WO2024089080A1 - Procédé de reconnaissance et de classification de marquages routiers surélevés - Google Patents

Procédé de reconnaissance et de classification de marquages routiers surélevés Download PDF

Info

Publication number
WO2024089080A1
WO2024089080A1 PCT/EP2023/079734 EP2023079734W WO2024089080A1 WO 2024089080 A1 WO2024089080 A1 WO 2024089080A1 EP 2023079734 W EP2023079734 W EP 2023079734W WO 2024089080 A1 WO2024089080 A1 WO 2024089080A1
Authority
WO
WIPO (PCT)
Prior art keywords
road markings
coded
carried out
raised road
lidar system
Prior art date
Application number
PCT/EP2023/079734
Other languages
German (de)
English (en)
Inventor
Annette Frederiksen
Zoltan Ersek
Axel Fink
Mustafa Kamil
Mario Lietz
Alf Neustadt
Arne Josten
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 WO2024089080A1 publication Critical patent/WO2024089080A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Definitions

  • the invention relates to a method for detecting and classifying raised road markings using a LiDAR system of a vehicle.
  • the LiDAR system comprises a transmitting unit, a receiving unit, at least one laser beam source and at least one detector. Furthermore, the invention relates to the use of the method in a LiDAR system for the reliable detection and drivability classification of raised road markings.
  • DE 10 2011 082 477 A1 relates to a method and a system for creating a digital image of a vehicle's surroundings.
  • the system represents a driver assistance system for autonomous driving.
  • measurement data on the vehicle's surroundings are recorded using a vehicle-based first sensor system and at least one optically detectable marking that is fixedly arranged in the vehicle's surroundings is recorded using a vehicle-based video system.
  • At least one optically detectable characteristic of the at least one marking is recognized from the recording data of the video system and the relative position and orientation of the marking to the vehicle's surroundings is determined.
  • EP 3 529 561 Bl relates to a system and a method for generating digital road models from aerial or satellite images and from vehicle-recorded data.
  • At least one trajectory of a vehicle for the at least one road section is received in a vehicle-external database.
  • At least one image is received which contains at least shows parts of the at least one road section, wherein the image has a perspective that corresponds to an image taken from an elevated position substantially vertically downwards.
  • the at least one trajectory is superimposed with the at least one image such that the at least one trajectory corresponds to the course of a road in the at least one image.
  • the at least one image is then analyzed in a corridor that extends along the trajectory and encloses it, and driving or position-relevant features of the road section in the corridor are recognized.
  • DE 10 2019 106 213 A1 relates to a method for determining at least one item of position information of at least one object in a surveillance area using an optical detection device, as well as to an optical detection device.
  • a method for determining at least one item of position information of at least one object in a surveillance area using an optical detection device, as well as the detection device, are described here.
  • at least one optical transmission signal with a main transmission signal propagation axis is sent into the surveillance area. At least part of the at least one transmission signal is reflected as a reception signal at an object present in the surveillance area, and at least part of the reception signal, the initial signal propagation main axis of which runs parallel to the main transmission signal propagation axis at least on the side facing the object, is varied.
  • the LiDAR sensor system has the task of reliably detecting objects with particularly low reflectivity (e.g. 5%) at a great distance, such as 200 m, as well as retroreflectors with particularly high reflectivity (e.g. 10,000%) at a short distance (e.g. a few meters).
  • the resulting dynamic factor between the darkest and the brightest object to be detected is up to 2000 at the same distance; in addition, there is the part of the signal intensity that scales quadratically with the distance (has a degrading effect).
  • the LiDAR sensor system is set up according to functional reliability on If the detection of weakly reflective objects at the greatest possible distance is limited, the probability of optical saturation of the detector with scattered light-induced false detections, also known as "crosstalk", increases. This is a significant effect, especially for close and highly reflective objects.
  • the challenge here is to design the optical design within a LiDAR sensor system consisting of transmit and receive lenses, laser diodes and detector pixels in such a way that the dynamic range can be reliably recorded.
  • a method for detecting and classifying raised road markings by means of a LiDAR system of a vehicle comprising a transmitting unit, a receiving unit, at least one laser beam source and at least one detector, with at least the following method steps, which are carried out individually or in combination with one another: a) carrying out a comparison between a map containing information on the course of the road and possible raised road markings that can be detected along the course of the road by the LiDAR system, b) determining normal road markings from at least one intensity-coded or background-light-coded 3D point cloud and comparing them with possible raised road markings that can be detected along the course of the road by the LiDAR system, c) determining context-sensitive information from an accompanying infrastructure or from a traffic planning relevance of installation locations of raised road markings and d) analyzing the intensity-coded or background-light-coded 3D point cloud for regular patterns of an arrangement of raised road markings.
  • the method proposed according to the invention can achieve a reliable distinction between false detections produced by raised road markings and objects that cannot actually be driven over.
