Abnormality determination device, abnormality determination system, and abnormality determination method

Abstract

To provide a technology that can more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of a traveling body even in a situation where vibrations may occur due to the movement of the traveling body.SOLUTION: An information processing device (10) includes: an image acquisition unit (111) that acquires a plurality of images captured at a plurality of positions by an imaging device installed on a traveling body; an image selection unit (112) that selects an image that is not a blurred image from the plurality of images; a feature calculation unit (113) that calculates a feature amount of the image selected by the image selection unit (112); and an abnormality determination unit (114) that determines an abnormality in at least one of the position, attitude, and trajectory of the traveling body based on the feature amount calculated by the feature calculation unit (113) and a reference feature amount calculated from a reference image, and outputs the determination result.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique for determining an abnormality in a traveling body such as a crane. [Background technology]

[0002] There are known techniques for determining abnormalities in a moving object such as a crane. For example, Patent Document 1 describes a moving object system that detects positional deviations using images captured by a camera with a fixed imaging direction. Patent Document 2 discloses a lifting device that detects an abnormality when the difference between the position of a detection object detected at a first time and the position of a detection object detected at a second time is equal to or greater than a certain value. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-27711 A [Patent Document 2] JP 2022-155991 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in Patent Document 1 has a problem in that, even if there is nothing abnormal in the moving object itself, the image is blurred due to vibrations caused by the movement of the moving object, and it is erroneously determined that the moving object is out of position. The technology described in Patent Document 2 has a similar problem.

[0005] One aspect of the present invention aims to realize a technology that can more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of a moving body, even in situations where vibrations may occur due to the movement of the moving body. [Means for solving the problem]

[0006] In order to solve the above problems, an abnormality determination device according to one embodiment of the present invention includes an image acquisition unit that acquires a plurality of images taken at a plurality of positions by an imaging device installed on a moving body, an image selection unit that selects an image from the plurality of images that is not a blurred image, a feature calculation unit that calculates features of the image selected by the image selection unit, and an abnormality determination unit that determines abnormality in at least one of the position, attitude, and trajectory of the moving body based on the features calculated by the feature calculation unit and reference features calculated from a reference image, and outputs a determination result.

[0007] According to the above configuration, even if the image is blurred due to vibrations caused by the movement of the moving object, it is possible to more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of the moving object.

[0008] In the above abnormality determination device, the image acquisition unit may acquire an image obtained by the photographing device photographing a specified subject, and the feature amount may include at least one of a center of gravity and a tilt of the subject in the image.

[0009] According to the above configuration, by determining an abnormality using at least one of the center of gravity and the inclination of the subject, it is possible to reduce the processing load associated with the determination process.

[0010] The abnormality determination device may further include a memory unit that stores the reference feature for each of a plurality of reference positions, and the abnormality determination unit may select a reference feature corresponding to the position of the vehicle from the plurality of reference feature, and determine the abnormality based on the selected reference feature and the feature calculated by the feature calculation unit.

[0011] According to the above configuration, it is possible to determine whether or not there is an abnormality in the moving object at a plurality of positions.

[0012] In the above abnormality judgment device, the abnormality judgment unit may execute a first output process of judging an abnormality in the moving body at a plurality of positions and outputting a judgment result for each position, and a second output process of compiling statistics of the judgment results for each position and outputting the statistical results.

[0013] According to the above configuration, it is possible to judge an abnormality for each position and to comprehensively judge an abnormality in the moving object.

[0014] In the above-mentioned abnormality judgment device, when the abnormality judgment unit judges that an abnormality has occurred at multiple consecutive positions, it may output information indicating the possibility of an abnormality in at least one of a portion related to the entire road on which the moving body travels and the moving body itself.

[0015] According to the above configuration, it is possible to determine an abnormality not only in the moving object but also in the road on which the moving object travels.

[0016] In the above abnormality judgment device, when the abnormality judgment unit judges that an abnormality exists at an individual position, it may output information indicating the possibility of an abnormality in the portion of the road on which the moving body travels that is judged to be abnormal.

[0017] According to the above configuration, it is possible to notify an abnormality in a road on which a moving object is traveling.

