WO2013091626A1 - Verfahren zur kalibrierung einer verkehrsüberwachungskamera zu einem lagesensor - Google Patents
Verfahren zur kalibrierung einer verkehrsüberwachungskamera zu einem lagesensor Download PDFInfo
- Publication number
- WO2013091626A1 WO2013091626A1 PCT/DE2012/100393 DE2012100393W WO2013091626A1 WO 2013091626 A1 WO2013091626 A1 WO 2013091626A1 DE 2012100393 W DE2012100393 W DE 2012100393W WO 2013091626 A1 WO2013091626 A1 WO 2013091626A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image data
- camera
- extract stream
- stream
- sensor
- Prior art date
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
- G01S13/91—Radar or analogous systems specially adapted for specific applications for traffic 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
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
- G01S7/4004—Means for monitoring or calibrating of parts of a radar system
- G01S7/4026—Antenna boresight
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/497—Means for monitoring or calibrating
- G01S7/4972—Alignment of sensor
Definitions
- an image capturing measuring system When using an image capturing measuring system is usually a digital camera for taking pictures together with special sensors for
- Receiver surface of the camera imaged object points (pixels) to the
- Sensor measured object points are determined. In particular, from the
- Traffic measurement known method for detecting traffic violations and the unambiguous assignment of a monitoring or measurement result to the detected vehicle is a precise calibration is a prerequisite for approval of such a measurement system.
- the measuring devices such as the position sensor and the camera to each other and to a monitored area within a framework, which are defined for example in a set-up rule for the respective measuring system.
- a framework which are defined for example in a set-up rule for the respective measuring system.
- the published patent application DE 10 2009 013 667 A1 describes a method with which a predefined positional relationship, which is determined by the spatial relationship between a laser scanner and a digital camera, is established for a traffic monitoring device.
- the laser scanner and the digital camera are roughly aligned with each other so that a surveillance area within the scan angle range of the laser scanner is completely covered by the object field of the digital camera at a given photo point.
- the spatial relationship between the laser scanner (henceforth: position sensor) and the digital camera (henceforth: camera) is determined by the spatial relationship of the laser coordinate system (henceforth sensor coordinate system) to the camera coordinate system.
- the laser coordinate system is determined by a Laserscanachse (henceforth: sensor axis), which is perpendicular to a receiver surface, as well as the location of the scan plane and represents a polar coordinate system.
- Through the scan field (henceforth: sensor area) of the position sensor moving objects can by detecting a Distance value and the scan angle at the time of detection (henceforth: measurement time) are assigned to a location in the sensor area.
- the camera coordinate system is determined by the optical axis of the camera and its receiver matrix and represents a Cartesian coordinate system. Mappings are made with regard to their position in the image plane (on the receiver matrix) via the knowledge of the position of the receiving image elements (pixels) in lines and columns certain receiver matrix detected.
- the spatial relationship is established in two steps. In a first step, a rough adaptation of sensor and camera coordinate system is first calculated. In a second step, a fine adjustment is made in a user-led, manual process.
- the measured values of the position sensor which describe a spatially distributed number of measuring points corresponding to a vehicle contour and the scanning range orientation in a polar coordinate system, are transformed into a Cartesian coordinate system assigned to the position sensor.
- This can then be transformed into a Cartesian coordinate system assigned to the camera.
- This is done by computational translational displacements along the axes of the coordinate system of the position sensor and by a conversion of the measured values, taking into account the known imaging characteristic of the camera.
- the coarse amounts of the translational displacements result from the distances between the axes of the coordinate systems of the position sensor and the camera and are known due to a fixed positional relationship between position sensor and camera.
- the transformation thus generated still requires the adaptation of the rotational rotation and the fine adjustment of the translational displacements.
- the fine adjustment is done by a user in one interactive process by means of a suitable device for image processing.
- a suitable device for image processing For this purpose, at least one photograph of the detected vehicle is superimposed with a visually illustrated measurement structure, which was generated from the number of measured values formed at the time the photo was taken, and shifted and rotated by the user in such a way that the vehicle is superimposed as ideally as possible by the measurement structure.
