or a cylindrical shape. It may be. The same applies to the subsequent drawings. Further, as described above, the processing target image plane R3 may be a circular area including the plane area R1 of the spatial model MD, or may be an annular area not including the plane area R1 of the spatial model MD.

  Next, various units included in the control unit 1 will be described.

  The coordinate association means 10 is a means for associating coordinates on the input image plane where the input image captured by the camera 2 is located, coordinates on the space model MD, and coordinates on the processing target image plane R3. For example, various parameters relating to the camera 2 such as optical center, focal length, CCD size, optical axis direction vector, camera horizontal direction vector, projection method, etc., which are set in advance or input via the input unit 3 And the coordinates on the input image plane, the coordinates on the space model MD, and the processing target image based on the predetermined positional relationship among the input image plane, the spatial model MD, and the processing target image plane R3. The coordinates on the plane R3 are associated with each other, and the corresponding relationship is stored in the input image / space model correspondence map 40 and the space model / processing object image correspondence map 41 of the storage unit 4. .

  When the processing target image is not generated, the coordinate association unit 10 associates the coordinates on the spatial model MD with the coordinates on the processing target image plane R3, and the spatial model / processing target of the corresponding relationship. The storage in the image correspondence map 41 is omitted.

  The output image generation unit 11 is a unit for generating an output image. For example, by performing scale conversion, affine conversion, or distortion conversion on the processing target image, the coordinates on the processing target image plane R3 and the output image are changed. The input image / space model in which the coordinates on the output image plane that is positioned are associated, the correspondence is stored in the processing target image / output image correspondence map 42 of the storage unit 4, and the value is stored in the coordinate association means 10. With reference to the correspondence map 40 and the spatial model / processing object image correspondence map 41, the value of each pixel in the output image (for example, the luminance value, hue value, saturation value, etc.) and the value of each pixel in the input image. To generate an output image.

  Further, the output image generation means 11 is preset or input via the input unit 3, the optical center of the virtual camera, the focal length, the CCD size, the optical axis direction vector, the camera horizontal direction vector, the projection method. The coordinates on the processing target image plane R3 and the coordinates on the output image plane where the output image is located are associated with each other based on various parameters such as the processing target image / output image correspondence map 42 in the storage unit 4. And the values of each pixel in the output image (for example, the luminance value) while referring to the input image / spatial model correspondence map 40 and the spatial model / processing object image correspondence map 41 stored by the coordinate matching means 10. , Hue value, saturation value, etc.) and the value of each pixel in the input image are associated with each other to generate an output image.

  Note that the output image generation unit 11 may generate the output image by changing the scale of the processing target image without using the concept of the virtual camera.

  Further, when the processing target image is not generated, the output image generation unit 11 associates the coordinates on the space model MD with the coordinates on the output image plane in accordance with the applied image conversion process, and the input image / space model. With reference to the correspondence map 40, the output image is generated by associating the value of each pixel in the output image (for example, luminance value, hue value, saturation value, etc.) with the value of each pixel in the input image. In this case, the output image generation unit 11 omits the association between the coordinates on the processing target image plane R3 and the coordinates on the output image plane, and the storage of the correspondence relationship in the processing target image / output image correspondence map 42. To do.

  Next, an example of specific processing by the coordinate association unit 10 and the output image generation unit 11 will be described.

  The coordinate association means 10 can associate the coordinates on the input image plane with the coordinates on the space model using, for example, a Hamilton quaternion.

  FIG. 5 is a diagram for explaining the correspondence between the coordinates on the input image plane and the coordinates on the space model. The input image plane of the camera 2 has UVW orthogonal coordinates with the optical center C of the camera 2 as the origin. The space model is represented as a three-dimensional surface in the XYZ orthogonal coordinate system.

  First, the coordinate association unit 10 converts the coordinates on the space model (coordinates on the XYZ coordinate system) into coordinates on the input image plane (coordinates on the UVW coordinate system), so that the origin of the XYZ coordinate system is optically converted. After moving parallel to the center C (the origin of the UVW coordinate system), the X axis is the U axis, the Y axis is the V axis, and the Z axis is the -W axis (the sign "-" indicates that the direction is reversed) This means that the XYZ coordinate system is rotated so that the UVW coordinate system coincides with the + W direction in front of the camera and the XYZ coordinate system in the −Z direction vertically below.

  When there are a plurality of cameras 2, each of the cameras 2 has an individual UVW coordinate system. Therefore, the coordinate association unit 10 uses an XYZ coordinate system in parallel with each of the plurality of UVW coordinate systems. It will be moved and rotated.

  In the above conversion, the XYZ coordinate system is translated so that the optical center C of the camera 2 is the origin of the XYZ coordinate system, and then the Z axis is rotated so as to coincide with the −W axis. Since it is realized by rotating to coincide with the axis, the coordinate matching means 10 can combine these two rotations into one rotation calculation by describing this transformation in Hamilton's quaternion. it can.

  By the way, the rotation for making one vector A coincide with another vector B corresponds to the process of rotating the vector A and the vector B by the angle formed by using the normal line of the surface extending between the vector A and the vector B as an axis. If the angle is θ, from the inner product of the vector A and the vector B, the angle θ is

It will be expressed as

  Further, the unit vector N of the normal line between the vector A and the vector B is obtained from the outer product of the vector A and the vector B.

It will be expressed as

  Note that the quaternion has i, j, and k as imaginary units,

In this embodiment, the quaternion Q is represented by t as a real component and a, b, and c as pure imaginary components.

The conjugate quaternion of the quaternion Q is

It shall be represented by

  The quaternion Q can represent a three-dimensional vector (a, b, c) with pure imaginary components a, b, c while setting the real component t to 0 (zero), and t, a, b , C can also be used to express a rotational motion with an arbitrary vector as an axis.

  Further, the quaternion Q can be expressed as a single rotation operation by integrating a plurality of continuous rotation operations. For example, an arbitrary point S (sx, sy, sz) can be expressed as an arbitrary unit vector. A point D (ex, ey, ez) when rotated by an angle θ with C (l, m, n) as an axis can be expressed as follows.