  • a map comparison is carried out based on a geoposition of the vehicle with the map or observations of vehicles driving ahead in a cloud-based database.
  • an approximation of an analytically describable curve or a geometric plane is carried out according to method step d), which is carried out in such a way that the possible raised road markings to be recognized are suitably connected to one another and a continuous check for plausibility is carried out.
  • a regular repetition of possible raised road markings to be detected can advantageously be carried out according to method step d), each at the same distance from one another along the analytically describable curve or the geometric plane.
  • a circle can be drawn around possible raised road markings to be recognized, such that intersection points of adjacent circles form horizontal, vertical or mutually orthogonal straight lines. Arrangement patterns of road markings can be extrapolated using the horizontal, vertical or mutually orthogonal straight lines.
  • geometric plausibility checks are carried out according to method step d) to determine a geometric regularity of the occurrence of raised road markings for demarcation against individual objects lying on the road.
  • a targeted forecast is carried out in such a way that a targeted extrapolation to further raised road markings is carried out from the intensity-coded 3D point cloud on the basis of less visible raised road markings as a continuation of an edge geometric regularity.
  • a comparison is made between the intensity-coded 3D point clouds on the one hand and the background-light-coded 3D point clouds on the other.
  • An intensity-coded 3D point cloud is a cloud of 3D points with a brightness value corresponding to the received signal of the reflected laser pulse.
  • a background-light-coded 3D point cloud is a cloud of 3D points that have a brightness value that corresponds to the brightness of the received background noise signal.
  • the invention relates to the use of the method in a LiDAR system for the reliable detection and overridability classification of raised road markings.
  • the solution proposed according to the invention in the form of the method according to the invention enables a reliable detection and classification of the ability to drive over raised road markings. This enables an accurate distinction to be made between these and objects that cannot actually be driven over, for example warning beacons, traffic signs or the like, which have a not inconsiderable height so that the vehicle and its occupants would inevitably be damaged.
  • the solution proposed according to the invention enables a reliable detection and classification of raised road markings by analyzing geometric structures, installation models, number, distance and drop in the optical crosstalk intensity, over distance and angle as well as other recurring regularities. Of crucial importance in the method proposed according to the invention is that a raised road marking rarely appears alone and without context.
  • a raised road marking is generally used in conjunction with other raised road markings and is associated with accompanying infrastructure or traffic planning relevance with regard to the installation location.
  • Examples of danger spots include, for example, merging lanes, the proximity an airport, motorway junctions, construction sites or the like.
  • the solution proposed according to the invention can be used to reliably distinguish between false detection induced by raised road markings and objects that cannot actually be driven over, for example in the form of warning beacons extending in a vertical direction.
  • the method proposed according to the invention can achieve a not inconsiderable improvement in the processed point cloud quality after optical crosstalk filtering and thus a considerable improvement in the performance of a LiDAR sensor system.
  • the solution proposed according to the invention can effectively compensate for optical crosstalk that occurs after it has been detected.
  • the method proposed according to the invention can ensure that the LiDAR sensor of a LiDAR sensor system generates a crosstalk-free point cloud when raised road markings occur. This makes it easy and reliable to identify a key source of the optical crosstalk that occurs.
  • the method proposed according to the invention can support data integrity within the SD point cloud.
  • Figure 1 a vehicle with a LiDAR system in front of a raised lane marking, a lane course and a 3D point cloud derived from the lane course,
  • Figure 2 shows a raised road marking, emerging crosstalk areas and identified crosstalk areas and a tolerance range limited by them
  • Figure 3 is an exemplary representation of raised road markings arranged in regular patterns along lanes of a curved roadway
  • Figure 4 shows a perspective view of a narrowing of the roadway, bordered by pairs of raised road markings on both sides, as well as an extrapolation of this scene and
  • Figure 5 a circle made up of a number of raised road markings, bounded by two line patterns.
  • Figure 1 shows a vehicle 10 that is equipped with a LiDAR system 36.
  • a roadway 12 In front of the vehicle 10, there is a roadway 12 that has a raised road marking 14 that is in the field of view of the LiDAR system 36.
  • This raised road marking 14 has a height 16 that is usually a few centimeters.
  • Figure 1 also shows a field of view of the scene extending in front of the vehicle 10.
  • a roadway 20 is shown in this scene as a straight line 22.
  • warning beacons 26 which extend in a vertical direction from the surface of the roadway 12.
  • two raised road markings 14 at a distance from each other.