- the superimposed measuring structure is taken over into the photo and thus simultaneously serves to mark the detected vehicle z. B. in the case of a photo of a multi-lane roadway.
- the invention has for its object to propose a method by which the unknown spatial relationship between a position sensor and a camera can be determined fully automatically.
- the object is achieved by a method according to claim 1.
- the implementation of the method according to the invention requires that a camera and a position sensor are provided, which are directed onto a roadway.
- the camera having a Cartesian camera coordinate system passing through the optical axis of the camera, the plane of the receiver matrix and the direction of the rows and columns of the pixels of the receiver matrix is determined so that the roadway is aligned, that a part of the roadway is detected by the object field of the camera.
- the position sensor which has a polar sensor coordinate system, which is determined by a sensor axis and a receiver surface
- the sensor coordinate system is designed polar.
- the relative position of the two coordinate systems to each other is given, but not known. To gain knowledge about the relative position is the purpose of the calibration.
- the object field and the sensor area can be subregions of one another, overlap or else lie next to or away from each other.
- the position sensor can, for. B. be a radar sensor or a laser scanner. By reflection of radiation on a vehicle passing through the sensor area, it receives measurement data for a plurality of successive measuring times, which are recorded as a measured data stream and supplied to a computer. The measured data are distance and angle values and thus form polar coordinates of measuring points in the sensor area.
- the measurement data generated by a vehicle is typical for a vehicle and can be extracted from the measurement data stream.
- the extracted measurement data of the measurement data stream are referred to below as measurement data extract stream.
- the inventive method is basically applicable to any objects. Preferably, however, the objects are vehicles.
- image data corresponding to a vehicle or a salient area of a vehicle is extracted.
- the extracted image data will hereinafter be referred to as the formed image data extract stream.
- the measured data extract stream and the formed image data extract stream are generated by means of a computer and by methods known to the person skilled in the art.
- the trajectory of the vehicle can be derived from the measured data extract stream and the image data extract stream formed, that is, the lane which describes the vehicle as it is being driven during the acquisition.
- this is only of interest if the object field and the sensor area do not overlap or overlap only very slightly, as a result of which a vehicle is not or only a few times captured at one location both by the position sensor and by the camera.
- a stationary detection of a vehicle with the position sensor and the camera or the creation of location-identical pseudomessage or image data is the prerequisite for being able to calibrate the camera to the position sensor.
- an artificial image data extract stream is generated from the measured data extract stream, which is then brought into conformity with the image data extract stream formed by known error calculation methods.
- the prior knowledge of the intrinsic parameters of the camera is not mandatory, but facilitates the effort for the estimation of the parameters. It is also conceivable via compensation calculations that the intrinsic parameters of the camera are also determined within the framework of error calculation methods. A direct comparison of the formed image data extract stream with the measured data extract stream is not possible since the measured data extract stream in 3D space is determined while an image data extract stream in a 2D area is determined.
- a comparison be made of traces of the formed image data extract stream and the artificial image data extract stream.
- it is determined with which rotation angle and with which spatial offset at least one of the image data extract streams to be rotated and spatially offset in order to achieve a match of the formed image data extract stream and the artificial image data extract stream.
- a match equals a predetermined similarity of the formed image data extract stream and the artificial image data extract stream.
- the image data extract stream both the formed and the artificial, can thus be interpreted in the sense of a visual representation as an image track (track).
- the artificially generated track can thus be compared with the tracks given by the formed image data extract stream.
- an image data extract stream is referred to by the skilled person as optical flow and refers to the track or tracks left by moving objects in the object field or in the sensor area. Comparable is the optical flow with the tracks that are used in a nocturnal long-term photographic exposure, z. B. a busy road, are displayed.
- the measured data extract stream is filmed with a virtual camera.
- the comparison with an acceptance by means of a virtual camera is used below for a simplified explanation of the method according to the invention.