Here, in this embodiment, if the quaternion representing the rotation that makes the Z axis coincide with the −W axis is Qz, the point X on the X axis in the XYZ coordinate system is moved to the point X ′. X '

It will be expressed as

  In this embodiment, if the quaternion representing the rotation that matches the line connecting the point X ′ on the X axis and the origin to the U axis is Qx, “the Z axis matches the −W axis, , The quaternion R representing "rotation to match the X axis with the U axis"

It will be expressed as

  As described above, the coordinate P ′ when an arbitrary coordinate P on the space model (XYZ coordinate system) is expressed by a coordinate on the input image plane (UVW coordinate system) is

Since the quaternion R is invariable in each of the cameras 2, the coordinate association unit 10 thereafter performs the above calculation to obtain the coordinates on the space model (XYZ coordinate system). It can be converted into coordinates on the input image plane (UVW coordinate system).

  After the coordinates on the space model (XYZ coordinate system) are converted to the coordinates on the input image plane (UVW coordinate system), the coordinate association means 10 determines the optical center C (coordinates on the UVW coordinate system) of the camera 2 and the space. An incident angle α formed by a line segment CP ′ connecting an arbitrary coordinate P on the model with a coordinate P ′ represented in the UVW coordinate system and the optical axis G of the camera 2 is calculated.

  In addition, the coordinate association unit 10 includes an intersection E between the plane H and the optical axis G, and a coordinate P ′ in a plane H that is parallel to the input image plane R4 (for example, CCD plane) of the camera 2 and includes the coordinate P ′. Are calculated, and the deviation angle φ formed by the line segment EP ′ connecting the two and the U ′ axis in the plane H, and the length of the line segment EP ′.

  In the optical system of the camera, the image height h is usually a function of the incident angle α and the focal length f. Therefore, the coordinate matching means 10 performs normal projection (h = ftanα) and orthographic projection (h = fsinα). Image height by selecting an appropriate projection method such as stereo projection (h = 2 ftan (α / 2)), equisolid angle projection (h = 2 fsin (α / 2)), equidistant projection (h = fα), etc. Calculate h.

  Thereafter, the coordinate matching means 10 decomposes the calculated image height h into U and V components on the UV coordinate system by the declination φ, and is a numerical value corresponding to the pixel size per pixel of the input image plane R4. By dividing, the coordinates P (P ′) on the space model MD can be associated with the coordinates on the input image plane R4.

  If the pixel size per pixel in the U-axis direction of the input image plane R4 is aU and the pixel size per pixel in the V-axis direction of the input image plane R4 is aV, the coordinates P (P The coordinates (u, v) on the input image plane R4 corresponding to ') are

It will be expressed as

  In this way, the coordinate association unit 10 associates the coordinates on the space model MD with the coordinates on one or a plurality of input image planes R4 existing for each camera, and coordinates on the space model MD, the camera identifier. And the coordinates on the input image plane R4 are stored in the input image / space model correspondence map 40 in association with each other.

  Further, since the coordinate association unit 10 calculates the coordinate conversion using the quaternion, unlike the case where the coordinate conversion is calculated using the Euler angle, there is an advantage that no gimbal lock is generated. . However, the coordinate association unit 10 is not limited to the one that calculates the coordinate conversion using the quaternion, and may perform the coordinate conversion using the Euler angle.

  Note that, when it is possible to associate the coordinates on the plurality of input image planes R4, the coordinate associating means 10 inputs the coordinates P (P ′) on the spatial model MD with respect to the camera having the smallest incident angle α. It may be associated with coordinates on the image plane R4, or may be associated with coordinates on the input image plane R4 selected by the operator.

  Next, a process of reprojecting coordinates on the curved surface area R2 (coordinates having a component in the Z-axis direction) among the coordinates on the spatial model MD onto the processing target image plane R3 on the XY plane will be described.

  FIG. 6 is a diagram for explaining the association between coordinates by the coordinate association means 10, and FIG. 6A shows an input image plane R4 of the camera 2 that employs a normal projection (h = ftanα) as an example. FIG. 6 is a diagram showing a correspondence relationship between the coordinates on the upper surface and the coordinates on the space model MD, and the coordinate associating means 10 displays the coordinates on the input image plane R4 of the camera 2 and the space model MD corresponding to the coordinates. Both the coordinates are made to correspond to each other so that each of the line segments connecting the coordinates passes through the optical center C of the camera 2.

  In the example of FIG. 6A, the coordinate association means 10 associates the coordinate K1 on the input image plane R4 of the camera 2 with the coordinate L1 on the plane area R1 of the space model MD, and inputs the image 2 R4 of the camera 2. The upper coordinate K2 is associated with the coordinate L2 on the curved surface region R2 of the space model MD. At this time, both the line segment K1-L1 and the line segment K2-L2 pass through the optical center C of the camera 2.

  In addition, when the camera 2 employs a projection method other than normal projection (for example, orthographic projection, stereoscopic projection, equisolid angle projection, equidistant projection, etc.), the coordinate association unit 10 uses each projection method. Accordingly, the coordinates K1 and K2 on the input image plane R4 of the camera 2 are associated with the coordinates L1 and L2 on the space model MD.

  Specifically, the coordinate association unit 10 is configured to use a predetermined function (for example, orthographic projection (h = fsin α), stereoscopic projection (h = 2 ftan (α / 2)), or equal solid angle projection (h = 2 fsin (α / 2)), equidistant projection (h = fα), etc.), the coordinates on the input image plane are associated with the coordinates on the space model MD. In this case, the line segment K1-L1 and the line segment K2-L2 do not pass through the optical center C of the camera 2.

  FIG. 6B is a diagram showing a correspondence relationship between coordinates on the curved surface region R2 of the space model MD and coordinates on the processing target image plane R3, and the coordinate association unit 10 is positioned on the XZ plane. The parallel line group PL that forms an angle β with the processing target image plane R3 is introduced, and the coordinates on the curved surface region R2 of the spatial model MD and the processing target image corresponding to the coordinates are introduced. The coordinates on the plane R3 are associated with each other such that the coordinates are on one of the parallel line groups PL.

  In the example of FIG. 6B, the coordinate matching means 10 assumes that the coordinate L2 on the curved surface region R2 of the space model MD and the coordinate M2 on the processing target image plane R3 are on a common parallel line, and both coordinates are obtained. Make it correspond.