  • an intensity-coded or background-light-coded 3D point cloud 28 is shown, which represents the recording of the scene according to the course of the roadway 20 by the LiDAR system 36. From the representation of the intensity-coded or background-light-coded 3D point cloud 28 according to Figure 1, it can be seen that the warning beacons 26 extending in the vertical direction are shown as objects 30 classified as non-driveable. In contrast, the raised road markings 14 on the roadway 12, which are spaced apart from one another in the scene, are shown as objects 32 extending in the horizontal direction, and thus as objects 34 that are reproduced in a distorted manner. Despite the relatively low construction height 16 of the raised road markings 14, they appear as extended objects 32 in the intensity-coded or background-light-coded 3D point cloud 28 and cannot be clearly classified as drivable due to their crosstalk properties.
  • the representation according to Figure 1.1 schematically shows the components of the LiDAR system 36 that are installed in the vehicle 10 shown in Figure 1.
  • the LiDAR system 36 comprises a transmitting unit 38 that includes at least one laser beam source 46.
  • the LiDAR system 36 also comprises a receiving unit 44 that contains a detector 48 onto which radiation reflected from an object detected by the LiDAR system 36 is reflected.
  • Said LiDAR system 36 can also comprise other components that are not shown in detail here and is generally arranged in the front area of the vehicle 10 to detect the scene in front of the vehicle 10.
  • Figure 2 shows a representation of a raised road marking 14 and crosstalk areas 18 emanating from it.
  • Figure 2 shows that the raised road marking 14 has a first retroreflective surface 40 and a second retroreflective surface 42 opposite it.
  • Said retroreflective surfaces 40, 42 are recorded by a LiDAR system 36 as an intensity-coded or background-light-coded 3D point cloud 28.
  • a LiDAR system 36 Above and below the raised road marking 14 there are crosstalk areas 18, which can be divided into a tolerance range 50 and identified crosstalk areas 52.
  • the identified crosstalk areas 52 are areas identified as safe crosstalk areas 52. Based on the crosstalk areas 18, it cannot be determined whether the raised road marking 14 can be correctly classified as being drivable. Therefore, such detection by the LiDAR system 36 would result in an unjustified false braking or an unjustified abort of a lane change with the resulting disadvantages for driving experience, trajectory planning and accident safety.
  • a crosstalk point 54 can be misclassified as an object point 56, which will occur with a probability of, for example, less than 5%.
  • Reference number 56 designates an object point that is misclassified as optical crosstalk, although the object point 56 is part of the raised road marking 14.
  • Figure 2 uses the object point 56 to visualize a key performance requirement, i.e. the object point 56 must be recognized by the LiDAR system 36.
  • a reliable detection and reliable overridability classification of raised road markings 14 can be carried out, which is achieved by an analysis of geometric structures, installation models, number, distance and drop of the Crosstalk intensity can be measured over distance and angle as well as other regularities.
  • the decisive factor in this context is the fact that a raised road marking 14 rarely occurs alone or free of context, such as other raised road markings 14, an accompanying infrastructure or traffic planning relevance of installation locations, such as near an airport, in merging areas, at danger points or the like.
  • the method proposed according to the invention is based on the fundamental approach that raised road markings 14 rarely appear alone, but that they appear in arrangements 60 of regular patterns 78, as shown in Figures 3, 4 and 5.
  • 14 different information sources can be used to detect and reliably classify raised road markings, either individually or in combination in the sense of information fusion.
  • a comparison can be made between a map with information on the course of the road and raised road markings 14 that can possibly be recognized on a curve.
  • a map comparison is carried out based on the geoposition of the vehicle 10 with the map or by observing vehicles driving ahead, for example via a cloud-based database.
  • a road marking is used from an intensity-coded or a background-light-coded 3D point cloud 28 and a comparison is made with raised road markings 14 that may be recognizable on a curve 24, as shown for example in Figure 3.
  • a method step c) context-sensitive information of an accompanying infrastructure or traffic planning relevance of installation locations of infrastructure components, for example for danger spots, to indicate proximity to an airport or hospital, or as an indication of lane junctions, government buildings, tunnels, etc.
  • the intensity-coded or background-light-coded 3D point cloud 28 can also be used to detect the occurrence of regular patterns 78 of arrangements 60 of raised road markings 14.
  • a search is carried out for the occurrence of regular patterns 78 within which the raised road markings 14 are located at certain positions.
  • an approximation of an analytically describable curve 62 can be made, as shown in Figure 3, or a geometric plane 65 can be shown (see Figure 3), within which the possible raised road markings 14 to be recognized are suitably connected to one another and a continuous check for plausibility is carried out.
  • the intensity-coded or background-light-coded 3D point cloud 28 can also be examined for regularly occurring repetitions of possible raised road markings 14 to be recognized, which each have an equal distance 76 from one another, wherein the regular repetition of possible raised road markings 14 to be recognized with the same distance 76 from one another can be found along curves 24 or straight lines 22 according to the roadway course 20.
  • a circle 70 can be mentally drawn around a possible raised road marking 14 to be recognized, which circle has a sufficiently large radius, so that the resulting intersection points of the circles 70 result in straight lines that are orthogonal to one another, both horizontally and vertically and relative to one another, and run parallel to one another.
