[go: up one dir, main page]

EP2917759A1 - Method and device for recognising traffic signs for a vehicle - Google Patents

Method and device for recognising traffic signs for a vehicle

Info

Publication number
EP2917759A1
EP2917759A1 EP13795994.6A EP13795994A EP2917759A1 EP 2917759 A1 EP2917759 A1 EP 2917759A1 EP 13795994 A EP13795994 A EP 13795994A EP 2917759 A1 EP2917759 A1 EP 2917759A1
Authority
EP
European Patent Office
Prior art keywords
information
traffic sign
data
traffic
radar
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Withdrawn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
EP13795994.6A
Other languages
German (de)
French (fr)
Inventor
Marc Fischer
Peter Van Der Vegte
Ulrich Möller
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.)
Conti Temic Microelectronic GmbH
Original Assignee
Conti Temic Microelectronic 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 Conti Temic Microelectronic GmbH filed Critical Conti Temic Microelectronic GmbH
Publication of EP2917759A1 publication Critical patent/EP2917759A1/en
Withdrawn legal-status Critical Current

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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
    • G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
    • G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9321—Velocity regulation, e.g. cruise control
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9322—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using additional data, e.g. driver condition, road state or weather data
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9323—Alternative operation using light waves
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9329—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles cooperating with reflectors or transponders

Definitions

  • Radio-based systems for traffic sign recognition are state of the art.
  • a traffic sign transmits its meaning and possibly its position via radio to a radio receiver in the vehicle.
  • Traffic signs are detected by a camera sensor system in the vehicle. Such systems can be supported by a navigation system with electronic map.
  • the traffic sign recognition (VZE) with a camera system is based on two essential steps. Step 1 is the search for circular (e.g., for speed limits) or rectangular structures (e.g., location signs). If suitable candidates are recognized, they are classified in a further step. There are e.g. detected with the help of pattern recognition numbers.
  • An essential idea of the invention is to support the traffic sign recognition based on a camera system by information from a radar or Lidarsensorsystems.
  • a radar or Lidarsensorsystems For this purpose, in particular sensor systems can be used, which are used for an ACC function or an emergency brake function.
  • Based on the data of a radar sensor or Lidarsensors at least one of following information
  • the at least one information from radar or lidar data is used to check the plausibility of data from the camera sensor. This applies in particular to one of the information a) -e) according to
  • a traffic sign or a potential traffic sign is detected by radar, this can be communicated to the VZE. There, the information (presence, distance, size, direction, etc.) can be used for plausibility.
  • an image processing for the evaluation of camera data is provided such that in a region in which an information according to a) -e) is present, a targeted search is made for traffic signs; through a more detailed evaluation of the
  • the country information can by a navigation device or a radio information (c2x, radio, traffic, ...) or by a Envelope detection sensor can be provided.
  • the latter for example, by a camera sensor, the
  • image processing for evaluating camera data is provided in such a way that traffic signs are searched only in a region in which information according to a) -e) exists. This procedure saves computing time when processing the image data of a camera system or because the computing time for
  • Scope evaluated for a traffic sign This is especially true in a multi-vehicle environment
  • Traffic signs can be spatially assigned to these structures. This can be particularly characteristic of a
  • Plausibilmaschine serve to discard or confirm potential traffic signs, depending on the location of the potential traffic signs to the track-limiting structures.
  • the distance or position information can be used for an assignment.
  • position of the traffic sign is decisive for the assignment to the lane, street etc. Knowing the location of the traffic sign so you can relate this with your own lane. For example, distant signs can be discarded if they are not assigned to their own lane.
  • an image processing for the evaluation of camera data is such
  • the presence of a traffic sign based on data from a radar or lidar system in
  • Position information with navigation data are correlated.
  • Position information with navigation data are correlated.
  • the strength of the radiation reflected on an object or quantities which can be deduced therefrom e.g.
  • Radar or lidar backscatter cross section; road sign are due to their nature (usually metal) good reflectors, ie for the recognition can be exploited that the remindstreuquerrough or the strength of the reflection must exceed a predetermined threshold or must be within a predetermined range of values
  • traffic signs are stationary objects, so that can be used for the recognition that the relative speed of
  • Relative speed to other stationary objects e.g. Crash barriers, must be zero.
  • the predetermined range of values may in particular be derived from further information, e.g. the position of the object
  • Gantries static objects that have a relatively large extent and that are located above the carriageway are located above the carriageway.
  • Probability value assigned which indicates the probability with which the corresponding object
  • Traffic sign could be.
  • information about the position of an object is additionally provided with information of a
  • Navigation system correlates. Especially near intersections, there is an increased probability for

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Mechanical Engineering (AREA)

Abstract

Disclosed are a method and a device for recognising traffic signs with an environment detection sensor system for a vehicle, comprising at least one camera sensor and a radar sensor and/or LIDAR sensor. One the basis of the data from the at least one radar sensor and/or LIDAR sensor, at least one of the following pieces of information is obtained and used for traffic sign recognition: the presence of a traffic sign or - the size of a traffic sign, - position of a traffic sign, - distance and/or orientation of a traffic sign, - bridge-like structure, - position and/or type of preceding vehicle, - position of lane-delimiting structures.