[0018] In addition, the abnormality determination system of the present invention includes a running body that transports an article, a photographing device installed on the running body, an image acquisition unit that acquires a plurality of images photographed by the photographing device, an image selection unit that selects an image from the plurality of images that is not a blurred image, a feature calculation unit that calculates features of the image selected by the image selection unit, and an abnormality determination unit that determines abnormality in at least one of a position, attitude, and trajectory of the running body based on the features calculated by the feature calculation unit and reference features calculated from a reference image, and outputs a determination result.

[0019] According to the above configuration, even if the image is blurred due to vibrations caused by the movement of the moving object, it is possible to more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of the moving object.

[0020] In addition, the abnormality determination method of the present invention is a method in which an information processing device executes the following steps: an image acquisition step of acquiring multiple images captured by an imaging device installed on a moving body; an image selection step of selecting an image from the multiple images that is not a blurred image; a feature calculation step of calculating features of the image selected in the image selection step; and an abnormality determination step of determining an abnormality in at least one of the position, attitude, and trajectory of the moving body based on the features calculated in the feature calculation step and reference features calculated from a reference image, and outputting a determination result.

[0021] According to the above configuration, even if the image is blurred due to vibrations caused by the movement of the moving object, it is possible to more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of the moving object.

[0022] The abnormality judgment device according to each aspect of the present invention may be realized by a computer. In this case, the control program for the abnormality judgment device, which causes a computer to operate as each part (software element) of the abnormality judgment device, and the computer-readable recording medium on which the control program is recorded, also fall within the scope of the present invention. Effect of the Invention

[0023] According to one aspect of the present invention, even in a situation where vibrations may occur due to the movement of a moving body, it is possible to more appropriately determine abnormalities in at least one of the position, attitude, and trajectory of a moving body. [Brief description of the drawings]

[0024] [Figure 1] 1 is a schematic diagram of a condition diagnosis support system according to an embodiment of the present invention. [Diagram 2]FIG. 2 is a top view of a crane according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing an example of an image captured by a camera according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of a rail according to an embodiment of the present invention. [Diagram 5] 1 is a block diagram showing an example of a configuration of an information processing device according to an embodiment of the present invention. [Figure 6] FIG. 4 is a diagram showing an example of diagnostic data according to the embodiment of the present invention. [Figure 7] FIG. 2 is a flow chart showing an example of the flow of an abnormality determination method according to an embodiment of the present invention. [Figure 8] FIG. 13 is a diagram showing an example of a judgment graph according to the embodiment of the present invention. [Figure 9] FIG. 13 is a diagram showing an example of a judgment graph according to the embodiment of the present invention. [Figure 10] FIG. 13 is a diagram showing an example of a judgment graph according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] [Embodiment] <1. Configuration of condition diagnosis support system> 1 is a schematic diagram of a condition diagnosis support system 1 according to the present embodiment. The condition diagnosis support system 1 is a system that supports diagnosis of the condition of a crane 30, and is an example of an abnormality determination system according to the present disclosure. The condition diagnosis support system 1 includes an information processing device 10, a crane controller 20, a crane 30, and a camera 50.

[0026] The information processing device 10 is a device having a function for supporting the diagnosis of the state of the crane 30, and is an example of an abnormality determination device according to the present disclosure. The information processing device 10 is, for example, a general-purpose computer device, but is not limited to this. The crane controller 20 controls the crane 30 to move an object such as a slab 70 placed in a yard 80. Note that, although the example of FIG. 1 illustrates a case where a slab 70 is placed in the yard 80, the object placed in the yard 80 is not limited to a slab, and may be, for example, another object used in construction.

[0027] The crane 30 is a traveling body that moves objects such as slabs 70 placed in a yard 80. The crane 30 may be operated by being operated by an operator, or may be operated under the control of a crane controller 20. The camera 50 is an imaging device installed on the crane 30. Images captured by the camera 50 are output to an information processing device 10 and used for diagnosing the condition of the crane 30.

[0028] The operation device 60 includes an operation panel operated by an operator who manages the yard 80, and supplies information according to the operation contents of the operator to the information processing device 10. The operation device 60 also receives a diagnosis result from the information processing device 10, and outputs an image showing the diagnosis result on a display device or outputs a warning sound. The yard 80 is a storage area where items such as slabs 70 are placed.

