EP3545506A1 - Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement - Google Patents

Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement

Info

Publication number
EP3545506A1
EP3545506A1 EP17780746.8A EP17780746A EP3545506A1 EP 3545506 A1 EP3545506 A1 EP 3545506A1 EP 17780746 A EP17780746 A EP 17780746A EP 3545506 A1 EP3545506 A1 EP 3545506A1
Authority
EP
European Patent Office
Prior art keywords
detected
raised object
raised
video images
video
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP17780746.8A
Other languages
German (de)
English (en)
Inventor
Stefan Nordbruch
Felix Hess
Andreas Lehn
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Robert Bosch GmbH
Original Assignee
Robert Bosch GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Robert Bosch GmbH filed Critical Robert Bosch GmbH
Publication of EP3545506A1 publication Critical patent/EP3545506A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/182—Network patterns, e.g. roads or rivers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/097—Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Definitions

  • the invention relates to a method for detecting a raised object located within a parking space, for example a parking garage, in particular within a driving path of a parking space.
  • the invention further relates to a system for detecting a raised object located within a parking space, for example a parking garage, in particular within a driving path of a parking space.
  • the invention further relates to a parking lot.
  • the invention further relates to a computer program.
  • the published patent application DE 10 2015 201 209 A1 shows a valet parking system for the automatic transfer of a vehicle from a transfer zone to an assigned parking space within a predetermined parking space.
  • the known system comprises a parking space monitoring system with at least one stationarily arranged sensor unit.
  • the parking lot monitoring system is designed to run within the given parking space
  • the object on which the invention is based is to provide a concept for the efficient detection of a raised object located within a parking space, for example a parking garage, in particular within a driving path of a parking space. This object is achieved by means of the subject matter of the independent claims. Advantageous embodiments of the invention are the subject of each dependent subclaims.
  • Overlapping area overlaps comprising the following steps:
  • Detection of a raised object the detected raised object is real.
  • a system for detecting a raised object located within a parking lot the system being configured to perform the method of detecting a raised object located within a parking lot.
  • a parking lot which includes the system for detecting a raised object located within a parking lot.
  • a computer program comprising program code for performing the method of detecting a raised object located within a parking lot when the computer program is executed on a computer.
  • the invention is based on the finding that the above object can be achieved by the fact that based on successively recorded
  • Video images is checked whether an initially detected raised object real is or not. This means, in particular, that a result, which was determined based on the video images recorded for the first time, wherein the result indicates that a raised object was detected, is verified or checked by temporal tracking of the first detected object.
  • the object detected for the first time can be made efficiently plausible. For, as a rule, it is the case, for example, that an object can not suddenly disappear.
  • the object, if it is actually real, should also be detected in an analysis of video images taken in time to the video image in which the object was first detected, and there, for example, have the same properties as before.
  • the technical advantage is achieved that false alarms can be reduced or avoided, which advantageously allows efficient operation of the parking lot and, for example, an efficient operation of driving without drivers within the parking lot
  • the technical advantage is achieved that objects can be recognized efficiently, so that a collision with such objects can be prevented.
  • the technical advantage is brought about that a concept for efficiently detecting a raised object located within a parking lot can be provided.
  • the video images are transformed into a bird's eye view, so be rectified.
  • the rectified video images are then compared. For example, if all of the rectified video images of the overlap area have no differences, ie are the same or identical, or have differences which are at most a predetermined tolerance value
  • Video camera is not the same as the other video cameras.
  • Video image of the other video cameras to distinguish a difference greater than the predetermined tolerance value.
  • a sublime object is detected.
  • a result is determined that indicates that a raised object has been detected.
  • a raised object can be efficiently detected by means of the at least two video cameras.
  • a parking space in the sense of the description is in particular a parking lot for motor vehicles.
  • the parking lot is for example a parking garage or a
  • An object to be detected is located, for example, within a driving path of the parking lot.
  • a raised object refers in particular to an object whose height is at least 10 cm relative to a floor of the parking lot.
  • the raised object is located, for example, on a floor of the
  • Parkplatzes for example, on a roadway or within a
  • Driving range so for example within a driving tube
  • a rectification of the recorded video images comprises in particular respectively a transformation of the recorded ones
  • Video images in the bird's eye view This means, in particular, that the recorded video images are transformed, for example, into a birds-eye view. As a result, the subsequent comparison can be carried out particularly efficiently in an advantageous manner.