Description

Verfahren und Vorrichtung zur Erkennung von Verkehrszeichen für ein Fahrzeug Method and device for detecting traffic signs for a vehicle
Funkbasierte Systeme zur Verkehrszeichenerkennung sind Stand der Technik. Ein Verkehrszeichen überträgt seinen Sinngehalt und ggf. seine Position via Funk an einem Funkempfänger im Fahrzeug . Radio-based systems for traffic sign recognition are state of the art. A traffic sign transmits its meaning and possibly its position via radio to a radio receiver in the vehicle.
Ein alternativer Ansatz zur Verkehrszeichenerkennung ist bereits in Serienfahrzeugen umgesetzt. Verkehrszeichen werden mit einem Kamerasensorsystem im Fahrzeug erkannt. Solche Systeme können von einem Navigationssystem mit elektronischer Karte unterstützt werden. Die Verkehrszeichenerkennung (VZE) mit einem Kamerasystem beruht auf zwei wesentlichen Schritten. Schritt 1 ist die Suche nach kreisförmigen (z.B. für Geschwindigkeitsbegrenzungen) bzw. rechteckigen Strukturen (z.B. Ortsschilder). Sind geeignete Kandidaten erkannt, so werden sie in einem weiteren Schritt klassifiziert. Es werden z.B. mit Hilfe von Mustererkennung Zahlen erkannt.  An alternative approach to traffic sign recognition has already been implemented in production vehicles. Traffic signs are detected by a camera sensor system in the vehicle. Such systems can be supported by a navigation system with electronic map. The traffic sign recognition (VZE) with a camera system is based on two essential steps. Step 1 is the search for circular (e.g., for speed limits) or rectangular structures (e.g., location signs). If suitable candidates are recognized, they are classified in a further step. There are e.g. detected with the help of pattern recognition numbers.
Es ist die Aufgabe der hier vorliegenden Erfindung die Funktion eines Systems zur Verkehrszeichenerkennung, das auf Daten eines Kamerasensorsystems basiert, zu verbessern. It is the object of the present invention to improve the function of a traffic sign recognition system based on data from a camera sensor system.
Diese Aufgabe wird durch die Merkmale der unabhängigen Ansprüche gelöst. This object is solved by the features of the independent claims.
Ein wesentlicher Gedanke der Erfindung ist es, die Verkehrszeichenerkennung basierend auf einem Kamerasystem, durch Informationen eines Radar- oder Lidarsensorsystems zu unterstützen. Hierzu können insbesondere Sensorsysteme verwendet werden, die für eine ACC-Funktion oder eine Notbremsfunktion eingesetzt werden. Basierend auf den Daten eines Radarsensors bzw. Lidarsensors wird zumindest eine der folgenden Informationen An essential idea of the invention is to support the traffic sign recognition based on a camera system by information from a radar or Lidarsensorsystems. For this purpose, in particular sensor systems can be used, which are used for an ACC function or an emergency brake function. Based on the data of a radar sensor or Lidarsensors at least one of following information
- das Vorhandensein eines Verkehrszeichens oder  - the presence of a traffic sign or
- die Größe eines Verkehrszeichens  - the size of a traffic sign
- Position eines Verkehrszeichens  - Position of a traffic sign
- Entfernung und/oder Richtung eines Verkehrszeichens - Distance and / or direction of a traffic sign
- Brückenartige Struktur, insbesondere Schilderbrücke- Bridge-like structure, in particular gantries
- Position oder Art vorausfahrendes Fahrzeug, Position or type of vehicle ahead,
insbesondere LKW  especially trucks
- Position spurbegrenzender Strukturen  - Position of track-limiting structures
gewonnen und zur Verkehrszeichenerkennung genutzt. won and used for traffic sign recognition.
In einer bevorzugten Ausgestaltung der Erfindung wird die zumindest eine Information aus Radar- bzw. Lidardaten zur Plausibilisierung von Daten des Kamerasensors genutzt. Dies gilt insbesondere für eine der Informationen a)-e) gemäß In a preferred embodiment of the invention, the at least one information from radar or lidar data is used to check the plausibility of data from the camera sensor. This applies in particular to one of the information a) -e) according to
Anspruch 1. Claim 1.
Wird mittels Radar ein Verkehrszeichen oder ein potentielles Verkehrszeichen erkannt, so kann dies der VZE mitgeteilt werden. Dort kann die Information (Vorhandensein, Entfernung, Größe, Richtung etc.) zur Plausibilisierung verwendet werden.  If a traffic sign or a potential traffic sign is detected by radar, this can be communicated to the VZE. There, the information (presence, distance, size, direction, etc.) can be used for plausibility.
In einer weiteren positiven Ausgestaltung der Erfindung ist eine Bildverarbeitung zur Auswertung von Kameradaten derart vorgesehen, dass in einem Bereich, in dem eine Information nach a)-e) vorliegt, gezielt nach Verkehrszeichen gesucht wird, das kann z.B. durch eine genauere Auswertung der In a further advantageous embodiment of the invention, an image processing for the evaluation of camera data is provided such that in a region in which an information according to a) -e) is present, a targeted search is made for traffic signs; through a more detailed evaluation of the