[0029] (Crane configuration) FIG. 2 is a top view of crane 30. In FIG. 2, the vertical direction is the y-axis direction, the running direction of crane 30 is the z-axis direction, and the lateral direction is the x-axis direction. The view seen from the positive direction of the y-axis is the top view. Crane 30 is an overhead crane that runs on rails 90 installed along the wall of yard 80. Crane 30 comprises a main body 31, a lateral crab 32, and a hoisting device 33. Note that crane 30 also comprises other components (e.g., a traveling device, etc.), but these are not shown here to avoid cluttering the drawing.

[0030] The main body 31 travels on the rails 90 in the travel direction (z-axis direction in the figure). The traverse crab 32 is a crab that moves in the traverse direction (x-axis direction in the figure) and is equipped with a hoisting device (not shown) and a traverse device (not shown), etc. The hoist 33 is a member that lifts an article placed in the yard 80 or lowers a transported article to the yard 80. The main body 31 of the crane 30 moves in the travel direction and the traverse crab 32 moves in the traverse direction, whereby the hoist 33 moves within the yard 80. The crane controller 20 moves the hoist 33 above the article to be moved, and a bucket or the like attached to the hoist 33 grasps and moves the article placed in the yard 80.

[0031] The camera 50 is installed on the crane 30 in an orientation that captures the negative direction of the z axis, and captures an image of a mark 81 placed on a wall surface of the yard 80. The mark 81 is, for example, an image attached to the wall surface of the yard 80, and is an example of a subject according to the present disclosure. However, the mark 81 is not limited to the above example, and may be, for example, a predetermined object placed within the yard 80.

[0032] FIG. 3 is a diagram showing a specific example of an image captured by the camera 50. In the example of FIG. 3, the image 51 captured by the camera 50 includes a mark 81. In this embodiment, the information processing device 10 diagnoses the condition of the crane 30 and the like using a plurality of images captured by the camera 50 fixed to the crane 30. Hereinafter, the image captured by the camera 50 is also referred to as a "captured image." A plurality of reference positions are set in the yard 80 in the travel direction of the crane 30, and the camera 50 captures images at each of the plurality of reference positions. For example, positions at distances of 0 m, 100 m, 300 m, and 500 m from a predetermined position in the travel direction of the crane 30 are set as reference positions.

[0033] Rail 90 is provided along the wall of yard 80. Rail 90 is an example of a travelway according to the present disclosure. Fig. 4 is a diagram showing an example of the appearance of rail 90. In the example of Fig. 4, rail 90 is configured by connecting a plurality of rail members 90a, 90b, etc. When crane 30 passes through connecting portion 91 of rail 90, crane 30 vibrates, and due to this vibration, images captured by camera 50 are particularly likely to be blurred.

[0034] (Configuration of information processing device) Fig. 5 is a block diagram showing an example of a configuration of the information processing device 10. In Fig. 5, the information processing device 10 includes a control unit 11, a storage unit 12, a communication IF 13, and an input / output IF 24. The control unit 11 includes an image acquisition unit 111, an image selection unit 112, a feature calculation unit 113, and an abnormality determination unit 114.

[0035] The image acquisition unit 111 acquires a plurality of images captured at a plurality of positions by the camera 50 installed on the crane 30. As an example, the image acquisition unit 111 acquires an image obtained by the camera 50 capturing an image of the mark 81.

[0036] The image selection unit 112 selects a non-blurred image from among the multiple images. Here, a blurred image is an image in which the subject is not clearly captured due to the movement of the camera 50 during exposure. Since the crane 30 on which the camera 50 is installed travels on the rails 90, the image captured by the camera 50 may be blurred due to vibrations caused by the travel of the crane 30.

[0037] The image selection unit 112 analyzes the image captured by the camera 50 and determines whether the image is a blurred image based on the analysis result. As an example, the image selection unit 112 performs edge detection processing on the image and determines whether the image is a blurred image based on the detection result. In this case, the image selection unit 112 may, for example, detect edges in the image and determine that the image is a blurred image when there are few edges detected. More specifically, the image selection unit 112 may, for example, perform edge detection processing on the image and determine that the image is a blurred image when the amount of edges detected is equal to or less than a predetermined threshold.