  • a large number of geometric plausibility checks can be applied to the intensity-coded 3D point cloud 28.
  • the aim is to prove the occurrence of a geometric regularity as a distinguishing feature for example, to a single lost load lying on lane 12.
  • setup models of raised road markings 14 can be generated as clear indications of these as man-made, artificial infrastructure measures. For example, a speed warning can be surrounded by a circular collection of raised road markings 14, as shown in Figure 5, for example, so that for recognition only a correlation of the intensity-coded or background-light-coded 3D point cloud 28 with a circular pattern (see position 70 in Figure 5) would have to be carried out.
  • Optical crosstalk 18 itself can also provide reliable information for detecting raised road markings 14.
  • the intensity of false detections decreases with the angle of view in the LiDAR system 36 and over the distance in a non-linear but analytically describable manner. Not only can currently available information sources be used to make the classification decision, but it is also possible to look ahead in a targeted manner, resulting in an extrapolation 68, as shown in connection with Figure 4.
  • the extrapolation 68 is derived from a few visible raised road markings 14, so that a continuation of a once recognized geometric regularity, in the case of Figure 4 a regular distance 76 between the individual raised road markings 14 and a gradual reduction in the distance between them, can be concluded, so that the extrapolation 68 of the further course of the roadway 12 indicated in Figure 4 results.
  • retroreflective surfaces 40, 42 basically reflect the incident light back in the same direction from which it entered, retroreflective surfaces 40, 42 appear less intense in background light-coded point clouds 28 than in intensity-coded 3D point clouds 28, since the background light of the first-mentioned coding is not measured.
  • the Sunlight is not reflected to the LiDAR sensor, but back into the sky.
  • Figure 3 shows a representation of raised road markings 14 which are arranged, for example, along lanes 80 of the roadway 12 in regular patterns 78.
  • Figure 3 shows that the individual raised road markings 14 have a very low construction height 16, i.e. represent objects that can be driven over.
  • the raised road markings 14 serve as boundaries of lanes 80 of a multi-lane roadway 12.
  • the individual raised road markings 14 are provided in an arrangement 60 which, on the one hand, is adapted to the curve 24 of the individual lanes 80 of the roadway 12 and, on the other hand, has a regular distance 76 from one another. In the vertical direction, the individual raised road markings 14 are evenly spaced from one another and in this context serve as boundaries of the individual lanes 80 of the roadway 12.
  • the arrangement 60 of the individual raised road markings 14 is shown in Figure 3 as an analytically describable curve 62.
  • the roadway 12 with a number of lanes 80, which are separated from one another by the regular patterns 78 of raised road markings 14, is delimited by a road edge 64 on the right-hand side.
  • a geometric plane 65 is designated which represents a straight course 22 of the roadway 12.
  • Figure 4 shows that the raised road markings 14 arranged in pairs on the right and left in the geometric plane 65 are arranged at identical distances 76 from one another.
  • an extrapolation 68 can be obtained from the geometric plane 65, which continues the recognized regular pattern 78 of the arrangement 60 according to the straight course 22 along the roadway 12.
  • further information regarding the route further ahead of the vehicle 10, i.e. the roadway 12 can be obtained from a few visible raised road markings 14 by means of extrapolation 68.
  • Figure 5 shows a geometric plane 65 which is defined by a first line pattern 72 on the left side and by a second line pattern 74 on the right side is limited. From the illustration according to Figure 5 it can be seen that the individual raised road markings 14 are arranged along the first line pattern 72 and the second line pattern 74 in regular patterns 78 with an identical distance 76 from one another. In the middle, for example between the two line patterns 72, 74, a circle 70 made up of individual raised road markings 14 arranged in a regular pattern 78 is shown. In relation to the pattern of the circle 70, the individual raised road markings 14 have an identical distance 76 from one another.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé de reconnaissance et de classification de marquages routiers surélevés (14) au moyen d'un système lidar (36) d'un véhicule (10). Le système lidar (36) comprend une unité d'émission (38), une unité de réception (44), au moins une source de faisceau laser (46) et au moins un détecteur (48). Les étapes suivantes du procédé sont exécutées individuellement ou en combinaison : a) la comparaison d'une carte, qui contient des informations sur la route (20), avec d'éventuels marquages routiers surélevés (14) à reconnaître le long de la route (20) par le système lidar (36) ; b) la détermination de marquages routiers normaux à partir d'au moins un nuage de points 3D codé selon l'intensité ou la lumière de fond (28) et la comparaison avec d'éventuels marquages routiers surélevés (14) à reconnaître le long de la route (20) par le système lidar (36) ; c) la détermination d'informations contextuelles provenant d'une infrastructure d'accompagnement ou d'un plan de circulation concernant les emplacements d'installation des marquages routiers surélevés (14) ; et/ou d) l'analyse du nuage de points 3D codé selon l'intensité ou la lumière de fond (28) pour rechercher des motifs réguliers (78) d'un agencement (60) de marquages routiers surélevés (14).
PCT/EP2023/079734 2022-10-26 2023-10-25 Procédé de reconnaissance et de classification de marquages routiers surélevés WO2024089080A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102022211343.8A DE102022211343A1 (de) 2022-10-26 2022-10-26 Verfahren zur Erkennung und Klassifizierung erhöhter Fahrbahnmarkierungen
DE102022211343.8 2022-10-26