- Virtual camera shooting is similar to rendering a 3D model in a CAD program onto a 2D line drawing, the location and rotation of that virtual camera compared to the (real) camera coordinate system used as the reference coordinate system gives an actually required rotation angle as well as an actually required spatial offset to a relative position between Describe sensor coordinate system and camera coordinate system (hereafter: coordinate systems).
- a pictorial representation is, in general terms, an image of a 3D object on a 2D projection surface.
- a projection can be applied to any type of 3D objects, such as these, z. B. including their movement parameters, are recognized by modern measuring systems. These measuring systems provide, for example, the location and speed of the appropriate objects. If these 3D objects, including their tracks, are then imaged on a two-dimensional artificial track as an artificial image data extract stream, this artificial image data extract stream can be compared manually and / or automatically with the image data extract stream formed. In a simple case, the formed image data extract stream and the artificial image data extract stream are comparable by determining geometric distances of points or regions of the respective tracks.
- the artificial image data extract stream serves as a comparison data stream to the formed image data extract stream.
- Positional parameters are preferably given by at least one rotation angle and by at least one spatial offset.
- the rotation angle denotes an angle about which a virtual optical axis of the virtual camera is to tilt in order to image a 3D object from the same angle as the (real) camera.
- the virtual camera describes a rotating movement (rotation).
- the 3D object projected in this way and projected onto a 2D surface may have a different spatial position than the 3D object imaged by means of the camera.
- the difference of the local positions represents the Spatial displacement.
- this means that the angle of rotation indicates the rotation of the virtual camera that is required to convert the measured data extract stream into the artificial image data extract stream.
- the spatial offset can be determined from the difference of the spatial positions of formed image data extract stream and artificial image data extract stream.
- the coordinate system of the camera in particular a point of the coordinate system, is selected.
- the origin point can be chosen if it is a Cartesian coordinate system or a base point of a coordinate axis, if it is a polar coordinate system.
- the choice of another reference point is also known and possible.
- the measurement data extract stream is converted into an artificial 3D object in an artificial space using these estimated attitude parameters.
- the conversion of points of the artificial 3D object into points of an artificial projection on a 2D surface is done using the virtual Camera, which has the same intrinsic parameters as the camera. Since the measured data extract stream embodies a time profile of measured data, a projection of the measured data extract stream gives a temporal sequence of the artificial dots on the 2D area-and thus the artificial image data extract stream.
- the artificial image data extract stream can be generated using the estimated rotation angle and the estimated spatial offset.
- the virtual camera is rotated around the 3D object until a sufficient similarity or coincidence is detected between the formed image data extract stream and the artificial image data extract stream. In this case, an actually required rotation angle is determined.
- the estimated rotation angle can then be corrected accordingly. From the comparison of the artificial image data extract stream and the formed image data extract stream, an actually required spatial offset is determined.
- the estimated spatial offset can then be corrected.
- the relative position of the coordinate systems can be determined without using estimated position parameters.
- This step can be skipped in the method according to the invention since only the relative relationship between sensor and camera coordinate system is of interest.
- the formed image data extract stream is generated in the prior art method of the present invention, the combination of an artificial 3D rotation of the measurement data extract stream with a subsequent 3D / 2D artificial projection is new. From the comparison of the formed image data extract stream with the artificial image data extract stream, a correct determination of the relative position between the sensor coordinate system and the camera coordinate system is made possible.
- the position sensor can also provide information on the direction of travel and speed of the vehicle.
- the data is used like the location information for the adjustment calculation.
- the speed and the direction from the measured data extract stream are converted into a virtual optical flow, and this virtual optical flow is compared with the real optical flow from the image data extract stream in the context of the error compensation method.
- a large variety of appropriate object points of a vehicle are matched with a large plurality of pixels of the imaged vehicle.
- measurement points within the sensor coordinate system are transformed into pixels within the camera coordinate system.
- a transformation rule is derived, according to which later determined measurement data can be assigned to image data, as long as the orientation of the camera and the position sensor relative to one another does not change.