[0038] Furthermore, the image selection unit 112 may determine that an image is blurred when the thickness of an edge detected by the edge detection process is thick. More specifically, the image selection unit 112 may execute the edge detection process on the captured image, and determine that the image is blurred when a statistical value (average value, etc.) of the thickness of the detected edge is equal to or greater than a predetermined threshold.

[0039] Also, the image selection unit 112 may determine whether the captured image is a blurred image based on the luminance of the captured image. More specifically, the image selection unit 112 may determine that the captured image is a blurred image when the range of luminance of the captured image is small (for example, when the difference between the maximum and minimum luminance values ​​is equal to or less than a predetermined threshold value). Also, the image selection unit 112 may determine that the captured image is a blurred image when the average value of luminance of the captured image is equal to or greater than a threshold value. Alternatively, the image selection unit 112 may determine that the captured image is a blurred image by comparing the magnitude of edge amounts by general image processing, for example. In this case, since the target image is determined in advance, the amount of edges obtained in the captured image is assumed to be within a certain range, and the image selection unit 112 may determine that the captured image is a blurred image when it falls below that range.

[0040] The feature calculation unit 113 calculates the feature amount of the image selected by the image selection unit 112. Here, the feature amount of the image is information that indicates the feature of the image, and includes, as an example, at least one of the center of gravity and the tilt of the mark 81 in the image. As an example, the feature calculation unit 113 detects the mark 81 from the image captured by the camera 50, calculates the center of gravity of the detected mark 81, and calculates the tilt of the detected mark 81.

[0041] The abnormality determination unit 114 determines abnormality in at least one of the position, posture, and trajectory of the crane 30 based on the feature amount calculated by the feature calculation unit 113 and the reference feature amount D2 calculated from the reference image, and outputs the determination result. The abnormality in the position of the crane 30 is a positional deviation in the x-axis direction, y-axis direction, or z-axis direction of the crane 30. The abnormality in the position occurs, for example, when an abnormality such as deformation occurs in the rail 90, or when an abnormality such as deformation occurs in the traveling device of the crane 30. Furthermore, the abnormality in the posture means that the posture of the crane 30 deviates from the reference posture. Here, examples of the posture of the crane 30 include, but are not limited to, the inclination and rotation amount of the main body part 31 with respect to the rail 90, or the inclination and rotation amount of the traverse club 32 with respect to the main body part 31 (or the rail 90). Furthermore, the abnormality in the trajectory of the crane 30 means that the time change in the position of the crane 30 deviates from the time change in the reference position. An abnormality in posture and an abnormality in track also occur, for example, when an abnormality such as deformation occurs in the rail 90, or when an abnormality such as deformation occurs in the traveling gear of the crane 30. The reference feature amount D2 is stored in advance, for example, in the storage unit 12. Details of the process performed by the abnormality determination unit 114 will be described later.

[0042] The storage unit 12 stores various data necessary for the processing executed by the information processing device 10. In particular, the storage unit 12 stores image data D1, reference feature amount D2, diagnostic data D3, diagnostic result data D4, and counter D5. The image data D1 is data representing an image captured by the camera 50. The reference feature amount D2 is referred to in the determination processing of the abnormality determination unit 114. As an example, the storage unit 12 stores the reference feature amount D2 for each of a plurality of reference positions.

[0043] The diagnostic data D3 is data that the abnormality determination unit 114 refers to in the determination process. Fig. 6 is a diagram showing an example of the diagnostic data D3. In the example of Fig. 6, the diagnostic data D3 has the following items associated with each other: "identification information", "time", "position", "work state", "load", "image", "characteristic position", "posture", and "number of blurred images". Of these items, the "identification information" item stores information that identifies the diagnostic data D3 (e.g., "P1", "P2", etc.).

[0044] The "time" field stores information indicating the time when the image included in the diagnostic data D3 was captured. The "position" field stores information indicating the position of the crane 30 in the traveling direction at the time of the diagnostic data D3.

[0045] The "working state" item stores information indicating the working state of the crane 30 at the time of the diagnostic data D3 (e.g., "running", "stopped", etc.). The "load" item stores information indicating the load on the crane 30 at the time of the diagnostic data D3.