Publications (1)

Publication Number Publication Date
WO2024089080A1 true WO2024089080A1 (fr) 2024-05-02

Family

ID=88598861

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2023/079734 WO2024089080A1 (fr) 2022-10-26 2023-10-25 Procédé de reconnaissance et de classification de marquages routiers surélevés

Country Status (2)

Country Link
DE (1) DE102022211343A1 (fr)
WO (1) WO2024089080A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011082477A1 (de) 2011-09-12 2013-03-14 Robert Bosch Gmbh Verfahren und System zur Erstellung einer digitalen Abbildung eines Fahrzeugumfeldes
WO2019161134A1 (fr) * 2018-02-14 2019-08-22 TuSimple Localisation de marquage de voie
WO2020154967A1 (fr) * 2019-01-30 2020-08-06 Baidu.Com Times Technology (Beijing) Co., Ltd. Système de partition de carte pour véhicules autonomes
DE102019106213A1 (de) 2019-03-12 2020-10-01 Valeo Schalter Und Sensoren Gmbh Verfahren zur Bestimmung wenigstens einer Positionsinformation wenigstens eines Objekts in einem Überwachungsbereich mit einer optischen Detektionsvorrichtung und optische Detektionsvorrichtung
EP3529561B1 (fr) 2016-10-18 2020-12-09 Continental Automotive GmbH Système et procédé permettant de produire des modèles routiers numériques à partir d'images aériennes et satellitaires et de donnes collectées par des véhicules

