JP2019125314A - Tip attachment discrimination device - Google Patents

Abstract

To accurately discriminate a tip attachment kind without using a distance distribution.SOLUTION: A work device 20 includes at its tip, a tip attachment 25 which can be exchanged with plural kinds of attachments. A camera 40 can photograph images in a movable range of the tip attachment 25. A work device attitude sensor 30 detects an attitude of the work device 20. A controller 60 sets a detection frame (F) that is a frame of a range containing the tip attachment 25 in an image photographed by the camera 40, on the basis of the attitude of the work device 20 detected by the work device attitude sensor 30. The controller 60 discriminates a kind of the tip attachment 25 on the basis of the image of the tip attachment 25 in the detection frame (F).SELECTED DRAWING: Figure 1

Description

  The present invention relates to a tip attachment determination device that determines the type of tip attachment of a working machine.

  For example, Patent Document 1 describes a technology in which a distance sensor measures a distance distribution including a tip attachment (an attachment in the document) and recognizes the tip attachment based on the distance distribution (see, for example, reference).

JP, 2017-157016, A

  In the technology described in the document, the type of tip attachment is recognized based on the distance distribution. A distance sensor is used to measure the distance distribution. However, the distance sensor may be more expensive than a monocular camera or the like. In addition, when determining the type of tip attachment, it is important to secure the accuracy of the determination.

  Therefore, an object of the present invention is to provide a tip attachment determination device that can accurately determine the type of tip attachment without using a distance distribution.

  The tip attachment determination device of the present invention includes a work device, a camera, a work device posture sensor, and a controller. The work device is attached to the upper swing body of the work machine and has a plurality of types of replaceable tip attachments at its tip. The camera is attached to the upper swing body and can capture an image within a movable range of the tip attachment. The work device posture sensor detects the posture of the work device. The controller sets a detection frame which is a frame of a range including the tip attachment in the image captured by the camera, based on the posture of the work device detected by the work device posture sensor. The controller determines the type of the tip attachment based on an image of the tip attachment in the detection frame.

  According to the above configuration, the type of tip attachment can be accurately determined without using a distance distribution.

It is the figure which looked at work machine 10 from the side. It is a block diagram of tip attachment distinction device 1 provided in work machine 10 shown in FIG. It is a flowchart of the tip attachment discrimination device 1 shown in FIG. It is an image photographed by the camera 40 shown in FIG. It is an image photographed by the camera 40 shown in FIG. It is the FIG. 1 equivalent view which shows the state which the tip attachment 25 shown in FIG. 1 has entered into the blind spot of the camera 40. FIG.

  The tip attachment determination device 1 shown in FIG. 1 will be described with reference to FIGS.

  The tip attachment determination device 1 is a device that automatically determines the type of the tip attachment 25 and is provided in the work machine 10. The work machine 10 is a machine that performs work such as construction work, and is, for example, a construction machine, such as a shovel. The work machine 10 includes a lower traveling body 11, an upper swing body 13, a work device 20, a work device posture sensor 30, a camera 40, a monitor 50 shown in FIG. 2, and a controller 60.

  The lower traveling body 11 is a portion for causing the working machine 10 to travel as shown in FIG. 1 and includes, for example, a crawler. The bottom surface 11 b of the lower traveling body 11 (the bottom surface of the work machine 10) is in contact with the ground contact surface A. The upper swing body 13 is provided above the lower traveling body 11 and can be pivoted with respect to the lower traveling body 11. The upper swing body 13 includes a cab 13 c (driver's cab).

  The work device 20 is a device attached to the upper swing body 13 to perform work. The working device 20 includes a boom 21, an arm 23, and a tip attachment 25. The boom 21 is rotatably attached to the upper swing body 13. The arm 23 is rotatably attached to the boom 21.

  The tip attachment 25 is provided at the tip of the working device 20. The tip attachment 25 can be replaced with a plurality of types. The types of tip attachments 25 include buckets (example shown in FIG. 1), clamshells, scissors-like devices, hammers, magnets, and the like. The tip attachment 25 is rotatably attached to the arm 23. A reference position of the tip attachment 25 is referred to as a reference position 25b. The reference position 25 b is a position determined regardless of the type of the tip attachment 25. The reference position 25 b is, for example, a proximal end portion of the distal end attachment 25, and is, for example, a rotation axis (a bucket pin or the like) of the distal end attachment 25 with respect to the arm 23. In FIGS. 2 and 3, the tip attachment 25 is described as “tip ATT”.