[0046] The "image" item stores image data representing images captured at the time of the diagnostic data D3. The information stored in this item may be address information indicating the storage location of the image data. In the example of FIG. 7, image data representing 30 images captured at one reference position is stored in this "image" item.

[0047] The "characteristic position" field stores information indicating the x and y coordinates of the center of gravity of the mark 81, which is a characteristic amount calculated by the characteristic calculation unit 113 for the captured image of the diagnostic data D3. The "inclination" field stores information indicating the inclination of the mark 81, which is a characteristic amount calculated by the characteristic calculation unit 113 for the captured image of the diagnostic data.

[0048] The "Number of blurred images" field stores information indicating how many of the 30 images captured at each reference position are blurred images. For example, if there are zero blurred images, this field stores "0." On the other hand, if there are three blurred images, this field stores "3."

[0049] The diagnosis result data D4 is data indicating the determination result of the abnormality determination unit 114. As an example, the diagnosis result data D4 includes at least one of information indicating the determination result for each reference position and information indicating a statistical result of the determination result for each reference position.

[0050] The information indicating the judgment result for each reference position is information indicating the judgment result at each of the multiple reference positions by the abnormality judgment unit 114. For example, when the feature amount of the image calculated for a certain reference position does not fall within a predetermined range, the abnormality judgment unit 114 stores information indicating that the judgment result for that reference position is abnormal in the storage unit 12 as the diagnosis result data D4.

[0051] Moreover, the information indicating the statistical result of the judgment result for each reference position is, for example, information indicating the abnormal / normal judgment result based on the result of counting the number of times it is judged to be abnormal for each reference position (counter D5). The counter D5 is information indicating the result of counting the number of times it is judged to be abnormal at each of the multiple reference positions. For example, when the counter D5 is equal to or greater than a threshold value, the abnormality judgment unit 114 may judge that there is a possibility of an abnormality at the reference position corresponding to the counter D5.

[0052] The communication IF13 is an interface for communicating with other computers. The communication IF13 may include an interface for communicating with other computers without a network, such as a Bluetooth (registered trademark) interface. The communication IF13 may also include an interface for communicating with other computers via a LAN (Local Area Network), such as a Wi-Fi (registered trademark) interface. An input device and / or an output device are connected to the input / output IF14. An example of the input / output IF14 is a USB.

[0053] <2. Flow of abnormality determination method> Fig. 6 is a flow diagram showing an example of the flow of an abnormality determination method S1 performed by the condition diagnosis support system 1. In the example of Fig. 6, a case will be described in which the camera 50 captures an image of a mark 81. Note that some steps may be executed in parallel or in a different order.

[0054] In step S11, the crane controller 20 controls the crane 30 to travel and transport an article. In step S12, the information processing device 10 acquires position information indicating the position of the crane 30 from the crane controller 20.

[0055] In step S13, the crane 30 moves within the yard 80 under the control of the crane controller 20, and the camera 50 photographs the mark 81 while the crane 30 is moving. In step S14 (image acquisition step), the image acquisition unit 111 acquires a plurality of images captured by the camera 50, and stores the acquired captured images in the memory unit 12.

[0056] In step S15 (image selection step), the image selection unit 112 selects a non-blurred image from among the multiple images stored in the storage unit 12. That is, the image selection unit 112 determines whether each of the multiple images stored in the storage unit 12 is a blurred image, and selects an image determined to be a non-blurred image.

[0057] In step S16, image selection unit 112 checks the number of images selected in step S15 (i.e., the number of non-blurred images). As an example, image selection unit 112 determines that the number of images is sufficient if the number of images is equal to or greater than a predetermined threshold, and determines that the number of images is insufficient if the number of images is less than the threshold. If the check result is OK (OK in step S16), image selection unit 112 proceeds to processing of step S17. On the other hand, if the check result is NG (NG in step S16), image selection unit 112 proceeds to processing of step S21.

[0058] In step S17 (feature calculation step), the feature calculation unit 113 calculates the feature amount of the image selected by the image selection unit 112. As an example, the feature calculation unit 113 calculates the center of gravity and the inclination of the mark 81 included in each image for each image selected by the image selection unit 112.