  The coordinate association means 10 can associate the coordinates on the plane area R1 of the spatial model MD with the coordinates on the processing target image plane R3 using the parallel line group PL in the same manner as the coordinates on the curved surface area R2. However, in the example of FIG. 6B, since the plane area R1 and the processing target image plane R3 are a common plane, the coordinates L1 on the plane area R1 of the spatial model MD and the processing target image plane R3 The coordinate M1 has the same coordinate value.

  In this way, the coordinate association unit 10 associates the coordinates on the spatial model MD with the coordinates on the processing target image plane R3, and associates the coordinates on the spatial model MD with the coordinates on the processing target image R3. It is stored in the spatial model / processing object image correspondence map 41.

  FIG. 6C is a diagram illustrating a correspondence relationship between the coordinates on the processing target image plane R3 and the coordinates on the output image plane R5 of the virtual camera 2V that adopts the normal projection (h = ftanα) as an example. The output image generation means 11 passes through the optical center CV of the virtual camera 2V each of the line segments connecting the coordinates on the output image plane R5 of the virtual camera 2V and the coordinates on the processing target image plane R3 corresponding to the coordinates. In this way, the two coordinates are associated with each other.

  In the example of FIG. 6C, the output image generation unit 11 associates the coordinates N1 on the output image plane R5 of the virtual camera 2V with the coordinates M1 on the processing target image plane R3 (plane area R1 of the space model MD). The coordinate N2 on the output image plane R5 of the virtual camera 2V is associated with the coordinate M2 on the processing target image plane R3. At this time, both the line segment M1-N1 and the line segment M2-N2 pass through the optical center CV of the virtual camera 2V.

  Note that when the virtual camera 2V employs a projection method other than normal projection (for example, orthographic projection, stereoscopic projection, equisolid angle projection, equidistant projection, etc.), the output image generation unit 11 uses each projection method. Accordingly, the coordinates N1 and N2 on the output image plane R5 of the virtual camera 2V are associated with the coordinates M1 and M2 on the processing target image plane R3.

  Specifically, the output image generation means 11 is a predetermined function (for example, orthographic projection (h = fsin α), stereoscopic projection (h = 2 ftan (α / 2)), equal solid angle projection (h = 2 fsin (α / 2)), equidistant projection (h = fα), etc.), the coordinates on the output image plane R5 and the coordinates on the processing target image plane R3 are associated with each other. In this case, the line segment M1-N1 and the line segment M2-N2 do not pass through the optical center CV of the virtual camera 2V.

  In this way, the output image generation unit 11 associates the coordinates on the output image plane R5 with the coordinates on the processing target image plane R3, and sets the coordinates on the output image plane R5 and the coordinates on the processing target image R3. Each of the output images is stored in the processing target image / output image correspondence map 42 in association with each other in the output image while referring to the input image / spatial model correspondence map 40 and the spatial model / processing target image correspondence map 41 stored by the coordinate matching means 10. An output image is generated by associating the pixel value with the value of each pixel in the input image.

  FIG. 6D is a combination of FIGS. 6A to 6C. The camera 2, the virtual camera 2V, the plane area R1 and the curved area R2 of the space model MD, and the processing target. The mutual positional relationship of image plane R3 is shown.

  Next, the operation of the parallel line group PL introduced by the coordinate association unit 10 to associate the coordinates on the space model MD with the coordinates on the processing target image plane R3 will be described with reference to FIG.

  FIG. 7A is a diagram in the case where the angle β is formed between the parallel line group PL positioned on the XZ plane and the processing target image plane R3, and FIG. 7B is the diagram on the XZ plane. It is a figure in case angle (beta) 1 ((beta) 1> (beta)) is formed between the parallel line group PL and the process target image plane R3. Also, each of the coordinates La to Ld on the curved surface region R2 of the spatial model MD in FIGS. 7A and 7B corresponds to the coordinates Ma to Md on the processing target image plane R3, respectively. Assume that the intervals between the coordinates La to Ld in FIG. 7A are equal to the intervals between the coordinates La to Ld in FIG. The parallel line group PL is assumed to exist on the XZ plane for the purpose of explanation, but actually exists so as to extend radially from all points on the Z axis toward the processing target image plane R3. It shall be. In this case, the Z axis is referred to as a “reprojection axis”.

  As shown in FIGS. 7A and 7B, the distance between the coordinates Ma to Md on the processing target image plane R3 is such that the angle between the parallel line group PL and the processing target image plane R3 is the same. As it increases, it decreases linearly (it decreases uniformly regardless of the distance between the curved surface region R2 of the spatial model MD and each of the coordinates Ma to Md). On the other hand, since the coordinate group on the plane region R1 of the space model MD is not converted into the coordinate group on the processing target image plane R3 in the example of FIG. 7, the interval between the coordinate groups does not change. .

  The change in the interval between these coordinate groups is such that only the image portion corresponding to the image projected on the curved surface region R2 of the spatial model MD is linearly enlarged or out of the image portion on the output image plane R5 (see FIG. 6). It means to be reduced.

  Next, an alternative example of the parallel line group PL introduced by the coordinate association unit 10 to associate the coordinates on the space model MD with the coordinates on the processing target image plane R3 will be described with reference to FIG.

  FIG. 8A is a diagram in the case where all of the auxiliary line groups AL located on the XZ plane extend from the start point T1 on the Z axis toward the processing target image plane R3, and FIG. It is a figure in case all the line groups AL extend toward the process target image plane R3 from the starting point T2 (T2> T1) on the Z axis. 8A and 8B, the coordinates La to Ld on the curved surface region R2 of the spatial model MD correspond to the coordinates Ma to Md on the processing target image plane R3 ( In the example of FIG. 8A, the coordinates Mc and Md are not shown because they are outside the region of the processing target image plane R3.) The intervals between the coordinates La to Ld in FIG. It is assumed that the interval between the coordinates La to Ld in 8 (B) is equal. The auxiliary line group AL is assumed to exist on the XZ plane for the purpose of explanation, but actually exists so as to extend radially from an arbitrary point on the Z axis toward the processing target image plane R3. It shall be. As in FIG. 7, the Z axis in this case is referred to as a “reprojection axis”.

