EP2788917A1 - Method for evaluating image data of a vehicle camera taking into account information about rain - Google Patents

Method for evaluating image data of a vehicle camera taking into account information about rain

Info

Publication number
EP2788917A1
EP2788917A1 EP12805925.0A EP12805925A EP2788917A1 EP 2788917 A1 EP2788917 A1 EP 2788917A1 EP 12805925 A EP12805925 A EP 12805925A EP 2788917 A1 EP2788917 A1 EP 2788917A1
Authority
EP
European Patent Office
Prior art keywords
image data
information
evaluation
vehicle camera
rain
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Withdrawn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
EP12805925.0A
Other languages
German (de)
French (fr)
Inventor
Matthias Strauss
Matthias Komar
Stefan Hegemann
Dieter KRÖKEL
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
Continental Teves AG and Co OHG
Original Assignee
Conti Temic Microelectronic GmbH
Continental Teves AG and Co OHG
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, Continental Teves AG and Co OHG filed Critical Conti Temic Microelectronic GmbH
Publication of EP2788917A1 publication Critical patent/EP2788917A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
    • B60R2300/8053—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for bad weather conditions or night vision

Definitions

  • the invention relates to a method for evaluating image data of a vehicle camera, which is used in particular in a driver assistance system.
  • rain sensors and light sensors are integrated to control windshield wipers or light.
  • cameras are integrated as a basis for assistance or comfort functions, is increasingly transferred to perform the rain or light detection also with the camera.
  • WO 2010/072198 A1 a rain detection with the help of a camera is described, which is used simultaneously for automotive driver assistance functions.
  • Rain detection is a bifocal optics used, which images a portion of the windshield sharp on a portion of the image sensor of the camera.
  • EP 2057583 B1 shows a camera-based
  • Driver assistance function for the automatic lighting control of headlamps which distinguishes vehicle lights of preceding or oncoming vehicles from reflectors.
  • the headlamps of the own vehicle can be controlled so automatically that dazzling of drivers of preceding and oncoming vehicles is prevented.
  • the range and distribution of the lighting through the headlights can be adapted accordingly to preceding and oncoming vehicles.
  • Object of the present invention is to meet these difficulties.
  • a basic idea of the invention is to use information from a rain or light sensor system to adapt assistant and object recognition functions from data of a vehicle camera accordingly.
  • An inventive method for evaluating image data (or a method for object recognition by means of) a vehicle camera provides that information about raindrops on a pane and / or information about detected lighting conditions in the field of vision of the vehicle camera in the evaluation of the image data (or recognition of objects ).
  • Information about raindrops is in particular their number and size, whereby also hailstones, snowflakes, ice crystals and dirt particles are regarded as raindrops in the sense of the claimed invention.
  • Information about detected lighting conditions are in particular ambient brightness (eg day / night, tunnel passage), whereby individual light sources such as street lamps or vehicle lights may be part of the detected lighting conditions.
  • the information is determined from the image data. That is, the vehicle camera also serves as a rain and / or light sensor, e.g. in a partial region of the image sensor as shown in WO 2010/072198 A1. The detection of rain and / or light conditions is now for the (further) evaluation of image data or object recognition for
  • At least one criterion eg a threshold value
  • at least one criterion for detecting edges in the image from the image data can be varied depending on the information (about raindrops on the pane and / or detected light conditions in the field of vision of the vehicle camera).
  • edge-based evaluation methods should be adjusted in their thresholds. Accordingly, several parameterizations can be provided depending on the weather situation and used depending on the detected weather conditions.
  • a quality criterion of the image data can be derived from the information, which is taken into account in the evaluation of the image data.
  • individual assistance functions can be completely switched off if the quality of the sensor signals is no longer sufficient, ie, if a minimum quality criterion of the image data is undershot.
  • assistance functions that provide a cruise control are limited in the maximum controllable speed.
  • a distance control (ACC) in heavy rain at higher speeds can no longer be activated and this is communicated to the driver.
  • the maximum activatable or controllable speed is preferably determined as a function of a quality criterion of the image data.
  • a "blockage detection” can be performed. When it rains i. d. R. the windscreen wipers on. These can cover image areas. In this case, tracking of objects in successive frames of an image sequence (object tracking) can be made more stable against dropouts of individual images. This means that objects can be classified as valid over several cycles, even if individual measurements are missing.
  • this also applies to a water surge detection, because even here objects may not be seen on individual images of a sequence of images.
  • advantageously already safely triggered functions can remain active and a triggering of new functions can be prevented.
  • vehicle rear fronts can be detected and classified with the camera.
  • the recognition works first edge-based.
  • the first step is to look for basic properties in the image such as rear lights, vehicle contours, or a shadow under the vehicle.
  • the headlight recognition can then be considered even more, because due to the darkness hardly any other properties are visible. Especially the lighting plays a decisive role in the number and quality of the measuring points.
  • the illumination limit can be used as a detection limit for safe detection of unlit objects in the vehicle environment.
  • the classification of the detected vehicles can also be adapted in their parameters or in the manner of execution to the weather situation. So special classifiers can be used for different weather conditions.
  • the signal qualities provided by the camera or other weather-dependent sensors such as e.g. Lidar or PMD (Photonic Mixing Device) delivered objects are better assessed, so in particular a quality criterion of the image data from the information on rain or light conditions can be derived.
  • Lidar or PMD Photonic Mixing Device
  • Classification algorithms can also be adapted to the extraction of color information.
  • line markers often appear as a black line on a light background, regardless of their own color (yellow / white). With this knowledge, line marker recognition algorithms can be made more robust.
  • Another possibility is to use the vehicle lighting (low beam, high beam,
  • Fog lights accordingly activate / adapt to get possibly remaining color information.
  • Preference may also special lamps that dazzle little but have the appropriate light temperature, additionally attached to the vehicle and activated.
  • For highly automated driving up to autonomous driving it is of particular interest how far into the future (or way in the direction of travel) a defined signal security can be guaranteed. Thus, highly automated systems can adjust the driving speed accordingly. A faster driving would then be possible only manually.