  The work device posture sensor 30 is a sensor that detects the posture of the work device 20 shown in FIG. 1. The work device attitude sensor 30 includes a boom angle sensor 31, an arm angle sensor 33, and a tip attachment angle sensor 35. The boom angle sensor 31 detects an angle of the boom 21 (boom 21 angle) with respect to the upper swing body 13. For example, the boom angle sensor 31 is an angle sensor (encoder) provided at the base end of the boom 21. For example, the arm angle sensor 33 and the tip attachment angle sensor 35 are also similar in that they are angle sensors. For example, the boom angle sensor 31 may detect the boom 21 angle by detecting the amount of expansion and contraction of the boom cylinder that drives the boom 21. In this case, the expansion and contraction amount of the boom cylinder is converted into the boom 21 angle. The arm angle sensor 33 and the tip attachment angle sensor 35 are also similar in that the angle may be detected by detecting the amount of expansion and contraction of the cylinder. The arm angle sensor 33 detects an angle of the arm 23 (arm 23 angle) with respect to the boom 21. The tip attachment angle sensor 35 detects an angle of the tip attachment 25 (tip attachment 25 angle) with respect to the arm 23.

  The camera 40 (imaging device) can capture an image within the movable range of the tip attachment 25. The camera 40 captures an image of the work device 20 and the periphery thereof. It is preferable that the camera 40 can capture the entire range assumed as the movable range of the tip attachment 25. The camera 40 may be attached to the upper swing body 13, for example, attached to the cab 13c (for example, upper left front etc.), and may be attached to a portion of the upper swing body 13 other than the cab 13c, for example. The camera 40 is fixed to the upper swing body 13. The camera 40 may be movable (for example, pivotable) with respect to the upper swing body 13. The camera 40 may be, for example, a monocular camera, and may be, for example, a stereo camera. In order to reduce the cost of the camera 40, the camera 40 is preferably a monocular camera. The camera 40 preferably has a zoom function (optical zoom function). Specifically, it is preferable that the zoom position (focal length) of the camera 40 be continuously variable between the telephoto side and the wide angle side. Note that FIG. 1 shows an example of the angle of view 40 a of the camera 40.

  The monitor 50 displays various information. The monitor 50 may display an image captured by the camera 40 (see FIG. 4). The monitor 50 may display a detection frame F (see FIG. 4) (details will be described below). The monitor 50 may display the determination result of the type of the tip attachment 25.

  As shown in FIG. 2, the controller 60 (control unit) performs input / output of signals (information), calculation (determination, calculation), and the like. The controller 60 includes a first controller 61 (main control unit) and a second controller 62 (auxiliary control unit). The first controller 61 controls the operation of the work machine 10 (see FIG. 1). The first controller 61 performs acquisition, processing, storage, and the like of information related to the work machine 10. The first controller 61 is connected to the work device attitude sensor 30, the camera 40, and the monitor 50. The second controller 62 determines (specifies) the type of the tip attachment 25 from the image information including the tip attachment 25 (see FIG. 4). The second controller 62 is a recognition unit that executes image recognition by artificial intelligence (AI). The first controller 61 and the second controller 62 may be integrated into one. Also, at least one of the first controller 61 and the second controller 62 may be divided more finely (for example, by different types of functions).

(Operation)
The operation of the tip attachment determination device 1 (mainly the operation of the controller 60) will be described with reference to the flowchart shown in FIG. In the following, each component (camera 40, controller 60, etc.) of the tip attachment determination device 1 will be mainly described with reference to FIG. 1, and each step of the flowchart will be described with reference to FIG.

  In step S11, the camera 40 captures an image including the tip attachment 25 (captures continuously in time). The controller 60 acquires information (image information, video information) of an image (see FIG. 4) (hereinafter, also referred to as “camera image Im”) captured by the camera 40. Examples of the image captured by the camera 40 are shown in FIGS. 4 and 5. FIG. 5 shows a state (remote state) in which the tip attachment 25 is farther from the camera 40 than in the state (proximity state) shown in FIG. 4. In addition, illustration of parts other than the working machine 10 was abbreviate | omitted in FIG. 4 and FIG.

  In step S13, the work device posture sensor 30 detects the posture of the work device 20. More specifically, the boom angle sensor 31 detects the boom 21 angle, the arm angle sensor 33 detects the arm 23 angle, and the tip attachment angle sensor 35 detects the tip attachment 25 angle. Then, the controller 60 acquires posture information of the work device 20 detected by the work device posture sensor 30. The controller 60 can acquire (calculate, predict, etc.) the relative position of the reference position 25b with respect to the upper swing body 13 based on the boom 21 angle and the arm 23 angle. The controller 60 can obtain the approximate position of the tip attachment 25 based on the position of the reference position 25b and the tip attachment 25 angle (details will be described later).