  As shown in FIGS. 8A and 8B, the distance between the coordinates Ma to Md on the processing target image plane R3 is the distance (high) between the starting point of the auxiliary line group AL and the origin O. As the distance between the curved surface region R2 of the space model MD and each of the coordinates Ma to Md is larger, the width of reduction of each interval is larger. On the other hand, since the coordinate group on the plane region R1 of the spatial model MD is not converted into the coordinate group on the processing target image plane R3 in the example of FIG. 8, the interval between the coordinate groups does not change. .

  The change in the interval between these coordinate groups corresponds to the image projected on the curved surface region R2 of the spatial model MD in the image portion on the output image plane R5 (see FIG. 6), as in the case of the parallel line group PL. It means that only the image portion is enlarged or reduced nonlinearly.

  In this way, the image generation device 100 does not affect the image portion (for example, a road surface image) of the output image corresponding to the image projected on the plane region R1 of the space model MD, and does not affect the space model MD. Since the image portion (for example, a horizontal image) of the output image corresponding to the image projected on the curved surface area R2 can be linearly or nonlinearly enlarged or reduced, the road surface image in the vicinity of the excavator 60 Without affecting the excavator 60 (virtual image when viewed from directly above), an object located in the periphery of the excavator 60 (an object in the image when viewed in the horizontal direction from the excavator 60) can be quickly and flexibly The visibility of the blind spot area of the excavator 60 can be improved.

  Next, referring to FIG. 9, the image generation apparatus 100 generates a processing target image (hereinafter referred to as “processing target image generation processing”), and an output image using the generated processing target image. Processing to be generated (hereinafter referred to as “output image generation processing”) will be described. FIG. 9 is a flowchart showing the flow of the processing target image generation process (steps S1 to S3) and the output image generation process (steps S4 to S6). Further, it is assumed that the arrangement of the camera 2 (input image plane R4), the space model (plane area R1 and curved surface area R2), and the processing target image plane R3 is determined in advance.

  First, the control unit 1 associates the coordinates on the processing target image plane R3 with the coordinates on the space model MD using the coordinate association unit 10 (step S1).

  Specifically, the coordinate association unit 10 obtains an angle formed between the parallel line group PL and the processing target image plane R3, and the parallel line group PL extending from one coordinate on the processing target image plane R3. One point that intersects the curved surface region R2 of the space model MD is calculated, and a coordinate on the curved surface region R2 corresponding to the calculated point is set to one on the curved surface region R2 corresponding to the one coordinate on the processing target image plane R3. The coordinates are derived as coordinates, and the corresponding relationship is stored in the space model / processing object image correspondence map 41. It should be noted that the angle formed between the parallel line group PL and the processing target image plane R3 may be a value stored in advance in the storage unit 4 or the like. It may be a value to be entered.

  In addition, when one coordinate on the processing target image plane R3 matches one coordinate on the plane area R1 of the space model MD, the coordinate association unit 10 uses the one coordinate on the plane area R1 as the processing target image. It is derived as one coordinate corresponding to the one coordinate on the plane R3, and the correspondence is stored in the space model / processing object image correspondence map 41.

  Thereafter, the control unit 1 causes the coordinate association unit 10 to associate one coordinate on the spatial model MD derived by the above-described processing with a coordinate on the input image plane R4 (step S2).

  Specifically, the coordinate association unit 10 acquires the coordinates of the optical center C of the camera 2 that employs normal projection (h = ftanα), is a line segment extending from one coordinate on the space model MD, and the optical center A point where the line segment passing through C intersects the input image plane R4 is calculated, and the coordinates on the input image plane R4 corresponding to the calculated point are set on the input image plane R4 corresponding to the one coordinate on the space model MD. And the corresponding relationship is stored in the input image / space model correspondence map 40.

  Thereafter, the control unit 1 determines whether or not all the coordinates on the processing target image plane R3 are associated with the coordinates on the space model MD and the coordinates on the input image plane R4 (step S3), and all the coordinates are still set. Are determined to be not associated (NO in step S3), the processes in steps S1 and S2 are repeated.

  On the other hand, when it is determined that all the coordinates are associated (YES in step S3), the control unit 1 ends the processing target image generation process, starts the output image generation process, and outputs the output image generation unit 11. Thus, the coordinates on the processing target image plane R3 are associated with the coordinates on the output image plane R5 (step S4).

  Specifically, the output image generation unit 11 generates an output image by performing scale conversion, affine conversion, or distortion conversion on the processing target image, and is determined by the content of the applied scale conversion, affine conversion, or distortion conversion. The correspondence relationship between the coordinates on the processing target image plane R3 and the coordinates on the output image plane R5 is stored in the processing target image / output image correspondence map 42.

  Alternatively, when generating the output image using the virtual camera 2V, the output image generation unit 11 calculates the coordinates on the output image plane R5 from the coordinates on the processing target image plane R3 according to the adopted projection method. The correspondence relationship may be stored in the processing target image / output image correspondence map 42.

  Alternatively, when generating an output image using the virtual camera 2V that employs normal projection (h = ftanα), the output image generation unit 11 acquires the coordinates of the optical center CV of the virtual camera 2V, A line segment extending from one coordinate on the output image plane R5 and calculating a point where a line segment passing through the optical center CV intersects the processing target image plane R3, and on the processing target image plane R3 corresponding to the calculated point. The coordinates may be derived as one coordinate on the processing target image plane R3 corresponding to the one coordinate on the output image plane R5, and the correspondence relationship may be stored in the processing target image / output image correspondence map 42.

  After that, the control unit 1 uses the output image generation unit 11 to refer to the input image / space model correspondence map 40, the space model / processing target image correspondence map 41, and the processing target image / output image correspondence map 42. Correspondence between coordinates on R4 and coordinates on space model MD, correspondence between coordinates on space model MD and coordinates on processing target image plane R3, and coordinates on processing target image plane R3 and output image plane R5 The correspondence with the upper coordinates is traced, and values (for example, luminance values, hue values, saturation values, etc.) possessed by the coordinates on the input image plane R4 corresponding to the respective coordinates on the output image plane R5 are acquired. Then, the acquired value is adopted as the value of each coordinate on the corresponding output image plane R5 (step S5). When a plurality of coordinates on the plurality of input image planes R4 correspond to one coordinate on the output image plane R5, the output image generation unit 11 respectively outputs the plurality of coordinates on the plurality of input image planes R4. A statistical value (for example, an average value, a maximum value, a minimum value, an intermediate value, or the like) based on the value of L is derived, and the statistical value is adopted as the value of the one coordinate on the output image plane R5. Good.