Abstract

The invention relates to a method for evaluating image data of a vehicle camera. Information about rain drops on a window in the field of vision of the vehicle camera is taken into account in the evaluation of the image data.

Description

Verfahren zur Auswertung von Bilddaten einer Fahrzeugkamera unter Berücksichtigung von Informationen über Regen Method for evaluating image data of a vehicle camera taking into account information about rain
Die Erfindung betrifft ein Verfahren zur Auswertung von Bilddaten einer Fahrzeugkamera, das insbesondere bei einem Fahrerassistenzsystem zum Einsatz kommt. The invention relates to a method for evaluating image data of a vehicle camera, which is used in particular in a driver assistance system.
In vielen Fahrzeugen sind heute schon Regensensoren und Lichtsensoren integriert, um Scheibenwischer bzw. Licht anzusteuern. Da es immer mehr Fahrzeuge gibt, in die auch Kameras als Basis für Assistenz- oder Komfortfunktionen integriert sind, wird zunehmend dazu übergegangen, die Regen- bzw. Lichterkennung ebenfalls mit der Kamera durchzuführen . In many vehicles today rain sensors and light sensors are integrated to control windshield wipers or light. As there are more and more vehicles, in which cameras are integrated as a basis for assistance or comfort functions, is increasingly transferred to perform the rain or light detection also with the camera.
In der WO 2010/072198 A1 wird eine Regenerkennung mit Hilfe einer Kamera beschrieben, die gleichzeitig für automotive Fahrerassistenzfunktionen eingesetzt wird. ZurIn WO 2010/072198 A1 a rain detection with the help of a camera is described, which is used simultaneously for automotive driver assistance functions. to
Regenerkennung wird eine bifokale Optik genutzt, die einen Teilbereich der Windschutzscheibe scharf auf einen Teilbereich des Bildsensors der Kamera abbildet. Rain detection is a bifocal optics used, which images a portion of the windshield sharp on a portion of the image sensor of the camera.
EP 2057583 Bl zeigt eine kamerabasierteEP 2057583 B1 shows a camera-based
Fahrerassistenzfunktion zur automatischen Lichtsteuerung von Frontscheinwerfern, die Fahrzeuglichter vorausfahrender oder entgegenkommender Fahrzeuge von Reflektoren unterscheidet. Dadurch können die Frontscheinwerfer des eigenen Fahrzeugs derart automatische gesteuert werden, dass eine Blendung von Fahrern vorausfahrender und entgegenkommender Fahrzeuge verhindert wird. Reichweite und Verteilung der Beleuchtung durch die Frontscheinwerfer können entsprechend an vorausfahrende und entgegenkommende Fahrzeuge angepasst werden. Driver assistance function for the automatic lighting control of headlamps, which distinguishes vehicle lights of preceding or oncoming vehicles from reflectors. Thereby, the headlamps of the own vehicle can be controlled so automatically that dazzling of drivers of preceding and oncoming vehicles is prevented. The range and distribution of the lighting through the headlights can be adapted accordingly to preceding and oncoming vehicles.
Schwierigkeiten entstehen bei kamerabasiertenDifficulties arise with camera-based
Fahrerassistenzfunktionen durch Umwelteinflüsse wie Regen oder Dunkelheit bei Nacht, die die Abbildungsqualität der Kamera deutlich beeinträchtigen können. Driver assistance functions due to environmental influences such as rain or darkness at night, which can significantly affect the imaging quality of the camera.
Aufgabe der vorliegenden Erfindung ist es, diesen Schwierigkeiten zu begegnen. Object of the present invention is to meet these difficulties.
Eine Grundidee der Erfindung liegt darin, Informationen aus einer Regen- bzw. Lichtsensorik zu nutzen, um Assistenz- und Objekterkennungsfunktionen aus Daten einer Fahrzeugkamera entsprechend anzupassen. A basic idea of the invention is to use information from a rain or light sensor system to adapt assistant and object recognition functions from data of a vehicle camera accordingly.
Ein erfindungsgemäßes Verfahren zur Auswertung von Bilddaten (bzw. ein Verfahren zur Objekterkennung mittels) einer Fahrzeugkamera sieht vor, dass Informationen über Regentropfen auf einer Scheibe und/oder Informationen über erkannte Lichtverhältnisse im Sichtbereich der Fahrzeugkamera bei der Auswertung der Bilddaten (bzw. Erkennung von Objekten) berücksichtigt werden. An inventive method for evaluating image data (or a method for object recognition by means of) a vehicle camera provides that information about raindrops on a pane and / or information about detected lighting conditions in the field of vision of the vehicle camera in the evaluation of the image data (or recognition of objects ).
Informationen über Regentropfen sind insbesondere deren Anzahl und Größe, wobei auch Hagelkörner, Schneeflocken, Eiskristalle und Schmutzpartikel als Regentropfen im Sinne der beanspruchten Erfindung angesehen werden. Informationen über erkannte Lichtverhältnisse sind insbesondere Umgebungshelligkeit (z.B. Tag/Nacht, Tunneldurchfahrt) , wobei auch einzelne Lichtquellen wie beispielsweise Straßenlampen oder Fahrzeuglichter Bestandteil der erkannten Lichtverhältnisse sein können. Information about raindrops is in particular their number and size, whereby also hailstones, snowflakes, ice crystals and dirt particles are regarded as raindrops in the sense of the claimed invention. Information about detected lighting conditions are in particular ambient brightness (eg day / night, tunnel passage), whereby individual light sources such as street lamps or vehicle lights may be part of the detected lighting conditions.
Vorteile werden darin gesehen, dass die Auswertung von Bilddaten bzw. die Erkennung von Objekten durch die Berücksichtigung der Informationen über Regentropfen bzw. Lichtverhältnisse zuverlässiger wird. DieAdvantages are seen in the fact that the evaluation of image data or the recognition of objects by the consideration of information about raindrops or lighting conditions is reliable. The
Erkennungssicherheiten von Objekten können dadurch besser abgeschätzt werden, so dass schwierige Situationen trotzdem vom Kamerasystem gemeistert werden können. Detection security of objects can thus be better estimated, so that difficult situations can still be mastered by the camera system.
Gemäß einer bevorzugten Ausführungsform werden die Informationen (Regentropfen bzw. Lichtverhältnisse) aus den Bilddaten ermittelt werden. Das heißt die Fahrzeugkamera dient zugleich als Regen- und/oder Lichtsensor, z.B. in einem Teilbereich des Bildsensors wie in WO 2010/072198 A1 gezeigt. Die Erkennung von Regen und/oder Lichtverhältnissen wird nun für die (weitere) Auswertung von Bilddaten oder Objekterkennung fürAccording to a preferred embodiment, the information (raindrops or light conditions) is determined from the image data. That is, the vehicle camera also serves as a rain and / or light sensor, e.g. in a partial region of the image sensor as shown in WO 2010/072198 A1. The detection of rain and / or light conditions is now for the (further) evaluation of image data or object recognition for
Fahrerassistenzfunktionen berücksichtigt . Driver assistance functions taken into account.
Dadurch kann insbesondere die Auswirkung von Regen und/oder Licht auf Kamerafunktionen besser abgeschätzt werden, da dieselbe Kamera die Wetter-/Lichtsituation direkt erkennt und die sich ergebenden Sichteigenschaften somit am besten abgeschätzt werden kann. Vorteilhaft kann bei der Auswertung der Bilddaten mindestens ein Kriterium (z.B. ein Schwellwert) zu einer Erkennung von Kanten im Bild aus den Bilddaten von den Informationen (über Regentropfen auf der Scheibe und/oder erkannte Lichtverhältnisse im Sichtbereich der Fahrzeugkamera) abhängig variiert werden kann. As a result, in particular the effect of rain and / or light on camera functions can be better estimated, since the same camera directly recognizes the weather / light situation and thus the resulting sighting properties can best be estimated. Advantageously, when evaluating the image data, at least one criterion (eg a threshold value) for detecting edges in the image from the image data can be varied depending on the information (about raindrops on the pane and / or detected light conditions in the field of vision of the vehicle camera).
Aus einer erkannten Regenstärke kann beispielsweise die Beeinflussung der von der Kamera gesehenen Kanten (Hell /Dunkel oder Farbübergange) abgeschätzt werden. Bei Regen fallen diese Kantenübergänge meist weicher aus, was bedeutet, dass der Gradient der Kante weniger steil ist als das ohne Regen der Fall wäre. Entsprechend sollten also kantenbasierte Auswertungserfahren in ihren Schwellwerten angepasst werden. Entsprechend können mehrere Parametrierungen, je nach Wettersituation vorgesehen werden und je nach detektierter Wetterlage genutzt werden. From a detected rainfall, for example, the influence on the edges seen by the camera (light / dark or color transitions) can be estimated. In the rain, these edge transitions tend to be softer, which means that the gradient of the edge is less steep than it would be without rain. Accordingly, edge-based evaluation methods should be adjusted in their thresholds. Accordingly, several parameterizations can be provided depending on the weather situation and used depending on the detected weather conditions.
