Intrusion Detection System

Abstract

To provide an intrusion detection system capable of accurately detecting intrusion of an object into a work area, except for a work machine working in the work area.SOLUTION: An intrusion detection system includes a GNSS sensor that acquires the position of a work machine 20 that is working within a work area 70, a LiDAR 2 that is provided outside the work area 70 and acquires point cloud data indicating the distance to an object located inside or outside the work area 70, position calculation means for calculating the position of each point of the point cloud data, identifying means for identifying, as specific data, a portion corresponding to the work machine 20 from the point cloud data based on the position of the work machine 20 and the position of each point of the point cloud data, and detection means for detecting, based on point cloud data other than the specific data, intrusion of an object into the work area 70.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an intrusion detection system that detects an object other than a working machine working in a work area from entering the work area.

Background Art

[0002] Patent Document 1 discloses an interference prevention device that sets first to sixth regions around a working machine and determines the presence or absence of a person in each of the first to sixth regions. In Patent Document 1, the presence or absence of a person is determined based on information from an object sensor provided on the working machine.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, when detecting from the outside of the work area that an object other than the working machine working in the work area has entered the work area, it is impossible to distinguish between the working machine working in the work area and the object that has entered the work area, and the working machine working in the work area may be erroneously detected as an object that has entered the work area.

[0005] An object of the present invention is to provide an intrusion detection system capable of accurately detecting an object other than a working machine working in a work area from entering the work area.

Means for Solving the Problems

[0006] The present invention is characterized by having: mechanical position acquisition means for acquiring the position of a working machine during work within a work area; a point cloud data acquisition unit provided outside the work area for acquiring point cloud data indicating the distances to objects located inside and outside the work area; position calculation means for calculating the positions of the respective points of the point cloud data; identification means for identifying, as specific data, a portion corresponding to the working machine within the work area from among the point cloud data based on the position of the working machine and the positions of the respective points of the point cloud data; and detection means for detecting that an object has entered the work area based on the point cloud data other than the specific data.

Effect of the Invention

[0007] According to the present invention, a portion corresponding to a working machine during work within a work area is identified as specific data from among the point cloud data. Then, based on the point cloud data other than the specific data, it is detected that an object has entered the work area. Among the point cloud data, the portion corresponding to the working machine during work within the work area has been identified as specific data, so the point cloud data other than the specific data that has entered the work area is that of an object other than the working machine during work within the work area. Thereby, it is possible to accurately detect that an object other than the working machine during work within the work area has entered the work area.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0009] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

[0010] [First Embodiment] (Configuration of the Work Machine) The intrusion detection system according to the first embodiment of the present invention detects an object other than the work machine working in the work area from entering the work area. As shown in FIG. 1 which is a side view of the work machine 20, the work machine 20 is a machine that performs work with the attachment 30, for example, a hydraulic excavator. The work machine 20 has a machine body 24 including a lower traveling body 21 and an upper revolving body 22, an attachment 30, and a cylinder 40.

[0011] The lower traveling body 21 is a part that makes the work machine 20 travel and includes, for example, crawlers. The upper revolving body 22 is rotatably attached to the upper part of the lower traveling body 21 via a slewing device 25. A cab (driver's cab) 23 is provided at the front of the upper revolving body 22.

[0012] The attachment 30 is attached to the upper revolving body 22 so as to be rotatable in the vertical direction. The attachment 30 includes a boom 31, an arm 32, and a bucket 33. The boom 31 is attached to the upper revolving body 22 so as to be rotatable (pivotable) in the vertical direction. The arm 32 is attached to the boom 31 so as to be rotatable in the vertical direction. The bucket 33 is attached to the arm 32 so as to be rotatable in the front-rear direction. The bucket 33 is a part that performs operations such as excavation, leveling, and scooping of earth and sand (the object to be transported). Note that the object to be transported held by the bucket 33 is not limited to earth and sand, and may be stones or waste (such as industrial waste).

[0013] The cylinder 40 can rotate the attachment 30 hydraulically. The cylinder 40 is a hydraulic telescopic cylinder. The cylinder 40 includes a boom cylinder 41, an arm cylinder 42, and a bucket cylinder 43.

[0014] The boom cylinder 41 rotates the boom 31 with respect to the upper slewing body 22. The base end portion of the boom cylinder 41 is rotatably attached to the upper slewing body 22. The tip end portion of the boom cylinder 41 is rotatably attached to the boom 31.

[0015] The arm cylinder 42 rotates the arm 32 with respect to the boom 31. The base end portion of the arm cylinder 42 is rotatably attached to the boom 31. The tip end portion of the arm cylinder 42 is rotatably attached to the arm 32.