  Thereafter, the control unit 1 determines whether or not all the coordinate values on the output image plane R5 are associated with the coordinate values on the input image plane R4 (step S6), and all the coordinate values are still associated. If it is determined that it is not attached (NO in step S6), the processes in steps S4 and S5 are repeated.

  On the other hand, if the control unit 1 determines that all coordinate values are associated (YES in step S6), the control unit 1 generates an output image and ends the series of processes.

  Note that, when the processing target image is not generated, the image generation apparatus 100 omits the processing target image generation processing, and sets “coordinates on the processing target image plane” in step S4 in the output image generation processing to “on the spatial model”. It shall be read as "coordinates".

  With the above configuration, the image generation apparatus 100 can generate a processing target image and an output image that allow the operator to intuitively grasp the positional relationship between the construction machine and the surrounding obstacle.

  Further, the image generation apparatus 100 associates coordinates on the processing target image plane R3 from the processing target image plane R3 to the input image plane R4 through the spatial model MD, thereby obtaining the coordinates on the processing target image plane R3. One or more coordinates on R4 can be reliably associated, and compared with a case where coordinates are associated in the order from the input image plane R4 to the processing target image plane R3 via the spatial model MD (in this case) Can reliably correspond each coordinate on the input image plane R4 to one or a plurality of coordinates on the processing target image plane R3. However, a part of the coordinates on the processing target image plane R3 is part of the input image plane R4. In some cases, the coordinates may not be associated with any of the above coordinates, and in such a case, it is necessary to perform interpolation processing or the like on a part of the coordinates on the processing target image plane R3). It is possible to rapidly generate.

  Further, when enlarging or reducing only the image corresponding to the curved surface region R2 of the space model MD, the image generating apparatus 100 changes the angle formed between the parallel line group PL and the processing target image plane R3. Thus, it is possible to realize a desired enlargement or reduction without rewriting the contents of the input image / space model correspondence map 40 only by rewriting only the portion related to the curved surface region R2 in the space model / processing object image correspondence map 41. .

  Further, when changing the appearance of the output image, the image generating apparatus 100 simply rewrites the processing target image / output image correspondence map 42 by changing the values of various parameters relating to scale conversion, affine transformation, or distortion transformation. The desired output image (scale-converted image, affine-transformed image, or distortion-converted image) can be generated without rewriting the contents of the input image / space model correspondence map 40 and the space model / processing object image correspondence map 41.

  Similarly, when changing the viewpoint of the output image, the image generating apparatus 100 simply changes the values of various parameters of the virtual camera 2V and rewrites the processing target image / output image correspondence map 42 to change the input image / space. An output image (viewpoint conversion image) viewed from a desired viewpoint can be generated without rewriting the contents of the model correspondence map 40 and the space model / processing object image correspondence map 41.

  FIG. 10 is a display example when an output image generated using input images of two cameras 2 (the right side camera 2R and the rear camera 2B) mounted on the excavator 60 is displayed on the display unit 5. .

  The image generation apparatus 100 projects the input images of the two cameras 2 onto the plane region R1 and the curved surface region R2 of the space model MD, and then reprojects them onto the processing target image plane R3 to generate a processing target image. Then, an image conversion process (for example, scale conversion, affine conversion, distortion conversion, viewpoint conversion process, etc.) is performed on the generated processing target image to generate an output image, and the vicinity of the excavator 60 can be seen from above. An image looking down (image in the plane region R1) and an image of the periphery viewed from the excavator 60 in the horizontal direction (image in the processing target image plane R3) are displayed at the same time.

  When the image generation apparatus 100 does not generate the processing target image, the output image is generated by performing image conversion processing (for example, viewpoint conversion processing) on the image projected on the space model MD. Shall.

  The output image is trimmed in a circle so that the image when the excavator 60 performs the turning motion can be displayed without a sense of incongruity, and the center CTR of the circle is on the cylindrical central axis of the space model MD and the excavator 60 is turned. It is generated so as to be on the axis PV, and is displayed so as to rotate about its center CTR in accordance with the turning operation of the excavator 60. In this case, the cylindrical central axis of the space model MD may or may not coincide with the reprojection axis.

  The radius of the space model MD is, for example, 5 meters, and the angle formed between the parallel line group PL and the processing target image plane R3 or the starting point height of the auxiliary line group AL is the turning of the shovel 60. When an object (for example, a worker) exists at a position away from the center by a maximum reachable distance (for example, 12 meters) of the excavation attachment E, the object is sufficiently large (for example, 7) It can be set to be displayed.

  Further, the output image may be a CG image of the excavator 60 arranged so that the front of the excavator 60 coincides with the upper part of the screen of the display unit 5 and the turning center thereof coincides with the center CTR. This is to make the positional relationship between the shovel 60 and the object appearing in the output image easier to understand. Note that a frame image including various kinds of information such as an orientation may be arranged around the output image.

  Next, with reference to FIGS. 11 to 13, when the image generation apparatus 100 generates an output image portion corresponding to the overlapping area of the imaging ranges of the two cameras, the object in the output image portion disappears. A process for preventing this will be described.

  FIG. 11 shows input images of the three cameras 2 (left side camera 2L, right side camera 2R, and rear camera 2B) mounted on the excavator 60, and output images generated using these input images. FIG.

  The image generating apparatus 100 projects the coordinates on the input image plane of each of the three cameras 2 to the coordinates on the plane area R1 and the curved area R2 of the space model MD, and then reprojects them on the processing target image plane R3. To generate a processing target image. Then, the image generation apparatus 100 generates an output image by performing image conversion processing (for example, scale conversion, affine conversion, distortion conversion, viewpoint conversion processing, etc.) on the generated processing target image. The image generating apparatus 100 includes an image in which the vicinity of the excavator 60 is looked down from above (an image in the plane region R1) and an image in which the periphery is viewed from the shovel 60 in the horizontal direction (an image in the processing target image plane R3). Display the output image.