Bilddaten mit erhöhter (Rechen-) Intensität erfolgen oder es wird gezielt nach zuvor in einem Speicher hinterlegten Image data with increased (arithmetic) intensity done or it is targeted to previously stored in a memory
zusammenhängenden Strukturen oder Mustern oder Farben gesucht, die typisch für der Form und dem Inhalt von Verkehrszeichen sind. Insbesondere können die hinterlegten Vorlagen related structures or patterns or colors that are typical of the shape and content of traffic signs. In particular, the deposited templates
länderspezifisch ausgewählt werden. Die Länderinformation kann durch ein Navigationsgerät oder eine Funkinformation (c2x, Radio, Verkehrsfunk, ... ) oder durch einen Umfelderfassungssensor zur Verfügung gestellt werden. Letzteres z.B. durch einen Kamerasensor, der zur selected country-specific. The country information can by a navigation device or a radio information (c2x, radio, traffic, ...) or by a Envelope detection sensor can be provided. The latter, for example, by a camera sensor, the
Verkehrszeichenerkennung ausgebildet ist. Durch dieses Traffic sign recognition is formed. Because of this
Vorgehen wird sichergestellt, dass kein Verkehrszeichen übersehen wird. This procedure ensures that no traffic signs are overlooked.
In einer weiteren positiven Ausgestaltung der Erfindung ist eine Bildverarbeitung zur Auswertung von Kameradaten derart vorgesehen, dass nur in einem Bereich, in dem eine Information nach a)-e) vorliegt, nach Verkehrszeichen gesucht wird. Dieses Vorgehen spart Rechenzeit bei der Verarbeitung der Bilddaten eine Kamerasystems bzw. da die Rechenzeit zur In a further advantageous embodiment of the invention, image processing for evaluating camera data is provided in such a way that traffic signs are searched only in a region in which information according to a) -e) exists. This procedure saves computing time when processing the image data of a camera system or because the computing time for
Datenverarbeitung begrenzt ist, kann eine Data processing is limited, one can
rechenzeitintensivere und damit bessere Auswertung der rchenzeitintensivere and thus better evaluation of
Kameradaten bzgl. Verkehrszeichen in den vorgegebenen Camera data regarding traffic signs in the given
Bereichen durchgeführt werden. Areas are carried out.
In einer weiteren positiven Ausgestaltung der Erfindung wird eine der Informationen c) oder d) für die Zuordnung des In a further advantageous embodiment of the invention, one of the information c) or d) for the assignment of the
Geltungsbereichs für ein Verkehrszeichen ausgewertet. Dies gilt insbesondere in einer Fahrzeugumgebung mit mehreren Scope evaluated for a traffic sign. This is especially true in a multi-vehicle environment
Fahrspuren. Mit Hilfe eines Radar- bzw. Lidarsensorsystems können spurbegrenzende Strukturen (z.B. Leitplanken) g) erkannt werden. Von einem Radar- bzw. Lidarsensorsystem erkannte Lanes. With the aid of a radar or lidar sensor system, track-limiting structures (for example crash barriers) g) can be detected. Detected by a radar or Lidarsensorsystem
Verkehrszeichen können räumlich diesen Strukturen zugeordnet werden. Dies kann insbesondere als Merkmal für eine Traffic signs can be spatially assigned to these structures. This can be particularly characteristic of a
Plausibilisierung dienen, um potentielle Verkehrszeichen zu verwerfen oder zu bestätigen, je nach Lage der potentiellen Verkehrszeichen zu den spurbegrenzenden Strukturen. Plausibilisierung serve to discard or confirm potential traffic signs, depending on the location of the potential traffic signs to the track-limiting structures.
Insbesondere kann die Entfernungs- bzw. Positionsinformation für eine Zuordnung verwendet werden. Speziell bei mehrspurigen Straßen, Einmündungen, Parallelstraßen etc. ist Position des Verkehrsschildes maßgebend für die Zuordnung zur Spur, Straße etc. Kennt man den Ort des Verkehrszeichens so kann man diesen mit der eigenen Fahrspur in Beziehung bringen. Z.B. können weit entfernte Schilder verworfen werden, wenn sie nicht der eigenen Fahrspur zugeordnet sind. In particular, the distance or position information can be used for an assignment. Especially with multi-lane roads, junctions, parallel roads, etc., position of the traffic sign is decisive for the assignment to the lane, street etc. Knowing the location of the traffic sign so you can relate this with your own lane. For example, distant signs can be discarded if they are not assigned to their own lane.
In einer bevorzugten Ausgestaltung der Erfindung ist eine Bildverarbeitung zur Auswertung von Kameradaten derart In a preferred embodiment of the invention, an image processing for the evaluation of camera data is such
vorgesehen, dass in einem Bereich, in dem eine Information nach f) vorliegt, nicht nach Verkehrszeichen gesucht wird. provided that in an area in which an information according to f) is present, not looking for traffic signs.