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011082477A1 (de) 2011-09-12 2013-03-14 Robert Bosch Gmbh Verfahren und System zur Erstellung einer digitalen Abbildung eines Fahrzeugumfeldes
EP3529561B1 (fr) 2016-10-18 2020-12-09 Continental Automotive GmbH Système et procédé permettant de produire des modèles routiers numériques à partir d'images aériennes et satellitaires et de donnes collectées par des véhicules
WO2019161134A1 (fr) * 2018-02-14 2019-08-22 TuSimple Localisation de marquage de voie
WO2020154967A1 (fr) * 2019-01-30 2020-08-06 Baidu.Com Times Technology (Beijing) Co., Ltd. Système de partition de carte pour véhicules autonomes
DE102019106213A1 (de) 2019-03-12 2020-10-01 Valeo Schalter Und Sensoren Gmbh Verfahren zur Bestimmung wenigstens einer Positionsinformation wenigstens eines Objekts in einem Überwachungsbereich mit einer optischen Detektionsvorrichtung und optische Detektionsvorrichtung

Also Published As

Publication number Publication date
DE102022211343A1 (de) 2024-05-02

Similar Documents

Publication Publication Date Title
DE10114932B4 (de) Dreidimensionale Umfelderfassung
EP1557692B1 (fr) Procédé de détection des emplacements dangereux et/ou des chantiers de construction marqués à proximité des routes
DE102004016024B4 (de) Ausfilterung eines stillstehenden Objekts für ein Seitenobjekterfassungssystem
EP2824478B1 (fr) Capteur optoélectronique et procédé destiné à la détection d'objets et à la détermination de distance dans une zone de surveillance
EP1267178B1 (fr) Procédé de traitement d'une image à haute définition
DE69113881T2 (de) Verfahren und Gerät zur Vermeidung einer Kollision zwischen einem Kraftfahrzeug und Hindernissen.
EP1628141B1 (fr) Procède de triangulation ayant des diodes laser et une caméra pour determiner la distance pour les applications arret-demarrage des véhicules automobiles
DE102009006113A1 (de) Vorrichtung und Verfahren zur Sensorfusion mit dynamischen Objekten
DE102004003850A1 (de) Verfahren zur Erkennung von Markierungen auf einer Fahrbahn
EP3857256B1 (fr) Procédé de détection d'usagers de la voie publique
DE102018104243B3 (de) Verfahren und System zur Erkennung von für ein Fahrzeug geeigneten Parklücken
DE3642196A1 (de) Optoelektronische kollisionsschutzvorrichtung fuer fahrzeuge
DE102018008442A1 (de) Verfahren zur Wetter- und/oder Sichtweitenerkennung
DE102009031319A1 (de) Verfahren und System zur Bestimmung einer Fahrzeugklasse
DE102014212216A1 (de) Verfahren und Fahrerassistenzsystem zur Erfassung eines Fahrzeugumfel-des
EP3193276B1 (fr) Dispositif de detection et procede destine a la reconnaissance d'essieux de vehicule
EP1298012B1 (fr) Procédé de reconnaissance et de poursuite d'objets
DE10148070A1 (de) Verfahren zur Erkennung und Verfolgung von Objekten
DE10148062A1 (de) Verfahren zur Verarbeitung eines tiefenaufgelösten Bildes
DE10344299B4 (de) Klassifizierung der in einer Umgebung eines Kraftfahrzeugs befindlichen Objekte
WO2024089080A1 (fr) Procédé de reconnaissance et de classification de marquages routiers surélevés
DE102016116782A1 (de) System und Verfahren zum Erfassen von Eigenschaften mindestens eines Rades eines Schienenfahrzeugs
DE102019201088A1 (de) Verfahren zum Erkennen von Fahrbahnmarkierungen
DE102018121158A1 (de) Verfahren zum Erfassen von Bodenabtastpunkten und Fahrerunterstützungssystem, das dafür konfiguriert ist, ein derartiges Verfahren auszuführen
WO2023039620A1 (fr) Procédé de mesure du volume de trafic à l'aide de das

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: 23798170

Country of ref document: EP

Kind code of ref document: A1