- the measurement data can be converted into the image data by mathematical displacement and rotation and compared with the image data actually obtained.
- a camera (box b) and a position sensor (box h) are positioned relative to each other such that a sensor area is detected by the position sensor and an object field by the camera.
- Sensor area and object field are aligned with each other so that an object to be detected moves through both the sensor area and the object field.
- the sensor area and the object field may overlap completely or partially. They also can not be aligned overlapping.
- the position sensor and camera are positioned according to a set-up rule, which defines the minimum and maximum allowable distances as well as the lowest and highest rotation angles between the sensor axis of the position sensor and the optical axis of the camera.
- the explanation is given by means of two moving vehicles.
- the camera has a receiver matrix with a Cartesian coordinate system.
- the position sensor has a receiver unit (not shown), by means of which measurement data from the sensor area can be detected at measurement instants. The measured data can be stored assigned to the measurement times.
- a number of image recordings of the object field are recorded successively in time as a sequence of images and stored in a computing unit (not shown) (box c).
- a computing unit not shown
- the contour is recognized and stored in some selected image recordings of the image sequence.
- Those image data by which the contour is described are extracted from the image recordings of the image sequence and an image data extract stream is formed therefrom and stored as educated image data extract stream (box d). Due to the image data extract stream formed, the two detected vehicles can be displayed (shown in a highly schematic manner as angled arrows). Box e) can be displayed. The formed image data extract stream is passed to a comparison unit (represented by box f) where it is compared to an artificial image data extract stream (see below).
- the contribution of the position sensor when carrying out the method according to the invention is that measured values are acquired at measuring times in the sensor area and stored as measured data associated with the measuring times. Due to the chronological sequence of acquired measurement data, a measurement data stream is given.
- the position sensor which has a sensor coordinate system with a sensor axis, the vehicles are detected in the sensor area and tracked during their movement through the sensor area (tracking). At each measurement time, those data are extracted from the measurement data, which are each assigned to one of the vehicles.
- the relative position of the vehicles to the sensor coordinate system is continuously given by data triples of angle, distance and speed as measured data.
- a movement path (lane, lane) of each vehicle can be derived from the measurement data stream, which describes the respective vehicle during its movement through the sensor area. This also makes it possible to track two or more vehicles at the same time.
- the two vehicles are tracked (see schematically in box j) (box i).
- Estimated positional parameters are created for the position sensor.
- the sensor axis and the optical axis are arranged with a relative position to each other, which can be specified by a rotation angle and a spatial offset.
- both the value of the rotation angle and the value of the spatial offset can lie only within a respective area defined by the setup rule.
- an estimated rotation angle and estimated spatial displacement are selected (Box k2).
- the measured data extract stream of each vehicle is converted and the respective vehicle is displayed as a 3D object.
- a rotation of a virtual camera is performed and each 3D object is imaged by the virtual camera, thereby projecting the 3D object into a 2D surface (box 11).
- the 3D object can be translated to account for the estimated spatial offset.
- the same intrinsic parameters that the camera (box b) has (box 12) are assumed.
- Data points of the 3D object are transferred to data points in the 2D area. Since the measured data extract current comprises a number of measuring times, the projection shows a movement path (lane) of the vehicle in the sensor area (box j).
- the data points in the 2D area yield an artificial image data extract stream (box m).
- This artificial image data extract stream is transferred to the comparison unit (box f) and compared with the formed image data stream and matched. If necessary, a further rotation is performed by a further rotation angle. If a better match of the image data extract streams is achieved by the further rotation, the further rotation angle is used to correct the estimated rotation angle.
- a further spatial offset is determined. If a better match of the image data extract streams is achieved by the further spatial offset, the further spatial offset is used to correct the estimated spatial offset.
- the actually required rotation angle and the actually required spatial offset describe as positional parameters a relative position of the coordinate systems to one another.
- a transformation rule can be derived, by means of which points of a coordinate system can be converted into points of the other coordinate system.
