Classifications

• • 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
  • B61L15/0072—On-board train data handling
• • 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

Definitions

• the invention relates to a calibration method for a railway vehicle camera according to the preamble of patent entitlement 1, a calibration system for a Bruschka mera according to the preamble of claim 3 and a railway vehicle with railway vehicle camera according to the preamble of claim. 7
• Rail vehicles are part of a modern transport infrastructure track-bound transport and transport, for example, rolling on or under of one or two rails (tracks), floating above or below a magnetic field or hanging on steel cables move.
• track-bound transport and Transportmit tel are rail vehicles based on a wheel-rail system, either a private traction (Triebwa conditions) or pulled or pushed by a locomotive and in which predominantly steel wheels with a flange on two steel rails railways are the most widespread.
• the object underlying the invention is to provide a calibration method and calibration system for a train vehicle camera and a railway vehicle with railway vehicle camera, with the train vehicle camera can be calibrated in a simple and cost-effective manner.
• the object is achieved on the basis of the Oberbe handle of claim 3 defined calibration system by the features specified in the characterizing part of claim 3.
• a correction value is calculated on the basis of a calibration image corresponding, metadata-related reference image of the reference images as a difference value to a Referenzposi tion in the metadata-related reference image based on the Po se information
• the calculated correction value is used to generate camera calibration information or to interpret the image information in the calibration image.
• At least one camera mounted on the railway or rail vehicle continuously picks up the area in front of the vehicle. This corresponds wholly or partly to the perspective of the driver. Alternatively or additionally, another camera is mounted so that the area in front of the vehicle is continuously picked up from a stationary, driving lane-topping position in or on the railway vehicle.
• Another technical feature for problem solving which is relevant to the invention is, in addition to the at least one camera, metadata required over the railway line. Namely, if the vehicle is according to this metadata on a Fahrspurab section with straight lane course, it can be determined based on the lane course in the picture, the position and orientation of the camera, a so-called pose, in relation to the lane, in particular special the tracks. Based on this information, a correction value can be calculated to an image taken by the railway vehicle / rail vehicle camera or a reference camera.
• the calculated correction value to the reference position can be used to interpret the recorded image information accordingly.
• the calculated correction value can be used for the precise determination of the image section.
• the calibration ie the calculation of the difference values to the reference position
• the calibration can be performed by a cloud-based service and only the calibration information can be returned to the camera system.
• the advantage of the invention is that after the installation of one or more cameras in a railway vehicle on agile or even manual calibration of the camera system is not agile.
• the calibration method can also be applied to different types of cameras as well as different recording characteristics. For example, cameras with different lenses (telephoto or wide-angle lens) are used.
• FIGS 1 to 3 show:
• FIG. 1 shows a calibration system in conjunction with a railway vehicle camera as part of a railway vehicle, in particular a rail vehicle,
• FIG. 2 shows an exemplary representation of a reference image that has been taken from the perspective of a vehicle driver.
• FIGURE 3 is an exemplary illustration of a calibration image that has been taken as the image in FIGURE 2 from the perspective of the driver.
• FIG. 1 shows a calibration system KS in conjunction with a railway vehicle camera BFZK as part of a train driving tool BFZ, in particular a rail vehicle SFZ.
• the Ka libr istssystem KS is preferably designed as a cloud-based system and includes a memory device SPE and an evaluation / calculation unit ABE, both for Ka librieren the railway vehicle camera BFZK are connected to this.
• the railway vehicle BFZ, SFZ, V orzugs- example at least from the partial perspective of aharimon rers FZF and / or from a stationary, lane coach the position in or on the railway vehicle BFZ, SFZ, of a railway BST, which may be formed as a rail track SST, for example, with respect to a the railway vehicle BFZ, SFZ vorgela gererten route range FSB a plurality of each of the route range FSB representing, detected by the reference images RBI.
• the acquired reference images RBI are stored in the storage device SPE of the calibration system KS.
• SPE Me tartz MD are stored on the detected in the images railway line BST, SST.
• metadata is data that literally refers to characteristics or characteristics of the railway line BST, SST recorded in the images.
• SFZ as the preferably at least from the partial perspective of driving convincing driver FZF and / or from the stationary, driving lane four-end position in or on the railway vehicle BFZ, SFZ, of egg nem section of the railway line BST, SST with a straight course of a lane, for example, straight course of rails or tracks, again with respect to the train vehicle BFZ, SFZ upstream route distance FSB with the Bahnfahr camera BFZK calibration images to be metadata MD, with or on their basis the section of the railway line BST, SST with straight course of the traffic lane can be determined, loaded from the storage device SPE into the train driving camera BFZK. Due to this loading of the metadata MD into the railway vehicle camera BFZK, the latter acquires a calibration image KBI MD , which is transmitted to or loaded into the evaluation / calculation unit ABE.
• the evaluation / calculation unit ABE is also connected to the SpeI cher worn SPE and forms with this a functional unit FE such that
• a metadata-related reference image RBI MD of the reference images RBI corresponding to the calibration image KBI MD and uploaded to the evaluation / calculation unit ABE is uploaded by the evaluation / calculation unit ABE into the evaluation / calculation unit ABE in accordance with FIG .
• a correction value KW is calculated on the basis of the calibration image KBI MD corresponding, metadata-related reference image RBI MD as a difference value to a reference position in the metadata-related reference image RBI MD based on the pose information, wherein by comparing the Lane course in the two images according to FIGURES 2 and 3 can be closed to the position of the camera to be calibrated,
• a camera calibration information KKI is generated on the basis of the calculated correction value KW or the image information can be interpreted in the calibration image KBI MD .
• the evaluation / calculation unit ABE to be connected to an image analysis device BAV and the calculated correction value KW to be used for the exact determination of an image section in image analysis carried out in the image analysis device BAV by rail or rail, for example by On the basis of a lane-based image analysis, as described in the international patent application with the file reference
• the image analysis device BAV is preferably like the calibration system KS in conjunction with the Bruschka mera BFZK part of the railway vehicle BFZ, SFZ.

Landscapes

• Engineering & Computer Science (AREA)
• Mechanical Engineering (AREA)
• Image Processing (AREA)
• Studio Devices (AREA)
• Length Measuring Devices By Optical Means (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=66685558

Family Applications (1)

Country Status (5)

Families Citing this family (2)

Family Cites Families (8)

• 2018
  • 2018-05-29 DE DE102018208512.9A patent/DE102018208512A1/de not_active Ceased
• 2019
  • 2019-05-08 CN CN201980036363.1A patent/CN112154090B/zh active Active
  • 2019-05-08 RU RU2020142257A patent/RU2762164C1/ru active
  • 2019-05-08 WO PCT/EP2019/061793 patent/WO2019228766A1/de unknown
  • 2019-05-08 EP EP19727831.0A patent/EP3802266A1/de active Pending

Also Published As

Similar Documents

Legal Events