  In FIG. 11, the input image of the right-side camera 2R and the input image of the rear camera 2B each capture a person in the overlapping area of the imaging range of the right-side camera 2R and the imaging range of the rear camera 2B (right side). (See region R10 surrounded by a two-dot chain line in the input image of the direction camera 2R and region R11 surrounded by a two-dot chain line in the input image of the rear camera 2B.)

  However, if the coordinates on the output image plane are associated with the coordinates on the input image plane for the camera with the smallest incident angle, the output image loses the person in the overlapping area (one point in the output image). (See region R12 surrounded by a chain line.)

  Therefore, in the output image portion corresponding to the overlapping region, the image generation device 100 associates the region on the input image plane of the rear camera 2B with the coordinate on the input image plane of the right-side camera 2R. The area is mixed to prevent the object in the overlapping area from disappearing.

  FIG. 12 is a diagram for explaining the disappearance prevention process for preventing the disappearance of the object in the overlapping region of the imaging ranges of the two cameras.

  FIG. 12A is a diagram showing an output image portion corresponding to an overlapping area between the imaging range of the right camera 2R and the imaging range of the rear camera 2B, and corresponds to the rectangular area R13 indicated by the dotted line in FIG.

  In FIG. 12A, a gray area PR1 is an image area in which the input image portion of the rear camera 2B is arranged, and each coordinate on the output image plane corresponding to the area PR1 has a rear camera. Coordinates on the 2B input image plane are associated.

  On the other hand, a region PR2 filled with white is an image region in which the input image portion of the right side camera 2R is arranged, and each coordinate on the output image plane corresponding to the portion PR2 has an input image plane of the right side camera 2R. The upper coordinates are associated.

  In the present embodiment, the region PR1 and the region PR2 are arranged so as to form a stripe pattern, and the boundary line of the portion where the regions PR1 and the region PR2 are alternately arranged in a stripe shape is centered on the turning center of the excavator 60. Determined by concentric circles on a horizontal plane. The center position of the concentric circles can be arbitrarily set, and may be, for example, the intersection of the extension line of the optical axis of the rear camera 2B and the extension line of the optical axis of the right side camera 2R. Also, the boundary line forming the stripe pattern can be arbitrarily set, and may be determined by a group of straight lines parallel to the front-rear direction or the left-right direction of the shovel 60. It may be defined by a group of straight lines forming an angle. Further, the boundary line forming the stripe pattern may be defined by a straight line group extending radially from the turning center of the excavator 60.

  FIG. 12B is a top view showing the situation of the space area diagonally right behind the shovel 60, and shows the current situation of the space area imaged by both the rear camera 2B and the right-side camera 2R. In addition, FIG. 12B shows that a line L is drawn on the road surface obliquely rearward to the right of the excavator 60, and a solid object OB exists.

  FIG. 12C shows a part of an output image generated based on an input image obtained by actually capturing the spatial region shown in FIG. 12B with the rear camera 2B and the right-side camera 2R.

  Specifically, the image OB1 is expanded in the extension direction of the line connecting the rear camera 2B and the three-dimensional object OB by the viewpoint conversion for generating the road surface image of the three-dimensional object OB in the input image of the rear camera 2B. Represents what was done. That is, the image OB1 is a part of the image of the three-dimensional object OB displayed when the road surface image in the output image portion is generated using the input image of the rear camera 2B.

  Further, the image OB2 is expanded in the extension direction of the line connecting the right-side camera 2R and the three-dimensional object OB by the viewpoint conversion for generating the road surface image of the three-dimensional object OB in the input image of the right rear camera 2R. Represents a thing. That is, the image OB2 is a part of an image of the three-dimensional object OB displayed when a road surface image in the output image portion is generated using the input image of the right side camera 2R.

  Note that the image LG of the line L drawn on the road surface is not affected by viewpoint conversion for generating a road surface image, and is displayed without being expanded in any direction.

  As described above, the image generating apparatus 100 includes the region PR1 in which the coordinates on the input image plane of the rear camera 2B are associated with the region PR2 in which the coordinates on the input image plane of the right-side camera 2R are associated in the overlapping region. Mix. As a result, the image generation apparatus 100 displays both the two images OB1 and OB2 related to one solid object OB on the output image, and prevents the solid object OB from disappearing from the output image.

  FIG. 13 is a comparison diagram showing the difference between the output image of FIG. 11 and the output image obtained by applying the loss prevention process to the output image of FIG. 11, and FIG. 13 (A) is the output image of FIG. FIG. 13B shows an output image after the disappearance prevention process is applied. In the region R12 surrounded by the alternate long and short dash line in FIG. 13A, the person disappears, whereas in the region R14 surrounded by the alternate long and short dash line in FIG. 13B, the person is displayed without disappearing.

  However, as shown in FIG. 12C, since the image OB1 is derived from the image of the three-dimensional object OB in the input image of the rear camera 2B, it appears only in the region PR1 and is displayed with a part cut away. The Similarly, since the image OB2 is derived from the image of the three-dimensional object OB in the input image of the right side camera 2R, the image OB2 appears only in the region PR2, and is displayed in a partially cutout state.

  Therefore, the image generation apparatus 100 recognizes that the images OB1 and OB2 are images derived from the three-dimensional object OB, not a pattern on the road surface, so that the display mode of the images OB1 and OB2 has higher visibility. Try to change things.

  Specifically, the image generation apparatus 100 performs an edge detection process on the output image portion corresponding to the overlapping region, and determines whether the edge belongs to the three-dimensional object image based on the detected edge arrangement. To do. In addition, the image generation apparatus 100 detects a three-dimensional object image area, which is an area where a three-dimensional object image should exist, based on the arrangement of edges determined to belong to the three-dimensional object image. Control the display mode of the area.

  FIG. 14 is a diagram for explaining the process for improving the visibility of the three-dimensional object in the output image portion corresponding to the overlapping area, and FIG. 14 (A) shows a diagram for explaining the edge detection process. FIG. 14B shows a diagram for explaining the end point detection process, and FIG. 14C shows a diagram for explaining the three-dimensional object image region detection process.

  FIG. 14A shows an edge image obtained by performing edge detection processing on the output image portion shown in FIG. In this embodiment, edge detection is performed along a boundary line that forms a striped pattern. That is, when the difference between the luminance values of adjacent pixels on the circumference of each concentric circle centered on the turning center of the excavator 60 is equal to or greater than a predetermined value, at least one of the two pixels forms an edge point. Detected as a pixel.