  • Video images in the sense of this description also include in particular the case where the image information or the video images differ by a maximum of a predetermined tolerance value.” Only differences greater than the predetermined tolerance value result in a detection of an object small differences in the
  • Brightness and / or color information are allowed to make the statement that the image information or the video images are the same or the same or are identical, as long as the differences are smaller than the predetermined tolerance value.
  • step c) comprises determining an object speed, wherein the determined object speed is compared with a predetermined object speed threshold value, it being determined depending on the comparison whether the detected raised object is real.
  • the technical advantage is brought about that it can be efficiently determined whether the detected raised object is real. Because for real objects within a parking lot, certain speeds are usually expected. For example, an object speed of 150 km / h is not plausible. In this case, the detected object is not real.
  • An object speed threshold is, for example, 60 km / h,
  • step c) comprises determining a movement of the detected raised object, wherein it is determined whether the movement of the detected raised object is plausible, it being determined depending on the plausibility check, whether the detected raised object is real ,
  • the technical advantage is brought about that it can be efficiently determined whether the detected raised object is real. Because for real objects within a parking lot, certain movements are usually expected. Objects of the order of magnitude of a motor vehicle can not move vertically upward or change direction by 90 °. For smaller objects, no such statement can be made, because, for example, people can jump in the air. Determining the plausibility of the movement is performed, for example, depending on a size of the detected object. Objects that have a size that is in the
  • Magnitude of a motor vehicle is subject, for example, the above-mentioned movement restrictions.
  • step c) comprises determining whether, and if so, at which location in the video images, the detected sublime object moves into the respective video image or moves out of the respective video image.
  • the detected raised object is real if the detected object moves in the edge as a location in the respective video image respectively moves out of the respective video image at the edge as a location.
  • the detected raised object is not real if the detected object appears within the video image in the video image, respectively, disappears within the video image from the video image without having traversed the edge of the video image.
  • This embodiment is based on the recognition that raised objects in a scene (in this case the video images) can only move over the edge of the scene or leave the scene again only via the edge. In the middle of a scene, within the scene, an object can not appear or appear or disappear.
  • the technical advantage is brought about that it can be efficiently determined whether the detected raised object is real.
  • Classifying the detected raised object it is determined depending on the classification, whether the detected raised object is real. As a result, for example, the technical advantage is brought about that it can be efficiently determined whether the detected raised object is real. Because within a parking lot usually only certain objects are expected. In addition, the knowledge about the object type or the type of the object can be efficiently used for determining whether the detected object is real.
  • step c) includes checking whether the classification changes over time, wherein determining whether the object is real is performed in response to that check. In particular, when a change is detected, it is determined that the object is not real. Especially if no
  • the classification includes, for example, that a size, that is to say in particular a length and / or a height and / or a width, of the detected object is determined.
  • step c) comprises determining a dynamic property of the detected object, wherein the determined dynamic property of the detected object with a
  • predetermined reference value is determined, it being determined depending on the comparison, whether the detected raised object is real.
  • a dynamic property is, for example, a speed, an acceleration, a direction of movement.
  • an object-specific speed threshold value is determined as the
  • Object speed threshold is specified for the comparison.
  • the technical advantage is achieved that determining whether the detected object is real can be carried out object-specifically.
  • an object-specific reference value is predetermined for the comparison with the determined dynamic property.
  • the technical advantage is achieved that determining whether the detected object is real can be carried out object-specifically.
  • the technical advantage is achieved that determining whether the detected object is real can be carried out object-specifically.
  • This embodiment is based on the recognition that different objects move differently.
  • a person usually moves differently than a motor vehicle.
  • a person can turn on the spot, which a motor vehicle usually can not.
  • persons have different movement profiles than motor vehicles.
  • a sublime object can not even be a motor vehicle and later a pedestrian.
  • a detected object is classified into one of the following classes of object types: motor vehicle, pedestrian, cyclist, animal,
  • Motor vehicles ordering a service personnel to the video cameras, performing a functional check of the video cameras, adjusting a respective target trajectory to be traveled by motor vehicles driving inside the parking lot to bypass a portion of the parking area comprising the overlapping area, shutting off the