- the trajectories can be derived by extrapolating acquired measurement data and forming pseudo measurement data. The pseudo measurement data allow the description of trajectories outside the sensor range.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE112012005369.9T DE112012005369A5 (de) | 2011-12-22 | 2012-12-20 | Verfahren zur Kalibrierung einer Kamera zu einem Lagesensor |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102011056948.0 | 2011-12-22 | ||
DE102011056948A DE102011056948A1 (de) | 2011-12-22 | 2011-12-22 | Verfahren zur Kalibrierung einer Kamera zu einem Lagesensor |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013091626A1 true WO2013091626A1 (de) | 2013-06-27 |
Family
ID=47594168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/DE2012/100393 WO2013091626A1 (de) | 2011-12-22 | 2012-12-20 | Verfahren zur kalibrierung einer verkehrsüberwachungskamera zu einem lagesensor |
Country Status (2)
Country | Link |
---|---|
DE (2) | DE102011056948A1 (de) |
WO (1) | WO2013091626A1 (de) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103837869B (zh) * | 2014-02-26 | 2016-06-01 | 北京工业大学 | 基于向量关系的单线激光雷达和ccd相机标定方法 |
DE102017109039A1 (de) | 2017-04-27 | 2018-10-31 | Sick Ag | Verfahren zur Kalibrierung einer Kamera und eines Laserscanners |
CN108597234A (zh) * | 2018-05-10 | 2018-09-28 | 芜湖航飞科技股份有限公司 | 一种基于高分辨率雷达的智能交通检测仪 |
FR3096786B1 (fr) * | 2019-05-27 | 2021-05-14 | Idemia Identity & Security France | Procédé et dispositif de configuration d’un radar routier |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1760491A2 (de) * | 2005-09-02 | 2007-03-07 | Delphi Technologies, Inc. | Verfahren zur Kalkulation unbekannter Parameter für Fahrzeugobjekterkennungssysteme |
US20100235129A1 (en) * | 2009-03-10 | 2010-09-16 | Honeywell International Inc. | Calibration of multi-sensor system |
DE102009013667A1 (de) | 2009-03-24 | 2010-09-30 | Jenoptik Robot Gmbh | Verfahren zur Herstellung einer bekannnten festen räumlichen Beziehung zwischen einem Laserscanner und einer Digitalkamera zur Verkehrsüberwachung |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030179308A1 (en) * | 2002-03-19 | 2003-09-25 | Lucia Zamorano | Augmented tracking using video, computed data and/or sensing technologies |
DE102004033114A1 (de) * | 2004-07-08 | 2006-01-26 | Ibeo Automobile Sensor Gmbh | Verfahren zur Kalibrierung eines Abstandsbildsensors |
DE102010012811B4 (de) * | 2010-03-23 | 2013-08-08 | Jenoptik Robot Gmbh | Verfahren zur Messung von Geschwindigkeiten und Zuordnung der gemessenen Geschwindigkeiten zu angemessenen Fahrzeugen durch Erfassen und Zusammenführen von Objekt-Trackingdaten und Bild-Trackingdaten |
-
2011
- 2011-12-22 DE DE102011056948A patent/DE102011056948A1/de not_active Ceased
-
2012
- 2012-12-20 DE DE112012005369.9T patent/DE112012005369A5/de not_active Withdrawn
- 2012-12-20 WO PCT/DE2012/100393 patent/WO2013091626A1/de active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1760491A2 (de) * | 2005-09-02 | 2007-03-07 | Delphi Technologies, Inc. | Verfahren zur Kalkulation unbekannter Parameter für Fahrzeugobjekterkennungssysteme |
US20100235129A1 (en) * | 2009-03-10 | 2010-09-16 | Honeywell International Inc. | Calibration of multi-sensor system |
DE102009013667A1 (de) | 2009-03-24 | 2010-09-30 | Jenoptik Robot Gmbh | Verfahren zur Herstellung einer bekannnten festen räumlichen Beziehung zwischen einem Laserscanner und einer Digitalkamera zur Verkehrsüberwachung |
Also Published As
Publication number | Publication date |