[0016] The bucket cylinder 43 rotates the bucket 33 with respect to the arm 32. The base end portion of the bucket cylinder 43 is rotatably attached to the arm 32. The tip end portion of the bucket cylinder 43 is rotatably attached to a link member 34 that is rotatably attached to the bucket 33.

[0017] The work machine 20 also has an angle sensor 52 and an inclination angle sensor 60.

[0018] The angle sensor 52 detects the slewing angle of the upper slewing body 22 with respect to the lower traveling body 21. The angle sensor 52 is, for example, an encoder, a resolver, or a gyro sensor. In the present embodiment, the slewing angle of the upper slewing body 22 when the front of the upper slewing body 22 coincides with the front of the lower traveling body 21 is set to 0°.

[0019] The inclination angle sensor 60 detects the posture of the attachment 30. The inclination angle sensor 60 includes a boom inclination angle sensor 61, an arm inclination angle sensor 62, and a bucket inclination angle sensor 63.

[0020] The boom tilt angle sensor 61 is attached to the boom 31 and detects the attitude of the boom 31. The boom tilt angle sensor 61 is a sensor that acquires the tilt angle of the boom 31 with respect to the horizontal line, and is, for example, an inclination (acceleration) sensor or the like. Note that the boom tilt angle sensor 61 may be a rotation angle sensor that detects the rotation angle of the boom foot pin (base end of the boom), or a stroke sensor that detects the stroke amount of the boom cylinder 41.

[0021] The arm tilt angle sensor 62 is attached to the arm 32 and detects the attitude of the arm 32. The arm tilt angle sensor 62 is a sensor that acquires the tilt angle of the arm 32 with respect to the horizontal line, and is, for example, an inclination (acceleration) sensor or the like. Note that the arm tilt angle sensor 62 may be a rotation angle sensor that detects the rotation angle of the arm connecting pin (base end of the arm), or a stroke sensor that detects the stroke amount of the arm cylinder 42.

[0022] The bucket tilt angle sensor 63 is attached to the link member 34 and detects the attitude of the bucket 33. The bucket tilt angle sensor 63 is a sensor that acquires the tilt angle of the bucket 33 with respect to the horizontal line, and is, for example, an inclination (acceleration) sensor or the like. Note that the bucket tilt angle sensor 63 may be a rotation angle sensor that detects the rotation angle of the bucket connecting pin (base end of the bucket), or a stroke sensor that detects the stroke amount of the bucket cylinder 43.

[0023] As shown in FIG. 2, which is a diagram showing the working machine 20 working in the working area, the working machine 20 works in the working area 70. The intrusion detection system 1 detects from outside the working area 70 that an object other than the working machine 20 working in the working area 70 has intruded into the working area 70. In this case, it is necessary to distinguish between the working machine 20 working in the working area 70 and an object other than the working machine 20 that has intruded into the working area 70.

[0024] (Circuit Configuration of Intrusion Detection System and Working Machine) As shown in FIG. 3 which is a circuit diagram of the intrusion detection system 1 and the working machine 20, the working machine 20 includes a working machine side controller 11, a storage device 12, a GNSS sensor 13, and a working machine side communication device 14.

[0025] Information regarding the turning angle (posture) of the upper slewing body 22 with respect to the lower traveling body 21 detected by the angle sensor 52 is input to the working machine side controller 11. Further, information regarding the posture of the boom 31 detected by the boom tilt angle sensor 61 is input to the working machine side controller 11. Further, information regarding the posture of the arm 32 detected by the arm tilt angle sensor 62 is input to the working machine side controller 11. Further, information regarding the posture of the bucket 33 detected by the bucket tilt angle sensor 63 is input to the working machine side controller 11.

[0026] The storage device 12 stores information regarding the dimensions of the working machine 20 (dimensions of the attachment 30) and the shape of the working machine 20 (shape of the attachment 30).

[0027] The GNSS (Global Navigation Satellite System) sensor (machine position acquisition means) 13 acquires the position of the working machine 20 during operation within the work area. The GNSS sensor 13 is a positioning sensor and acquires the position of the working machine 20 in the global coordinate system. Note that instead of the GNSS sensor 13, a positioning sensor such as a GPS sensor or a distance measuring sensor such as a total station may be used.

[0028] The working machine side communication device 14 can communicate with the communication device 3 of the intrusion detection system 1 described later.

[0029] The intrusion detection system 1 includes a LiDAR 2, a communication device 3, and a controller 5.