  In step S20, the controller 60 sets (generates) the detection frame F shown in FIG. The detection frame F is a frame in an image (camera image Im) captured by the camera 40 (see FIG. 1), and is a frame of a range including the tip attachment 25. An image inside the detection frame F is used to determine the type of the tip attachment 25. The image outside the detection frame F is not used to determine the type of the tip attachment 25.

(Setting of detection frame F)
For example, the position, size, and shape of the detection frame F in the camera image Im (on the image, in the image) are set as follows. The detection frame F is set such that the entire outer shape of the tip attachment 25 is included (fit) inside the detection frame F.

  A portion (background portion) outside the outer shape of the tip attachment 25 in the camera image Im becomes unnecessary information (noise) when the tip attachment 25 is determined. Therefore, the detection frame F is preferably set so that the background portion in the detection frame F is as small as possible. It is preferable that the detection frame F be as small as possible within a range in which the entire outer shape of the tip attachment 25 fits inside the detection frame F. For example, it is preferable that the tip attachment 25 be seen at the center of the inside of the detection frame F.

(Setting of detection frame F based on the posture of work device 20)
The position of the camera image Im and the size and the size of the tip attachment 25 appear depend on the posture of the working device 20. For example, as the tip attachment 25 is farther from the camera 40, the tip attachment 25 appears smaller (see FIG. 5). For example, as the tip attachment 25 is at a higher position, the tip attachment 25 appears in the upper position in the camera image Im. For example, depending on the angle of the tip attachment 25 with respect to the arm 23, the aspect ratio of the tip attachment 25 in the camera image Im changes.

  Therefore, the detection frame F is set based on the posture of the work device 20. For example, the detection frame F is set based on the position of the reference position 25b in the camera image Im. For example, the position of the reference position 25b in the camera image Im is acquired (calculated, predicted, etc.) based on the boom 21 angle and the arm 23 angle. For example, the position of the reference position 25b in the camera image Im is based on the position of the reference position 25b (with respect to the camera 40 (see FIG. 1)) relative to the upper swing body 13 determined based on the boom 21 angle and the arm 23 angle. It is acquired. The detection frame F is set based on the tip attachment 25 angle.

  As described above, the controller 60 sets the detection frame F based on the attitude of the work device 20. Therefore, the controller 60 does not have to use a process (object detection algorithm) for detecting the tip attachment 25 from the camera image Im. Therefore, the calculation load of the controller 60 can be reduced accordingly. In addition, since it is not necessary to use an object detection algorithm, there is no possibility of erroneously recognizing the detection position of the tip attachment 25 which is the target of type discrimination. For example, it is assumed that there is a case in which the tip attachment 25 not attached to the arm 23 (not a target of type determination) is shown in the camera image Im. Even in this case, since the tip attachment 25 which is not the target of determination is reflected outside the detection frame F, it is not the target of the type determination.

(Setting of detection frame F based on information of structure of work machine 10)
The position of the camera image Im and the size and the size of the tip attachment 25 appear depend on the structure of the work machine 10. For example, depending on the length of the boom 21 and the length of the arm 23, the position, size, and the like of the tip attachment 25 in the camera image Im change. Further, for example, depending on the size of the work machine 10 (e.g., "○ ト ン class" or the like), the type of tip attachment 25 assumed to be provided in the work device 20 changes. Then, the position, size, and the like of the tip attachment 25 in the camera image Im change.

  Therefore, it is preferable that the detection frame F is set based not only on the detection value of the work device posture sensor 30 but also on information (structure information) of the structure of the work machine 10. This structural information is, for example, included in the main specifications of the work machine 10. This structure information may be preset (stored) in the controller 60, for example, or may be acquired by some means. The structure information includes, for example, information on the upper swing body 13, information on the boom 21, and information on the arm 23. This structural information includes, for example, the sizes (sizes) and relative positions of the upper swing body 13, the boom 21, and the arm 23, respectively. The structural information includes the position of the camera 40 with respect to the upper swing body 13. The controller 60 can obtain (calculate) the attitude of the work device 20 more accurately by using not only the detection value of the work device attitude sensor 30 but also the structure information of the work machine 10, for example, the reference position 25b more accurately Can be obtained (calculated). As a result, the background portion in the detection frame F can be further reduced, and the accuracy of the type determination of the tip attachment 25 can be improved.