Es werden mit einem Radar- bzw. Lidarsensorsystem vorausfahrende Fahrzeuge, insbesondere Lastkraftwagen, erkannt und diese Information wird der Verkehrszeichenerkennung zur Verfügung gestellt. Dies ist z.B. bei Fahrzeugen hilfreich, an deren Ende Hinweise in Form von Geschwindigkeitslimits angebracht sind. Diese haben keine Gültigkeit für die anderen Verkehrsteilnehmer . Vehicles driving ahead, in particular trucks, are detected by a radar or lidar sensor system, and this information is made available to traffic sign recognition. This is e.g. helpful in vehicles with hints in the form of speed limits at the end. These are not valid for the other road users.
Verzugsweise wird das Vorhandensein eines Verkehrszeichen basierend auf Daten eines Radar- bzw. Lidarsystems in Preferably, the presence of a traffic sign based on data from a radar or lidar system in
Abhängigkeit von zumindest einem der folgenden Parameter erkannt Depend on at least one of the following parameters detected
- Position des Objekts, insbesondere sind Verkehrszeichen am Fahrbahnrand oder über der Fahrbahn oder der Fahrspur angeordnet. Zusätzlich oder alternativ können die  - Position of the object, in particular traffic signs are arranged on the edge of the road or on the road or the lane. Additionally or alternatively, the
Positionsinformation mit Navigationsdaten korreliert werden. So kann z.B. davon ausgegangen werden, dass  Position information with navigation data are correlated. Thus, e.g. be assumed that
Verkehrszeichen in der Nähe von Kreuzungen verstärkt auftreten .  Traffic signs near intersections increasingly occur.
- Entfernung, insbesondere um die Relevanz eines  - Distance, especially the relevance of a
Verkehrszeichens für die eigene Fahrspur zu bewerten Rate traffic sign for own lane
- Stärke der an einem Objekt reflektierten Strahlung oder Größen die daraus abgeleitet werden können, wie z.B. The strength of the radiation reflected on an object or quantities which can be deduced therefrom, e.g.
Radar- oder Lidar Rückstreuquerschnitt; Verkehrszeichen sind aufgrund ihrer Beschaffenheit (i.d.R. aus Metall) gute Reflektoren, d.h. zur Erkennung kann ausgenutzt werden, dass der Rückstreuquerschnitt oder die Stärke der Reflektion einen vorgegebenen Schwellwert übersteigen muss bzw. in einem vorgegebenen Wertebereich liegen mussRadar or lidar backscatter cross section; road sign are due to their nature (usually metal) good reflectors, ie for the recognition can be exploited that the Rückstreuquerschnitt or the strength of the reflection must exceed a predetermined threshold or must be within a predetermined range of values
- Relativgeschwindigkeit, Verkehrszeichen sind stationäre Objekte, so dass zur Erkennung ausgenutzt werden kann, dass die Relativgeschwindigkeit der - Relativgeschwindigkeit, traffic signs are stationary objects, so that can be used for the recognition that the relative speed of
Fahrzeuggeschwindigkeit entsprechen muss, bzw. die  Vehicle speed must correspond, or the
Relativgeschwindigkeit zu anderen unbewegten Objekten, z.B. Leitplanken, gleich Null sein muss.  Relative speed to other stationary objects, e.g. Crash barriers, must be zero.
- Ausdehnung des Objekts; da die Größe von Verkehrszeichen standardisiert ist, kann nur ein Objekt mit Abmessungen in einem vorgegebenen Wertebereich, ein Verkehrszeichen sein. Der vorgegebene Wertebereich kann insbesondere von weiteren Informationen z.B. der Position der  - extension of the object; since the size of traffic signs is standardized, only an object with dimensions in a given range of values can be a traffic sign. The predetermined range of values may in particular be derived from further information, e.g. the position of the
Verkehrszeichen abhängen. Insbesondere sind  Depend on traffic signs. In particular are
Schilderbrücken statische Objekte, die eine relativ große Ausdehnung haben und die sich über der Fahrbahn befinden.  Gantries static objects that have a relatively large extent and that are located above the carriageway.
In einer positiven Ausgestaltung der Erfindung werden In a positive embodiment of the invention
basierend auf Radar- bzw. Lidardaten Objekte als potentielle Verkehrszeichen erkannt, zudem wird diesen Objekten eine Based on radar or Lidardaten objects detected as potential traffic signs, also these objects is a
Wahrscheinlichkeitswert zugeordnet, der angibt mit welcher Wahrscheinlichkeit das entsprechende Objekt ein Probability value assigned, which indicates the probability with which the corresponding object
Verkehrszeichen sein könnte. Vorzugsweise wird zur Bestimmung der Wahrscheinlichkeit eine Information zur Position eine Objekts zusätzlich mit einer Information eines Traffic sign could be. Preferably, to determine the probability, information about the position of an object is additionally provided with information of a
Navigationssystems korreliert. Insbesondere in der Nähe von Kreuzungen gibt es eine erhöhte Wahrscheinlichkeit für Navigation system correlates. Especially near intersections, there is an increased probability for
Verkehrszeichen . Traffic sign.