[0030] As shown in FIG. 2, a LiDAR (Light Detection and Ranging or Laser Imaging Detection and Ranging) (point cloud data acquisition unit) 2 is provided outside the work area 70. The LiDAR 2 acquires point cloud data indicating the distances from the position where the LiDAR 2 is attached to the objects located inside and outside the work area 70. An example of the point cloud data acquired by the LiDAR 2 is shown in FIG. 4. The inside of the cylinder illustrated in the middle of the figure is the work area 70.

[0031] Returning to FIG. 3, the communication device 3 can communicate with the work machine side communication device 14 of the work machine 20. The communication device 3 receives, from the work machine 20, information regarding the position of the work machine 20 acquired by the GNSS sensor 13. Further, the communication device 3 receives, from the work machine 20, information regarding the dimensions (dimensions of the attachment 30) and the shape (shape of the attachment 30) of the work machine 20 stored in the storage device 12. Further, the communication device 3 receives, from the work machine 20, information regarding the posture of the work machine 20 (posture of the upper swing body 22, posture of the attachment 30) detected by the angle sensor 52 and the inclination angle sensors 60 (boom inclination angle sensor 61, arm inclination angle sensor 62, bucket inclination angle sensor 63).

[0032] The controller 5 includes a coordinate conversion unit 81, a 3D model generation unit 82, a work machine identification unit 83, and an intrusion detection unit 84.

[0033] The coordinate conversion unit (position calculation means) 81 calculates the position of each point of the point cloud data acquired by the LiDAR 2. Specifically, the coordinate conversion unit 81 calculates the position (three-dimensional coordinates) of each point of the point cloud data in the global coordinate system using the position (coordinates) of the global coordinate system where the LiDAR 2 is attached and the distance from the LiDAR 2 to each point of the point cloud data.

[0034] The 3D model generation unit (3D shape data calculation means) 82 calculates the 3D shape data of the working machine 20 based on the information on the dimensions, shape, and posture of the working machine 20 received by the communication device 3. An example of the 3D shape data 75 of the working machine 20 calculated by the 3D model generation unit 82 is shown in FIG. 5.

[0035] Returning to FIG. 3, the working machine identification unit (identification means) 83 identifies, as specific data, the portion corresponding to the working machine 20 from the point cloud data based on the position of the working machine 20 and the positions of the respective points of the point cloud data. First, the working machine identification unit (superposition means) 83 superimposes the 3D shape data calculated by the 3D model generation unit 82 on the point cloud data at the position of the working machine 20. In FIG. 4, in the region surrounded by the dotted line 71, the 3D shape data 75 shown in FIG. 5 is superimposed on the point cloud data. The working machine identification unit 83 identifies, as specific data, the portion of the point cloud data where the 3D shape data 75 overlaps. This makes it possible to know which portion of the point cloud data corresponds to the working machine 20.

[0036] Returning to FIG. 3, the intrusion detection unit (detection means) 84 detects that an object has intruded into the working area based on the point cloud data other than the specific data. Since the portion of the point cloud data corresponding to the working machine 20 operating in the working area 70 is identified as specific data, the point cloud data other than the specific data that has intruded into the working area 70 belongs to an object other than the working machine 20 operating in the working area 70. Thereby, it is possible to accurately detect that an object other than the working machine 20 operating in the working area 70 has intruded into the working area 70.

[0037] (Effect) As described above, according to the intrusion detection system 1 according to the present embodiment, from the point cloud data, a portion corresponding to the working machine 20 that is working within the work area 70 is specified as specific data. Then, based on the point cloud data other than the specific data, it is detected that an object has invaded the work area 70. Among the point cloud data, the portion corresponding to the working machine 20 that is working within the work area 70 is specified as specific data. Therefore, the point cloud data other than the specific data that has invaded the work area 70 belongs to an object other than the working machine 20 that is working within the work area 70. Thereby, it is possible to accurately detect that an object other than the working machine 20 that is working within the work area 70 has invaded the work area 70.

[0038] Also, the machine position acquisition means is a positioning sensor or a distance measuring sensor such as the GNSS sensor 13. Thereby, the position of the working machine 20 that is working within the work area 70 can be accurately acquired. Therefore, the specific data can be accurately specified from the point cloud data.

[0039] Also, among the point cloud data, a portion where the three-dimensional shape data 75 of the working machine 20 overlaps is specified as specific data. By using the three-dimensional shape data 75 of the working machine 20, the specific data can be accurately specified.

[0040] [Second Embodiment] Next, the intrusion detection system 101 of the second embodiment will be described with reference to the drawings. Note that the description of the configuration common to the first embodiment and the effects thereof will be omitted, and mainly, the differences from the first embodiment will be described. Note that the same members as those in the first embodiment are denoted by the same reference numerals as those in the first embodiment.