  • Overlapping portion of the parking lot shutting off a parking space comprising the overlapping area, sending an error message to an operator via a communication network.
  • n video cameras are used, where n is greater than or equal to 3, wherein an object is detected when, based on the comparison, it is determined that there is already a
  • Overlap range from the other recorded overlap ranges or that at least m overlap ranges are different from the other overlap ranges, where m is greater than 1 and less than n, or that all n overlap ranges are different.
  • the more cameras are used and the more overlap areas should differ the more accurate the concept according to the invention, that is to say in particular the method according to the invention, can narrow down the footprint of the raised object.
  • the overlapping area is illuminated differently relative to at least one video camera compared to the other video cameras. This causes, for example, the technical advantage that an object can be detected efficiently. Because if one side of the object is preferred or illuminated differently than other sides of the object, it is possible to identify differences in the recorded video images in an efficient manner particularly easily and efficiently.
  • That the overlap area is differently illuminated relative to at least one video camera compared to the other video cameras means, for example, that a light source is located within the parking lot that illuminates the overlap area from the direction of the at least one video camera.
  • a light source is located within the parking lot that illuminates the overlap area from the direction of the at least one video camera.
  • no illumination ie no further light sources, is provided from the directions of the other video cameras or different illuminations are provided, for example light sources which are operated with different light intensities.
  • the overlapping area comprises a driving area for motor vehicles.
  • the parking space is set up or designed to execute or execute the method for detecting a raised object located within a parking space.
  • Car parked raised object is executed or carried out.
  • n video cameras are provided, where n is greater than or equal to 3.
  • step b determining a result, whether in the
  • Detecting overlapping areas detecting a raised object based on the comparison. That is to say, in particular, according to one embodiment, a data processing device is provided which is designed to carry out one or more or all of the steps described above.
  • the data processing device comprises, for example, one or more processors, which are for example comprised by at least one of the following elements: video camera or video cameras and / or arithmetic unit, which is different from the video cameras.
  • At least one of the steps listed above in connection with the data processing device is performed by means of at least one of the video cameras and / or by means of a computing unit which is different from the video cameras.
  • the computing unit has the technical advantage of efficiently creating redundancy. If the video camera the
  • the technical advantage causes the video camera is used efficiently.
  • a lighting device is provided.
  • the illumination device is designed to illuminate the overlapping area differently relative to at least one video camera compared to the other video cameras.
  • the lighting device comprises, for example, one or more
  • Light sources which are arranged spatially distributed within the parking lot.
  • the light sources are arranged, for example, such that the
  • Overlapping area is illuminated differently from different directions.
  • the overlapping area is spot-like illuminated from a preferred direction, for example by means of the illumination device.
  • the overlapping area is illuminated from a single direction.
  • the light sources are arranged, for example, on a ceiling or on a pillar or on a wall, generally on an infrastructure element of the parking lot.
  • n is greater than or equal to 3.
  • Overlap area is monitored by exactly three or from exactly four video cameras, their respective field of view in the respective
  • Overlap area overlaps In one embodiment, it is provided that a plurality of video cameras are provided, respectively, whose respective viewing area each overlap in an overlapping area. This means, in particular, that here several overlapping areas are detected by means of a plurality of video cameras, that is to say in particular monitored.
  • one or more respectively all video cameras are arranged at a height of at least 2 m, in particular 2.5 m, relative to a floor of the parking lot.
  • 1 is a flowchart of a method for detecting a raised object located within a parking lot
  • Fig. 4 shows two video cameras that monitor a floor of a parking lot
  • FIG. 5 shows the two video cameras of FIG. 4 in detecting a raised object
  • FIG. 1 shows a flow diagram of a method for detecting a raised object located within a parking space using at least two video cameras spatially distributed within the parking space, the respective viewing area of which overlaps in an overlapping area.
  • the method comprises the following steps:
  • Step 103 or step 105 includes, for example, the following steps:
  • the step of rectification comprises in particular that the recorded video images are transformed into a bird's-eye view. This has the technical advantage in particular that the video images can then be compared efficiently.
  • a detected raised object may be classified, for example, as follows: motor vehicle, pedestrian, cyclist, animal, stroller, miscellaneous.
  • Fig. 2 shows a system 201 for detecting a within a
  • the system 201 is configured to perform or perform the method of detecting a raised object located within a parking lot.