  When setting the detection frame F using the structure information of the work machine 10, the controller 60 can perform processing as in the following [Example A1] or [Example A2]. [Example A1] First, the rough detection frame F is set based on the posture of the work device 20 without using the structure information of the work machine 10. Thereafter, the detection frame F may be corrected based on the structure information of the work machine 10. [Example A2] The detection frame F may be set from the beginning based on the structure information of the work machine 10 and the posture of the work device 20 without performing the correction as in the above [Example A1]. The shape of the detection frame F is a rectangle in the example shown in FIG. 4, but it may be a polygon other than a quadrangle, a circle, an ellipse, or a shape close to these.

  In addition, even if there is no structure information of the working machine 10, the structure of the working machine 10 is roughly determined (it is limited within a certain range). Therefore, even when the controller 60 does not acquire the structural information of the work machine 10, the detection frame F can be set so as to include the tip attachment 25.

(Change of detection frame F)
The controller 60 sequentially changes the setting of the detection frame F according to the change of the posture of the work device 20. Specifically, for example, the detection frame F is changed as follows. When the position of the reference position 25b in the camera image Im changes, the controller 60 changes the position of the detection frame F according to the position after the change of the reference position 25b. When the reference position 25b moves away from the camera 40 and the tip attachment 25 shown in the camera image Im becomes smaller, the controller 60 reduces the detection frame F. Similarly, the controller 60 enlarges the detection frame F when the reference position 25 b approaches the camera 40 and the tip attachment 25 reflected in the camera image Im becomes large. The controller 60 changes the aspect ratio of the detection frame F when it is assumed that the angle of the tip attachment 25 with respect to the arm 23 changes and the aspect ratio of the tip attachment 25 shown in the camera image Im changes.

  In step S31, as shown in FIG. 6, it is determined whether or not the position of the tip attachment 25 can be a blind spot of the camera 40. For example, the tip attachment 25 may enter a blind spot of the camera 40 at the time of excavating work of the work machine 10 or the like. In order to make this determination, a predetermined posture condition is set in advance in the controller 60. The predetermined posture condition is a condition of the posture of the working device 20, and is a condition under which the position of the tip attachment 25 can be a blind spot of the camera 40. Specifically, (at least a part of) the tip attachment 25 may be disposed on the side (Z2 side) opposite to the side (Z1 side) on which the work machine 10 is disposed with respect to the ground contact surface A of the work machine 10 It is a condition. The ground plane A is a virtual plane parallel to the bottom surface 11 b and including the bottom surface 11 b. When the ground plane A is a horizontal plane, the above-mentioned “side opposite to the side where the work machine 10 is disposed (Z1 side) to the ground plane A (Z2 side)” is the lower side with respect to the ground plane A .

  At the time of step S31, the type of the tip attachment 25 is unknown, and the structure (size, shape, etc.) of the tip attachment 25 is unknown. Therefore, even if the posture of the working device 20 is known, it is unclear whether the tip attachment 25 is actually disposed closer to the Z2 side than the ground plane A. Therefore, for example, the posture of the working device 20 is set such that the largest tip attachment 25 of the tip attachments 25 assumed to be provided to the working device 20 is disposed on the Z2 side with respect to the ground plane A. It may be a condition. For example, the predetermined posture condition may be set based on the distance from the ground plane A to the reference position 25b.

  As shown in FIG. 1, when the posture of the working device 20 detected by the working device posture sensor 30 does not satisfy the predetermined posture condition (YES in step S31), the process proceeds to step S33 (the controller 60 attaches the tip) 25 types of discrimination may be performed). As shown in FIG. 6, when the posture of the work device 20 satisfies the predetermined posture condition (NO in S31), the controller 60 does not determine the type of the tip attachment 25. In this case, the current flow is ended and, for example, the process returns to "start". As described above, when the tip attachment 25 is disposed at a position where the camera 40 can become a blind spot, the type of the tip attachment 25 is not determined, so erroneous determination can be eliminated and unnecessary processing is eliminated. be able to.

  In the flowchart shown in FIG. 3, after the image information of the camera 40 shown in FIG. 1 is acquired (S11), the posture information of the working device 20 is acquired (S13), and the determination of step S31 is performed. On the other hand, in a state where the image information of the camera 40 is not acquired (state in which the process of S11 is not performed), the posture information of the work device 20 may be acquired (S13) and the determination of step S31 may be performed ( The same applies to the determination in step S33). Then, when the posture of the work device 20 does not satisfy the predetermined posture condition (NO in step S31), the current flow may be ended (the same applies to NO in step S33). In this case, the controller 60 does not acquire the image information of the camera 40, and does not determine the type of the tip attachment 25.