[0041] In the first embodiment, the 3D model generation unit 82 calculates the three-dimensional shape data 75 of the working machine 20, and the working machine identification unit 83 identifies the specific data by superimposing the calculated three-dimensional shape data 75 on the point cloud data. In contrast, in the present embodiment, the point cloud data acquired by the LiDAR 2 is clustered into cluster point clouds, and the cluster point cloud that matches the position of the working machine 20 is identified as the specific data.

[0042] (Circuit Configuration of Intrusion Detection System and Working Machine) As shown in FIG. 6, which is a circuit diagram of the intrusion detection system 101 and the working machine 20, the controller 105 of the intrusion detection system 101 includes a clustering unit 85, a working machine identification unit 83, and an intrusion detection unit 84.

[0043] The clustering unit (clustering means) 85 clusters the point cloud data acquired by the LiDAR 2 into cluster point clouds. An example of the cluster point clouds 76 located inside and outside the working area 70 is shown in FIG. 7. The clustering unit (position calculation means) 85 calculates the position of the cluster point cloud 76 in the global coordinate system using the position (coordinates) of the global coordinate system where the LiDAR 2 is attached and the distance from the LiDAR 2 to the cluster point cloud 76.

[0044] The working machine identification unit 83 identifies the cluster point cloud that matches the position of the working machine 20 acquired by the GNSS sensor 13 as the specific data. The intrusion detection unit 84 detects that an object has invaded the working area 70 based on the point cloud data other than the specific data.

[0045] In this way, by clustering the point cloud data into cluster point clouds, it is easier to identify the specific data. Also, since it is not necessary to calculate the three-dimensional shape data 75 of the working machine 20, it is less affected by noise. Also, even for working machines 20 with different dimensions, the specific data can be preferably identified by clustering the point cloud data.

[0046] The rest is the same as in the first embodiment, so the description thereof is omitted.

[0047] (Effect) As described above, according to the intrusion detection system 101 according to the present embodiment, the cluster point group that matches the position of the work machine 20 is specified as specific data. By clustering the point cloud data into a cluster point group, it is possible to easily specify the specific data. Further, since it is not necessary to calculate the three-dimensional shape data 75 of the work machine 20, it is less affected by noise. Further, even for work machines 20 with different dimensions, the specific data can be suitably specified by clustering the point cloud data.

[0048] [Third Embodiment] Next, the intrusion detection system 201 of the third embodiment will be described with reference to the drawings. Note that the description of the configuration common to the second embodiment and the effects achieved thereby will be omitted, and mainly the differences from the second embodiment will be described. Note that the same members as those in the second embodiment are denoted by the same reference numerals as those in the first embodiment.

[0049] In the first and second embodiments, the specific data was specified using the information on the position of the work machine 20 acquired by the GNSS sensor 13. In contrast, in the present embodiment, the position of the work machine 20 is acquired using the camera 4 (see FIG. 2).

[0050] (Circuit Configuration of Intrusion Detection System and Work Machine) As shown in FIG. 8, which is a circuit diagram of the intrusion detection system 201 and the work machine 20, the intrusion detection system 201 includes a LiDAR 2, a camera 4, and a controller 205. The controller 205 includes a clustering unit 85, a machine position calculation unit 86, a work machine specification unit 83, and an intrusion detection unit 84. The camera 4 and the machine position calculation unit 86 constitute a machine position acquisition means.

[0051] As shown in FIG. 1, a target 90 capable of acquiring the position of the working machine 20 from outside the working machine 20 is provided on the upper swing body 22 of the working machine 20. In the present embodiment, the target 90 is an AR marker. An AR marker is a sign on which an image to be superimposed on the real space in AR (augmented reality) and identification information for designating the position thereof are written. Note that in addition to the information on the position of the working machine 20, the target 90 may be capable of acquiring information such as the dimensions of the working machine 20 from outside the working machine 20.

[0052] As shown in FIG. 2, the camera (imaging means) 4 is provided outside the work area 70. The camera 4 images the target 90 provided on the upper swing body 22.

[0053] Returning to FIG. 8, the machine position calculation unit (machine position calculation means) 86 calculates the position of the working machine 20 based on the target 90 imaged by the camera 4. The machine position calculation unit 86 calculates the position of the target 90 in the global coordinate system using the position (coordinates) of the global coordinate system to which the camera 4 is attached and the distance from the camera 4 to the target 90. At this time, it is not necessary to communicate between the intrusion detection system 201 (outside the working machine 20) and the working machine 20. Therefore, even when the working machine 20 does not mount a communication device, the position of the working machine 20 can be acquired.

