Garbage Detection System

Abstract

To provide a garbage quality detection system capable of accurately associating a region of garbage image data for detecting garbage quality with a region of a surface of real garbage.SOLUTION: A garbage quality detection system 2 comprises: a photographing device 28 that photographs garbage to acquire image data; a level gauge 30 that measures a height of the garbage at a prescribed horizontal position; a boundary calculation device 36 that calculates a boundary, in the image data, of a prescribed virtual region 14 which becomes a unit region for evaluating garbage quality on the basis of the horizontal position, the height, and the image data; and a feature amount calculation device 38 that calculates the feature amount of the garbage in the virtual region 14 from the image data within the boundary.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a garbage detection system.

Background Art

[0002] The collected garbage includes low-quality garbage with poor combustion efficiency, such as garbage with a large amount of moisture. When the content ratio of low-quality garbage in the garbage input into the incineration facility varies greatly, it becomes difficult to achieve stable combustion. Therefore, the collected garbage is temporarily stored in a pit and stirred using a crane. After the garbage is homogenized by stirring, it is input into the combustion facility.

[0003] In order to efficiently homogenize garbage, it is important to be able to determine the quality of garbage for each predetermined area of the garbage. For example, among the stored garbage, the garbage in the area determined to have a high content of low-quality garbage is grasped by a crane and moved to the area determined to have a low content of low-quality garbage, so that the garbage can be efficiently homogenized. Technologies for determining the quality of garbage in the pit are disclosed in Japanese Patent Application Laid-Open No. 2016-216228 and Japanese Patent Application Laid-Open No. 2019-160153.

[0004] In the crane control system for the pit disclosed in Japanese Patent Application Laid-Open No. 2016-216228, an infrared irradiation device irradiates infrared rays toward the garbage, and an imaging device captures the reflected light. In this image, it is determined that the higher the brightness, the lower the moisture content, and thus the quality of the garbage is judged.

[0005] In the garbage quality estimation system disclosed in Japanese Patent Application Laid-Open No. 2019-160153, the image captured by the imaging unit is corrected based on the height information measured by the laser rangefinder so that all areas of the garbage are on the same height plane. This image is divided into evaluation areas, and the variation in the area of the bright or dark part in each area is calculated to evaluate the mixing degree.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] The height of the garbage stored in the pit is not constant. The surface of the garbage has irregularities. On the other hand, the image data of the surface of the garbage taken to determine the quality of the garbage is a two-dimensional image. It is possible that the correspondence between the area in the image data for determining the garbage quality and the area on the actual surface of the garbage is shifted. In this case, for example, even if an attempt is made to grasp the area determined to have poor garbage quality from the image data with the bucket of the crane, the garbage at a position shifted from this area will be grasped. This can prevent efficient homogenization of garbage quality.

[0008] An object of the present invention is to provide a garbage quality detection system in which an area in image data of garbage for detecting garbage quality and an area on the actual surface of the garbage can be accurately associated.

Means for Solving the Problems

[0009] The present invention relates to a garbage quality detection system for garbage stored in a pit. This garbage quality detection system includes a photographing device that photographs the garbage to obtain image data, a level meter that measures the height of the garbage at a predetermined horizontal position, and a boundary calculation device that calculates the boundary of a predetermined virtual area that is a unit area when evaluating the garbage quality based on the horizontal position, height, and the image data, and a feature amount calculation device that obtains the feature amount of the garbage in the virtual area from the image data within the boundary.

[0010] Preferably, the boundary calculation device calculates the boundary of the virtual area in the image data based on the horizontal position and height of the vertices of the virtual area on the surface of the garbage.

[0011] The boundary calculation device may calculate the boundary of the virtual area in the image data based on the horizontal position and height of the vertex of the virtual area at the average height position of the garbage in the virtual area.

[0012] Preferably, the garbage quality detection system further includes a first calibration device. The first calibration device performs calibration for associating the coordinates in the image data with the positions in the pit based on the image data captured by the imaging device with a predetermined measurement point of the crane used in the pit positioned at a plurality of different locations in the pit.

[0013] Preferably, the garbage quality detection system further includes a second calibration device. The second calibration device performs calibration for associating the measurement results of the level meter with the positions in the pit based on the horizontal coordinates and height of a predetermined measurement point on the first side wall of the pit measured by the level meter and the horizontal coordinates and height of a predetermined measurement point on the second side wall perpendicular to the first side wall.

[0014] Preferably, the feature amount is the amount of moisture contained in the garbage.

[0015] The present invention relates to a method for detecting the quality of garbage stored in a pit. This garbage quality detection method includes a step of capturing an image of the garbage surface with an imaging device to obtain image data, a step of measuring the height of the garbage at a predetermined horizontal position with a level meter, a step of calculating the boundary of a predetermined virtual area, which is a unit area for evaluating garbage quality, in the image data based on the horizontal position and height and the image data, and a step of obtaining a feature amount of the garbage in this virtual area from the image data within the boundary. including.

[0016] Preferably, the garbage detection method further includes a calibration process of the imaging device. This calibration process of the imaging device includes: a step of obtaining image data by positioning a predetermined measurement point of the crane at a plurality of different locations in the pit and imaging using the imaging device and a step of performing calibration for associating the coordinates in the image data with the positions in the pit based on the coordinates of the measurement points in the image data and includes.

[0017] Preferably, the garbage detection method further includes a calibration process of the level gauge. This calibration process of the level gauge includes: a step of measuring, with the level gauge, the horizontal coordinates and height of a predetermined measurement point on the first side wall of the pit and the horizontal coordinates and height of a predetermined measurement point on the second side wall perpendicular to the first side wall and a step of performing calibration for associating the measurement result of the level gauge with the position in the pit based on the result of the measurement and includes.

[0018] The garbage storage facility according to the present invention includes a pit for storing garbage, a crane for stirring the garbage, and a garbage detection system. The garbage detection system includes an imaging device for imaging the garbage to obtain image data, a level gauge for measuring the height of the garbage at a predetermined horizontal position, a boundary calculation device for calculating the boundary in the image data of a predetermined virtual area that is a unit area when evaluating the garbage quality based on the horizontal position, height, and the image data, and a feature amount calculation device for obtaining the feature amount of the garbage in this virtual area from the image data within the boundary. The crane stirs the garbage based on the feature amount of the garbage.

Advantages of the Invention

[0019] In the garbage quality detection system according to the present invention, the boundary of the virtual region in the image data is calculated from the image data of the garbage captured by the imaging device and the height at the predetermined horizontal position of the garbage measured by the level meter. The feature amount of the garbage is calculated from the image data within the boundary of each virtual region. As a result, the region where the feature amount of the garbage is calculated in the image data and the region of the actual surface of the garbage are accurately associated with each other. By using this garbage quality detection system, efficient homogenization of garbage quality can be realized.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0021] Hereinafter, the present invention will be described in detail based on preferred embodiments with reference to the drawings as appropriate.

[0022] [First Embodiment] FIG. 1 is a schematic view showing a garbage storage facility 1 including a garbage quality detection system 2 according to the present invention. This garbage storage facility 1 includes a pit 4, a crane 6, and a garbage quality detection system 2. FIG. 1 also shows a hopper 8 which is an inlet for garbage into an incinerator (not shown), and the garbage (stored garbage 10) stored in the pit 4. FIG. 2 is a schematic view showing an enlarged view of the pit 4, a part of the crane 6, and the garbage quality detection system 2.

[0023] The pit 4 temporarily stores garbage. The pit 4 is box-shaped, surrounded by four side walls 12 (a first side wall 12a, a second side wall 12b, a third side wall 12c, and a fourth side wall 12d) and a floor. The normal direction of the first side wall 12a is orthogonal to the normal directions of the second side wall 12b and the fourth side wall 12d. The normal direction of the third side wall 12c is orthogonal to the normal directions of the second side wall 12b and the fourth side wall 12d. The normal direction of the floor is orthogonal to any of the normal directions of these four side walls 12. Although not shown, at least one of the side walls 12 is provided with an input door for throwing garbage into the pit 4.

[0024] In order to specify the position within the pit 4, a three-dimensional reference coordinate axis is defined in the pit 4. In FIG. 2, this coordinate axis is shown by an x-axis, a y-axis, and a z-axis that are orthogonal to each other. The x-axis and the y-axis are horizontal coordinate axes, and the z-axis is a vertical coordinate axis. In this embodiment, the x-axis is parallel to the normal directions of the first side wall 12a and the third side wall 12c of the pit 4, and the y-axis is parallel to the normal directions of the second side wall 12b and the fourth side wall 12d. The z-axis is parallel to the normal direction of the floor. The reference coordinate axis is not limited to this determination method. The reference coordinate axis may be determined as long as it can specify the three-dimensional position within the pit 4.

[0025] In the pit 4, a "virtual area 14" which is a unit area for evaluating the quality of garbage is defined. In FIG. 2, an example of the virtual area 14 is represented by a two-dot chain line. As shown in FIG. 2, in plan view, a plurality of virtual areas 14 are arranged two-dimensionally. The pit 4 is divided into a plurality of virtual areas 14. In this embodiment, the pit 4 is divided into virtual areas 14 by a plurality of virtual dividing lines extending parallel to the x-axis and a plurality of virtual dividing lines extending parallel to the y-axis. Each virtual area 14 is rectangular in plan view. In this specification, a point having the same horizontal coordinate as the vertex of this rectangle in plan view is referred to as the vertex of this virtual area 14. The position and size of each virtual area 14 are determined in advance. As will be described later, the virtual area 14 is used for positioning the garbage grabbed by the crane 6 when the garbage is agitated by the crane 6. In this embodiment, the size of the virtual area 14 is set to a size that the crane 6 can grab at one time.

[0026] As shown in FIG. 1, the crane 6 includes a pair of rails 16 extending in the front-rear direction (the vertical direction of the paper surface of FIG. 1), a garter 18 spanned between these rails 16, a trolley 20 positioned on the garter, a rope 22 extending from the trolley 20, a bucket 24 suspended from the trolley 20 via the rope 22, and a drive controller 26. By the garter 18 moving back and forth on the rails 16 and the trolley 20 moving left and right on the garter 18, the bucket 24 can move back and forth, left and right. By the trolley 20 winding up or winding down the rope 22, the bucket 24 can move in the vertical direction. The bucket 24 can move to a desired position within the pit 4. The bucket 24 can be opened and closed. The bucket 24 can grab or release the garbage. The drive controller 26 controls the movements of the garter 18 and the trolley 20 to move the bucket 24 to a desired position. The drive controller 26 can control the opening and closing of the bucket 24. Thereby, the crane 6 can grab the stored garbage 10 at a predetermined position and move it to another predetermined position. The crane 6 can grab the garbage with the bucket 24 and input this garbage into the hopper 8.

[0027] Incidentally, the drive controller 26 is configured to be able to grasp the position of the girder 18, the position of the trolley 20, and the length of the rope 22 in the reference coordinate axis. The drive controller 26 can grasp the coordinates of the bucket 24 in the reference coordinate axis. The drive controller 26 can move the bucket 24 to a predetermined coordinate in the reference coordinate axis.

[0028] The structure of the crane 6 is not limited to the above structure. The crane 6 only needs to be able to grasp the stored waste 10 at a predetermined position in the pit 4 and move it to a predetermined position.

[0029] The waste quality detection system 2 detects the quality of the stored waste 10 in the pit 4. The detected waste quality is sent to the drive controller 26 of the crane 6 and used for stirring the stored waste 10 by the crane 6.

[0030] FIG. 3 shows the configuration of the waste quality detection system 2 according to an embodiment of the present invention. The waste quality detection system 2 includes a photographing device 28, a level meter 30, a first calibration device 32, a second calibration device 34, a boundary calculation device 36, and a feature amount calculation device 38. This figure also shows the internal configuration of the boundary calculation device 36, which will be described later. In this embodiment, the first calibration device 32, the second calibration device 34, the boundary calculation device 36, and the feature amount calculation device 38 are realized by an arithmetic unit (computer), a memory, and a program. These are realized by operating the arithmetic unit with a program. In FIG. 2, the first calibration device 32, the second calibration device 34, the boundary calculation device 36, and the feature amount calculation device 38 are represented by one box.

[0031] The imaging device 28 captures the stored waste 10 in the pit 4 to obtain image data. As shown in FIG. 2, the imaging device 28 is attached to the upper end of the side wall 12. The imaging device 28 is attached at a position where all the virtual regions 14 can be imaged. In this embodiment, the imaging device 28 is attached to the upper end of the third side wall 12c. The position where the imaging device 28 is attached is not limited to the third side wall 12c. As long as all the virtual regions 14 can be imaged, the imaging device 28 may be attached at other positions. In this embodiment, there is one imaging device 28. A plurality of imaging devices 28 may be attached to the pit 4. For example, two imaging devices 28 may be attached to the pit 4, one imaging device 28 may image half of the virtual regions 14 among all the virtual regions 14, and the other imaging device 28 may image the remaining half of the virtual regions 14.

[0032] Although not shown, the imaging device 28 includes a camera that images the surface of the stored waste 10 in the pit 4 and an illuminator that irradiates light onto the surface of the stored waste 10. This camera is a normal RGB camera. As will be described later, in this embodiment, the waste detection system 2 detects the amount of moisture contained in the waste as a feature amount of the waste. Therefore, in this embodiment, the illuminator can irradiate light having a wavelength that is easily absorbed by water (absorption band light) and light having a wavelength that is hardly absorbed by water (non-absorption band light) separately. The camera captures the reflected light of the light irradiated by the illuminator and images the surface of the waste. The camera can also image the surface of the stored waste 10 using natural light without using the illuminator.

[0033] Although not shown, the imaging device 28 may further include a filter exchanger, and the illuminator may be configured to irradiate light including absorption band light and non-absorption band light. The filter exchanger controls whether to attach a first band-pass filter that allows only absorption band light to pass through to the camera or a second band-pass filter that allows only non-absorption band light to pass through. It is possible to separately perform the imaging of the stored waste 10 with the camera equipped with the first band-pass filter and the imaging of the stored waste 10 with the camera equipped with the second band-pass filter.

[0034] Although not shown, the imaging device 28 may be configured to include a first camera and a second camera, and the illuminator may irradiate light including absorption band light and non-absorption band light. A first band-pass filter that allows only absorption band light to pass is attached to the first camera, and a second band-pass filter that allows only non-absorption band light to pass is attached to the second camera. It is possible to photograph the stored waste 10 with the first camera equipped with the first band-pass filter and the stored waste 10 with the second camera equipped with the second band-pass filter simultaneously or separately.

[0035] The configuration of the imaging device 28 is not limited to the above. For example, a spectral camera may be used as the camera, or an infrared camera may be used. The imaging device 28 can take various configurations depending on the feature amount to be detected.

[0036] The level meter 30 measures the height of the stored waste 10 at a predetermined horizontal position in the pit 4. In other words, the level meter 30 measures the three-dimensional coordinates (x, y, z) of the stored waste 10 at a predetermined position on the surface. The level meter 30 is attached to the upper end of the side wall 12. In this embodiment, as shown in FIG. 2, the level meter 30 is attached to the upper end of the third side wall 12c. The level meter 30 may be attached at other positions. In this embodiment, there is one level meter 30. A plurality of level meters 30 may be attached to the pit 4. For example, two level meters 30 may be attached to the pit 4, one level meter 30 may measure the height of the stored waste 10 located in half of the virtual region 14 of the entire virtual region 14, and the other level meter 30 may measure the height of the stored waste 10 located in the remaining half of the virtual region 14.

[0037] In this embodiment, the level gauge 30 is a laser distance meter. The level gauge 30 irradiates a laser beam toward the surface of the waste, measures the time until the laser beam is reflected back from the waste surface, and measures the distance d to the position. When the angles formed by the irradiated laser beam with the x-axis, y-axis, and z-axis of the reference coordinate system are θx, θy, and θz respectively, the distances on the respective coordinate axes from the position of the level gauge 30 to this surface position are (d×cosθx, d×cosθy, d×cosθz). From this distance and the coordinates of the level gauge 30, the three-dimensional coordinates of a predetermined position on the waste surface can be obtained.

[0038] As shown by the arrow S in FIG. 2, the level gauge 30 scans radially on a single plane with a pulsed laser beam. Further, the level gauge 30 can rotate so that the laser beam can be irradiated in the vertical direction. Thereby, the level gauge 30 can measure the three-dimensional coordinates of the surface of the stored waste 10 in the pit 4 over the entire surface.

[0039] The first calibration device 32 performs calibration for associating the position in the pit 4 with the coordinates in the image data captured by the imaging device 28. In this embodiment, the coordinates in the image data are associated with the coordinates in the reference coordinate axes. Specifically, the first calibration device 32 determines the parameters of the conversion formula for converting the coordinates in the reference coordinate axes into the coordinates in the image data captured by the imaging device 28. The conversion formula with the parameters determined is used in the coordinate conversion unit 42 of the boundary calculation device 36 described later.

[0040] The conversion from the coordinates (xb, yb, zb) in the reference coordinate axes to the coordinates (xc, yc, zc) in the imaging device 28 is represented by the following formula (1).

Equation

Equation

[0041] In the determination of the parameters by the first calibration device 32, for a plurality of positions (measurement points) in the pit 4, a coordinate set (Pi, Qi) (i = 1, 2, ···) of the coordinates Pi (xbi, ybi, zbi) in the reference coordinate system and the coordinates Qi (ui, vi) in the image data when the measurement point is imaged by the imaging device 28 is prepared.

[0042] FIG. 4 shows a state of preparing the coordinate set (Pi, Qi). In this embodiment, the connection point M between the bucket 24 and the rope 22 of the crane 6 is used as the measurement point. The drive controller 26 moves the connection point M to a position where the coordinates in the reference coordinate axes are P1, and the imaging device 28 captures the pit 4 at this time. The image data at this location is obtained. The connection point M is moved to a position where the coordinates in the reference coordinate axes are P2, and the same measurement is performed. By repeating this, a plurality of image data are obtained.

[0043] The position of the connection point M in each image data is measured, and the coordinates Qi in the image data of the measurement point whose coordinates in the reference coordinate axes are Pi are obtained. A coordinate set (Pi, Qi) (i = 1, 2, ···) at a plurality of measurement points in the pit 4 is prepared. In this embodiment, the coordinate set is prepared at 10 measurement points.

[0044] In this embodiment, the coordinates of the connection point M in the image data are measured by software. For example, by coloring the connection point M with a color different from its surroundings and searching for the position of this color with software, the coordinates of the connection point M can be obtained. The coordinates of the connection point M in the image data may also be measured by an operator from the image data.

[0045] In the above embodiment, the drive controller 26 of the crane 6 moves the connection point M to the position of the coordinate Pi, thereby obtaining the coordinate Pi on the reference coordinate axis of the measurement point. The coordinate Pi on the reference coordinate axis of the measurement point may also be obtained by measuring it with the level gauge 30. In this case, it is necessary to execute the second calibration described later before the first calibration.

[0046] In the above embodiment, the connection point M between the bucket 24 and the rope 22 is set as the measurement point. The measurement point is not limited to this position. The measurement point may be, for example, the tip of the bucket 24. The measurement point may be set so that it can be located at a desired location within the pit 4.

[0047] The first calibration device 32 determines the parameters of the formulas (1) and (2) so that a plurality of coordinate sets (Pi, Qi) satisfy the relationships of the above formulas (1) and (2). Conventional methods are used for this determination. In this embodiment, this determination is made using functions of OpenCV (Open Source Computer Vision Library). The first calibration device 32 determines the parameters of the conversion formulas (1) and (2) from the coordinates on the reference coordinate axis to the coordinates in the image data.

[0048] The second calibration device 34 performs calibration to associate the position at the pit 4 with the measurement result of the level meter 30. As described above, in the level meter 30, the three-dimensional coordinates of the object in the reference coordinate axes are calculated based on the distance to the object measured by irradiating a laser beam and the angle formed by the laser beam with the reference coordinate axes at this time. The second calibration device 34 associates the measurement result of the level meter 30 with the coordinates in the reference coordinates by associating the direction in which the level meter 30 irradiates the laser beam with the angle formed by this direction with each axis of the reference coordinate axes. For this purpose, the coordinates measured by the level meter 30 are prepared for a plurality of positions (measurement points) in the pit 4.

[0049] FIG. 5 shows a state in which the level meter 30 prepares the coordinates of the measurement points. In this embodiment, the measurement points are provided on the side wall 12 of the pit 4. In this embodiment, the level meter 30 measures the coordinates of three measurement points A, B, and C on the first side wall 12a and three measurement points D, E, and F on the second side wall 12b. The measurement points A, B, and C may be located anywhere on the first side wall 12a as long as they are not arranged in a straight line. The measurement points D, E, and F may be located anywhere on the second side wall 12b as long as they are not arranged in a straight line.

[0050] The second calibration device 34 specifies the normal direction (direction parallel to the x-axis) of the first side wall 12a from the coordinates of the measurement points A, B, and C, and specifies the normal direction (direction parallel to the y-axis) of the second side wall 12b from the coordinates of the measurement points D, E, and F. The normal direction (direction parallel to the z-axis) of the floor of the pit 4 is specified as the direction perpendicular to both the direction parallel to the x-axis and the direction parallel to the y-axis. The second calibration device 34 obtains the angle between the reference coordinate axes and the coordinate axes of the level meter 30 from the directions of these coordinate axes and the directions of the coordinate axes of the level meter 30. In other words, the second calibration device 34 associates the direction in which the level meter 30 emits the laser beam with the angle formed by this direction with each axis of the reference coordinate axes. By using this, the level meter 30 can output the coordinates of the garbage used in the boundary calculation device 36 in the coordinates of the reference coordinate system.

[0051] The method of providing the measurement points is not limited to the above. Although not shown in the drawings, for example, two measurement points G and H having the same height may be provided on the first side wall 12a, and two measurement points I and J having the same height may be provided on the second side wall 12b. Marks of these measurement points are attached to the side wall 12 in advance, and the level meter 30 measures the coordinates of these marks. The second calibration device 34 specifies the direction parallel to the y-axis from the vector of the difference between the coordinates of the measurement point G and the coordinates of the measurement point H, and specifies the direction parallel to the x-axis from the vector of the difference between the coordinates of the measurement point I and the coordinates of the measurement point J. The direction parallel to the z-axis can be specified as the direction perpendicular to both the direction parallel to the x-axis and the direction parallel to the y-axis. By specifying the directions of these coordinate axes, the second calibration device 34 associates the direction in which the level meter 30 emits the laser beam with the angles formed by this direction and the respective axes of the reference coordinate axes.

[0052] The boundary calculation device 36 calculates the boundary of the virtual region 14 on the surface of the stored waste 10 from the image data captured by the imaging device 28 and the height of the garbage at a predetermined position measured by the level meter 30. As shown in FIG. 3, the boundary calculation device 36 includes a boundary point setting unit 40, a coordinate conversion unit 42, and a boundary setting unit 44.

[0053] The boundary point setting unit 40 sets a plurality of points (boundary points) for representing the virtual region 14 on the surface of the stored waste 10 for each virtual region 14. In this embodiment, the vertices of the virtual region 14 on the surface of the stored waste 10 are set as these boundary points. For example, if the coordinates of the four vertices of the virtual region 14 in the xy plane are (x1, y1), (x2, y1), (x2, y2), (x1, y2), and the heights of the respective vertices on the surface of the stored waste 10 measured by the level meter 30 are z1, z2, z3, and z4, then four points with coordinates (x1, y1, z1), (x2, y1, z2), (x2, y2, z3), (x1, y2, z4) are set as the boundary points.

[0054] Fig. 6 shows how boundary points are set. Fig. 6(a) is an example of the image data of the stored garbage 10 captured by the imaging device 28, and Fig. 6(b) is a view of this stored garbage 10 in the x-axis - z-axis plane at the position of the dividing line of the virtual region 14 parallel to the x-axis. In Fig. 6(b), the two-dot dash line represents the position of the dividing line parallel to the y-axis. In Fig. 6(b), the symbols p1 and p2 represent the boundary points of the virtual region 14 located at the leftmost of the figure. The symbols p2 and p3 represent the boundary points of the virtual region 14 located second from the left in the figure.

[0055] In the coordinate conversion unit 42, the coordinates of each boundary point on the reference coordinate axes are converted into the coordinates in the image data. In this conversion, the formulas (1) and (2) for which the parameters have been set by the first calibration device 32 are used. Thereby, the coordinates (u1, v1), (u2, v2), (u3, v3), (v4, v4) of the boundary points in the image data are obtained. This conversion is carried out for each virtual region 14. In Fig. 6(a), for some of the virtual regions 14, the boundary points in the obtained image data are shown. In Fig. 6(a), the vertices of the square drawn overlapping the surface of the stored garbage 10 are the boundary points in the image data obtained by the above conversion.

[0056] The boundary setting unit 44 sets the boundary of the virtual region 14 in the image data by connecting the boundary points in the image data. In Fig. 6(a), for some of the virtual regions 14, the boundary of the virtual region 14 set in the image data is shown.

[0057] In the above-described embodiment, the four vertices of the virtual region 14 on the surface of the stored waste 10 are set as boundary points. The number of boundary points may be increased from this. For example, the midpoint of adjacent vertices among these four vertices may be added as a boundary point. In this case, the number of boundary points becomes 8, and their coordinates are (x1, y1, z1), ((x1 + x2) / 2, y1, z5), (x2, y1, z2), (x2, (y1 + y2) / 2, z6), (x2, y2, z3), ((x1 + x2) / 2, y2, z7), (x1, y2, z4), (x1, (y1 + y2) / 2, z8). Here, z5, z6, z7, and z8 are the heights of the stored waste 10 at the added midpoints, respectively. The coordinate conversion unit 42 converts these coordinates, and the boundary setting unit 44 connects the boundary points in the image data, thereby determining the virtual region 14 in the image data.

[0058] Depending on the shape of the surface of the stored waste 10 in the virtual region 14, the position of the added boundary point may be changed. For example, the point with the highest height or the lowest height between adjacent vertices may be added as a boundary point.

[0059] Depending on the shape of the surface of the stored waste 10 in the virtual region 14, the number of boundary points may be changed. For example, in the virtual region 14 where the height difference of the unevenness on the surface of the stored waste 10 is greater than a predetermined value, the number of boundary points may be set to 8 as described above, and in the virtual region 14 where the height difference of the unevenness is less than or equal to this predetermined value, the number of boundary points may be set to 4 as described above.

[0060] The feature quantity calculation device 38 obtains the feature quantity of the garbage for each virtual area 14 in the image data. That is, the virtual area 14 serves as an evaluation unit when obtaining the feature quantity of the garbage. In this embodiment, the moisture content contained in the garbage is detected as the feature quantity of the garbage. In this embodiment, the feature quantity calculation device 38 uses the image data (moisture evaluation image) taken by irradiating the stored garbage 10 in the pit 4 with absorption band light and the image data (reference image) taken by irradiating non-absorption band light. In the moisture evaluation image, since light is absorbed more in garbage with a large moisture content, it becomes a dark image. In the reference image, since the amount of light absorbed by moisture is small, even garbage with a large moisture content becomes a bright image. For the image data of each of the moisture evaluation image and the reference image, the virtual area 14 has been determined by the boundary calculation device 36.

[0061] As the moisture evaluation image, the image data taken with a first band-pass filter attached to the camera may be used, and as the reference image, the image data taken with a second band-pass filter attached to the camera may be used. In these shootings, the illuminator irradiates light including both absorption band light and non-absorption band light.

[0062] In this embodiment, the feature quantity calculation device 38 calculates the average luminance Lw in the moisture evaluation image and the average luminance Lr in the reference image for each virtual area 14. The difference between these (Lr - Lw) is used as the feature quantity representing the moisture content of this virtual area 14. The larger this difference (Lr - Lw), the more moisture is determined to be present. The larger this difference, the lower the garbage quality is considered.

[0063] The method for calculating the feature quantity representing the moisture content is not limited to the above. The ratio of the average luminance Lw to the average luminance Lr (Lw / Lr) may be used as the feature quantity representing the moisture content of this virtual area 14. The smaller this ratio (Lw / Lr), the more moisture is determined to be present. Also, the attenuation rate of the average luminance of the moisture evaluation image with respect to the reference image ((Lr - Lw) / Lr) may be used as the feature quantity representing the moisture content of this virtual area 14. The larger this attenuation rate ((Lr - Lw) / Lr), the more moisture is determined to be present.

[0064] The following describes a garbage detection method using this garbage detection system 2. This garbage detection method (A) A calibration process of the imaging device 28, (B) A calibration process of the level gauge 30 and (C) A garbage detection process are included. The process of (A) is implemented when the state of the imaging device 28 changes, such as when the normal imaging device 28 is installed or when parts are replaced. The process of (B) is implemented when the state of the level gauge 30 changes, such as when the normal level gauge 30 is installed or when parts are replaced. The processes of (A) and (B) are preparatory processes for accurately detecting the quality of garbage. The process of (C) is implemented every time when detecting the quality of garbage.

[0065] In the above process of (A), the first calibration device 32 is used. This process (A1) A process of obtaining image data for each case where a predetermined measurement point of the crane 6 is positioned at a plurality of different locations within the pit 4 using the imaging device 28 and (A2) A process of performing calibration for associating the coordinates in the image data with the coordinates on the reference coordinate axes based on the coordinates of the measurement point in the image data are included.

[0066] In the above process of (A1), image data is obtained by positioning the measurement point at a location where the coordinates on the basic coordinate axes are P1 and photographing this with the imaging device 28. Another image data is obtained by moving the measurement point to a position where the coordinates on the basic coordinate axes are P2 and photographing this with the imaging device 28. By repeating this, image data when the measurement point provided on the crane 6 is positioned at a plurality of different locations within the pit 4 is obtained.

[0067] In the step (A2), the coordinates of the measurement points are measured from the respective image data, thereby obtaining the coordinates Qi. As a result, a plurality of coordinate sets (Pi, Qi) are obtained. The parameters of the formulas (1) and (2) are determined using the functions of OpenCV so that the coordinate sets (Pi, Qi) satisfy the formulas (1) and (2).

[0068] In the step (A1), after photographing one measurement point and obtaining the coordinate Qi from this image data, the next measurement point may be photographed. In this case, in the step (A2), the process of determining the parameters of the formulas (1) and (2) is performed.

[0069] The coordinates of the measurement points in the reference coordinate system may be measured by the level gauge 30. In this case, in the step (A1), the pit 4 is photographed by the photographing device 28, and the coordinates of the measurement points are measured by the level gauge 30. In the step (A2), the process of determining the parameters of the formulas (1) and (2) is performed.

[0070] In the step (B), the second calibration device 34 is used. This step is (B1) A step of measuring the coordinates of a plurality of measurement points located on the first side wall 12a and a plurality of measurement points located on the second side wall 12b perpendicular to the first side wall 12a with the level gauge 30 and (B2) A step of performing calibration for associating the measurement result with the coordinates in the reference coordinate axis with the level gauge 30 based on the above measurement result including.

[0071] In the step (B2), the direction in which the level gauge 30 irradiates the laser beam and the angles formed by this with the respective axes of the reference coordinate axis are associated with the coordinates of the measurement points measured by the level gauge 30 in the step (B1).

[0072] In the step (C), the quality of the stored waste 10 in the pit 4 is detected. This step is (C1) A step of photographing the surface of the stored waste 10 to obtain image data (C2) Step of measuring the height of the stored waste 10 (C3) Step of setting boundary points for representing the virtual region 14 on the surface of the stored waste 10 (C4) Step of converting the coordinates of the boundary points into coordinates in the image data (C5) Step of setting the boundary of the virtual region 14 in the image data And (C6) Step of detecting the feature amount of the waste for each virtual region 14 in the image data It includes.

[0073] Regarding the step of (C1) and the step of (C2), either may be carried out first. However, it is preferable that the step of (C1) and the step of (C2) are carried out without leaving as much time as possible. It is preferable that these are carried out at a time interval in which the state of the waste in the pit 4 does not change when the step of (C1) is carried out and when the step of (C2) is carried out.

[0074] In the step of (C1) above, the imaging device 28 is used and the surface of the stored waste 10 is imaged. In this embodiment, a moisture evaluation image obtained by imaging after irradiating absorption band light and a reference image obtained by imaging using non-absorption band light are obtained.

[0075] In the step of (C2) above, using the level meter 30, the height of the stored waste 10 at a predetermined position is measured. The coordinates of the surface of the stored waste 10 are obtained.

[0076] In the step of (C3) above, the boundary calculation device 36 is used. The vertices of the virtual region 14 on the surface of the stored waste 10 are set as boundary points.

[0077] In the step of (C4) above, the coordinates of each boundary point on the reference coordinate axis are converted into coordinates in the image data by the aforementioned formulas (1) and (2).

[0078] In the step of (C5) above, for each of the moisture evaluation image and the reference image, by connecting the boundary points in the image data, the boundary of the virtual region 14 in the image data is set.

[0079] In the step (C6), within the boundary of each virtual region 14, the average luminance in the moisture evaluation image and the average luminance in the reference image are calculated. The average luminance in the moisture evaluation image is compared with the average luminance in the reference image. Thereby, for each virtual region 14, its moisture content is detected as a feature amount.

[0080] The waste quality detected by the waste quality detection system 2 is sent to the drive controller 26 of the crane 6 and used for stirring the stored waste 10 in the crane 6. For example, the crane 6 grabs the waste in the virtual region 14 with a large moisture content and drops it into the virtual region 14 with a small moisture content. At this time, for example, the waste in the virtual region 14 with the largest moisture content is dropped into the virtual region 14 with the smallest moisture content, and the waste in the virtual region 14 with the next largest moisture content is dropped into the virtual region 14 with the next smallest moisture content. For the waste after this stirring, the steps (C1)-(C6) are performed by the waste quality detection system 2, and the waste quality is detected. The detection of the waste quality by the waste quality detection system 2 and the stirring by the crane 6 are repeated a predetermined number of times. By repeating the detection of the waste quality and the stirring, the waste quality is homogenized.

[0081] Hereinafter, the effects of the present invention will be described.

[0082] In the waste quality detection system 2 according to the present invention, from the image data of the stored waste 10 photographed by the photographing device 28 and the height at a predetermined horizontal coordinate of the stored waste 10 measured by the level meter 30, the boundary of the virtual region 14 in the image data is calculated. The feature amount of the waste is calculated from the image data within each virtual region 14. In this detection system 2, since the boundary of the virtual region 14 in the image data is calculated and the feature amount of the waste is calculated within this virtual region 14, the region where the feature amount of the waste is calculated in the image data and the region of the surface of the actual stored waste 10 are accurately associated with each other. By using this waste quality detection system 2, efficient homogenization of the waste quality can be realized.

[0083] In this embodiment, the vertices of the virtual region 14 on the surface of the stored waste 10 are regarded as boundary points, and based on the coordinates of the boundary points, the coordinates of the boundary points in the image data of the virtual region 14 are calculated. From the coordinates of the boundary points in the image data, the boundary of the virtual region 14 in the image data is calculated. This method is simple. With this method, the boundary of the virtual region 14 in the image data can be calculated efficiently.

[0084] In this embodiment, a predetermined position of the crane 6 is set as a measurement point, and this measurement point is positioned at a plurality of different locations within the pit 4 and photographed by the photographing device 28. A set of the coordinates of the measurement point in the image data obtained thereby and the coordinates of this measurement point on the reference coordinate axes is prepared. Based on this set of coordinates, parameters for associating the coordinates on the reference coordinate axes with the coordinates in the image data are determined. In this waste quality detection system 2, the measurement point can be set at a desired position within the pit 4. With this method, the coordinates on the reference coordinate axes and the coordinates in the image data can be accurately associated.

[0085] In this embodiment, since a predetermined position of the crane 6 is set as the measurement point, the coordinates of the measurement point on the reference coordinate axes can be grasped by the drive controller 26 of the crane 6. Thereby, the coordinates of the measurement point on the reference coordinate axes can be easily obtained.

[0086] The coordinates of the measurement point on the reference coordinate axes may be measured by the level gauge 30. Thereby, the coordinates of the measurement point on the reference coordinate axes can be accurately obtained.

[0087] In this embodiment, based on the coordinates measured by the level gauge 30 for a predetermined measurement point provided on the first side wall 12a of the pit 4 and a predetermined measurement point provided on the second side wall 12b perpendicular to the first side wall 12a, and the coordinates of these on the reference coordinate axes, the coordinates on the level gauge 30 and the coordinates on the reference coordinate axes are associated. With this method, the association between the coordinates on the level gauge 30 and the coordinates on the reference coordinate axes can be easily and accurately achieved.

[0088] [Second Embodiment] FIG. 7 is a block diagram showing a garbage quality detection system 50 according to another embodiment of the present invention. This garbage quality detection system 50 is the same as the garbage quality detection system 2 of the embodiment in FIG. 3 except for the boundary calculation device 52. Hereinafter, the boundary calculation device 52 will be described. As shown in FIG. 7, the boundary calculation device 52 includes a virtual area average height calculation unit 54, a boundary point setting unit 56, a coordinate conversion unit 58, and a boundary setting unit 60.

[0089] In the virtual area average height calculation unit 54, the average height of the stored garbage 10 in each virtual area 14 is calculated from the coordinates of the surface of the stored garbage 10 measured by the level meter 30.

[0090] In the boundary point setting unit 56, for each virtual area 14, the vertex of this virtual area 14 at the average height position of this virtual area 14 is set as a boundary point. FIG. 8 shows how the boundary points are set. FIG. 8(a) is an example of image data of the stored garbage 10 taken by the imaging device 28, and FIG. 8(b) is a view of this stored garbage 10 in the x - z plane at the position of the dividing line of the virtual area 14 parallel to the x - axis. The symbol H in FIG. 8(b) represents a horizontal plane having the average height of the virtual area 14. The vertex of the virtual area 14 at the position of this plane H is set as a boundary point. For example, if the coordinates of the vertices of one virtual area 14 on the surface of the stored garbage 10 are (x1, y1, z1), (x2, y1, z2), (x2, y2, z3), and (x1, y2, z4), and the average height of the stored garbage 10 in this virtual area 14 is za, then four points with coordinates (x1, y1, za), (x2, y1, za), (x2, y2, za), and (x1, y2, za) are set as boundary points. In FIG. 8(b), the symbols p1 and p2 represent the boundary points of the virtual area 14 located at the leftmost of the figure. The symbols p3 and p4 represent the boundary points of the virtual area 14 located second from the left in the figure.

[0091] In the coordinate conversion unit 58, the coordinates of each boundary point are converted into coordinates in the image data. This conversion is performed according to the above equations (1) and (2). As a result, the coordinates (u1, v1), (u2, v2), (u3, v3), (v4, v4) of the boundary points in the image data of the boundary points are obtained. In FIG. 8(a), for a part of the virtual region 14, the boundary points in the obtained image data are shown. In FIG. 8(a), the vertices of the rectangle drawn overlapping the surface of the stored garbage 10 are the boundary points in the image data obtained by the above conversion.

[0092] In the boundary setting unit 60, by connecting the boundary points in the image data, the boundary of the virtual region 14 in the image data is set. In FIG. 8(a), for a part of the virtual region 14, the boundary of the virtual region 14 set in the image data is shown.

[0093] In the above embodiment, the average height of the garbage is calculated in the virtual region 14, and for each virtual region 14, the vertices of the virtual region 14 at the average height position of this virtual region 14 are set as boundary points. The central height of the garbage (the height at the center between the highest and lowest places) may be calculated in the virtual region 14, and for each virtual region 14, the vertices of the virtual region 14 at the central height position of this virtual region 14 are set as boundary points.

[0094] In this embodiment, for each virtual region 14, the average height or the central height of the stored garbage 10 in this virtual region 14 on the reference coordinate axis is calculated, and based on the vertices of the virtual region 14 at this height, the coordinates of the boundary points in the image data are calculated. From the coordinates of the boundary points in the image data, the boundary of the virtual region 14 in the image data is calculated. This method is simple. By this method, the boundary of the virtual region 14 in the image data can be calculated efficiently.

[0095] As described above, in this garbage detection system, the area where the feature amount of garbage is calculated in the image data can be easily and accurately associated with the area of the actual garbage surface. By using this garbage detection system, efficient homogenization of garbage quality can be achieved. From this, the superiority of the present invention is clear.

Industrial Applicability

[0096] The garbage detection system described above can be applied to various garbage storage facilities.

Explanation of Signs

[0097] 1 ··· Garbage storage equipment 2 ··· Garbage detection system 4 ··· Pit 6 ··· Crane 8 ··· Hopper 10 ··· Stored garbage 12 ··· Side wall 14 ··· Virtual area 22 ··· Rope 24 ··· Bucket 26 ··· Drive control unit 28 ··· Photographing device 30 ··· Level meter 32 ··· First calibration device 34 ··· Second calibration device 36, 52 ··· Boundary calculation device 38 ··· Feature amount calculation device 40, 56 ··· Boundary point setting unit 42, 58 ··· Coordinate conversion unit 44, 60 ··· Boundary setting unit

Claims

1. A garbage quality detection system for garbage stored in a pit, comprising: A photographing device that photographs the garbage to obtain image data; A level meter that measures the height of the garbage at a predetermined horizontal position; A boundary calculation device that calculates the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data; A feature amount calculation device that obtains the feature amount of the garbage in the virtual area from the image data within the boundary; And comprising: The boundary calculation device calculates the boundary of the virtual area in the image data based on the horizontal position and height of the vertex of the virtual area on the surface of the garbage. A garbage quality detection system.

2. A garbage quality detection system for garbage stored in a pit, comprising: A photographing device that photographs the garbage to obtain image data; A level meter that measures the height of the garbage at a predetermined horizontal position; A boundary calculation device that calculates the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data; A feature amount calculation device that obtains the feature amount of the garbage in the virtual area from the image data within the boundary; And comprising: The boundary calculation device calculates the boundary of the virtual area in the image data based on the horizontal position and height of the vertex of the virtual area at the average height position of the garbage in the virtual area. A garbage quality detection system.

3. A garbage quality detection system for garbage stored in a pit, comprising: A photographing device that photographs the garbage to obtain image data; A level meter that measures the height of the garbage at a predetermined horizontal position; A boundary calculation device that calculates the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data; A feature amount calculation device that obtains the feature amount of the garbage in the virtual area from the image data within the boundary; And comprising: Further comprising a first calibration device, The first calibration device performs calibration for associating the coordinates in the image data with the position in the pit based on the image data photographed by the photographing device with a predetermined measurement point of a crane used in the pit positioned at a plurality of different locations in the pit. A garbage quality detection system.

4. A garbage quality detection system for garbage stored in a pit, comprising: An imaging device that captures the garbage to obtain image data, A level meter that measures the height of the garbage at a predetermined horizontal position, A boundary calculation device that calculates the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data, A feature amount calculation device that obtains the feature amount of the garbage in the virtual area from the image data within the boundary Comprising, Further comprising a second calibration device, The second calibration device performs calibration for associating the measurement result by the level meter with the position in the pit based on the horizontal coordinates and height of a predetermined measurement point on the first side wall of the pit and the horizontal coordinates and height of a predetermined measurement point on the second side wall perpendicular to the first side wall measured by the level meter. A garbage quality detection system.

5. The garbage quality detection system according to any one of claims 1 to 4, wherein the feature amount is the amount of moisture contained in the garbage.

6. A garbage quality detection method for garbage stored in a pit, A step of capturing the surface of the garbage with an imaging device to obtain image data, A step of measuring the height of the garbage at a predetermined horizontal position with a level meter, A step of calculating the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data And A step of obtaining the feature amount of the garbage in this virtual area from the image data within the boundary Including, Further including a calibration step of the imaging device, The calibration step of the imaging device is A step of positioning a predetermined measurement point of the crane at a plurality of different locations in the pit and capturing images using the imaging device to obtain image data And A step of performing calibration for associating the coordinates in the image data with the position in the pit based on the coordinates of the measurement point in the image data A garbage quality detection method including.

7. A garbage quality detection method for garbage stored in a pit, A step of capturing the surface of the garbage with an imaging device to obtain image data, A step of measuring the height of the garbage at a predetermined horizontal position with a level meter, A step of calculating the boundary in the image data of a predetermined virtual area that is a unit area for evaluating garbage quality based on the horizontal position, height, and the image data And A step of obtaining the feature amount of the garbage in this virtual area from the image data within the boundary Including, further including the calibration process of the level meter, the calibration process of the level meter being, in the level meter, measuring the horizontal coordinates and height of a predetermined measurement point on the first side wall of the pit, and the horizontal coordinates and height of a predetermined measurement point on the second side wall perpendicular to the first side wall and performing calibration for associating the measurement result by the level meter with the position in the pit based on the result of the measurement A garbage detection method including this.

8. A garbage storage facility comprising a pit for storing garbage, a crane for stirring the garbage, and a garbage detection system, the garbage detection system including a photographing device for photographing the garbage to obtain image data, a level meter for measuring the height of the garbage at a predetermined horizontal position, a boundary calculation device for calculating the boundary of a predetermined virtual region that is a unit region when evaluating the garbage quality based on the horizontal position, height, and the image data, and a feature amount calculation device for obtaining the feature amount of the garbage in this virtual region from the image data within the boundary and comprising, the crane stirring the garbage based on the feature amount of the garbage, the boundary calculation device calculating the boundary of the virtual region in the image data based on the horizontal position and height of the vertex of the virtual region on the surface of the garbage.

Images