  In step S33, the controller 60 determines the corresponding distance L corresponding to the distance from the camera 40 to the tip attachment 25. If the corresponding distance L is too long, the tip attachment 25 appears small in the camera image Im shown in FIG. 5, and even if the image of the tip attachment 25 is enlarged, it becomes unclear and the accuracy of discrimination of the type of the tip attachment 25 can not be ensured. There is a case. Therefore, it is determined whether the corresponding distance L shown in FIG. 1 is a size that can ensure the accuracy of the determination. More specifically, the controller 60 obtains a corresponding distance L corresponding to the distance from the tip attachment 25 to the camera 40 based on the posture of the working device 20 detected by the working device posture sensor 30.

  At the time of step S33, the type of the tip attachment 25 is unknown, and the structure of the tip attachment 25 is unknown. Therefore, the actual distance from the camera 40 to the tip attachment 25 is unknown. Therefore, in the determination of step S33, the corresponding distance L corresponding to the actual distance from the camera 40 to the tip attachment 25 is used. For example, the corresponding distance L may be the distance from the camera 40 to the reference position 25b (the same applies to step S35). For example, the corresponding distance L may be the distance between the largest tip attachment 25 of the tip attachments 25 assumed to be provided to the working device 20 and the camera 40 (same as in step S35).

  If the corresponding distance L is equal to or less than a predetermined first predetermined distance (YES in step S33), the process proceeds to step S35 (the controller 60 may determine the type of the tip attachment 25). The value of the first predetermined distance is preset in the controller 60. The first predetermined distance is set in accordance with whether or not the determination accuracy of the tip attachment 25 can be ensured. For example, the first predetermined distance is set in accordance with the camera 40 performance, the determination ability of the second controller 62, and the like (the same applies to the second predetermined distance used in step S35). In addition, for example, when the zoom function of the camera 40 is used, it is only necessary to ensure the accuracy of the determination of the distal end attachment 25 in the state where the zoom position is at the most telephoto side. The first predetermined distance is 5 m in the example shown in FIG. 3, but can be set variously.

  When the corresponding distance L is larger than the first predetermined distance (NO in step S33), the controller 60 does not determine the type of the tip attachment 25. In this case, the current flow is ended and, for example, the process returns to "start". As described above, when the corresponding distance L corresponding to the distance from the camera 40 to the distal end attachment 25 is large and there is a possibility that the accuracy of the determination of the type of the distal end attachment 25 can not be secured, the determination of the type of the distal end attachment 25 I can not do it. Therefore, erroneous determination can be eliminated, and unnecessary processing can be eliminated.

  In step S35, the controller 60 determines, based on the corresponding distance L, whether or not the zoom position of the camera 40 is to be on the telephoto side of the wide-angle side. If the corresponding distance L is equal to or greater than the second predetermined distance (YES in step S35), the process proceeds to step S37. The value of the second predetermined distance is preset in the controller 60. The second predetermined distance is smaller than the first predetermined distance. The second predetermined distance is 3 m in the example shown in FIG. 3, but can be set variously. If the corresponding distance L is less than the second predetermined distance (NO in step S35), the zoom position of the camera 40 is set to the widest angle side, and the process proceeds to step S40. Note that although it is possible to set which distance is to be the corresponding distance L in various ways, the corresponding distance L used in the determination of step S33 and the corresponding distance L used in the determination of step S35 may be the same or different You may

  In step S37, the controller 60 sets the zoom position of the camera 40 to a position closer to the telephoto side than to the wide angle side. As the corresponding distance L is farther, the zoom position of the camera 40 is set to the telephoto side, and the image including the detection frame F is enlarged. This control is performed when the corresponding distance L is equal to or less than the first predetermined value (YES in S33) (for example, 5 m or less) and equal to or more than the second predetermined value (YES in S35) (for example, 3 m or more) . By setting the zoom position of the camera 40 to the telephoto side, the image of the tip attachment 25 becomes clearer than when the image of the tip attachment 25 is stretched and enlarged as it is, and the accuracy of determination of the type of the tip attachment 25 is improved. Can.

  In step S40, the controller 60 (the second controller 62 (see FIG. 2)) determines the type of the tip attachment 25. This determination is performed based on the image of the tip attachment 25 in the detection frame F. This determination is performed by comparing the feature amount of the tip attachment 25 acquired from the image of the tip attachment 25 in the detection frame F with the feature amount preset in the controller 60. The feature amount used for the determination is, for example, the shape (outer shape) of the outline of the tip attachment 25.