[0054] The clustering unit 85 clusters the point cloud data acquired by the LiDAR 2 into cluster point clouds. The working machine identification unit 83 identifies the cluster point cloud that matches the position of the working machine 20 as specific data. The intrusion detection unit 84 detects that an object has intruded into the work area 70 based on the point cloud data other than the specific data.

[0055] The rest is the same as that of the second embodiment, and the description thereof is omitted.

[0056] (Effect) As described above, according to the intrusion detection system 201 according to the present embodiment, the position of the working machine 20 is calculated based on the landmark 90 imaged by the camera 4. At this time, there is no need to communicate between the outside of the working machine 20 and the working machine 20. Therefore, even when the working machine 20 is not equipped with a communication device, the position of the working machine 20 can be acquired.

[0057] As described above, the embodiments of the present invention have been described. However, these are merely examples, and do not particularly limit the present invention. For example, the specific configuration can be appropriately changed in design. In addition, the actions and effects described in the embodiments of the invention are merely a list of the most suitable actions and effects resulting from the present invention, and the actions and effects according to the present invention are not limited to those described in the embodiments of the invention.

Explanation of reference numerals

[0058] 1,101,201 Intrusion detection system 2 LiDAR (point cloud data acquisition unit) 3 Communication device 4 Camera (imaging means) 5,105,205 Controller 11 Working machine side controller 12 Storage device 13 GNSS sensor (machine position acquisition means) 14 Working machine side communication device 20 Working machine 21 Lower traveling body 22 Upper slewing body 23 Cab 24 Machine body 25 Slewing device 30 Attachment 31 Boom 32 Arm 33 Bucket 34 Link member 40 Cylinder 41 Boom cylinder 42 Arm cylinder 43 Bucket cylinder 52 Angle sensor 60 Inclination Angle Sensor 61 Boom Inclination Angle Sensor 62 Arm Inclination Angle Sensor 63 Bucket Inclination Angle Sensor 70 Working Area 71 Dashed Line 75 Three-Dimensional Shape Data 76 Cluster Point Cloud 81 Coordinate Conversion Unit (Position Calculation Means) 82 3D Model Generation Unit (Three-Dimensional Shape Data Calculation Means) 83 Work Machine Identification Unit (Identification Means, Superposition Means) 84 Intrusion Detection Unit (Detection Means) 85 Clustering Unit (Clustering Means, Position Calculation Means) 86 Machine Position Calculation Unit (Machine Position Calculation Means) 90 Mark

Claims

1. Mechanical position acquisition means for acquiring the position of a working machine during operation within a work area, A point cloud data acquisition unit provided outside the work area for acquiring point cloud data indicating the distances to objects located inside and outside the work area, Position calculation means for calculating the position of each point of the point cloud data, Specific means for specifying, as specific data, a portion corresponding to the working machine from among the point cloud data based on the position of the working machine and the positions of the points of the point cloud data, Detection means for detecting that an object has entered the work area based on the point cloud data other than the specific data, An intrusion detection system characterized by comprising the above.

2. The intrusion detection system according to claim 1, wherein the mechanical position acquisition means is a positioning sensor or a distance measuring sensor.

3. The working machine is provided with a mark that enables the position of the working machine to be acquired from outside the working machine, The mechanical position acquisition means Imaging means for imaging the mark, Mechanical position calculation means for calculating the position of the working machine based on the mark imaged by the imaging means, The intrusion detection system according to claim 1, characterized by comprising the above.

4. Three-dimensional shape data calculation means for calculating three-dimensional shape data of the working machine based on the dimensions, shape, and posture of the working machine, Superposition means for superposing the three-dimensional shape data on the point cloud data at the position of the working machine, Comprising The intrusion detection system according to claim 1 or 2, wherein the specific means specifies, as the specific data, a portion of the point cloud data where the three-dimensional shape data overlaps.

5. Clustering means for clustering the point cloud data into cluster point clouds, The position calculation means calculates the position of the cluster point cloud, The intrusion detection system according to any one of claims 1 to 3, wherein the specific means specifies, as the specific data, the cluster point cloud that matches the position of the working machine.

6. The intrusion detection system further comprises a communication device capable of communicating with the working machine, The mechanical position acquisition means is provided on the working machine, The communication device receives information regarding the position of the working machine acquired by the mechanical position acquisition means from the working machine, The intrusion detection system according to claim 1 or 2, wherein the specific means specifies the specific data using information regarding the position of the work machine.

7. The detection means determines that an object other than the work machine that is working within the work area is an object other than the specific data in the point cloud data, and detects the object other than the work machine as an object that has intruded into the work area. The intrusion detection system according to any one of claims 1 to 6.

Images