  FIG. 14B is an image showing the position of each end point of the edge line formed by the detected edge point as shown in FIG. Each black circle in the figure represents an end point of the edge line. Note that the edge line that is not divided by the width of the stripe pattern by the stripe pattern is derived from the image LG of the line L drawn on the road surface, and the edge line that is divided by the width of the stripe pattern by the stripe pattern is the solid object OB. Derived from the images OB1 and OB2.

  The coordinates of the end point of the edge line are used to determine whether or not the edge line can be connected to another edge line.

  Specifically, another position that is closest to the position of one end point (first end point) of one edge line in the direction of the straight line connecting the position of the rear camera 2B or the right side camera 2R and the first end point. The end point (second end point) of the edge line is extracted. Note that “the direction of a straight line connecting the position of the rear camera 2B or the right side camera 2R and the first end point”, which means an area where the second end point to be extracted can exist, has a width of a predetermined number of pixels. And When the distance between the first end point and the second end point is equal to or greater than a predetermined distance corresponding to the width of the stripe pattern, the edge line including the first end point and the edge line including the second end point can be connected. It is determined. That is, it is determined that these two edge lines represent a part of the outline of the three-dimensional object. This is because the image of the three-dimensional object is divided by the stripe pattern. On the other hand, when the distance between the first end point and the second end point is smaller than a predetermined distance corresponding to the width of the stripe pattern, the edge line including the first end point and the edge line including the second end point cannot be connected. It is determined. This is the case, for example, when the edge line including the first end point and the edge line including the second end point are both derived from the image LG of the line L drawn on the road surface. Therefore, the edge line derived from the image LG of the line L drawn on the road surface is not determined to represent a part of the outline of the three-dimensional object. Hereinafter, this determination process is referred to as a “connection determination process”.

  FIG. 14C is a diagram illustrating a state in which the edge lines that are determined to be connectable by the connection determination process among the edge lines illustrated in FIG. 14B are connected by a dotted line.

  A closed region surrounded by a plurality of edge lines and a dotted line connecting the edge lines is detected as a three-dimensional object image region that represents a three-dimensional object and should have an image without a defect.

  In addition, in the connection determination process, when there is no connection partner that satisfies the above-described conditions for another end point of the edge line determined to be connectable, the other end point becomes the end point of the nearest edge line. Connected. This is because the closed region is more reliably formed.

  In this embodiment, two three-dimensional object image regions OB1a and OB2a, which are regions where a non-defect image representing the three-dimensional object OB should exist, are detected. Note that the three-dimensional object image area OB1a is an area where the image of the three-dimensional object OB in the input image of the rear camera 2B is to be originally displayed, and the three-dimensional object image area OB2a is the three-dimensional object OB in the input image of the right-side camera 2R. This is the area where the image should be displayed.

  Thereafter, the control unit 1 of the image generation device 100 improves the visibility of the three-dimensional object OB in the output image by controlling the display mode of the three-dimensional object image region obtained as described above.

  Specifically, coordinates on the input image plane of the rear camera 2B are associated with the coordinates included in the three-dimensional object image region OB1a, and the right-side camera 2R is associated with each of the coordinates included in the three-dimensional object image region OB2a. Are coordinated on the input image plane.

  It should be noted that the arrangement other than the three-dimensional object image area OB1a and the three-dimensional object image area OB2a maintains the striped pattern arrangement, and coordinates on the input image plane of the rear camera 2B are associated with the coordinates included in the area PR1. The coordinates on the input image plane of the right-side camera 2R are associated with the coordinates included in the region PR2.

  FIG. 15 is a diagram illustrating an example of an output image obtained by controlling the display mode of the three-dimensional object image region.

  For example, FIG. 15A shows an image obtained by changing the display mode of the three-dimensional object image regions OB1a and OB2a.

  In FIG. 15A, an image OB1x corresponds to the image of the three-dimensional object OB in the input image of the rear camera 2B, and the image OB2x corresponds to the image of the three-dimensional object OB in the input image of the right-side camera 2R.

  Thus, unlike the images OB1 and OB2 in FIG. 12C, the image generating apparatus 100 can display the images OB1x and OB2x corresponding to the three-dimensional object OB without being divided into pieces. As a result, the image generation device 100 can improve the visibility of the three-dimensional object OB in the output image.

  Further, the image generating apparatus 100 can determine that both of the three-dimensional object image regions OB1a and OB2a are derived from the three-dimensional object OB based on the arrangement of the three-dimensional object image regions OB1a and OB2a. This is because the three-dimensional object image regions OB1a and OB2a overlap at the ground contact position of the three-dimensional object OB.

  Therefore, the image generation apparatus 100 may display an image corresponding to the three-dimensional object OB only in a region corresponding to one of the three-dimensional object image regions OB1a and OB2a in the output image. This is to prevent two images OB1x and OB2x from being displayed for one solid object OB.

  Specifically, the image generation apparatus 100 associates coordinates on the input image plane of either the rear camera 2B or the right-side camera 2R with coordinates included in both of the three-dimensional object image regions OB1a and OB2a.

  FIG. 15B shows an image when coordinates on the input image plane of the rear camera 2B are associated with coordinates included in both of the three-dimensional object image regions OB1a and OB2a. FIG. 15C shows an image when coordinates on the input image plane of the right-side camera 2R are associated with coordinates included in both the three-dimensional object image regions OB1a and OB2a.

  As described above, the image generation apparatus 100 does not display the two images OB1x and OB2x for one solid object OB as shown in FIG. 15A, and only one of the two images OB1x and OB2x. May be displayed. As a result, the image generation device 100 can further improve the visibility of the three-dimensional object OB in the output image.

  Note that the image generation apparatus 100 may change the display mode of the three-dimensional object image region by another method. For example, the image generation device 100 may correct the display mode of the portion where the solid object image is not displayed in the solid object image region based on the display mode of the portion where the solid object image is displayed. Good.