Insbesondere kann aus den Informationen ein Gütekriterium der Bilddaten abgeleitet wird, das bei der Auswertung der Bilddaten berücksichtigt wird. In particular, a quality criterion of the image data can be derived from the information, which is taken into account in the evaluation of the image data.
Bevorzugt können ab einer gewissen Regenstärke einzelne Assistenzfunktionen ganz abgeschaltet werden, wenn die Qualität der Sensorsignale nicht mehr ausreichend ist, wenn also ein minimales Gütekriterium der Bilddaten unterschritten wird. Preferably, starting from a certain rainfall, individual assistance functions can be completely switched off if the quality of the sensor signals is no longer sufficient, ie, if a minimum quality criterion of the image data is undershot.
Vorteilhaft werden Assistenzfunktionen, die eine Geschwindigkeitsregelung vorsehen, in der maximal regelbaren Geschwindigkeit begrenzt. So könnte insbesondere eine Abstandsregelung (ACC) bei starkem Regen bei höheren Geschwindigkeiten nicht mehr aktivierbar sein und dies dem Fahrer auch mitgeteilt werden. Die maximal aktivierbare oder regelbare Geschwindigkeit wird vorzugsweise in Abhängigkeit eines Gütekriteriums der Bilddaten bestimmt. Advantageously, assistance functions that provide a cruise control are limited in the maximum controllable speed. In particular a distance control (ACC) in heavy rain at higher speeds can no longer be activated and this is communicated to the driver. The maximum activatable or controllable speed is preferably determined as a function of a quality criterion of the image data.
Gemäß einer vorteilhaften Ausführungsform kann eine "blockage detection" (Blockiererkennung) durchgeführt werden. Bei Regen sind i. d. R. die Scheibenwischer an. Diese können Bildbereiche überdecken. In diesem Fall kann ein Verfolgen von Objekten in aufeinanderfolgenden Bildern einer Bildfolge (Objekttracking) stabiler gegenüber Ausfällen einzelner Bilder gemacht werden. So können Objekte auch über mehrere Zyklen als valide eingestuft werden, auch wenn einzelne Messungen fehlen. According to an advantageous embodiment, a "blockage detection" can be performed. When it rains i. d. R. the windscreen wipers on. These can cover image areas. In this case, tracking of objects in successive frames of an image sequence (object tracking) can be made more stable against dropouts of individual images. This means that objects can be classified as valid over several cycles, even if individual measurements are missing.
Bevorzugt gilt das auch für eine Wasserschwallerkennung, denn auch hier sind Objekte unter Umständen auf einzelnen Bildern einer Bilderfolge nicht mehr zu erkennen. Bei einem erkannten Wasserschwall können vorteilhaft bereits sicher ausgelöste Funktionen weiterhin aktiv bleiben und ein Auslösen neuer Funktionen unterbunden werden. Preferably, this also applies to a water surge detection, because even here objects may not be seen on individual images of a sequence of images. In the case of a detected water surge, advantageously already safely triggered functions can remain active and a triggering of new functions can be prevented.
Weitere vorteilhafte Ausgestaltungen der Erfindung ergeben sich aus den Unteransprüchen. Further advantageous embodiments of the invention will become apparent from the dependent claims.
Im Folgenden wird die Erfindung anhand von Ausführungsbeispielen näher erläutert. Mit der Kamera können z.B. Fahrzeugrückfronten erkannt und klassifiziert werden. Die Erkennung funktioniert zunächst kantenbasiert . In the following the invention will be explained in more detail by means of exemplary embodiments. For example, vehicle rear fronts can be detected and classified with the camera. The recognition works first edge-based.
Im ersten Schritt wird nach grundlegenden Eigenschaften im Bild gesucht wie Rückscheinwerfern, Fahrzeugkonturen, oder einem Schatten unter dem Fahrzeug.  The first step is to look for basic properties in the image such as rear lights, vehicle contours, or a shadow under the vehicle.
Da bei Regen meist keine Fahrzeugschatten vorhanden sind, kann hier z.B. größerer Wert auf die Scheinwerfer oder Kantenerkennung gelegt werden.  Since there are usually no vehicle shadows in the rain, here greater emphasis placed on the headlights or edge detection.
Bei Nacht kann die Scheinwerfererkennung dann noch stärker berücksichtigt werden, da aufgrund der Dunkelheit kaum noch andere Eigenschaften sichtbar sind. Gerade die Beleuchtung spielt eine maßgebliche Rolle bei der Anzahl und Qualität der Messpunkte.  At night, the headlight recognition can then be considered even more, because due to the darkness hardly any other properties are visible. Especially the lighting plays a decisive role in the number and quality of the measuring points.
Bei Nacht ist generell die Sichtweite einiger Funktionen praktisch auf die Scheinwerferleuchtweite begrenzt. Hier kann die Beleuchtungsgrenze als Erkennungsgrenze für sicheres Erkennen von unbeleuchteten Objekten in der Fahrzeugumgebung genutzt werden.  At night, the visibility of some functions is generally limited to the headlight range. Here, the illumination limit can be used as a detection limit for safe detection of unlit objects in the vehicle environment.
Im folgenden Schritt kann die Klassifikation der erkannten Fahrzeuge kann ebenfalls in ihren Parametern oder in der Ausführungsweise an die Wettersituation angepasst werden. So können spezielle Klassifikatoren für verschiedene Wetterbedingungen herangezogen werden. In the following step, the classification of the detected vehicles can also be adapted in their parameters or in the manner of execution to the weather situation. So special classifiers can be used for different weather conditions.
Es ist hierzu beispielsweise möglich unterschiedliche Klassifikationsalgorithmen/-parameter für verschiedene Wettersituationen zu entwickeln. Auch hier wird dann der Klassifikationsalgorithmus verwendet, der für die Entsprechenden Umgebungsverhältnisse (Regen/Licht) trainiert wurde. For example, it is possible to develop different classification algorithms / parameters for different weather situations. Again, the classification algorithm used for the Corresponding environmental conditions (rain / light) was trained.
Entsprechend der Wettersituation können auch einzelne Erkennungsalgorithmen ausgeschaltet und anderen mehr vertraut werden. Depending on the weather situation, individual recognition algorithms can be switched off and others become more familiar.
Desweiteren können die Signalqualitäten, der von der Kamera oder anderen wetterabhängigen Sensoren wie z.B. Lidar oder PMD (Photonic Mixing Device) gelieferten Objekte besser eingeschätzt werden, so kann insbesondere ein Gütekriterium der Bilddaten aus den Informationen zu Regen- bzw. Lichtverhältnissen abgeleitet werden.  Furthermore, the signal qualities provided by the camera or other weather-dependent sensors such as e.g. Lidar or PMD (Photonic Mixing Device) delivered objects are better assessed, so in particular a quality criterion of the image data from the information on rain or light conditions can be derived.
Neben der Kantenerkennung und denIn addition to edge detection and the
Klassifikationsalgorithmen kann auch die Gewinnung von Farbinformationen angepasst werden. Classification algorithms can also be adapted to the extraction of color information.
So erscheinen Linienmarkierung bei Nacht und Regen beispielsweise oft als schwarze Linie auf hellem Grund und das sogar unabhängig von ihrer eigenen Farbe (Gelb / Weiß) . Mit diesem Wissen, können Algorithmen zur Linienmarkierungserkennung robuster ausgelegt werden.  For example, at night and in rain, line markers often appear as a black line on a light background, regardless of their own color (yellow / white). With this knowledge, line marker recognition algorithms can be made more robust.
Eine andere Möglichkeit besteht darin, die Fahrzeugbeleuchtung (Abblendlicht, Fernlicht,Another possibility is to use the vehicle lighting (low beam, high beam,
Nebelscheinwerfer) entsprechend zu aktivieren/adaptieren, um möglicherweise noch verbleibende Farbinformationen zu erhalten. Bevorzugt können auch spezielle Lampen, die wenig blenden aber die entsprechende Lichttemperatur haben, zusätzlich am Fahrzeug angebracht und aktiviert werden. Für hoch automatisiertes Fahren bis hin zum autonomen Fahren ist von besonderem Interesse, wie weit in die Zukunft (bzw. Weg in Fahrtrichtung) eine definierte Signalsicherheit gewährleistet werden kann. Somit können hoch automatisierte Systeme die Fahrtgeschwindigkeit entsprechend anpassen. Eine zügigere Fahrweise wäre dann nur manuell möglich. Fog lights) accordingly activate / adapt to get possibly remaining color information. Preference may also special lamps that dazzle little but have the appropriate light temperature, additionally attached to the vehicle and activated. For highly automated driving up to autonomous driving, it is of particular interest how far into the future (or way in the direction of travel) a defined signal security can be guaranteed. Thus, highly automated systems can adjust the driving speed accordingly. A faster driving would then be possible only manually.

Claims

Patentansprüche claims
1. Verfahren zur Auswertung von Bilddaten einer Fahrzeugkamera, bei dem Informationen über Regentropfen auf einer Scheibe im Sichtbereich der Fahrzeugkamera bei der Auswertung der Bilddaten berücksichtigt werden. 1. A method for evaluating image data of a vehicle camera, in which information about raindrops on a pane in the field of view of the vehicle camera are taken into account in the evaluation of the image data.
2. Verfahren nach Anspruch 1, wobei Informationen über Lichtverhältnisse bei der Auswertung der Bilddaten berücksichtigt werden. 2. The method of claim 1, wherein information about lighting conditions in the evaluation of the image data are taken into account.
3. Verfahren nach Anspruch 1 oder 2, wobei die Informationen aus den Bilddaten der Fahrzeugkamera ermittelt werden. 3. The method of claim 1 or 2, wherein the information from the image data of the vehicle camera are determined.
4. Verfahren nach einem der vorhergehenden Ansprüche, wobei bei der Auswertung der Bilddaten mindestens ein Kriterium zu einer Erkennung von Kanten im Bild aus den Bilddaten in Abhängigkeit von den Informationen variiert werden kann. 4. The method according to any one of the preceding claims, wherein in the evaluation of the image data at least one criterion for detecting edges in the image from the image data in dependence on the information can be varied.
5. Verfahren nach einem der vorhergehenden Ansprüche, wobei bei der Auswertung der Bilddaten in Abhängigkeit von den Informationen eine Klassifikation von Objekten durchgeführt wird. 5. The method according to any one of the preceding claims, wherein in the evaluation of the image data in dependence on the information, a classification of objects is performed.
6. Verfahren nach einem der vorhergehenden Ansprüche, wobei aus den Informationen ein Gütekriterium der Bilddaten abgeleitet wird, das bei der Auswertung der Bilddaten berücksichtigt wird. 6. The method according to any one of the preceding claims, wherein from the information, a quality criterion of the image data is derived, which is taken into account in the evaluation of the image data.
7. Verfahren nach einem der vorhergehenden Ansprüche, wobei aus den Informationen über Regentropfen auf der Scheibe im Sichtbereich der Fahrzeugkamera ein Wasserschwall erkannt und bei der Auswertung der Bilddaten berücksichtigt wird. 7. The method according to any one of the preceding claims, wherein from the information about raindrops on the disc in the field of vision of the vehicle camera, a water surge detected and taken into account in the evaluation of the image data.
8. Verfahren nach einem der vorhergehenden Ansprüche, wobei aus den Informationen über Regentropfen auf der Scheibe im Sichtbereich der Fahrzeugkamera bei der Auswertung der Bilddaten berücksichtigt wird, dass Scheibenwischer bei einzelnen Bildern einer Bilderfolge Bildbereiche überdecken können. 8. The method according to any one of the preceding claims, wherein from the information about raindrops on the disc in the field of view of the vehicle camera in the evaluation of the image data is taken into account that windshield wipers can cover image areas in individual images of a sequence of images.
9. Verfahren nach einem der Ansprüche 6 bis 8, wobei eine Abschaltung von Fahrerassistenzfunktionen vorgenommen wird, wenn ein minimales Gütekriterium der Bilddaten nicht mehr gegeben ist. 9. The method according to any one of claims 6 to 8, wherein a shutdown of driver assistance functions is performed when a minimum quality criterion of the image data is no longer given.
10. Verfahren nach einem der Ansprüche 6 bis 9, wobei eine Geschwindigkeitsbegrenzung einer Abstandsfolgeregelung vorgenommen wird in Abhängigkeit des aus den Bilddaten abgeleiteten Gütekriteriums. 10. The method according to any one of claims 6 to 9, wherein a speed limit of a distance sequence control is carried out in dependence on the derived from the image data quality criterion.
EP12805925.0A 2011-12-05 2012-11-16 Method for evaluating image data of a vehicle camera taking into account information about rain Withdrawn EP2788917A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102011056051A DE102011056051A1 (en) 2011-12-05 2011-12-05 Method for evaluating image data of a vehicle camera taking into account information about rain
PCT/DE2012/100350 WO2013083120A1 (en) 2011-12-05 2012-11-16 Method for evaluating image data of a vehicle camera taking into account information about rain

Publications (1)

Publication Number Publication Date
EP2788917A1 true EP2788917A1 (en) 2014-10-15

Family

ID=47429482

Family Applications (1)

Application Number Title Priority Date Filing Date
EP12805925.0A Withdrawn EP2788917A1 (en) 2011-12-05 2012-11-16 Method for evaluating image data of a vehicle camera taking into account information about rain

Country Status (5)

Country Link
US (1) US9508015B2 (en)
EP (1) EP2788917A1 (en)
JP (1) JP2015510155A (en)
DE (2) DE102011056051A1 (en)
WO (1) WO2013083120A1 (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011103302A1 (en) 2011-06-03 2012-12-06 Conti Temic Microelectronic Gmbh Camera system for a vehicle
DE102012215287A1 (en) * 2012-08-29 2014-05-28 Bayerische Motoren Werke Aktiengesellschaft Method for operating a vehicle
DE102014209629A1 (en) * 2014-05-21 2015-11-26 Conti Temic Microelectronic Gmbh Method and driver assistance system for monitoring the surroundings of a vehicle
KR102368812B1 (en) * 2015-06-29 2022-02-28 엘지전자 주식회사 Method for vehicle driver assistance and Vehicle
WO2020112213A2 (en) * 2018-09-13 2020-06-04 Nvidia Corporation Deep neural network processing for sensor blindness detection in autonomous machine applications
CN112970029A (en) * 2018-09-13 2021-06-15 辉达公司 Deep neural network processing for sensor blind detection in autonomous machine applications
DE102018218733A1 (en) * 2018-10-31 2020-04-30 Robert Bosch Gmbh Method for supporting a camera-based environment detection of a means of transportation by means of road wetness information from a first ultrasonic sensor
DE102020106377A1 (en) 2020-03-09 2021-09-09 Bayerische Motoren Werke Aktiengesellschaft Method for operating an assistance system and assistance system
CN112414665B (en) * 2020-09-30 2023-06-09 中汽研（天津）汽车工程研究院有限公司 Wind tunnel test and evaluation method for vehicle side window rainwater vision management performance
DE102020215859A1 (en) 2020-12-15 2022-06-15 Conti Temic Microelectronic Gmbh Correction of images from a camera in rain, light and dirt
DE102020215860A1 (en) 2020-12-15 2022-06-15 Conti Temic Microelectronic Gmbh Correction of images from an all-round view camera system in the event of rain, light and dirt
US20230115240A1 (en) * 2021-10-13 2023-04-13 Arriver Software Llc Advanced driver-assistance systems feature activation control using digital map and on-board sensing to confirm safe vehicle operation

Family Cites Families (86)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4417385A1 (en) 1994-05-18 1995-11-23 Vdo Schindling Windscreen wiper control circuit
DE59509929D1 (en) 1994-07-06 2002-01-24 Volkswagen Ag Method for determining the visibility, in particular for the movement of a motor vehicle
JPH0830898A (en) * 1994-07-20 1996-02-02 Fujitsu Ltd Picture analysis device
DE19504606C2 (en) 1995-02-11 1999-01-07 Kostal Leopold Gmbh & Co Kg Optoelectronic device for detecting precipitation which is deposited on the outside of a transparent pane
JPH09189533A (en) 1996-01-11 1997-07-22 Tokai Rika Co Ltd Deposit sensor and deposit-sensitive wiper
WO1997029926A1 (en) 1996-02-13 1997-08-21 Marquardt Gmbh Optic sensor
JPH1090188A (en) 1996-09-13 1998-04-10 Mitsuba Corp Image recognition device
US6681163B2 (en) * 2001-10-04 2004-01-20 Gentex Corporation Moisture sensor and windshield fog detector
US5923027A (en) 1997-09-16 1999-07-13 Gentex Corporation Moisture sensor and windshield fog detector using an image sensor
DE19740364A1 (en) 1997-09-13 1999-03-25 Bosch Gmbh Robert Device for operating an optoelectronic rain sensor
DE19749331A1 (en) 1997-11-07 1999-05-20 Kostal Leopold Gmbh & Co Kg Method of detecting objects on motor vehicle windscreen
DE19803694C1 (en) 1998-01-30 1999-04-22 Kostal Leopold Gmbh & Co Kg Method of detecting objects on a transparent plate, e.g. a motor vehicle windscreen
DE19861428B4 (en) 1998-03-17 2008-01-10 Robert Bosch Gmbh Optical sensor
DE19909987C2 (en) 1999-03-06 2003-04-10 Kostal Leopold Gmbh & Co Kg Arrangement for detecting objects located on a windshield of a motor vehicle
JP2001160146A (en) 1999-12-01 2001-06-12 Matsushita Electric Ind Co Ltd Method and device for recognizing image
JP4414054B2 (en) * 2000-03-27 2010-02-10 本田技研工業株式会社 Object recognition device
US6392218B1 (en) 2000-04-07 2002-05-21 Iteris, Inc. Vehicle rain sensor
FR2810605B1 (en) 2000-06-22 2002-09-20 Valeo Systemes Dessuyage AUTOMATIC CONTROL EQUIPMENT FOR CLEANING A PLATE SURFACE HAVING VARIOUS DIRT CONDITIONS, AND IMPLEMENTATION METHOD
US6614043B2 (en) 2001-04-16 2003-09-02 Valeo Electrical Systems, Inc. Imaging rain sensor illumination positioning system
US6617564B2 (en) 2001-10-04 2003-09-09 Gentex Corporation Moisture sensor utilizing stereo imaging with an image sensor
DE10201522A1 (en) 2002-01-17 2003-07-31 Bosch Gmbh Robert Method and device for detecting visual impairments in image sensor systems
DE10301468B4 (en) * 2002-01-18 2010-08-05 Honda Giken Kogyo K.K. Device for monitoring the environment of a vehicle
JP3641250B2 (en) 2002-04-23 2005-04-20 三菱電機株式会社 Foreign object detection device on translucent surface
DE10219788C1 (en) * 2002-05-03 2003-11-13 Bosch Gmbh Robert Method and device for measuring visibility with image sensor systems
DE50301758D1 (en) 2002-05-18 2005-12-29 Elmos Semiconductor Ag RAIN SENSOR
DE10230200A1 (en) 2002-07-05 2004-01-22 Robert Bosch Gmbh Method and device for the detection of objects located on a surface of a transparent element
US8180099B2 (en) 2002-07-16 2012-05-15 Trw Limited Rain detection apparatus and method
DE10303047A1 (en) 2003-01-24 2004-08-05 Daimlerchrysler Ag Method and device for improving the visibility and for determining the weather situation
DE10303046A1 (en) 2003-01-24 2004-10-21 Daimlerchrysler Ag Quantitative estimation of visibility in motor vehicle, by using e.g. measurement of sharpness or contrast of image obtained from intensity differences of adjacent pixels
DE10316794A1 (en) 2003-04-11 2004-11-11 Audi Ag Rain sensor for road vehicle windscreen has camera looking forward through windscreen to observe raindrops and connected to transmission module and picture evaluation circuit
WO2004106858A1 (en) * 2003-05-29 2004-12-09 Olympus Corporation Stereo camera system and stereo optical module
JP4326999B2 (en) 2003-08-12 2009-09-09 株式会社日立製作所 Image processing system
JP2005225250A (en) 2004-02-10 2005-08-25 Murakami Corp On-vehicle surveillance device
JP2005233728A (en) 2004-02-18 2005-09-02 Denso Corp Photosensor device
US7458976B2 (en) 2005-03-02 2008-12-02 Advanced Medical Optics, Inc. Devices and methods for storing, loading, and delivering an intraocular lens
DE102004015040A1 (en) 2004-03-26 2005-10-13 Robert Bosch Gmbh Camera in a motor vehicle
JP2005292544A (en) 2004-04-01 2005-10-20 Matsushita Electric Ind Co Ltd Focusing mechanism
JP3934119B2 (en) 2004-06-14 2007-06-20 本田技研工業株式会社 Vehicle periphery monitoring device
DE102004037871B4 (en) 2004-08-04 2006-10-12 Siemens Ag Optical module for an outer vestibule in the direction of travel of a motor vehicle detecting assistance system
DE112005001898A5 (en) 2004-09-03 2007-08-09 Adc Automotive Distance Control Systems Gmbh Method for detecting precipitation on a pane
JP4241561B2 (en) 2004-09-28 2009-03-18 株式会社デンソー Raindrop detector
JP2006184844A (en) 2004-12-03 2006-07-13 Tochigi Nikon Corp Image forming optical system and imaging apparatus using the same
DE102005004513A1 (en) 2005-01-31 2006-03-09 Daimlerchrysler Ag Motor vehicle windscreen surface condensation detecting method, involves concluding focus width on condensation when object is identified in picture data set and when object has high picture sharpness than in picture data set
JP4479532B2 (en) * 2005-02-17 2010-06-09 株式会社デンソー Fog detection device by night image
US7660517B2 (en) * 2005-03-16 2010-02-09 The Trustees Of Columbia University In The City Of New York Systems and methods for reducing rain effects in images
US7253898B2 (en) 2005-03-31 2007-08-07 Hitachi, Ltd. System for detecting droplets on a translucent surface
JP4353127B2 (en) 2005-04-11 2009-10-28 株式会社デンソー Rain sensor
DE102005035812A1 (en) 2005-07-27 2007-02-08 Adc Automotive Distance Control Systems Gmbh Method of detecting soiling on a transparent pane
US7804980B2 (en) * 2005-08-24 2010-09-28 Denso Corporation Environment recognition device
EP1764835B1 (en) 2005-09-19 2008-01-23 CRF Societa'Consortile per Azioni Multifunctional optical sensor comprising a matrix of photodetectors coupled microlenses
DE102006008274B4 (en) 2006-02-22 2021-11-25 Continental Automotive Gmbh Motor vehicle with an optical detection device and method for operating a motor vehicle
JP5022609B2 (en) 2006-02-27 2012-09-12 日立オートモティブシステムズ株式会社 Imaging environment recognition device
DE102006010671A1 (en) 2006-03-08 2007-09-13 Leopold Kostal Gmbh & Co. Kg Camera arrangement for a motor vehicle
US20070216768A1 (en) 2006-03-14 2007-09-20 Ford Global Technologies, Llc Device and method for outwardly looking ir camera mounted inside vehicles particularly suited for pre-crash sensing and pedestrian detection
JP4668838B2 (en) 2006-05-16 2011-04-13 株式会社日本自動車部品総合研究所 Raindrop detection device and wiper control device
FR2901218B1 (en) 2006-05-22 2009-02-13 Valeo Vision Sa METHOD FOR DETECTING RAIN ON A SPRINKLER
FR2908527B1 (en) 2006-11-15 2009-01-16 Valeo Vision Sa PHOTOSENSITIVE SENSOR IN THE AUTOMOBILE DOMAIN
DE102006055908A1 (en) 2006-11-27 2008-05-29 Adc Automotive Distance Control Systems Gmbh Method for automatic high beam control
JP4654208B2 (en) * 2007-02-13 2011-03-16 日立オートモティブシステムズ株式会社 Vehicle environment recognition device
TWI495337B (en) 2007-08-04 2015-08-01 Omnivision Tech Inc Multi-region imaging systems
US7889086B2 (en) 2007-09-28 2011-02-15 Hella Kgaa Camera arrangement in a motor vehicle
JP4930316B2 (en) 2007-10-05 2012-05-16 株式会社デンソー Raindrop amount detection device, wiper control device and headlight control device using the same
EP2062777B1 (en) 2007-11-21 2010-06-16 Delphi Technologies, Inc. Optical module
DE102007061725A1 (en) 2007-12-20 2009-06-25 Robert Bosch Gmbh Method for checking the plausibility of at least one light detector of a driving light assistance device of a motor vehicle
WO2009131316A2 (en) 2008-04-21 2009-10-29 (주) 에프에쓰씨 Raindrop sensor
DE102008001679A1 (en) * 2008-05-09 2009-11-12 Robert Bosch Gmbh Method and device for processing recorded image information from a vehicle
JP5359175B2 (en) 2008-10-16 2013-12-04 株式会社デンソー Visibility state detection device and visibility securing device
DE102008043737A1 (en) 2008-11-14 2010-05-20 Robert Bosch Gmbh Method for detecting raindrops on disk, involves recording measured image in plane of disk and reference image is recorded in plane deviating from plane of disk
DE102008062977A1 (en) 2008-12-23 2010-06-24 Adc Automotive Distance Control Systems Gmbh Optical module with multifocal optics for the detection of distance and near range in one image
DE102009000004A1 (en) 2009-01-02 2010-07-08 Robert Bosch Gmbh Camera arrangement for a motor vehicle and motor vehicle with a camera arrangement
DE102009000003A1 (en) 2009-01-02 2010-07-08 Robert Bosch Gmbh Camera arrangement for detecting a wheel condition of a vehicle window
DE102009000005A1 (en) 2009-01-02 2010-07-08 Robert Bosch Gmbh Camera arrangement and method for detecting a vehicle environment
WO2010084521A1 (en) * 2009-01-20 2010-07-29 本田技研工業株式会社 Method and apparatus for identifying raindrops on a windshield
US8466960B2 (en) 2009-02-16 2013-06-18 Ricoh Company, Ltd. Liquid droplet recognition apparatus, raindrop recognition apparatus, and on-vehicle monitoring apparatus
EP2230496A1 (en) * 2009-03-16 2010-09-22 Autoliv Development AB Method and system for automatically detecting objects in front of a motor vehicle
CN102472840B (en) 2009-07-06 2015-05-20 康蒂特米克微电子有限公司 Optical module for simultaneously focusing on two fields of view
KR20110060495A (en) 2009-11-30 2011-06-08 동양기전 주식회사 Rain-sensor using light scattering
FR2956236B1 (en) * 2010-02-09 2012-11-30 France Etat Ponts Chaussees METHOD AND DEVICE FOR DETECTING DROPS IN A DIGITAL IMAGE; COMPUTER PROGRAM FOR IMPLEMENTING THIS METHOD.
JP5016073B2 (en) * 2010-02-12 2012-09-05 株式会社デンソー White line recognition device
US8362453B2 (en) 2010-02-24 2013-01-29 Niles Co., Ltd. Rain sensor
EP2646802A1 (en) 2010-11-30 2013-10-09 Conti Temic Microelectronic GmbH Detection of raindrops on a pane by means of a camera and lighting
JP5474254B2 (en) * 2011-02-24 2014-04-16 三菱電機株式会社 Navigation device, recommended speed calculation device, and recommended speed presentation device
DE102011103302A1 (en) 2011-06-03 2012-12-06 Conti Temic Microelectronic Gmbh Camera system for a vehicle
JP5561333B2 (en) 2011-11-02 2014-07-30 株式会社リコー Image processing apparatus, imaging method, program, and vehicle
DE102012200200B4 (en) 2012-01-09 2020-09-17 Robert Bosch Gmbh Camera system, in particular for a vehicle, and a vehicle
DE102014209197A1 (en) 2014-05-15 2015-11-19 Conti Temic Microelectronic Gmbh Apparatus and method for detecting precipitation for a motor vehicle