Claims

Patentansprüche  claims
1. Verfahren zur Erkennung von Verkehrszeichen mit einem 1. A method for detecting traffic signs with a
Umfelderfassungssensorsystem für ein Fahrzeug, das zumindest einen Kamerasensor und einen Radarsensor bzw. Lidarsensor umfasst ,  Environment detection sensor system for a vehicle comprising at least one camera sensor and a radar sensor or lidar sensor,
dadurch gekennzeichnet, dass  characterized in that
basierend auf den Daten des zumindest einen Radarsensors bzw. Lidarsensors zumindest eine der folgenden Informationen a) das Vorhandensein eines Verkehrszeichens oder  based on the data of at least one radar sensor or Lidarsensors at least one of the following information a) the presence of a traffic sign or
b) die Größe eines Verkehrszeichens  b) the size of a traffic sign
c) Position eines Verkehrszeichens  c) Position of a traffic sign
d) Entfernung und/oder Richtung eines Verkehrszeichens e) Brückenartige Struktur  d) Distance and / or direction of a road sign e) Bridge-like structure
f) Position oder Art vorausfahrendes Fahrzeug, insbesondere LKW  f) Position or type of vehicle driving ahead, in particular trucks
g) Position spurbegrenzender Strukturen gewonnen wird und zur Verkehrszeichenerkennung genutzt wird.  g) position of track-limiting structures is obtained and is used for traffic sign recognition.
2. Verfahren nach Anspruch 1, 2. The method according to claim 1,
dadurch gekennzeichnet, dass  characterized in that
die zumindest eine Information aus Radar- bzw. Lidardaten zur Plausibilisierung von Daten des Kamerasensors genutzt werden, insbesondere eine der Informationen a)-e).  the at least one information from radar or lidar data is used to check the plausibility of data from the camera sensor, in particular one of the information a) -e).
3. Verfahren nach einem der vorherigen Ansprüche, 3. The method according to any one of the preceding claims,
dadurch gekennzeichnet, dass  characterized in that
eine Bildverarbeitung zur Auswertung von Kameradaten derart vorgesehen ist, dass in einem Bereich, in dem eine  an image processing for evaluating camera data is provided such that in an area in which a
Information nach a)-e) vorliegt, gezielt nach  Information according to a) -e) is present, specifically according to
Verkehrszeichen gesucht wird. Verfahren nach einem der vorherigen Ansprüche, Traffic sign is searched. Method according to one of the preceding claims,
dadurch gekennzeichnet, dass characterized in that
eine Bildverarbeitung zur Auswertung von Kameradaten derart vorgesehen ist, dass nur in einem Bereich, in dem eine an image processing for the evaluation of camera data is provided such that only in an area in which a
Information nach a)-e) vorliegt, nach Verkehrszeichen gesucht wird. Information according to a) -e) is present, traffic signs are searched.
Verfahren nach einem der vorherigen Ansprüche, Method according to one of the preceding claims,
dadurch gekennzeichnet, dass characterized in that
eine der Informationen c) oder d) für die Zuordnung des Geltungsbereichs für ein Verkehrszeichen ausgewertet wird, insbesondere in einer Fahrzeugumgebung mit mehreren Fahrspuren . one of the information c) or d) is evaluated for the assignment of the scope for a traffic sign, in particular in a vehicle environment with several lanes.
Verfahren nach einem der vorherigen Ansprüche, Method according to one of the preceding claims,