  Specifically, for example, the image generating apparatus 100 includes, for example, image information of a part belonging to the region PR2 in the three-dimensional object image region OB1a, and two parts belonging to the region PR1 arranged so as to sandwich the portion belonging to the region PR2. Correct based on image information. That is, the image generating apparatus 100 interpolates the image information of the portion belonging to the region PR2 sandwiched between the two portions belonging to the region PR1 using the image information of these two portions. Note that the image information to be interpolated includes luminance, hue, saturation, and the like.

  Next, a process of correcting the output image by changing the display mode of the three-dimensional object image area (hereinafter referred to as “output image correction process”) will be described with reference to FIG. FIG. 16 is a flowchart showing the flow of the output image correction process, and the image generating apparatus 100 repeatedly executes the output image correction process at a predetermined cycle. The output image is a viewpoint conversion image including a road surface image generated based on the input images of the three cameras 2 (left camera 2L, right camera 2R, and rear camera 2B). Hereinafter, correction of the output image portion corresponding to the overlapping area of the imaging range of the rear camera 2B and the imaging range of the right camera 2R will be described. In addition, correction of the output image portion corresponding to the overlapping area between the imaging range of the rear camera 2B and the imaging range of the left camera 2L is omitted to avoid overlapping, but the same description is applied. .

  First, the control unit 1 of the image generation apparatus 100 performs edge detection processing on an output image portion corresponding to an overlapping area between the imaging range of the rear camera 2B and the imaging range of the right camera 2R (step S11). As a result, the control unit 1 acquires an edge image as shown in FIG.

  Thereafter, the control unit 1 detects the coordinates of the end points of the edge line based on the acquired edge image (step S12). At this time, the control unit 1 may execute processing for removing edge lines that are less than a predetermined length. This is to prevent unnecessary end points from being detected.

  After that, the control unit 1 detects an edge line that can be connected to another edge line based on the detected coordinates of the end point (step S13). Specifically, the control unit 1 corresponds to the width of the stripe pattern from the position of one end point of one edge line to the direction of a straight line connecting the position of the rear camera 2B or the right camera 2R and the end point. When the end point of another edge line exists at a position separated by a predetermined distance, it is determined that these two edge lines can be connected.

  Thereafter, the control unit 1 creates a closed region by connecting the edge lines determined to be connectable, and detects the closed region as a three-dimensional object image region (step S14).

  Thereafter, the control unit 1 modifies the output image by changing the display mode of the image area on the output image corresponding to the detected three-dimensional object image area (step S15).

  With the above configuration, the image generating apparatus 100 prevents the three-dimensional object from disappearing from the output image portion corresponding to the overlapping area of the imaging range of the rear camera 2B and the imaging range of the right-side camera 2R. The visibility of the three-dimensional object in the output image portion can be improved.

  Although the preferred embodiments of the present invention have been described in detail above, the present invention is not limited to the above-described embodiments, and various modifications and substitutions can be made to the above-described embodiments without departing from the scope of the present invention. Can be added.

  For example, in the above-described embodiment, the image generation apparatus 100 employs the cylindrical spatial model MD as the spatial model, but may employ a spatial model having other columnar shapes such as a polygonal column, A spatial model composed of two side surfaces may be adopted, or a spatial model having only side surfaces may be adopted.

  The image generating apparatus 100 is mounted with a camera on a self-propelled construction machine having movable members such as a bucket, an arm, a boom, and a turning mechanism. The image generating apparatus 100 moves and moves the construction machine while presenting a surrounding image to the driver. It is built in an operation support system that supports the operation of these movable members, but it is mounted with other cameras that have movable members such as industrial machines or fixed cranes but do not self-propelled together with the camera. You may incorporate in the operation assistance system which assists operation of another to-be-operated body.

  DESCRIPTION OF SYMBOLS 1 ... Control part 2 ... Camera 2L ... Left side camera 2R ... Right side camera 2B ... Rear camera 3 ... Input part 4 ... Memory | storage part 5 ... Display part 10 ... -Coordinate association means 11-Output image generation means 40-Input image / spatial model correspondence map 41-Spatial model-processing target image correspondence map 42-Processing target image / output image correspondence map 60- .... Excavator 61 ... Lower traveling body 62 ... Turning mechanism 63 ... Upper turning body 64 ... Cab

Claims (7)

An image generation method for generating an output image based on a plurality of input images captured by a plurality of cameras attached to an object to be operated,
The input image portions of the input images so that the input image portions of the two cameras corresponding to the overlapping region where the imaging ranges of the two cameras of the plurality of cameras overlap each other form a striped pattern in the output image. Place each one
Detecting an edge in an image portion corresponding to the overlap region in the output image, and determining whether the edge belongs to an image of a three-dimensional object based on the arrangement of the edge;
Detecting a three-dimensional object image region based on an arrangement of edges determined to belong to a three-dimensional object image, and controlling a display mode of the three-dimensional object image region;
An image generation method characterized by the above. The process of detecting an edge in the image portion corresponding to the overlapping region in the output image is performed along the direction of the stripe pattern,
The image generation method according to claim 1. The striped pattern is drawn by concentric circles,
The image generation method according to claim 1, wherein the image generation method is an image generation method. The three-dimensional object image region is associated with coordinates on one input image plane of two cameras.
The image generation method according to claim 1, wherein the image generation method is an image generation method. Of the three-dimensional object image region, the pixel value of the part where the three-dimensional object image is not displayed is corrected based on the pixel value of the part where the three-dimensional object image is displayed.
The image generation method according to claim 1, wherein the image generation method is an image generation method. An image generation apparatus including a control unit that generates an output image based on a plurality of input images captured by a plurality of cameras attached to an operated body,
The controller is
The input image portions of the input images so that the input image portions of the two cameras corresponding to the overlapping region where the imaging ranges of the two cameras of the plurality of cameras overlap each other form a striped pattern in the output image. Place each one
Detecting an edge in an image portion corresponding to the overlap region in the output image, and determining whether the edge belongs to an image of a three-dimensional object based on the arrangement of the edge;
Detecting a three-dimensional object image region based on an arrangement of edges determined to belong to a three-dimensional object image, and controlling a display mode of the three-dimensional object image region;
An image generation apparatus characterized by that. An operation support system that supports movement or operation of an object to be operated,
An image generation apparatus according to claim 6;
A display unit installed in an operation room for moving or operating the object to be operated and displaying an output image generated by the image generation device;
An operation support system comprising: