WO2018101455A1 - 設備巡視システム及び設備巡視方法 - Google Patents
設備巡視システム及び設備巡視方法 Download PDFInfo
- Publication number
- WO2018101455A1 WO2018101455A1 PCT/JP2017/043234 JP2017043234W WO2018101455A1 WO 2018101455 A1 WO2018101455 A1 WO 2018101455A1 JP 2017043234 W JP2017043234 W JP 2017043234W WO 2018101455 A1 WO2018101455 A1 WO 2018101455A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- alignment
- point group
- information
- area
- unit
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 32
- 238000000605 extraction Methods 0.000 claims abstract description 64
- 238000000926 separation method Methods 0.000 claims abstract description 41
- 238000007689 inspection Methods 0.000 claims description 29
- 238000003384 imaging method Methods 0.000 claims description 18
- 239000000284 extract Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 26
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 43
- 230000008859 change Effects 0.000 description 26
- 230000008569 process Effects 0.000 description 14
- 238000006243 chemical reaction Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000005484 gravity Effects 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 8
- 238000012937 correction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013519 translation Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000001483 mobilizing effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60M—POWER SUPPLY LINES, AND DEVICES ALONG RAILS, FOR ELECTRICALLY- PROPELLED VEHICLES
- B60M1/00—Power supply lines for contact with collector on vehicle
- B60M1/12—Trolley lines; Accessories therefor
- B60M1/28—Manufacturing or repairing trolley lines
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0081—On-board diagnosis or maintenance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position
Definitions
- This disclosure relates to an equipment inspection system and an equipment inspection method.
- FIG. 16 shows an example of foreign matter adhesion to the railway facility and damage to the railway facility.
- flying objects 15A such as a plastic bag or clothing adhere to the overhead wire, it causes damage to the passing railway vehicle.
- a part of a member that supports a beam or an overhead line is dropped, there may be a risk to passengers and the public due to deformation or collapse of the equipment. With regard to these failures, at present, maintenance inspectors actually inspect the state around the railway track visually to detect the presence of foreign matter and damage.
- Patent Document 1 discloses an obstacle detection system.
- a three-dimensional sensor is installed in a vehicle, a three-dimensional point cloud of the surrounding environment is acquired while moving on a track, and the vehicle area indicating the region of the vehicle is obtained from the acquired three-dimensional point group.
- Detect obstacles that enter
- the system of Patent Document 1 can detect foreign objects (such as vegetation) that have entered the operating vehicle area, foreign objects outside the operating vehicle area, such as flying objects attached to overhead lines, broken hangers, damaged substation facilities, etc.
- damage to the facility hereinafter simply referred to as “abnormal part” cannot be detected.
- FIG. 17 shows a specific example of a moving object around the track.
- examples of the moving object include a plant 16 ⁇ / b> A that fluctuates in the wind grown around the railway facility, and an automobile 16 ⁇ / b> B that travels on a road adjacent to the railway facility.
- the center of gravity position of the current three-dimensional point cloud is the three-dimensional point cloud when the moving object is not included. It will shift compared to.
- the present disclosure detects a normal location as an abnormal location due to misalignment due to the presence or absence of a moving object when detecting an abnormal location in the surrounding environment of a vehicle moving on a track (for example, a track).
- a track for example, a track.
- the present application includes a plurality of means for solving the above-described problems.
- an imaging device that captures an image of a surrounding environment of a vehicle moving on a track, and a reference alignment for each position on the track.
- a storage device that stores a point cloud and a reference difference extraction point cloud; a registration region separation unit that separates a registration point cloud from a three-dimensional point cloud obtained from the image; and the reference registration point cloud and the position
- An alignment unit that aligns the alignment point group and outputs alignment information; a difference extraction unit that extracts a difference between the three-dimensional point group transformed by the alignment information and the reference difference extraction point group;
- An equipment patrol system is provided.
- a step of photographing an image of a surrounding environment of a vehicle moving on a track by a photographing device, and a registration point from a three-dimensional point group obtained from the image by a registration region separating unit Separating the groups, aligning the reference alignment point group stored in the storage device with the alignment point group by the alignment unit, outputting alignment information, and the difference extraction unit,
- an equipment inspection method including a step of extracting a difference between the three-dimensional point group deformed by the alignment information and a reference difference extraction point group stored in the storage device.
- a normal location when detecting an abnormal location in the surrounding environment of a vehicle moving on a track (for example, a track), a normal location is detected as an abnormal location due to misalignment due to the presence or absence of a moving object. Can be prevented. Further features related to the present disclosure will become apparent from the description of the present specification and the accompanying drawings. Further, problems, configurations and effects other than those described above will be clarified by the description of the following examples.
- FIG. 1 is a diagram illustrating a configuration of an image processing apparatus according to a first embodiment. It is a figure for demonstrating point cloud DB. It is a figure explaining the coordinate calculation conversion method from a distance image to a three-dimensional point group. It is a figure which shows an example of the area
- FIG. 10 is a diagram for explaining a modified example of the first embodiment.
- FIG. 6 is a diagram illustrating a configuration of an image processing apparatus according to a second embodiment. It is a figure for demonstrating area
- 10 is an example of a flowchart for explaining processing of an alignment region separation unit according to the second embodiment.
- FIG. 10 is a diagram illustrating a configuration of an image processing apparatus according to a third embodiment.
- 12 is an example of a flowchart for explaining processing of an alignment region selection unit according to Embodiment 3; It is a figure explaining the foreign material adhesion to a railroad facility, and the damage of a railroad facility. It is a specific example of the moving object around a track.
- the following embodiment relates to a technique for automatically detecting an abnormal part (for example, a foreign object or a damaged facility) in the surrounding environment of a vehicle moving on a track.
- the track includes, for example, a track and a guide rail.
- the vehicle includes various vehicles that travel on a track such as a business vehicle, a test vehicle, and a maintenance vehicle.
- FIG. 1 is a diagram illustrating the configuration of a railway facility patrol system according to the first embodiment.
- the railway facility patrol system includes a vehicle 100 and a ground station 160.
- the vehicle 100 includes an imaging device 110, an image processing device 120, a vehicle position specifying device 130, a storage (storage device) 140, and a communication device 150.
- the vehicle 100 may be any vehicle that can travel along the railroad track, and may be not only a business vehicle but also a test vehicle or a railroad vehicle.
- the imaging device 110 acquires the distance image 200 of the surrounding environment of the vehicle 100 and outputs the distance image 200 to the image processing device 120.
- the imaging device 110 only needs to include a device that can acquire a distance image, such as a stereo camera or a TOF (Time-of-Flight) three-dimensional sensor.
- a device that can acquire a distance image such as a stereo camera or a TOF (Time-of-Flight) three-dimensional sensor.
- the detection distance of the photographing apparatus 110 is 0 to several tens of meters, and as an example, is 0 to 30 m.
- the imaging device 110 captures a forward range of the traveling direction of the vehicle 100 .
- the subject to be photographed by the photographing device 110 is not limited to the front range of the vehicle 100, and by appropriately changing the installation position of the photographing device 110, an arbitrary range (for example, with respect to the traveling direction) of all directions of the vehicle 100.
- a rear range, a horizontal range orthogonal to the traveling direction, etc.) can be set.
- the image processing device 120 receives the distance image 200 from the imaging device 110 as input information, receives the vehicle position information 210 from the vehicle position specifying device 130 as input information, and acquires reference three-dimensional point cloud information 230 from the storage 140.
- the image processing apparatus 120 executes a change area detection process based on the input information and outputs the change area information 220 to the communication apparatus 150.
- the change area is an area that is detected by comparing the past normal 3D point cloud and the current 3D point cloud, and regards this change area as an abnormal part (foreign matter or damaged part). Can do.
- the vehicle position specifying device 130 specifies the current position of the vehicle 100 using a GPS (Global Positioning System) device, an IMU (Inertial Measurement Unit) device, and the like, and outputs the vehicle position information 210 to the image processing device 120.
- the storage 140 holds information read by the image processing apparatus 120 as a database.
- the current position of the vehicle is specified by latitude / longitude and direction, but the position information of the vehicle is not limited to this.
- As the vehicle position information information on the distance from the starting point of the track (in kilometers) and information on each line (up, down, main line, sub main line, etc.) may be used.
- the communication device 150 receives the change area information 220 as input information and transmits it as a change area detection signal 240 to the ground station 160.
- a general line such as a mobile phone network may be used, or another network may be used.
- the processing device (not shown) of the ground station 160 receives the change area detection signal 240 transmitted from the communication device 150 of the vehicle 100 and presents the abnormal part to the maintenance inspector via the display device (for example, a display). May be performed.
- the ground station 160 may be provided with a document generation device (not shown), and by laying out information such as an abnormal location, a discovery date / time, etc. on a document via the document generation device, Business documents such as repair work instructions may be automatically generated.
- FIG. 2 is a diagram illustrating the configuration of the image processing apparatus according to the first embodiment.
- the image processing apparatus 120 includes a point group conversion unit 310, a registration region separation unit 320, a registration unit 330, a neighborhood search unit 340, and a difference extraction unit 350.
- the image processing apparatus 120 may be realized using, for example, a general-purpose computer. Each processing unit of the image processing apparatus 120 may be realized as a function of a program executed on a computer.
- the computer includes at least a processor such as a CPU (Central Processing Unit) and a storage unit such as a memory.
- the processing of the image processing apparatus 120 may be realized by storing a program code corresponding to each processing unit in a memory and executing a program code by a processor.
- the point cloud database (Database) 300 is a database mounted on the storage 140.
- FIG. 3 is an example of the point cloud DB 300.
- the point cloud DB 300 includes position information 500 and reference 3D point cloud information 540 as configuration items.
- the point cloud DB 300 includes past point cloud information that has been confirmed to be in a normal state at each position (position information 500) on the track.
- the point cloud DB 300 is a DB that stores reference information related to the surrounding environment of the vehicle 100 that is determined to be in a normal state.
- the reference three-dimensional point group information 540 includes a reference alignment point group 510 and a reference difference extraction point group 520.
- the reference alignment point group 510 is a point group used in the alignment process in the alignment unit 330.
- the reference alignment point group 510 may be a point group acquired from images of the photographing device 110 at each position on the track when traveling on the track in the past.
- the reference alignment point group 510 includes point groups acquired in the region 550 of FIG. 5 at each position on the track when the vehicle 100 has traveled on the track in the past.
- the reference difference extraction point group 520 is a point group serving as a reference for detecting a change area.
- the reference difference extraction point group 520 is a point group acquired from the image of the imaging device 110 at each position on the track when the vehicle 100 has traveled on the track in the past.
- the reference alignment point group 510, the reference difference extraction point group 520, and the position information 500 of the shooting location are associated with each other and held.
- Position information 500 holds each position on the track as latitude / longitude and direction information.
- Each of the reference alignment point group 510 and the reference difference extraction point group 520 holds a set of XYZ coordinates.
- information distance (km) from the starting point of the track) and information for each line (up, down, main line, sub main line, etc.) may be used.
- the point cloud DB 300 may be created from design information (for example, CAD data) of the track and its surrounding environment. According to this configuration, it is possible to detect the change area based on the design information.
- design information for example, CAD data
- the point cloud DB 300 may be applied to a purpose of checking whether the surrounding environment is constructed as designed by running the vehicle 100 after constructing the track and the surrounding environment. it can. This is because the change area information 220 detected by the image processing device 120 represents a difference from the design information, and thereby, a location that is not built as designed can be detected.
- the point group conversion unit 310 converts the distance image 200 input from the imaging device 110 into a three-dimensional point group 400, and outputs the three-dimensional point group 400 to the alignment region separation unit 320.
- FIG. 4 is a diagram for explaining a coordinate calculation conversion method from the distance image 200 to the three-dimensional point group 400.
- Each pixel of the distance image 200 is given by the distance L to the object, the angle ⁇ on the ZY plane from the center of the image, and the angle ⁇ on the XZ plane.
- the point group conversion unit 310 performs a conversion process from the distance image 200 to the coordinates of each point of the three-dimensional point group 400 based on Equation 1.
- the registration region separation unit 320 receives the three-dimensional point group 400 from the point group conversion unit 310 as input information, and positions the point group included in the registration region in the three-dimensional point group 400 as the registration point group 410. The result is output to the matching unit 330, and all of the three-dimensional point group 400 is output to the difference extraction unit 350 as the difference extraction point group 420.
- the parameter 360 that defines the alignment area may be stored in the storage 140, for example, and the alignment area separation unit 320 may acquire the parameter 360 that defines the alignment area from the storage 140. it can.
- FIG. 5 shows an example in which a point group included in the alignment area is extracted as the alignment point group.