  • the system 201 includes, for example:
  • a data processing device 205 configured to perform one or more of the following steps: step b), step c), determining a result of whether a raised object has been detected in the captured video images, detecting a raised object in the captured video images, determining whether the detected raised object is real, rectifying the captured video image, comparing the respective rectified video image with each other to detect a difference in the captured overlap areas, detecting a raised object based on the comparison.
  • Fig. 3 shows a parking lot 301.
  • the parking lot 301 includes the system 201 of FIG. 2.
  • FIG. 4 shows a first video camera 403 and a second video camera 405 that monitor a floor 401 of a parking lot.
  • the two video cameras 403, 405 are arranged, for example, on a ceiling (not shown).
  • the first video camera 403 has a first viewing area 407.
  • the second video camera 405 has a second viewing area 409.
  • the two Video cameras 403, 405 are arranged such that the two
  • Viewing regions 407, 409 overlap in an overlap region 41 1.
  • This overlapping area 41 1 is part of the floor 401.
  • a light source 413 is arranged, which illuminates the overlap region 41 1 from the direction of the second video camera 405.
  • the two video cameras 403, 405 each take video images of the
  • Overlap area 41 1 wherein the video images are rectified. If there is no raised object between the overlap area 41 1 and the video camera 403 or 405, respectively, the respective rectified video images do not differ from each other, at least not within a predetermined tolerance (the predetermined tolerance value). In this case, therefore, no difference will be detected so that accordingly no raised object is detected.
  • the overlapping area 41 1 is located, for example, on a driving area of the parking lot. So that means, for example, that on the
  • Fig. 5 shows the two video cameras 403, 405 in detecting a raised object 501.
  • the raised object 501 has opposite sides 503, 505:
  • the side 503 is hereinafter referred to as the right side (with respect to the paper plane).
  • Page 505 will be referred to as the
  • the raised object 501 looks different from the right side 503 than the left side 505.
  • the raised object 501 is located on the floor 401.
  • the raised object 501 is located between the overlapping area 41 1 and the two video cameras 403, 405.
  • the first video camera 403 detects the left side 505 of the raised object 501.
  • the second video camera 405 detects the right side 503 of the raised object 501.
  • the respective rectified video images thus differ, so that a difference is correspondingly detected.
  • the raised object 501 is then detected.
  • the differences are greater than the predetermined tolerance value.
  • the provision of the light source 413 causes the right side 503 to be illuminated more strongly than the left side 505. This has the technical advantage, for example, that the recorded and thus rectified video images differ in their brightness.
  • the raised object 501 is, for example, a motor vehicle traveling on the floor 401 of the parking lot.
  • the sides 503, 505 are, for example, front and rear sides of the motor vehicle or the right and left sides.
  • a non-raised, ie two-dimensional or flat, object is located on the floor 401, then the correspondingly rectified video images generally do not differ from each other within a predetermined tolerance.
  • a two-dimensional object is for example a leaf,
  • a raised object is detected in the recorded video images, it is provided, for example, that video images recorded temporally after these video images by the video cameras 403, 405 are analyzed analogously in order to acquire the object detected in the earlier images in these later recorded video images to verify.
  • the first detected object is not detected again, it is determined, for example, that the first detected object is not real.
  • the first raised object is detected, for example, it is provided that a
  • Object speed is determined and / or that both the first detected object and the again detected object are classified.
  • the determined object velocity is greater than a predetermined object velocity threshold, it is determined that the detected raised object is not real.
  • the two classifications should differ, it is determined that the detected raised object is not real.
  • one or more criteria are provided which, when satisfied, result in an object being detected in the video images.
  • one criterion is that a different rectified video image from a single video camera is already sufficient, for example, to detect a raised object regardless of whether the other video cameras are recording different or the same video images.
  • Another criterion is that all video cameras are on
  • Another criterion is, for example, that for n video cameras where n is greater than or equal to 3, m video cameras must each capture a different video image, where m is greater than 1 and less than n to detect a raised object regardless of whether the other video cameras record different or the same video pictures.
  • the information that an object has been detected is reported or sent, for example, to a parking lot management system.
  • the parking management system uses this information for planning or managing an operation of the parking lot.
  • the parking management system operates the parking lot based on the information.
  • This information is for example in a remote control of a
  • Motor vehicle used which is located within the parking lot. This means, for example, that the parking management system remotely controls a motor vehicle within the parking space based on the detected object (s).
  • This information is transmitted, for example, to motor vehicles traveling autonomously within the parking space via a wireless communication network.