dadurch gekennzeichnet, dass characterized in that
eine Bildverarbeitung zur Auswertung von Kameradaten derart vorgesehen ist, dass einem Bereich, in dem eine Information nach f) vorliegt, nicht nach Verkehrszeichen gesucht wird. an image processing for evaluating camera data is provided in such a way that a region in which information according to f) is present is not searched for traffic signs.
Verfahren nach einem der vorherigen Ansprüche, Method according to one of the preceding claims,
dadurch gekennzeichnet, dass characterized in that
ein Verkehrszeichen basierend auf Daten eines Radar- bzw. Lidarsystems in Abhängigkeit von zumindest einem der a traffic sign based on data of a radar or Lidarsystems depending on at least one of
folgenden Parameter erkannt wird following parameter is detected
- Position des Objekts  - Position of the object
- Entfernung  - Distance
- Stärke der Reflektion  - strength of the reflection
- Relativgeschwindigkeit  - relative speed
- Ausdehnung des Objekts - Extension of the object
8. Verfahren nach einem der vorherigen Ansprüche, 8. The method according to any one of the preceding claims,
dadurch gekennzeichnet, dass  characterized in that
basierend auf Daten eines Radar- bzw. Lidarsensors Objekte als mögliche Verkehrszeichen erkannt werden, wobei den  based on data of a radar or Lidarsensors objects are recognized as possible traffic signs, wherein the
Objekten ein Wahrscheinlichkeitswert zugeordnet wird, der angibt mit welcher Wahrscheinlichkeit das entsprechende Objekt ein Verkehrszeichen ist.  Assigning objects a probability value indicating the probability with which the corresponding object is a traffic sign.
9. Verfahren nach Anspruch 8 9. The method according to claim 8
dadurch gekennzeichnet, dass  characterized in that
eine Information zur Position eine Objekts zusätzlich mit einer Information eines Navigationssystems korreliert wird.  An information on the position of an object is additionally correlated with information of a navigation system.
10. Vorrichtung für ein Fahrzeug zur Erkennung von Verkehrszeichen, umfassend ein An apparatus for a vehicle for detecting traffic signs, comprising
- ein Radar- oder Lidarsensorsystem  - a radar or lidar sensor system
- ein Kamerasensorsystem  - a camera sensor system
- eine Steuer- oder Auswerteeinheit, die mit den genannten Sensorsystemen verbindbar ist und die einen elektronischen Speicher umfasst, auf dem ein Verfahren nach einem der vorherigen Ansprüche hinterlegt ist.  - A control or evaluation unit which is connectable to said sensor systems and which comprises an electronic memory on which a method according to one of the preceding claims is stored.
EP13795994.6A 2012-11-06 2013-10-21 Method and device for recognising traffic signs for a vehicle Withdrawn EP2917759A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102012110595.2A DE102012110595A1 (en) 2012-11-06 2012-11-06 Method and device for detecting traffic signs for a vehicle
PCT/DE2013/200238 WO2014071939A1 (en) 2012-11-06 2013-10-21 Method and device for recognising traffic signs for a vehicle

Publications (1)

Publication Number Publication Date
EP2917759A1 true EP2917759A1 (en) 2015-09-16

Family

ID=49674106

Family Applications (1)

Application Number Title Priority Date Filing Date
EP13795994.6A Withdrawn EP2917759A1 (en) 2012-11-06 2013-10-21 Method and device for recognising traffic signs for a vehicle

Country Status (5)