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2013083120A1 *

Also Published As

Publication number Publication date
JP2015510155A (en) 2015-04-02
WO2013083120A1 (en) 2013-06-13
DE102011056051A1 (en) 2013-06-06
US20150220792A1 (en) 2015-08-06
US9508015B2 (en) 2016-11-29
DE112012005077A5 (en) 2014-09-04

Similar Documents

Publication Publication Date Title
WO2013083120A1 (en) Method for evaluating image data of a vehicle camera taking into account information about rain
DE102011088130B4 (en) Method and device for detecting a braking situation
JP5879219B2 (en) In-vehicle environment recognition system
DE102014212162A1 (en) Headlight control device
DE102012209810A1 (en) Method and control unit for detecting a weather condition in an environment of a vehicle
EP1757485A1 (en) Method for adjusting the aiming of vehicle headlamps
DE102018203807A1 (en) Method and device for detecting and evaluating road conditions and weather-related environmental influences
DE102011077038A1 (en) Method and device for detecting objects in an environment of a vehicle
DE102009039179A1 (en) Headlight control device and vehicle headlight with headlight control device
EP2748035B1 (en) Method and control unit for adapting the luminosity of at least one headlamp of a vehicle
EP2864157A1 (en) Method for automatically adapting vehicle lighting to a surrounding area of a vehicle, lighting apparatus and vehicle having lighting
DE102012209514A1 (en) Method and device for detecting a visual impairment of a disc
DE102015003960A1 (en) Method for determining a visibility for a vehicle in fog
DE102011081362A1 (en) Method for determining surface quality of track for passing vehicle, involves outputting surface state signal indicating surface condition of the track when the comparison signal satisfies predetermined relationship
DE102005054497A1 (en) Motor vehicle, has control device that is controlled by transmitter and receiver, and dirt detecting device provided for controlling luminous intensity controlling unit that controls luminous intensity of rear lights
DE212013000187U1 (en) System Image of an outdoor scene using an application-specific image sensor
DE10104734A1 (en) Car control system uses infrared images to control vehicles head-lights and other units
DE102006003646A1 (en) Method for adaptation of light transmitted from illuminating device in vehicle, involves determining driver activity in automatic manner
KR100660561B1 (en) Vision based intelligent smart wiper system and its control method
DE102008062642A1 (en) Vehicle rear light controlling method, involves evaluating surrounding state of vehicle for determining intensity and amount on roadway, and adjusting intensity of lighting functions of lights depending on light absorbing characteristics
DE102013022050A1 (en) Method for tracking a target vehicle, in particular a motorcycle, by means of a motor vehicle, camera system and motor vehicle
CH701327A2 (en) Device for adaptive operation of standard tail lamp for passenger car, has speed sensor and standard rain sensor connected with control device, which is connected with standard tail lamp to regulate luminous intensity of standard tail lamp
DE102016004289A1 (en) Method and device for controlling a vehicle lighting and vehicle with such a device
EP2748759A1 (en) Method and device for detecting disturbing objects in the surrounding air of a vehicle
CN111376820A (en) Automatic control system for car lamp

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: 20140707

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

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

Owner name: CONTI TEMIC MICROELECTRONIC GMBH

Owner name: CONTINENTAL TEVES AG & CO. OHG

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: 20190219