  • Video cameras time after each other recorded video images respectively analyze and track the detected raised object in an object detection in time to determine whether the detected object is real.
  • the video cameras are arranged spatially distributed within a parking space, which may be designed, for example, as a parking garage or as a parking garage, such that each point of a driving range is seen or recorded or monitored by at least two, for example at least three, video cameras. This means that the respective viewing areas each overlap in overlapping areas, with the
  • video images are rectified before comparison.
  • the corresponding rectified video images of the video cameras are compared with each other. For example, it is envisaged that if all
  • Video cameras in the driving range see the same image information at a certain point or at a certain point, it is determined that there is no object on the respective visual beam between the specific location and the video cameras. In this respect, no object is detected. However, if, for example, the image information of a video camera differs from the other video cameras at this point, then it is clear that there must be a raised object on the viewing beam of this one video camera. In this respect, a raised object is detected.
  • the temporal video images following these rectified video images are analyzed analogously to these earlier rectified video images, ie in particular rectified and compared with one another. In particular, the result of this comparison is used to determine whether, in object detection based on the previous video images, the corresponding detected raised object is real.
  • Image information in the sense of this description includes in particular also the case that the image information is maximally by a predetermined
  • Image information is identical or identical, as long as the differences are smaller than the predetermined tolerance value.
  • an object is detected only when the differences in the rectified video images are greater than a predetermined tolerance or a predetermined tolerance
  • an autonomously or remotely controlled motor vehicle within the parking lot on predetermined areas the driving range moves.
  • the video cameras are arranged, for example, such that their viewing areas overlap in the driving range. This overlap is chosen so that each point on the boundary surfaces (eg floor, wall) in the driving range is viewed or monitored by at least three video cameras. In particular, the arrangement is chosen such that each point on the boundary surface is viewed or monitored from different perspectives.
  • Sight rays to track for example, three video cameras that see this point. If more video cameras should be available, it is for example provided that three video cameras with as many different perspectives are selected from the several cameras. If no raised object is located on the visual beams of the video cameras at this point, then all the video cameras see the same image information or image information, which differ by a maximum of a predetermined tolerance value (see Fig. 4).
  • a brightness or a color of the surface of the floor changes, for example, if the floor is wet by moisture, this does not interfere with detection of the boundary surface inasmuch as all the video cameras see the same changed brightness or color.
  • a two-dimensional object for example a sheet, paper or foliage, is lying on the ground, then this sublime is generally not detected according to the concept according to the invention since all video cameras have the same image information or image information which is at most a predetermined one
  • the visual beams of the video cameras no longer meet the boundary surface (overlap area) as expected, but instead see different views of the raised object and thus take different views
  • a sublime object is, for example, a person or a motor vehicle.
  • one video camera sees the front of the object while the other video camera sees the back of the object.
  • the two sides differ significantly and the raised object can thus be detected insofar as the recorded video images differ.
  • This effect can be enhanced, for example, by brighter illumination of the scene on one side, ie of the overlapping area, so that an overlook of raised objects can be efficiently excluded.
  • this object appears brighter on the more illuminated side than on the dimly lit side so that the video cameras see different image information. This is true even for monochrome objects.
  • Video cameras with corresponding overlapping area Video cameras with corresponding overlapping area
  • Illumination of the scene and the time tracking or tracking of a detected raised object advantageously makes it possible to efficiently determine whether a detected raised object is actually real, resulting in the sum that raised objects are detected or detected efficiently can.
  • the inventive concept is in particular very robust against changes in brightness or point changes in brightness, for example due to solar radiation.
  • the information that a raised object is detected can be passed to a higher-level control system.
  • This control system may, for example, stop or enter a remote-controlled motor vehicle
  • the control system is included, for example, by the parking lot management system.
  • AVP Automated Valet Parking
  • automatic parking In the context of such an AVP process, provision is made in particular for motor vehicles to be parked automatically within a parking space and to be guided automatically from their parking position to a pick-up position at the end of a parking period, at which the motor vehicle can be picked up by its owner.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Signal Processing (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Devices For Checking Fares Or Tickets At Control Points (AREA)