Country Link
US (1) US10223600B2 (en)
EP (1) EP2917759A1 (en)
JP (1) JP6469013B2 (en)
DE (2) DE102012110595A1 (en)
WO (1) WO2014071939A1 (en)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9164511B1 (en) * 2013-04-17 2015-10-20 Google Inc. Use of detected objects for image processing
JP5961207B2 (en) * 2014-03-28 2016-08-02 富士重工業株式会社 Outside environment recognition device
DE102014214713A1 (en) 2014-07-25 2016-01-28 Conti Temic Microelectronic Gmbh Method for operating an assistance system of a motor vehicle and assistance system
DE102014220571A1 (en) 2014-10-10 2016-04-14 Conti Temic Microelectronic Gmbh Method and device for detecting relevant traffic signs for a vehicle
US9530313B2 (en) * 2014-10-27 2016-12-27 Here Global B.V. Negative image for sign placement detection
WO2016080452A1 (en) * 2014-11-19 2016-05-26 エイディシーテクノロジー株式会社 Automatic driving control device
DE102015003963A1 (en) 2015-03-26 2015-08-20 Daimler Ag Device and method for detecting traffic signs
US10345107B2 (en) * 2016-06-22 2019-07-09 Aptiv Technologies Limited Automated vehicle sensor selection based on map data density and navigation feature density
CN107818288B (en) * 2016-09-13 2019-04-09 腾讯科技（深圳）有限公司 Signboard information acquisition method and device
DE102016118538A1 (en) * 2016-09-29 2018-03-29 Valeo Schalter Und Sensoren Gmbh Method for classifying a traffic sign in a surrounding area of a motor vehicle, computing device, driver assistance system and motor vehicle
US10528055B2 (en) * 2016-11-03 2020-01-07 Ford Global Technologies, Llc Road sign recognition
KR102383426B1 (en) 2016-12-15 2022-04-07 현대자동차주식회사 Apparatus and Method for determining toll gate section
KR20180106417A (en) * 2017-03-20 2018-10-01 현대자동차주식회사 System and Method for recognizing location of vehicle
DE102017218192A1 (en) * 2017-10-12 2019-04-18 Robert Bosch Gmbh Method and device for traffic sign recognition
US10627516B2 (en) * 2018-07-19 2020-04-21 Luminar Technologies, Inc. Adjustable pulse characteristics for ground detection in lidar systems
US10891501B2 (en) * 2019-01-28 2021-01-12 Uber Technologies, Inc. Automatically associating road sign information with road segments using image data
US11334089B1 (en) 2019-07-26 2022-05-17 Jeffrey W. Bryce Infrastructure markers for autonomous vehicles
CN111964673A (en) * 2020-08-25 2020-11-20 一汽解放汽车有限公司 Unmanned vehicle positioning system
DE102021202232A1 (en) 2021-03-09 2022-09-15 Robert Bosch Gesellschaft mit beschränkter Haftung Method for detecting a traffic sign using a LiDAR system
KR20240058610A (en) * 2022-10-26 2024-05-03 삼성전자주식회사 Sign apparatus for vehicle
CN116577752A (en) * 2023-04-18 2023-08-11 深圳优地科技有限公司 Method, device, electronic device and readable storage medium for identifying identification structure
JP2025036354A (en) * 2023-08-31 2025-03-14 北京地平▲線▼信息技▲術▼有限公司 Traffic sign detection method, device, storage medium, and electronic device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6414712B1 (en) * 1995-12-13 2002-07-02 Daimlerchrylsler, Ag Vehicle navigational system and signal processing method for said navigational system
US20100007728A1 (en) * 2006-10-13 2010-01-14 Continental Teves Ag & Co., Ohg System for Determining Objects

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19852631C2 (en) * 1998-11-14 2001-09-06 Daimler Chrysler Ag Device and method for traffic sign recognition
JP2002189075A (en) * 2000-12-20 2002-07-05 Fujitsu Ten Ltd Method for detecting stationary on-road object
DE10200784A1 (en) * 2002-01-11 2003-07-31 Audi Ag motor vehicle
US7633383B2 (en) * 2006-08-16 2009-12-15 International Business Machines Corporation Systems and arrangements for providing situational awareness to an operator of a vehicle
US20080243378A1 (en) * 2007-02-21 2008-10-02 Tele Atlas North America, Inc. System and method for vehicle navigation and piloting including absolute and relative coordinates
JP2008286566A (en) 2007-05-16 2008-11-27 Omron Corp On-vehicle device
DE102007034505A1 (en) * 2007-07-24 2009-01-29 Hella Kgaa Hueck & Co. Method and device for traffic sign recognition
CN101952688A (en) 2008-02-04 2011-01-19 电子地图北美公司 Method for map matching with sensor detected objects
JP5094658B2 (en) * 2008-09-19 2012-12-12 日立オートモティブシステムズ株式会社 Driving environment recognition device
DE102008043743A1 (en) * 2008-11-14 2010-05-20 Robert Bosch Gmbh Sensor signals e.g. video sensor signals, evaluating method for detecting e.g. traffic sign in surrounding of vehicle, involves evaluating information based on evaluation specification, and outputting information based on evaluation result
DE102009013326A1 (en) 2009-03-16 2009-11-12 Daimler Ag Vehicle controlling method, involves producing image of object, determining object data and surrounding data from image of object, and classifying object using object data and surrounding data
DE102010020330A1 (en) 2010-05-14 2011-11-17 Conti Temic Microelectronic Gmbh Method for detecting traffic signs
JP5747593B2 (en) 2011-03-22 2015-07-15 株式会社豊田中央研究所 Standard vehicle speed calculation device and program
TW201333896A (en) * 2012-02-14 2013-08-16 yan-hong Jiang Remote traffic management system using video radar
US9195914B2 (en) * 2012-09-05 2015-11-24 Google Inc. Construction zone sign detection

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6414712B1 (en) * 1995-12-13 2002-07-02 Daimlerchrylsler, Ag Vehicle navigational system and signal processing method for said navigational system
US20100007728A1 (en) * 2006-10-13 2010-01-14 Continental Teves Ag & Co., Ohg System for Determining Objects

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of WO2014071939A1 *

Also Published As

Publication number Publication date
US10223600B2 (en) 2019-03-05
WO2014071939A1 (en) 2014-05-15
JP6469013B2 (en) 2019-02-13
JP2016502178A (en) 2016-01-21
US20150220795A1 (en) 2015-08-06
DE102012110595A1 (en) 2014-05-08
DE112013005299A5 (en) 2015-07-16

Similar Documents

Publication Publication Date Title
WO2014071939A1 (en) Method and device for recognising traffic signs for a vehicle
DE102016120507B4 (en) PREDICTING VEHICLE MOVEMENTS USING DRIVER BODY LANGUAGE
DE102015100316B4 (en) Planning device for a sideways maneuver for an automated driving system
DE102014223363B4 (en) Method and device for localizing a motor vehicle in a fixed reference map
EP3292423B1 (en) Diagnostic method for a vision sensor of a vehicle and vehicle having a vision sensor
DE102017221691A1 (en) Method and device for self-localization of a vehicle
DE102014117751A1 (en) System and method for dynamically focusing vehicle sensors
DE102013104256A1 (en) Method and device for estimating the number of lanes
EP1557692B1 (en) Method for detecting marked hazardous locations and/or road works in the vicinity of roadways
EP3857256B1 (en) Method for detecting road users
DE102011081382A1 (en) Method and device for changing a light emission of at least one headlight of a vehicle
DE102021119871B4 (en) Method and processor circuit for operating an automated driving function with an object classifier in a motor vehicle, and motor vehicle
DE102014009627A1 (en) Method for reporting a free parking space for a vehicle
WO2018141447A1 (en) Method for localising a more highly automated, e.g. highly automated vehicle (hav) in a digital localisation map
DE102009039450A1 (en) Method for recognizing lane for car during e.g. snowfall, involves determining correctness of detected lane data based on arrangement of reflection markings, where lane data are corrected if required
DE102017211387A1 (en) System and method for automated maneuvering of an ego vehicle
EP3259614B1 (en) Method for ascertaining a piece of local information for a motor vehicle in relation to a driving corridor, and motor vehicle
DE102018217840A1 (en) Method and system for determining an environmental model for a vehicle
DE102016015405A1 (en) Comprehensive environmental detection for a car by means of radar
DE102017122969A1 (en) VEHICLE WITH ENVIRONMENTAL CONTEXTANALYSIS
DE102014216276B4 (en) Determining the position of motor vehicles using radar beacons
DE102016001101A1 (en) Method for detecting and identifying a driving maneuver of a road user and motor vehicle
DE102011055441A1 (en) Method for determining spacing between preceding and forthcoming motor cars by using mono camera in e.g. adaptive cruise control system, involves determining spacing between cars based on information about license plate number
EP4107545B1 (en) Method for estimating an intrinsic speed
WO2019048213A1 (en) METHOD AND DEVICE FOR CREATING A CARD

Legal Events

Date Code Title Description
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

17P Request for examination filed

Effective date: 20150608

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

RIN1 Information on inventor provided before grant (corrected)

Inventor name: FISCHER, MARC

Inventor name: VAN DER VEGTE, PETER

Inventor name: MOELLER, ULRICH

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20180315

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

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Effective date: 20200710