[0059] In step S18 (abnormality determination step), the abnormality determination unit 114 determines an abnormality in at least one of the position, posture, and trajectory of the crane 30 based on the feature amount calculated by the feature calculation unit 113 and the reference feature amount D2 calculated from the reference image, and outputs the determination result. As an example, the abnormality determination unit 114 selects a reference feature amount corresponding to the position of the crane 30 from the multiple reference feature amounts D2, and determines an abnormality based on the selected reference feature amount and the feature amount calculated by the feature calculation unit 113.

[0060] 8 to 10 are diagrams showing an example of the judgment condition referred to by the abnormality judgment unit 114. FIG. 8 shows an example of the judgment condition for the position of the center of gravity of the mark 81 when the position of the crane 30 is "500". In FIG. 8, the horizontal axis indicates the x coordinate of the center of gravity of the mark 81, and the vertical axis indicates the y coordinate of the center of gravity of the mark 81. In the example of FIG. 8, when the coordinate of the center of gravity calculated by the feature calculation unit 113 is included in the area A1, the abnormality judgment unit 114 judges that the state of the crane 30 is normal. On the other hand, when the coordinate of the center of gravity calculated by the feature calculation unit 113 is not included in the area A1, the abnormality judgment unit 114 judges that the state of the crane 30 is abnormal. The information indicating the area A1 is an example of a reference feature amount according to the present disclosure.

[0061] FIG. 9 shows an example of a judgment condition for the position of the center of gravity of mark 81 when the position of crane 30 is "300". In FIG. 9, the horizontal axis indicates the x-coordinate of the center of gravity of mark 81, and the vertical axis indicates the y-coordinate of the center of gravity of mark 81. In the example of FIG. 9, when the coordinates of the center of gravity calculated by feature calculation unit 113 are included in area A2, abnormality judgment unit 114 judges that the state of crane 30 is normal. On the other hand, when the coordinates of the center of gravity calculated by feature calculation unit 113 are not included in area A2, abnormality judgment unit 114 judges that the state of crane 30 is abnormal. Information indicating area A2 is an example of a reference feature amount according to the present disclosure.

[0062] As shown in FIGS. 8 and 9, different judgment conditions are set in advance depending on the position of the crane 30, and the abnormality judgment unit 114 judges the state of the crane using the judgment condition corresponding to the position of the crane 30.

[0063] FIG. 10 shows an example of a judgment condition related to the inclination of mark 81. In FIG. 10, the horizontal axis indicates the x-coordinate of the center of gravity of mark 81, and the vertical axis indicates the inclination of mark 81. In the example of FIG. 10, when a plot indicating the x-coordinate of the center of gravity and the inclination calculated by feature calculation unit 113 is included in area A3, abnormality judgment unit 114 judges that the state of crane 30 is abnormal. On the other hand, when a plot indicating the x-coordinate of the center of gravity and the inclination calculated by feature calculation unit 113 is not included in area A3, abnormality judgment unit 114 judges that the state of crane 30 is normal. Information indicating area A3 is an example of a reference feature amount according to the present disclosure.

[0064] 7, the abnormality determination unit 114 checks the counter D5 for each reference position, and if the number of abnormalities detected at each reference position is equal to or greater than a threshold, determines that the determination result for that reference position is abnormal. The abnormality determination unit 114 stores the determination result for each reference position in the storage unit 12 as diagnosis result data D4.

[0065] Furthermore, in step S20, the abnormality determination unit 114 collects statistics on the determination results for each position and performs a statistical determination for the entire area traveled by the crane 30. For example, when abnormalities are detected at a plurality of consecutive reference positions, the abnormality determination unit 114 may notify that there is a possibility of an abnormality in the camera 50. An abnormality in the camera 50 is, for example, an abnormality in which the camera 50 is not properly fixed to the crane 30, such as the camera 50 being tilted.

[0066] In step S21, the image selection unit 112 stores in the storage unit 12 diagnosis result data D4 indicating a diagnosis result that the number of images is insufficient.

[0067] In step S22, abnormality determination unit 114 determines whether to output an alarm based on diagnosis result data D4. As an example, abnormality determination unit 114 determines to output an alarm when diagnosis result data D4 stored in memory unit 12 contains information indicating an abnormality. On the other hand, when diagnosis result data D4 does not contain information indicating an abnormality, abnormality determination unit 114 determines not to output an alarm. If an alarm is to be output (YES in step S22), abnormality determination unit 114 proceeds to processing of step S23. On the other hand, if an alarm is not to be output (NO in step S22), abnormality determination unit 114 proceeds to processing of step S24.