Abstract

L'invention concerne un procédé de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement au moyen d'au moins deux caméras vidéo réparties dans l'espace à l'intérieur du parc de stationnement, les portées optiques desdites caméras se superposant dans une zone de chevauchement, ledit procédé comprenant les étapes suivantes : enregistrement d'images vidéo respectives de la zone de chevauchement au moyen des caméras vidéo, analyse des images vidéo enregistrées afin de détecter un objet saillant dans les images vidéo enregistrées, détermination, sur la base des images vidéo enregistrées, si, lors de la détection d'un objet saillant, l'objet saillant détecté est réel. La présente invention concerne en outre un système correspondant, un parc de stationnement ainsi qu'un programme d'ordinateur.
EP17780746.8A 2016-11-23 2017-10-09 Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement Withdrawn EP3545506A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102016223106.5A DE102016223106A1 (de) 2016-11-23 2016-11-23 Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
PCT/EP2017/075608 WO2018095640A1 (fr) 2016-11-23 2017-10-09 Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement

Publications (1)

Publication Number Publication Date
EP3545506A1 true EP3545506A1 (fr) 2019-10-02

Family

ID=60037618

Family Applications (1)

Application Number Title Priority Date Filing Date
EP17780746.8A Withdrawn EP3545506A1 (fr) 2016-11-23 2017-10-09 Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement

Country Status (6)

Country Link
US (1) US11080530B2 (fr)
EP (1) EP3545506A1 (fr)
JP (1) JP6806920B2 (fr)
CN (1) CN109983518B (fr)
DE (1) DE102016223106A1 (fr)
WO (1) WO2018095640A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016223171A1 (de) * 2016-11-23 2018-05-24 Robert Bosch Gmbh Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
DE102018217128A1 (de) * 2018-10-08 2020-04-09 Robert Bosch Gmbh Verfahren zur Erkennung von Entitäten
CN109657545B (zh) * 2018-11-10 2022-12-20 天津大学 一种基于多任务学习的行人检测方法
CN112468681B (zh) * 2019-09-06 2022-02-15 杭州海康威视数字技术股份有限公司 用于采集车辆信息的摄像装置

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3664892B2 (ja) * 1998-09-30 2005-06-29 松下電器産業株式会社 ステレオ画像処理方法および装置と侵入物体監視システム
JP3795810B2 (ja) * 2002-02-12 2006-07-12 株式会社東芝 物体検出方法及び装置
JP4854788B2 (ja) * 2007-07-04 2012-01-18 三菱電機株式会社 ナビゲーションシステム
DE102008023504A1 (de) * 2008-05-09 2009-11-19 Siemens Aktiengesellschaft Streckenüberwachungssystem für ein Fahrzeug und Verfahren zu dessen Betrieb
KR101182853B1 (ko) * 2008-12-19 2012-09-14 한국전자통신연구원 자동 주차 대행 시스템 및 방법
US20100258107A1 (en) 2009-04-09 2010-10-14 Chimex Pty Ltd Transportable wood-fired oven trailer
EP2372627A3 (fr) * 2010-04-01 2011-10-12 Richard E. Rowe Fourniture de services de ville utilisant des dispositifs mobiles et réseau de capteurs
JP5812598B2 (ja) * 2010-12-06 2015-11-17 富士通テン株式会社 物体検出装置
KR20120086140A (ko) * 2011-01-25 2012-08-02 한국전자통신연구원 맞춤 자동 주차 서비스를 제공하기 위한 단말과 장치 및 그 방법
US9129524B2 (en) * 2012-03-29 2015-09-08 Xerox Corporation Method of determining parking lot occupancy from digital camera images
US9171382B2 (en) 2012-08-06 2015-10-27 Cloudparc, Inc. Tracking speeding violations and controlling use of parking spaces using cameras
US8830322B2 (en) * 2012-08-06 2014-09-09 Cloudparc, Inc. Controlling use of a single multi-vehicle parking space and a restricted location within the single multi-vehicle parking space using multiple cameras
US9488483B2 (en) * 2013-05-17 2016-11-08 Honda Motor Co., Ltd. Localization using road markings
DE102014205180A1 (de) * 2014-03-20 2015-09-24 Robert Bosch Gmbh Verfahren und Vorrichtung zum Betreiben eines Fahrzeugs
US9858816B2 (en) 2014-05-21 2018-01-02 Regents Of The University Of Minnesota Determining parking space occupancy using a 3D representation
DE102014008578B4 (de) 2014-06-12 2016-02-18 Audi Ag Verfahren zur Ermittlung von Positionsdaten zur Nutzung beim Betrieb eines Fahrzeugsystems eines Kraftfahrzeugs und Positionsdatenermittlungs- und-verteilssystem
JP6405141B2 (ja) * 2014-07-22 2018-10-17 サクサ株式会社 撮像装置及び判定方法
JP6169544B2 (ja) * 2014-09-05 2017-07-26 本田技研工業株式会社 走行支援制御装置
DE102014221682A1 (de) * 2014-10-24 2016-04-28 Robert Bosch Gmbh Verfahren und Vorrichtung zum Betreiben eines Fahrzeugs
JP6354542B2 (ja) 2014-11-26 2018-07-11 株式会社デンソー 車両自動運転システム
DE102015201209A1 (de) 2015-01-26 2016-07-28 Robert Bosch Gmbh Valet Parking-Verfahren und Valet-Parking System
DE102015208053A1 (de) * 2015-04-30 2016-11-03 Robert Bosch Gmbh Verfahren und Vorrichtung zum Verringern einer Gefährdung für ein und/oder durch ein sich auf einem Parkplatz befindendes Fahrzeug