  More specifically, the first controller 61 shown in FIG. 2 cuts out the image in the detection frame F (see FIG. 4) under an arbitrary condition and timing (extracts and removes portions other than the detection frame F). The number of images in the detection frame F to be cut out may be one or a plurality (the determination may be performed based on a plurality of images). The first controller 61 outputs the clipped image to the second controller 62. In the second controller 62, an image (reference image) as a reference for determining the type of the tip attachment 25 is set in advance. The reference image includes images of various postures of various types of tip attachments 25. The second controller 62 acquires a feature (for example, a contour shape) from the image (input image) in the detection frame F input from the first controller 61. Then, the second controller 62 determines the type of the tip attachment 25 by comparing the feature amount of the input image and the feature amount of the reference image. As the tendency of the feature amount of the input image and the feature amount of the reference image is matched, the accuracy of the type determination of the tip attachment 25 becomes higher. Further, as the number of reference images is larger (the amount of learning is larger), the accuracy of the type determination of the tip attachment 25 is higher. Then, the second controller 62 outputs the determination result to the first controller 61.

  Here, when the camera 40 shown in FIG. 1 is fixed to the upper swing body 13, the imaging angle of the camera 40 with respect to the tip attachment 25 is limited as compared with the case where the camera 40 is not fixed to the upper swing body 13. Ru. Therefore, when the camera 40 is fixed to the upper swinging body 13, the reference image required to determine the type of the tip attachment 25 can be reduced (collection of the reference image becomes easy).

  In step S50, as shown in FIG. 3, the controller 60 outputs the determination result to the monitor 50. The determination result may be used for control of the work machine 10 (control of operation, etc.).

(Comparison with technology using distance sensor)
A case will be examined where the type of the tip attachment 25 shown in FIG. 1 is determined based on the distance distribution (distance image, depth distribution) detected by the distance sensor. In this case, there is a problem that the distance sensor is more expensive than a monocular camera. In addition, the distance sensor has a problem that the influence of dust is greater than that of a monocular camera. On the other hand, in the present embodiment, a monocular camera can be used as the camera 40. When the camera 40 is a monocular camera, these problems can be eliminated.

  In addition, a distance sensor such as a TOF (Time Of Flight) sensor has a narrower detection range (a narrow angle of view) than a monocular camera. Therefore, it is conceivable to measure the distance distribution around the tip attachment 25 using a distance sensor in a state in which the working device 20 is in a specific limited attitude, such as the attitude in which the tip attachment 25 is in contact with the ground. However, in this case, when the type of the tip attachment 25 is determined, it is necessary to set the working device 20 in a specific posture, which takes time and effort. On the other hand, in the present embodiment, when the type of the tip attachment 25 is determined, the posture of the working device 20 can be made almost arbitrary. Therefore, in the present embodiment, the degree of freedom of the posture of the working device 20 at the time of determining the type of the tip attachment 25 is high. More specifically, in the present embodiment, the tip attachment 25 is in any posture of the working device 20 except in a state where the type of the tip attachment 25 is not determined (NO in S31 of FIG. 3 and NO in S33). It is possible to determine the type of The conditions under which the type of the tip attachment 25 is not determined can be set variously.

(effect)
The effects of the tip attachment determination device 1 shown in FIG. 1 are as follows.

(Effect of the first invention)
The tip attachment determination device 1 includes a work device 20, a camera 40, a work device posture sensor 30, and a controller 60. The work device 20 is attached to the upper swing body 13 of the work machine 10. The working device 20 has a tip attachment 25 that can be replaced with a plurality of types at the tip (the tip of the working device 20). The camera 40 is attached to the upper swing body 13 and can capture an image within the movable range of the tip attachment 25. The work device posture sensor 30 detects the posture of the work device 20.

  [Configuration 1-1] The controller 60 is a detection frame F that is a frame of a range including the tip attachment 25 in the image captured by the camera 40 based on the posture of the work device 20 detected by the work device posture sensor 30. (See FIG. 4) (hereinafter, see FIG. 4 for the detection frame F).

  [Configuration 1-2] The controller 60 determines the type of the tip attachment 25 based on the image of the tip attachment 25 in the detection frame F.

  In the above [Configuration 1-2], the controller 60 determines the type of the tip attachment 25 based on an image. Therefore, the controller 60 can determine the type of the tip attachment 25 without using the distance distribution. As a result, the cost of the camera 40 can be reduced as compared to the case where the camera 40 needs to acquire the distance distribution.