[0068] In step S23, the abnormality determination unit 114 outputs an alarm based on the diagnosis result data D4. As an example, the abnormality determination unit 114 may output information for displaying an alarm screen on the operation device 60, or may output information for outputting an alarm sound. The operation device 60 displays an alarm screen on a display device or outputs an alarm sound based on information received from the information processing device 10.

[0069] The information output by the abnormality determination unit 114 in step S23 includes, for example, information indicating the possibility of an abnormality in at least one of the parts related to the crane 30 and the entire rail 90. In other words, when the abnormality determination unit 114 determines an abnormality at a plurality of consecutive positions, for example, the abnormality determination unit 114 outputs information indicating the possibility of an abnormality in at least one of the parts related to the entire rail 90 on which the crane 30 travels (all or part) and the crane 30. Here, the part related to the entire rail 90 is, for example, a building, the entire rail 90, or a part of the rail 90. When abnormalities are determined to be present continuously at a plurality of consecutive positions, an abnormality may occur in the crane 30, but an abnormality affecting the entire rail 90 may also occur. Therefore, for example, the abnormality determination unit 114 outputs both information indicating the possibility of an abnormality in the crane 30 and information indicating the possibility of an abnormality in the rail 90.

[0070] Moreover, the information output by the abnormality determination unit 114 in step S23 includes, as an example, information indicating the possibility of an abnormality in the portion determined to be abnormal in the rail 90. In other words, as an example, when the abnormality determination unit 114 determines an abnormality at each position, it outputs information indicating the possibility of an abnormality in the portion determined to be abnormal in the rail 90.

[0071] In step S24, abnormality determination unit 114 determines whether to end the process. If the process is to be ended (YES in step S24), abnormality determination unit 114 ends the process. On the other hand, if the process is not to be ended (NO in step S24), abnormality determination unit 114 returns to the process in step S12.

[0072] By repeating the processes of steps S12 to S24, the abnormality determination unit 114 performs the above-mentioned determination process for a plurality of reference positions (step S18) and outputs the determination results (step S23), as well as collating statistics on the determination results for each position (step S20) and outputting the statistical results (step S23). In other words, the abnormality determination unit 114 executes a first output process of judging an abnormality in the crane 30 at a plurality of positions and outputting the determination results for each position, and a second output process of collating statistics on the determination results for each position and outputting the statistical results.

[0073] <3. Effects of the condition diagnosis support system> As described above, according to this embodiment, the image selection unit 112 selects non-blurred images from the images captured at each of a plurality of reference positions, and the feature calculation unit 113 calculates feature amounts of the selected captured images. Furthermore, the abnormality determination unit 114 determines an abnormality in at least one of the position, posture, and trajectory of the crane 30 based on the feature amounts calculated by the feature calculation unit 113 and the reference feature amounts calculated from the reference image, and outputs the determination result.

[0074] When a camera is installed on an overhead crane such as the crane 30 according to this embodiment, the camera is likely to be blurred due to vibrations caused by the travel of the crane 30. In contrast, in this embodiment, blurred images are not used to diagnose the condition of the crane 30, etc., so that abnormalities in the crane 30, etc. can be more appropriately determined.

[0075] According to this embodiment, the reference feature D2 for determining the state of the crane 30, etc., for each of the plurality of reference positions is prepared in advance, so that the determination at each reference position can be made more appropriately. Also, in this embodiment, the center of gravity is calculated as the feature of the mark 81, so that the processing load related to the calculation of the feature can be reduced.

[0076] [Modifications] (Variation 1) In the above embodiment, the case where the traveling object to be judged for an abnormality is a crane 30 has been described, but the traveling object according to the present disclosure is not limited to a crane. For example, the traveling object according to the present disclosure may be a transport device that has a moving mechanism such as wheels or caterpillar tracks and transports an article by autonomous travel.