Also Published As

Publication number Publication date
CN109983518B (zh) 2022-08-23
JP6806920B2 (ja) 2021-01-06
US11080530B2 (en) 2021-08-03
US20190325225A1 (en) 2019-10-24
CN109983518A (zh) 2019-07-05
JP2020500390A (ja) 2020-01-09
DE102016223106A1 (de) 2018-05-24
WO2018095640A1 (fr) 2018-05-31

Similar Documents

Publication Publication Date Title
EP3187383B1 (fr) Procédé et dispositif d'actionnement externe d'un actionneur de véhicule automobile
EP3545507B1 (fr) Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement
DE102018203807A1 (de) Verfahren und Vorrichtung zur Erkennung und Bewertung von Fahrbahnzuständen und witterungsbedingten Umwelteinflüssen
WO2018095640A1 (fr) Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement
DE102012022336A1 (de) Verfahren zum Durchführen eines zumindest semi-autonomen Parkvorgangs eines Kraftfahrzeugs in eine Garage, Parkassistenzsystem und Kraftfahrzeug
WO2018095612A1 (fr) Procédé et système de détection d'un objet saillant se trouvant à l'intérieur d'un parc de stationnement
WO2009003793A2 (fr) Dispositif pour identifier et/ou classifier des modèles de mouvements dans une séquence d'images d'une scène de surveillance, procédé et programme informatique
DE102016223094A1 (de) Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
DE102015116542A1 (de) Verfahren zum Bestimmen einer Parkfläche zum Parken eines Kraftfahrzeugs, Fahrerassistenzsystem sowie Kraftfahrzeug
DE102018217746A1 (de) Verfahren zum Betrieb eines Fahrerassistenzsystems eines Kraftfahrzeugs und Kraftfahrzeug
DE102017212376A1 (de) Verfahren und System zum Detektieren eines freien Bereiches innerhalb eines Parkplatzes
DE102021116703A1 (de) Verfahren und System zur Vorhersage einer Trajektorie eines Zielfahrzeugs in einer Umgebung eines Fahrzeugs
DE102017212513A1 (de) Verfahren und System zum Detektieren eines freien Bereiches innerhalb eines Parkplatzes
DE102016114160A1 (de) Verfahren zum zumindest semi-autonomen Manövrieren eines Kraftfahrzeugs in eine Garage auf Grundlage von Ultraschallsignalen und Kamerabildern, Fahrerassistenzsystem sowie Kraftfahrzeug
DE102017123226A1 (de) Verfahren zum Bestimmen einer kritischen Höhe eines vorausliegenden Streckenabschnitts für ein Fahrzeug, das ein Zugfahrzeug und einen Anhänger umfasst
WO2020038944A1 (fr) Procédé et dispositif pour la detection d'objets sur des installations
EP4222039A1 (fr) Détection optique de voie ferrée
EP2254104B1 (fr) Procédé de reconnaissance automatique d'une modification de situation
DE102016223180A1 (de) Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
EP3576013A1 (fr) Évaluation d'un parcours d'une voie ferroviaire
DE102016223144A1 (de) Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
DE102017212379A1 (de) Verfahren und System zum Detektieren eines freien Bereiches innerhalb eines Parkplatzes
DE102021206475A1 (de) Hindernisdetektion im Gleisbereich auf Basis von Tiefendaten
DE102016223118A1 (de) Verfahren und System zum Detektieren eines sich innerhalb eines Parkplatzes befindenden erhabenen Objekts
DE102018010042A1 (de) Verfahren zum Erkennen wenigstens eines sich in einer Umgebung eines Kraftfahrzeugs befindenden Objekts

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20190624

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: ROBERT BOSCH GMBH

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20211005

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20220216