---|---|
DE102011056948A1 (de) | 2013-06-27 |
DE112012005369A5 (de) | 2014-08-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2234081B1 (de) | Verfahren zur Herstellung einer bekannten festen räumlichen Beziehung zwischen einem Laserscanner und einer Digitalkamera zur Verkehrsüberwachung | |
EP2993450B1 (de) | Verfahren und anordnung zur erfassung von akustischen und optischen informationen sowie ein entsprechendes computerprogramm und ein entsprechendes computerlesbares speichermedium | |
DE10219054B4 (de) | Verfahren und Vorrichtung zur Bestimmung der räumlichen Koordinaten eines Gegenstandes | |
DE102004033114A1 (de) | Verfahren zur Kalibrierung eines Abstandsbildsensors | |
DE102010012811B4 (de) | Verfahren zur Messung von Geschwindigkeiten und Zuordnung der gemessenen Geschwindigkeiten zu angemessenen Fahrzeugen durch Erfassen und Zusammenführen von Objekt-Trackingdaten und Bild-Trackingdaten | |
WO2008083869A1 (de) | Verfahren, vorrichtung und computerprogramm zur selbstkalibrierung einer überwachungskamera | |
DE102007020791A1 (de) | Fahrspurmarkierungs-Erkennungsvorrichtung | |
DE102016206493A1 (de) | Verfahren und Kamerasystem zur Entfernungsbestimmung von Objekten zu einem Fahrzeug | |
EP2189349A2 (de) | Verfahren und Vorrichtung zur Kompensation eines Rollwinkels | |
EP2573512A2 (de) | Verfahren und Anordnung zur Bestimmung der Lage eines Messpunktes im geometrischen Raum | |
EP1460454B1 (de) | Verfahren zur gemeinsamen Verarbeitung von tiefenaufgelösten Bildern und Videobildern | |
DE69829091T2 (de) | Messungsgerät | |
WO2013124056A1 (de) | Vorrichtung zur berührungslosen temperaturmessung und temperaturmessverfahren | |
WO2013091626A1 (de) | Verfahren zur kalibrierung einer verkehrsüberwachungskamera zu einem lagesensor | |
EP3642560A1 (de) | System, verfahren und marker zur positionsbestimmung eines beweglichen objektes im raum | |
DE102007021106B4 (de) | Verfahren und Vorrichtung zum Kalibrieren eines Kamerasystems | |
DE102014219423B4 (de) | Dynamisches Modell zur Kompensation von Verzeichnungen einer Windschutzscheibe | |
WO2018133890A1 (de) | Verfahren und vorrichtung zum erzeugen eines 3d-thermogramms | |
DE102017115587A1 (de) | Verfahren zum Bestimmen einer räumlichen Unsicherheit in Bildern eines Umgebungsbereiches eines Kraftfahrzeugs, Fahrerassistenzsystem sowie Kraftfahrzeug | |
DE102011001475B4 (de) | Verfahren und Vorrichtungen zur Positionsbestimmung | |
DE102014204360A1 (de) | Verfahren sowie Vorrichtung zur Abschätzung des Abstandes eines in Bewegung befindlichen Fahrzeuges von einem Objekt | |
DE102016009756A1 (de) | Verfahren zum Kalibrieren eines Sensorsystems eines Kraftfahrzeugs sowie Sensorsystem | |
DE102005005242A1 (de) | Verfahren und Vorrichtung zum Bestimmen eines Kameraoffsets | |
DE102010042821B4 (de) | Verfahren und Vorrichtung zur Bestimmung einer Basisbreite eines Stereo-Erfassungssystems | |
DE102012102600B3 (de) | Verfahren zur Verifizierung der Ausrichtung eines Verkehrsüberwachungsgerätes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12816449 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1120120053699 Country of ref document: DE Ref document number: 112012005369 Country of ref document: DE |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: R225 Ref document number: 112012005369 Country of ref document: DE Effective date: 20140828 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 12816449 Country of ref document: EP Kind code of ref document: A1 |