- the alignment region 550 is set by a plurality of parameters, and is, for example, a space in front of and above the vehicle 100.
- a space in front of and above the vehicle 100 (space obliquely upward with respect to the vehicle 100) is an area mainly including overhead lines and structures that support the overhead lines, and is an area where there are few moving objects.
- the alignment region 550 is set on the basis of a position that is Pf ahead of the vehicle 100 and a height Pv from the rail position.
- the alignment region 550 is represented as a three-dimensional space having a height P H , a depth P D , and a width P W.
- the alignment area 550 a space where there are few moving objects such as a person moving in a station building, another train traveling on an adjacent track, or a vehicle traveling on an adjacent road is set. preferable.
- Pf 3 to 6 m
- Pv 4 to 8 m
- P H 2 to 6 m
- P W 3 to 20 m
- P D 10 to 70 m. It is preferred that
- these parameters may be configured to be adjustable from the outside in accordance with the operational environment such as railway standards, vehicle height, and height of sensors attached to the vehicle.
- FIG. 6 is an example of the alignment area 550.
- the alignment region 550 is preferably set so as to include an object in which there is no moving object and the change in the state due to the environment is small.
- the alignment region 550 is set so as to include at least a part of the utility pole 610 arranged along the line and at least a part of a beam (beam) 620 passed between the utility poles 610.
- parameters (P W , P H, etc.) that define the alignment region 550 may be set so that the upper end portion of the utility pole 610 and the beam 620 are included.
- FIG. 7 shows another example of the alignment area 550.
- the alignment region 550 is set so as to include the slope 710 on the side surface side of the vehicle 100 from the viewpoint that a moving object does not exist and an object with a small change in state due to the environment or the like is included. Also good.
- the slope is a slope portion provided by cutting or raising the ground when laying a track.
- the imaging device 110 may be disposed on the roof of the vehicle, and a space upward with respect to the vehicle may be used as the alignment region 550.
- the alignment region 550 may be set such that a building such as a building adjacent to a railroad track, a roof of a station platform, or the like enters.
- FIG. 8 is an example of a flowchart for explaining the processing of the alignment region separation unit 320.
- the alignment region separation unit 320 first performs alignment region determination using each point of the three-dimensional point group 400 input from the point group conversion unit 310 as a target point group (step 800).
- the alignment region separation unit 320 determines whether or not the coordinates of the target point group are present in the alignment region 550.
- step 800 If it is determined in step 800 that the target point exists in the alignment region 550, the alignment region separation unit 320 adds the point to the alignment point group 410 (step 810), and then the step Proceed to 820.
- step 800 determines whether the target point exists in the alignment region 550. If it is determined in step 800 that the target point does not exist in the alignment region 550, the process proceeds to step 820.
- the alignment region separation unit 320 adds the target point to the difference extraction point group 420 (step 820).
- the alignment region separation unit 320 outputs the alignment point group 410 to the alignment unit 330 after the flow of FIG. 8 is completed for all the points of the 3D point group 400, and extracts the difference extraction point group 420 as a difference. To the unit 350.
- the neighborhood searching unit 340 receives the vehicle position information 210 from the vehicle position specifying device 130 as input information.
- the neighborhood search unit 340 searches the point cloud DB 300 using the vehicle location information 210 and reads the reference 3D point cloud information 540 associated with the location information 500 that is the nearest neighborhood of the vehicle location information 210. For example, when the vehicle position information 210 (Nlat, Nlon) is used, the neighborhood searching unit 340 determines that the location information 500 (Rlat, Rlon) having the smallest evaluation value V in Formula 2 is the nearest location information. May be.
- the neighborhood search unit 340 has the largest difference between the current kilometer and the kilometer of the position information 500.
- the position information 500 that becomes smaller may be determined to be the nearest position information.
- the neighborhood search unit 340 outputs the reference alignment point group 510 of the reference 3D point group information 540 to the alignment unit 330, and outputs the reference difference extraction point group 520 of the reference 3D point group information 540 to the difference extraction unit 350. To do.
- the alignment unit 330 receives the alignment point group 410 from the alignment region separation unit 320 as input information, and receives the reference alignment point group 510 from the neighborhood search unit 340 as input information.
- the alignment unit 330 aligns the alignment point group 410 with respect to the reference alignment point group 510.
- the alignment unit 330 may use a generally known ICP (Iterative Closest Point) method or NDT (Normal Distributions Transformation) method as a point cloud alignment method.
- the alignment unit 330 rotates and translates the alignment point group 410 to obtain a rotation and translation parameter (rotation and translational movement amount) that minimizes an error evaluation value with respect to the reference alignment point group 510.
- the rotation and translation parameters are referred to as “posture information 430”.
- the alignment unit 330 outputs the obtained rotation and translation parameters to the difference extraction unit 350 as posture information (alignment information) 430.
- posture information alignment information
- the rotation and translation parameter A, the coordinate vector R of the reference alignment point group 510, and the coordinate vector P of the corresponding alignment point group 410 have the relationship shown in Equation 3.
- the difference extraction unit 350 receives the difference extraction point group 420 as input information from the alignment region separation unit 320, receives the reference difference extraction point group 520 as input information from the neighborhood search unit 340, and receives posture information 430 from the alignment unit 330. Receive as input information.
- the difference extraction unit 350 transforms the difference extraction point group 420 based on the posture information 430. Specifically, the difference extraction unit 350 rotates and translates the difference extraction point group 420 based on the posture information 430 to calculate a deformed three-dimensional point group. The difference extraction unit 350 calculates the distance of the nearest point of the reference difference extraction point group 520 with respect to each point of the deformed three-dimensional point group (the coordinates of each deformed point). The difference extraction unit 350 outputs a point where the distance is more than the threshold TL to the communication device 150 as the change area information 220.
- Equation 4 is the difference extraction point when the posture information 430 is A, the coordinates of each point of the difference extraction point group 420 is P, the coordinates of the reference difference extraction point group 520 nearest to P are R, and the threshold TL. The determination of whether or not to include each point of the group 420 in the change area information 220 is shown.
- the difference extraction unit 350 transforms the coordinates P of each point of the difference extraction point group 420 according to the posture information A, and if the distance from the coordinate R of the point of the reference difference extraction point group 520 nearest to P is larger than the threshold TL.
- the point of the difference extraction point group 420 is output as the change area information 220. Otherwise, the difference extraction unit 350 does not handle the point of the difference extraction point group 420 as the change area information 220.
- the difference extraction process described here is an example, and the present invention is not limited to this.
- an imaging device eg, a three-dimensional sensor 110 mounted on the vehicle 100 acquires three-dimensional point cloud data around the vehicle.
- the alignment region separation unit 320 separates, as the alignment point group 410, the point group in the space with few moving objects from the three-dimensional point group 400. Thereby, it is possible to perform alignment processing in a space with few moving objects.
- the alignment unit 330 can stably align the past three-dimensional point group (reference alignment point group 510) and the current three-dimensional point group (alignment point group 410).
- the difference extraction unit 350 obtains the difference between the past three-dimensional point group in the normal state (reference difference extraction point group 520) and the current three-dimensional point group (difference extraction point group 420), thereby operating the vehicle. Detects abnormal parts such as foreign objects outside the area and damage to railway-related facilities.
- an alignment area 550 that excludes an area where a moving object is present as much as possible is set, and a point group for alignment is extracted from the alignment area 550. Therefore, this embodiment can prevent a normal location from being detected as an abnormal location due to misalignment due to the presence or absence of a moving object. Therefore, it is possible to stably detect foreign matters and damage in railway-related facilities outside the operating vehicle area.
- the difference extraction unit 350 may store the change area information 220 as abnormality information in the storage 140.
- the difference extraction unit 350 outputs the change area information 220 to the display device, and notifies the driver of the vehicle 100 or the like of a foreign object or facility damage via the display device. Good.
- the imaging device 110 may further include a camera sensor that outputs a camera image (two-dimensional image), and the ground station 160 may receive the two-dimensional image together with the change area information 220.
- the processing device of the ground station 160 obtains a correspondence relationship between each point of the change area (three-dimensional point group to be a difference) extracted by the difference extraction unit 350 and each pixel of the two-dimensional image, and uses the correspondence relationship.
- Information for example, marking with a frame or the like
- the processing device of the ground station 160 may display the two-dimensional image via a display device.
- the upper part of FIG. 9 is an example in which information indicating an abnormal part is displayed on the two-dimensional image.
- the display process of the abnormal part is not limited to such marking, and may be performed by another method that can recognize the abnormal part. According to this configuration, it is possible to present the abnormal part in a two-dimensional image that is easy for the user to see after grasping the abnormal part from the three-dimensional information.
- the document generation device of the ground station 160 lays out the above-described two-dimensional image and information such as the discovery date / location of the abnormal part according to a predetermined format, and performs work such as an equipment inspection report or a repair work instruction. Documents may be automatically generated.
- the lower diagram in FIG. 9 is an example in which a business document is generated by arranging a two-dimensional image showing an abnormal part in a predetermined format.
- Various information such as the time (date) and position where the abnormality is detected and the creator of the business document may be input to the area other than the two-dimensional image.
- the processing device and the document generation device on the ground station 160 side may be mounted on the vehicle 100.
- FIG. 10 is a diagram illustrating the configuration of the image processing apparatus 120 according to the second embodiment.
- symbol is attached
- the image processing apparatus 120 includes a point cloud conversion unit 310, a registration region separation unit 910, a registration unit 330, a neighborhood search unit 340, a difference extraction unit 350, and a region search unit 930.
- the area DB 920 is a database mounted on the storage 140.
- FIG. 11 shows an example of the area DB 920.
- the area DB 920 includes reference position information 1010 and alignment area candidate information 1020 as configuration items.
- the area DB 920 includes information on point groups that are candidates for the alignment area at each reference position (reference position information 1010) on the track.
- the alignment region separation unit 320 according to the first embodiment separates a point group in a predetermined space (alignment region 550) as the alignment point group 410, but the alignment region separation unit 910 according to the second embodiment. Can change the space for extracting the alignment point group 950 in accordance with the alignment area candidate information 1020 in the area DB 920.
- the area DB 920 holds information on appropriate alignment area candidates for each position on the track (railway track).
- the region DB 920 holds the region (electric pole and beam) in FIG. 6 as information on the alignment region candidate at a certain traveling position, and the region (slope) in FIG. 7 as the alignment region candidate at another traveling position. It may be held as information. Therefore, the accuracy of the alignment process in the alignment unit 330 is improved, and as a result, the accuracy of the extraction of the change area information in the difference extraction unit 350 is also improved.
- reference position information 1010 and alignment area candidate information 1020 are held in association with each other.
- the reference position information 1010 holds latitude / longitude representing the reference position and azimuth information representing the reference direction.
- information on the distance from the starting point of the track (about kilometer) and information on each line (up, down, main line, sub main line, etc.) may be used.
- the registration area candidate information 1020 holds a plurality of areas with few moving objects in the surrounding environment of the railway track as registration candidate areas.
- the alignment area candidate information 1020 holds a set of XYZ coordinates of the four vertices of the tetrahedron in relative coordinates with the reference position and reference direction as the origin. In this example, the alignment area candidate information 1020 holds information on four vertices of the tetrahedron, but is not limited to this, and information on other arbitrary spaces may be held.
- the region search unit 930 receives the vehicle position information 210 from the vehicle position specifying device 130 as input information.
- the area search unit 930 searches the area DB 920 using the vehicle position information 210 and reads the alignment area candidate information 1020 associated with the reference position information 1010 that is the closest to the vehicle position information 210.
- the area search unit 930 may output the alignment area candidate information 1020 as it is to the alignment area separation unit 910 as the alignment area 940, but may narrow down the alignment area candidate information 1020 using a predetermined condition.
- the conditions used here may include, for example, information on the measurement range of the three-dimensional sensor.
- FIG. 12 is an example of a process for narrowing down the alignment area candidate information. It is assumed that the area search unit 930 has acquired information on three alignment area candidates 1100, 1110, and 1120 as the alignment area candidate information 1020 from the area DB 920. The area search unit 930 reads the narrow-down conditions stored in the storage 140.
- the conditions used here are information on the measurement range of the three-dimensional sensor, and include information on the sensor proximity limit Lf and the sensor limit Ll in front of the vehicle.
- the region search unit 930 sets the first sensor limit surface 1130 and the second sensor limit surface 1140 based on the information on the sensor proximity limit Lf and the sensor limit Ll.
- the region search unit 930 is a region that is defined by the alignment region candidates 1100, 1110, and 1120 and that is included in the space between the first sensor limit surface 1130 and the second sensor limit surface 1140. Extract as region 940.
- the area search unit 930 outputs the extracted alignment area 940 to the alignment area separation unit 910. According to this configuration, the area search unit 930 narrows down the alignment area candidates according to the conditions and outputs them to the alignment area separation unit 910, so that the amount of processing performed thereafter is reduced.
- the speed of the point group separation process in the region separation unit 910 and the speed of the alignment process in the alignment unit 330 can be improved.
- the alignment region candidate (tetrahedron) 1100 is not included in the alignment region 940 because it exists behind the first sensor limit surface 1130 in the traveling direction of the vehicle 100.
- the alignment region candidate (tetrahedron) 1110 a part of the tetrahedron exists behind the first sensor limit surface 1130, so that portion is not included in the alignment region 940, and the remaining portion is positioned. It is included in the alignment area 940.
- the alignment region candidate (tetrahedron) 1120 exists in the space between the first sensor limit surface 1130 and the second sensor limit surface 1140, all the portions of the alignment region candidate 1120 are alignment regions. 940.
- the alignment region separation unit 910 receives the three-dimensional point cloud 400 from the point cloud conversion unit 310 as input information, and receives an alignment region 940 corresponding to the current position of the vehicle 100 as input information.
- the alignment region separation unit 910 outputs the point group included in the alignment region 940 in the 3D point group 400 to the alignment unit 330 as the alignment point group 950, and all of the 3D point group 400 is output.
- the difference extraction point group 420 is output to the difference extraction unit 350.
- FIG. 13 is an example of a flowchart for explaining the processing of the alignment region separation unit 910.
- the alignment region separation unit 910 first performs alignment region determination using each point of the three-dimensional point group 400 input from the point group conversion unit 310 as a target point group (step 1200).
- the alignment region separation unit 910 determines whether or not the coordinates of the target point group are present in the alignment region 940 output from the region search unit 930.
- step 1200 If it is determined in step 1200 that the target point is present in the alignment area 940, the alignment area separation unit 910 adds the point to the alignment point group 950 (step 1210), and then the step Proceed to 1220.
- step 1200 determines whether the target point exists in the alignment area 940. If it is determined in step 1200 that the target point does not exist in the alignment area 940, the process proceeds to step 1220.
- the alignment region separation unit 910 adds the target point to the difference extraction point group 420 (step 1220).
- the registration region separation unit 910 outputs the registration point group 950 to the registration unit 330 and extracts the difference extraction point group 420 after the flow of FIG. To the unit 350.
- the reference alignment point group 510 of the point cloud DB 300 of this embodiment holds a past point cloud corresponding to the alignment region 940.
- the alignment unit 330 aligns the alignment point group 950 with respect to the reference alignment point group 510.
- the processing of the neighborhood search unit 340 and the processing of the difference extraction unit 350 are the same as those in the first embodiment.
- the area search unit 930 searches for known peripheral alignment area candidate information 1020 from the area DB 920 based on the vehicle position information 210 of the vehicle position specifying device 130.
- the registration region separation unit 910 can extract the registration point group 950 from the three-dimensional point group 400 based on the registration region candidate information 1020.
- the alignment area can be specified more flexibly for each position of the vehicle.
- the space for extracting the alignment point group is a limited space in front of and above the vehicle 100 at any position on the track.
- An area that clearly does not include a moving object, such as a building adjacent to a railroad track, can also be used as an alignment area.
- the facility inspection system may include an interface and a processing unit (DB correction unit) for correcting the region DB 920.
- DB correction unit a processing unit for correcting the region DB 920.
- the user may input correction information via a predetermined interface on the display device, and the DB correction unit may correct the alignment area candidate information 1020 in the area DB 920 based on the input correction information.
- FIG. 14 is a diagram illustrating the configuration of the image processing apparatus 120 according to the third embodiment.
- symbol is attached
- the image processing apparatus 120 further includes an alignment region selection unit 1310 with respect to the configuration of FIG.
- the alignment region selection unit 1310 receives the three-dimensional point group 400 from the point group conversion unit 310 as input information, and acquires candidate region information 1300 stored in the storage 140 as input information.
- the candidate area information 1300 includes information on a plurality of candidate areas and priority order information on each candidate area.
- the alignment region selection unit 1310 determines the number of three-dimensional points in each candidate region of the three-dimensional point group 400 detected via the imaging device 110 according to the priority order, and the number of three-dimensional points is a predetermined number. The above area is selected as the alignment area.
- FIG. 15 is an example of a flowchart for explaining the processing of the alignment region selection unit 1310.
- the candidate area information 1300 includes information on the first area as the first priority and information on the second area as the second priority.
- the first region is a region including the utility pole 610 and the beam 620 illustrated in FIG. 6, and the second region is a region on the side surface side of the vehicle 100 illustrated in FIG. 7.
- the candidate area information 1300 may hold information on three or more areas.
- the alignment area selection unit 1310 acquires candidate area information 1300. Then, the candidate area information 1300 first determines whether or not the number of three-dimensional points in the first area of the three-dimensional point group 400 detected via the imaging device 110 is greater than or equal to the threshold Th (step 1400). ).
- step 1420 If it is determined in step 1400 that the number of three-dimensional points in the first region is equal to or greater than the threshold Th, the process proceeds to step 1420.
- the alignment area selection unit 1310 determines the first area as the alignment area (step 1420). Thereafter, the alignment area selection unit 1310 outputs the alignment area information 1320 to the alignment area separation unit 320.
- step 1400 if the number of three-dimensional points in the first region is less than the threshold value Th, the process proceeds to step 1410.
- the alignment area selection unit 1310 changes the alignment area to the second area having the second priority (step 1410). Thereafter, the process returns to step 1400, and if the condition of step 1400 is satisfied, the alignment area selection unit 1310 determines the second area as the alignment area (step 1420). If there are three or more candidate regions, steps 1400 and 1410 may be repeatedly executed by that number to determine the alignment region.
- the alignment area selection unit 1310 can select an alignment area according to the number of three-dimensional points in the alignment candidate area detected through the imaging apparatus 110 at that time.
- the utility pole 610 and the beam 620 shown in FIG. 6 are arranged at intervals of about 30 to 65 m along the track. Therefore, a situation occurs in which the utility pole 610 and the beam 620 are not included in the measurement range of the imaging device 110 while the vehicle 100 is traveling. In this case, since there is no point cloud in the first area (the area above and above the vehicle 100), the alignment cannot be performed well.
- the alignment area selection unit 1310 selects the second area (the area on the side surface of the vehicle 100) as the alignment area, and the three-dimensional point is within the second area. If the number is equal to or greater than the predetermined number, the second area is determined as the alignment area. Thus, according to the present embodiment, an area where a three-dimensional point group is detected can be selected as an alignment area.
- the alignment area selection unit 1310 can determine an area having a high priority and having a predetermined number of three-dimensional points as the alignment area.
- the reference alignment point group 510 of the point group DB 300 only needs to hold information corresponding to the area included in the candidate area information 1300.
- Other processes are the same as those in the first embodiment.
- the present embodiment can also be applied to the second embodiment.
- the alignment area selection unit 1310 receives a plurality of alignment areas as input information from the area search unit 930, and selects an area where the number of three-dimensional points is greater than or equal to a predetermined number among the alignment areas. May be determined as The alignment area selection unit 1310 may output information on the determined alignment area to the alignment area separation unit 910.
- the present disclosure is not limited to the above-described embodiments, and includes various modifications.
- the above-described embodiments have been described in detail for easy understanding of the present disclosure, and are not necessarily limited to those having all the configurations described.
- a part of the configuration of one embodiment can be replaced with the configuration of another embodiment.
- the structure of another Example can also be added to the structure of a certain Example.
- another configuration can be added, deleted, or replaced.
- the neighborhood search unit 340 obtains the reference three-dimensional point cloud information 540 from the point cloud DB 300 based on the current position information, but is not limited to this configuration.
- the reference three-dimensional point cloud information 540 is numbered for each position and linked to a number to obtain the reference three-dimensional point cloud information 540, or a tag is installed on the track, and the reference three-dimensional point cloud of the same tag A method for obtaining the information 540 may be implemented.
- Each configuration, function, and the like of the image processing device 120 may be realized by software by interpreting and executing a program that realizes each function by the processor.
- Information such as programs and files for realizing each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.
- each configuration or the like of the image processing apparatus 120 described above may be realized by hardware by designing part or all of the configuration by, for example, an integrated circuit.
- control lines and information lines indicate what is considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. All the components may be connected to each other.
- Reference alignment point group 520 ... Reference difference extraction point group 540 ... Reference three-dimensional point group information 910 ... Registration region separation unit 920 ... Region DB 930 ... Area search unit 940 ... Alignment area 950 ... Alignment point group 1010 ... Reference position information 1020 ... Alignment area candidate information 1310 ... Alignment area selection unit
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Description
図1は、実施例1に係る鉄道設備巡視システムの構成を説明する図である。鉄道設備巡視システムは、車両100と地上局160とから構成される。
図10は、実施例2に係る画像処理装置120の構成を説明する図である。上述の実施例1で説明した構成要素については、同じ符号を付して説明を省略する。
図14は、実施例3に係る画像処理装置120の構成を説明する図である。上述の実施例1で説明した構成要素については、同じ符号を付して説明を省略する。
110 …撮影装置
120 …画像処理装置
130 …車両位置特定装置
140 …ストレージ(記憶装置)
150 …通信装置
160 …地上局
200 …距離画像
210 …車両位置情報
220 …変化領域情報
230 …参照三次元点群情報
240 …変化領域検出信号
300 …点群DB
310 …点群変換部
320 …位置合せ領域分離部
330 …位置合せ部
340 …近傍検索部
350 …差分抽出部
400 …三次元点群
410 …位置合せ点群
420 …差分抽出点群
430 …姿勢情報(位置合せ情報)
500 …位置情報
510 …参照位置合せ点群
520 …参照差分抽出点群
540 …参照三次元点群情報
910 …位置合せ領域分離部
920 …領域DB
930 …領域検索部
940 …位置合せ領域
950 …位置合せ点群
1010 …基準位置情報
1020 …位置合せ領域候補情報
1310 …位置合せ領域選択部
Claims (11)
- 軌道上を移動する車両の周辺環境の画像を撮影する撮影装置と、
前記軌道上の位置ごとに参照位置合せ点群及び参照差分抽出点群を格納する記憶装置と、
前記画像から得られた三次元点群から、位置合せ点群を分離する位置合せ領域分離部と、
前記参照位置合せ点群と前記位置合せ点群とを位置合せし、位置合せ情報を出力する位置合せ部と、
前記位置合せ情報によって変形された前記三次元点群と前記参照差分抽出点群との差分を抽出する差分抽出部と
を備える設備巡視システム。 - 請求項1に記載の設備巡視システムにおいて、
前記位置合せ領域分離部は、前記三次元点群のうち、移動物体が少ない所定の空間内にある点群を前記位置合せ点群として出力する、設備巡視システム。 - 請求項2に記載の設備巡視システムにおいて、
前記所定の空間は、前記車両に対して斜め上方向、上方向、又は、側面側の空間である、設備巡視システム。 - 請求項3に記載の設備巡視システムにおいて、
前記所定の空間は、
前記軌道に沿って配置された電柱の一部及び前記電柱間の梁、又は
前記車両の側面側にある法面の一部
が含まれるように設定される、設備巡視システム。 - 請求項1に記載の設備巡視システムにおいて、
前記記憶装置は、前記軌道上の位置ごとに位置合せ領域候補情報を格納しており、
前記位置合せ領域分離部は、前記三次元点群のうち、前記位置合せ領域候補情報に含まれる点群を前記位置合せ点群として出力する、設備巡視システム。 - 請求項5に記載の設備巡視システムにおいて、
現在の前記車両の位置に基づいて前記記憶装置から前記位置合せ領域候補情報を検索する領域検索部をさらに備える設備巡視システム。 - 請求項6に記載の設備巡視システムにおいて、
前記領域検索部は、前記撮影装置の測定範囲に基づいて前記位置合せ領域候補情報を絞り込む、設備巡視システム。 - 請求項1に記載の設備巡視システムにおいて、
現在の前記車両の位置に基づいて前記記憶装置から前記参照位置合せ点群及び前記参照差分抽出点群を検索する近傍検索部をさらに備える設備巡視システム。 - 請求項1に記載の設備巡視システムにおいて、
複数の候補領域のうち、前記撮影装置を介して検出された三次元点の数が所定の数以上ある領域を位置合せ領域として決定する位置合せ領域選択部をさらに備える設備巡視システム。 - 請求項9に記載の設備巡視システムにおいて、
前記位置合せ領域選択部は、前記複数の候補領域を優先順位に従って選択する、設備巡視システム。 - 撮影装置によって、軌道上を移動する車両の周辺環境の画像を撮影するステップと、
位置合せ領域分離部によって、前記画像から得られた三次元点群から、位置合せ点群を分離するステップと、
位置合せ部によって、記憶装置に格納されている参照位置合せ点群と前記位置合せ点群とを位置合せし、位置合せ情報を出力するステップと、
差分抽出部によって、前記位置合せ情報によって変形された前記三次元点群と、前記記憶装置に格納されている参照差分抽出点群との差分を抽出するステップと
を含む設備巡視方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/465,373 US11113543B2 (en) | 2016-12-02 | 2017-12-01 | Facility inspection system and facility inspection method |
GB1907725.4A GB2571045B (en) | 2016-12-02 | 2017-12-01 | Facility inspection system and facility inspection method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016235278A JP6826421B2 (ja) | 2016-12-02 | 2016-12-02 | 設備巡視システム及び設備巡視方法 |
JP2016-235278 | 2016-12-02 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018101455A1 true WO2018101455A1 (ja) | 2018-06-07 |
Family
ID=62242498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/043234 WO2018101455A1 (ja) | 2016-12-02 | 2017-12-01 | 設備巡視システム及び設備巡視方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US11113543B2 (ja) |
JP (1) | JP6826421B2 (ja) |
GB (1) | GB2571045B (ja) |
WO (1) | WO2018101455A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109080664A (zh) * | 2018-08-10 | 2018-12-25 | 南京南瑞继保电气有限公司 | 基于三维结构的地铁站实时监控方法及应急处理预演方法 |
TWI665645B (zh) * | 2018-08-22 | 2019-07-11 | 南開科技大學 | 大樓巡邏路徑推薦與路徑照明控制系統及其方法 |
US20200378750A1 (en) * | 2019-05-29 | 2020-12-03 | Hitachi High-Tech Fine Systems Corporation | Overhead wire mutual separating situation measuring apparatus and overhead wire mutual separating situation measuring method |
WO2022018918A1 (ja) * | 2020-07-20 | 2022-01-27 | 株式会社 東芝 | 鉄道線路情報取得装置、及び鉄道線路情報取得方法 |
CN117197779A (zh) * | 2023-09-11 | 2023-12-08 | 苏州大学 | 一种基于双目视觉的轨道交通异物检测方法、装置及*** |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6843274B2 (ja) * | 2018-02-08 | 2021-03-17 | 三菱電機株式会社 | 障害物検出装置および障害物検出方法 |
US11294060B2 (en) * | 2018-04-18 | 2022-04-05 | Faraday & Future Inc. | System and method for lidar-based vehicular localization relating to autonomous navigation |
JP6947699B2 (ja) * | 2018-07-25 | 2021-10-13 | 公益財団法人鉄道総合技術研究所 | 情報処理装置および点群位置補正方法、ならびにプログラム |
JP7135568B2 (ja) | 2018-08-13 | 2022-09-13 | コニカミノルタ株式会社 | 画像検査装置、画像形成装置、及びプログラム |
JP7115228B2 (ja) * | 2018-11-06 | 2022-08-09 | オムロン株式会社 | 設備管理装置、設備管理方法、及び設備管理プログラム |
JP7433623B2 (ja) | 2019-11-18 | 2024-02-20 | 株式会社ベイシスコンサルティング | 構造物画像管理システム |
JP7375944B2 (ja) * | 2020-08-28 | 2023-11-08 | 日本電気株式会社 | 処理装置、異常検知システム、異常検知方法、及びプログラム |
WO2022244172A1 (ja) * | 2021-05-20 | 2022-11-24 | 三菱電機株式会社 | 情報処理装置、情報処理システム、情報処理方法、及び情報処理プログラム |
DE102022204216A1 (de) * | 2022-04-29 | 2023-11-02 | Siemens Mobility GmbH | Verfahren zur Zustandserfassung einer straßenseitigen Oberleitungsanlage |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06325298A (ja) * | 1993-05-13 | 1994-11-25 | Yazaki Corp | 車両周辺監視装置 |
JP2004042777A (ja) * | 2002-07-11 | 2004-02-12 | Matsushita Electric Ind Co Ltd | 障害物検知装置 |
JP2004352107A (ja) * | 2003-05-29 | 2004-12-16 | Aichi Corp | 鉄道設備管理装置 |
JP2005092516A (ja) * | 2003-09-17 | 2005-04-07 | Denso Corp | 車載用移動体検出装置 |
JP2007129560A (ja) * | 2005-11-04 | 2007-05-24 | Toyota Motor Corp | 物体検出装置 |
JP4106163B2 (ja) * | 1999-09-27 | 2008-06-25 | 株式会社東芝 | 障害物検出装置及びその方法 |
JP2010006295A (ja) * | 2008-06-30 | 2010-01-14 | Kobe Steel Ltd | 落下物検知装置、移動体および落下物検知方法 |
JP2016045330A (ja) * | 2014-08-22 | 2016-04-04 | 株式会社Ihi | 3次元点群データの位置合わせ方法と装置及びその移動体システム |
JP2016110210A (ja) * | 2014-12-02 | 2016-06-20 | 株式会社日立製作所 | 変化検出装置、変化検出方法、および、変化検出プログラム |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS59182352A (ja) * | 1983-03-31 | 1984-10-17 | Jeol Ltd | 核磁気共鳴測定方法 |
JPS6325298A (ja) * | 1986-03-12 | 1988-02-02 | Toray Ind Inc | 有機結晶の製造方法 |
JP4099907B2 (ja) * | 1999-06-18 | 2008-06-11 | ソニー株式会社 | 情報再生装置及び方法、並びに情報提供媒体 |
US7639842B2 (en) * | 2002-05-03 | 2009-12-29 | Imagetree Corp. | Remote sensing and probabilistic sampling based forest inventory method |
JP2010202017A (ja) | 2009-03-03 | 2010-09-16 | Mitsubishi Electric Corp | データ解析装置及びデータ解析方法及びプログラム |
JP5165649B2 (ja) * | 2009-07-30 | 2013-03-21 | 公益財団法人鉄道総合技術研究所 | 鉄道架線設備の状態監視システム |
US9810533B2 (en) * | 2011-04-27 | 2017-11-07 | Trimble Inc. | Railway track monitoring |
US8615110B2 (en) * | 2012-03-01 | 2013-12-24 | Herzog Railroad Services, Inc. | Automated track surveying and ditching |
US9796400B2 (en) * | 2013-11-27 | 2017-10-24 | Solfice Research, Inc. | Real time machine vision and point-cloud analysis for remote sensing and vehicle control |
GB2542115B (en) * | 2015-09-03 | 2017-11-15 | Rail Vision Europe Ltd | Rail track asset survey system |
US10474161B2 (en) * | 2017-07-03 | 2019-11-12 | Baidu Usa Llc | High resolution 3D point clouds generation from upsampled low resolution lidar 3D point clouds and camera images |
US20190039633A1 (en) * | 2017-08-02 | 2019-02-07 | Panton, Inc. | Railroad track anomaly detection |
-
2016
- 2016-12-02 JP JP2016235278A patent/JP6826421B2/ja active Active
-
2017
- 2017-12-01 US US16/465,373 patent/US11113543B2/en active Active
- 2017-12-01 GB GB1907725.4A patent/GB2571045B/en active Active
- 2017-12-01 WO PCT/JP2017/043234 patent/WO2018101455A1/ja active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06325298A (ja) * | 1993-05-13 | 1994-11-25 | Yazaki Corp | 車両周辺監視装置 |
JP4106163B2 (ja) * | 1999-09-27 | 2008-06-25 | 株式会社東芝 | 障害物検出装置及びその方法 |
JP2004042777A (ja) * | 2002-07-11 | 2004-02-12 | Matsushita Electric Ind Co Ltd | 障害物検知装置 |
JP2004352107A (ja) * | 2003-05-29 | 2004-12-16 | Aichi Corp | 鉄道設備管理装置 |
JP2005092516A (ja) * | 2003-09-17 | 2005-04-07 | Denso Corp | 車載用移動体検出装置 |
JP2007129560A (ja) * | 2005-11-04 | 2007-05-24 | Toyota Motor Corp | 物体検出装置 |
JP2010006295A (ja) * | 2008-06-30 | 2010-01-14 | Kobe Steel Ltd | 落下物検知装置、移動体および落下物検知方法 |
JP2016045330A (ja) * | 2014-08-22 | 2016-04-04 | 株式会社Ihi | 3次元点群データの位置合わせ方法と装置及びその移動体システム |
JP2016110210A (ja) * | 2014-12-02 | 2016-06-20 | 株式会社日立製作所 | 変化検出装置、変化検出方法、および、変化検出プログラム |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109080664A (zh) * | 2018-08-10 | 2018-12-25 | 南京南瑞继保电气有限公司 | 基于三维结构的地铁站实时监控方法及应急处理预演方法 |
TWI665645B (zh) * | 2018-08-22 | 2019-07-11 | 南開科技大學 | 大樓巡邏路徑推薦與路徑照明控制系統及其方法 |
US20200378750A1 (en) * | 2019-05-29 | 2020-12-03 | Hitachi High-Tech Fine Systems Corporation | Overhead wire mutual separating situation measuring apparatus and overhead wire mutual separating situation measuring method |
WO2022018918A1 (ja) * | 2020-07-20 | 2022-01-27 | 株式会社 東芝 | 鉄道線路情報取得装置、及び鉄道線路情報取得方法 |
JP2022020355A (ja) * | 2020-07-20 | 2022-02-01 | 株式会社東芝 | 鉄道線路情報取得装置、及び鉄道線路情報取得方法 |
JP7455690B2 (ja) | 2020-07-20 | 2024-03-26 | 株式会社東芝 | 鉄道線路情報取得装置、及び鉄道線路情報取得方法 |
CN117197779A (zh) * | 2023-09-11 | 2023-12-08 | 苏州大学 | 一种基于双目视觉的轨道交通异物检测方法、装置及*** |
Also Published As
Publication number | Publication date |
---|---|
GB2571045A (en) | 2019-08-14 |
US11113543B2 (en) | 2021-09-07 |
JP6826421B2 (ja) | 2021-02-03 |
JP2018090099A (ja) | 2018-06-14 |
GB201907725D0 (en) | 2019-07-17 |
US20190392225A1 (en) | 2019-12-26 |
GB2571045B (en) | 2022-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018101455A1 (ja) | 設備巡視システム及び設備巡視方法 | |
JP6812404B2 (ja) | 点群データを融合させるための方法、装置、コンピュータ読み取り可能な記憶媒体、及びコンピュータプログラム | |
CN108181635B (zh) | 一种用于输电线路交叉跨越分析的激光点云分类方法 | |
US10955854B2 (en) | Method and system for determining the position of a vehicle | |
JP2009068951A (ja) | 空中架線の管理システム | |
JP2018018461A (ja) | 情報処理装置、表示装置、情報処理方法、及びプログラム | |
KR102305328B1 (ko) | 카메라 기반의 자동화된 정밀도로지도 생성 시스템 및 방법 | |
US11002553B2 (en) | Method and device for executing at least one measure for increasing the safety of a vehicle | |
JP2017015598A (ja) | 測量データ処理装置、測量データ処理方法および測量データ処理用プログラム | |
JP6615065B2 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
CN103593678A (zh) | 一种大跨度桥梁车辆动态荷载分布检测方法 | |
JP6615066B2 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
JP2010202017A (ja) | データ解析装置及びデータ解析方法及びプログラム | |
JP2019078700A (ja) | 情報処理装置および情報処理システム | |
JP2014169939A (ja) | 架線位置計測装置及び方法 | |
WO2016031229A1 (ja) | 道路地図作成システム、データ処理装置および車載装置 | |
JP2017083245A (ja) | 建築限界判定装置 | |
JP2018017101A (ja) | 情報処理装置、情報処理方法、及びプログラム | |
US10621742B2 (en) | Method for producing a depth map | |
KR101674073B1 (ko) | 철도 시설물 공간 정보 구축 시스템 및 방법 | |
CN104422426A (zh) | 在高架道路区域内提供车辆导航信息的方法和设备 | |
CN112639803A (zh) | 用于识别设施处的物体的方法和组件 | |
JP6419260B1 (ja) | 交通情報取得装置、交通情報取得システム、交通情報取得方法、および交通情報取得プログラム | |
WO2021060599A1 (ko) | 레인을 검출하는 차량 및 방법 | |
US20210176434A1 (en) | Method and assembly for detecting corona discharges of a system comprising equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17876148 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 201907725 Country of ref document: GB Kind code of ref document: A Free format text: PCT FILING DATE = 20171201 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17876148 Country of ref document: EP Kind code of ref document: A1 |