  On the other hand, when the type of the tip attachment 25 is determined based on an image, it can be said that there is less information for determination by the distance information than in the case where it is performed using the distance distribution. Therefore, it is important to secure the accuracy of discrimination of the type of the tip attachment 25 even if the information for discrimination is small. Here, depending on the attitude of the working device 20, the manner in which the tip attachment 25 in the camera image Im appears (for example, position, size, shape, etc.) changes.

  Therefore, in the above [Configuration 1-1], the controller 60 sets the detection frame F including the tip attachment 25 based on the posture of the work device 20. Therefore, the controller 60 can set the detection frame F suitable for determining the type of the tip attachment 25. For example, the controller 60 can set the detection frame F so that the entire tip attachment 25 is included and the background portion around the tip attachment 25 is as small as possible. Therefore, compared with the case where the setting of the detection frame F based on the attitude | position of the working apparatus 20 is not performed, the precision of discrimination | determination of the kind of the tip attachment 25 can be improved. Therefore, the tip attachment determination device 1 can accurately determine the type of the tip attachment 25 without using the distance distribution.

(Effect of the second invention)
[Configuration 2] The camera 40 is fixed to the upper swing body 13.

  By the above [Configuration 2], the imaging angle of the camera 40 with respect to the tip attachment 25 is limited as compared with the case where the camera 40 is not fixed to the upper swing body 13. Therefore, the amount of information required to determine the type of the tip attachment 25 can be reduced.

(Effect of the third invention)
[Configuration 3] The controller 60 sequentially changes the setting of the detection frame F in accordance with the change in the posture of the work device 20 detected by the work device posture sensor 30.

  After the detection frame F is set by the above [Configuration 3], the controller 60 can determine the type of the tip attachment 25 even if the posture of the working device 20 changes.

(Effect of the fourth invention)
[Configuration 4] The controller 60 sets the detection frame F based on the information of the structure of the work machine 10.

  In the above [Configuration 1-1] and [Configuration 4], the controller 60 detects the detection frame F based on the posture of the work device 20 detected by the work device posture sensor 30 and the information of the structure of the work machine 10 Set Therefore, the controller 60 can set the detection frame F suitable for determining the type of the tip attachment 25 as compared to the case where the detection frame F is set based on only the posture of the work device 20.

(Effects of the fifth invention)
[Configuration 5] The camera 40 has a zoom function. The controller 60 moves the zoom position of the camera 40 to the telephoto side as the distance from the tip attachment 25 to the camera 40 increases, based on the posture of the work device 20 detected by the work device posture sensor 30. Do.

  By the above [Configuration 5], the resolution of the image of the tip attachment 25 in the detection frame F is increased by setting the zoom position of the camera 40 to the telephoto side even if the distance from the tip attachment 25 to the camera 40 increases. Can. Therefore, the accuracy of determination of the type of the tip attachment 25 can be improved.

(Effect of the sixth invention)
As shown in FIG. 6, the controller 60 is a condition of the posture of the work device 20 and is opposite to the side (Z1 side) on which the work machine 10 is disposed with respect to the ground plane A of the work machine 10 A predetermined posture condition which is a condition under which the distal end attachment 25 can be disposed on the Z2 side) is preset.

  [Configuration 6-1] If the posture of the work device 20 detected by the work device posture sensor 30 does not satisfy the predetermined posture condition (case of NO in step S31 of FIG. 3), the controller 60 causes the tip shown in FIG. The type of attachment 25 may be determined.

  [Configuration 6-2] The controller 60 controls the tip attachment shown in FIG. 6 when the posture of the work device 20 detected by the work device posture sensor 30 satisfies the predetermined posture condition (YES in step S31 of FIG. 3). Do not determine the 25 types.

  When the tip attachment 25 can be disposed on the Z2 side with respect to the ground surface A, at least a portion of the tip attachment 25 may enter the blind spot of the camera 40. Then, the type of the tip attachment 25 may not be determined or the accuracy of the determination may not be ensured. Therefore, the tip attachment determination device 1 includes the above [Configuration 6-2]. Therefore, it can suppress that the controller 60 misjudges the kind of front-end | tip attachment 25, and the useless process of the controller 60 can be eliminated. Further, with the above [Configuration 6-2], it is easy to determine the type of the tip attachment 25 in a state in which the accuracy in determining the type of the tip attachment 25 is secured (in a state where it is easy to determine). As a result, the accuracy of determination of the type of the tip attachment 25 can be improved.