[0077] (Variation 2) In the above-described embodiment, the condition diagnosis support system 1 includes the information processing device 10 and the crane controller 20, and the information processing device 10 includes the image acquisition unit 111, the image selection unit 112, the feature calculation unit 113, and the abnormality determination unit 114. The functional configuration of the condition diagnosis support system according to the present disclosure is not limited to the configuration exemplified in the above-described embodiment. For example, the functional division between the information processing device 10 and the crane controller 20 may be other than that shown in the above embodiment, and more specifically, for example, the abnormality determination unit 114 may be provided in the crane controller 20 instead of the information processing device 10. In addition, the configuration may be such that the functions of the information processing device 10 are divided and implemented by a plurality of devices.

[0078] [Software implementation example] The functions of the information processing device 10 can be realized by a program for causing a computer to function as the device, and a program for causing a computer to function as each control block of the device (particularly each part included in the control unit 11).

[0079] In this case, the information processing device 10 includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the above programs. The functions described in the above embodiments are realized by executing the above programs using the control device and the storage device.

[0080] The above program may be recorded in one or more computer-readable recording media, not temporarily. The recording media may or may not be included in the information processing device 10. In the latter case, the above program may be supplied to the information processing device 10 via any wired or wireless transmission medium.

[0081] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0082] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0083] 1 Condition diagnosis support system 10. Information processing device 20 Crane Controller 30 Crane 50 Camera 60 Operating device 70 Slab 80 yards 81 marks 90 Rail 111 Image acquisition unit 112 Image Selection Section 113 Feature Calculation Unit 114 Abnormality determination section

Claims

1. an image acquisition unit that acquires a plurality of images captured at a plurality of positions by an image capture device installed on the traveling body; an image selection unit that selects a non-blurred image from among the plurality of images; a feature calculation unit that calculates a feature amount of the image selected by the image selection unit; an abnormality determination unit that determines an abnormality in at least one of a position, a posture, and a trajectory of the vehicle based on the feature amount calculated by the feature calculation unit and a reference feature amount calculated from a reference image, and outputs a determination result; An abnormality determination device comprising:

2. The image acquisition unit acquires an image obtained by the photographing device photographing a predetermined subject, the feature amount includes at least one of a center of gravity and a tilt of the subject in the image; The abnormality determination device according to claim 1 .

3. a storage unit that stores the reference feature amount for each of a plurality of reference positions, the abnormality determination unit selects a reference feature corresponding to a position of the vehicle from among a plurality of reference feature amounts, and determines the abnormality based on the selected reference feature amount and the feature amount calculated by the feature calculation unit. The abnormality determination device according to claim 1 or 2.

4. The abnormality determination unit a first output process for determining an abnormality in the moving object at a plurality of positions and outputting a determination result for each position; and a second output process of collecting statistics of the determination results for each position and outputting the statistical results; The abnormality determination device according to claim 3 .

5. When the abnormality determination unit determines that an abnormality exists at a plurality of consecutive positions, the abnormality determination unit outputs information indicating a possibility of an abnormality in at least one of a portion related to the entire road on which the running body runs and the running body. The abnormality determination device according to claim 4.

6. When the abnormality determination unit determines that an abnormality exists at each position, the abnormality determination unit outputs information indicating a possibility of an abnormality in the portion determined to be abnormal in the road on which the traveling object travels. The abnormality determination device according to claim 4.

7. A traveling body that transports an article; A photographing device installed on the moving body; an image acquisition unit that acquires a plurality of images captured by the photographing device; an image selection unit that selects a non-blurred image from among the plurality of images; a feature calculation unit that calculates a feature amount of the image selected by the image selection unit; an abnormality determination unit that determines an abnormality in at least one of a position, a posture, and a trajectory of the vehicle based on the feature amount calculated by the feature calculation unit and a reference feature amount calculated from a reference image, and outputs a determination result; An abnormality determination system comprising:

8. an image acquiring step of acquiring a plurality of images captured by an image capturing device installed on the traveling body; an image selection step of selecting an image that is not a blurred image from among the plurality of images; a feature calculation step of calculating a feature amount of the image selected in the image selection step; an abnormality determination step of determining an abnormality in at least one of a position, a posture, and a trajectory of the vehicle based on the feature amount calculated in the feature calculation step and a reference feature amount calculated from a reference image, and outputting a determination result; The abnormality determination method is executed by an information processing device.

Images