(Effect of the seventh invention)
The controller 60 acquires the corresponding distance L corresponding to the distance from the tip attachment 25 to the camera 40 based on the posture of the work device 20 detected by the work device posture sensor 30.

  [Configuration 7-1] The controller 60 controls the tip attachment 25 shown in FIG. 1 when the corresponding distance L is less than or equal to a predetermined first predetermined distance (predetermined distance) (YES in step S33 in FIG. 3). The type may be determined.

  [Configuration 7-2] The controller 60 does not determine the type of the tip attachment 25 shown in FIG. 1 when the corresponding distance L is larger than the first predetermined distance (NO in step S33 in FIG. 3).

  As the corresponding distance L is larger (far), the tip attachment 25 may be smaller in the camera image Im (see FIG. 4), and it may be difficult to ensure the accuracy of determination of the type of the tip attachment 25. Therefore, the tip attachment determination device 1 includes the above [Configuration 7-2]. Therefore, it can suppress that the controller 60 misjudges the kind of front-end | tip attachment 25, and the useless process of the controller 60 can be eliminated. Further, with the above-described [Configuration 7-1], it is easy to determine the type of the tip attachment 25 in a state in which the accuracy of determination of the type of the tip attachment 25 is secured (in a state where it is easy to determine). As a result, the accuracy of determination of the type of the tip attachment 25 can be improved.

(Modification)
The above embodiments may be variously modified. For example, connections between blocks in the block diagram shown in FIG. 2 may be changed. For example, the order of the steps of the flowchart shown in FIG. 3 may be changed. For example, the number of components of the tip attachment determination device 1 shown in FIGS. 1 and 2 may be changed, or some of the components may not be provided.

  Some components of the tip attachment determination device 1 may be provided outside the work machine 10. For example, the second controller 62 shown in FIG. 2 may be provided outside the work machine 10. For example, the monitor 50 may not be provided.

DESCRIPTION OF SYMBOLS 1 tip attachment discrimination device 10 working machine 13 upper revolving unit 20 working device 25 tip attachment 30 working device posture sensor 40 camera 60 controller A ground plane F detection frame L distance (corresponding distance)

Claims (7)

A work device attached to an upper swing body of a work machine and having a plurality of exchangeable tip attachments at a tip portion;
A camera attached to the upper swing body capable of capturing an image within a movable range of the tip attachment;
A work device posture sensor that detects a posture of the work device;
Controller,
Equipped with
The controller
Based on the posture of the work device detected by the work device posture sensor, a detection frame which is a frame of a range including the tip attachment in the image captured by the camera is set;
The type of the tip attachment is determined based on the image of the tip attachment in the detection frame,
Tip attachment discrimination device. The tip attachment discriminating apparatus according to claim 1, wherein
The camera is fixed to the upper swing body.
Tip attachment discrimination device. It is a tip attachment distinction device according to claim 1 or 2, and.
The controller sequentially changes the setting of the detection frame according to a change in posture of the work device detected by the work device posture sensor.
Tip attachment discrimination device. It is a tip attachment distinction device according to any one of claims 1 to 3,
The controller sets the detection frame based on information on the structure of the work machine.
Tip attachment discrimination device. It is a tip attachment distinction device according to any one of claims 1 to 4,
The camera has a zoom function,
The controller
The zoom position of the camera is set to the telephoto side as the posture of the work device detected by the work device posture sensor is such that the distance from the tip attachment to the camera is longer.
Tip attachment discrimination device. It is a tip attachment distinction device according to any one of claims 1 to 5, wherein
The controller has a predetermined posture that is a condition of the posture of the work device, the tip attachment may be arranged on the side opposite to the side where the work machine is arranged with respect to the ground contact surface of the work machine The conditions are preset and
The controller
When the posture of the work device detected by the work device posture sensor does not satisfy the predetermined posture condition, the type of the tip attachment may be determined.
When the posture of the work device detected by the work device posture sensor satisfies the predetermined posture condition, the type of the tip attachment is not determined.
Tip attachment discrimination device. It is a tip attachment distinction device according to any one of claims 1 to 6,
The controller
Based on the posture of the work device detected by the work device posture sensor, a corresponding distance corresponding to the distance from the tip attachment to the camera is acquired;
When the corresponding distance is equal to or less than a predetermined distance, the type of the tip attachment may be determined.
When the corresponding distance is larger than the predetermined distance, the type of the tip attachment is not determined.
Tip attachment discrimination device.