EP4315275A1 - Verfahren und system zur bestimmung von informationen bezüglich der eigenbewegung eines fahrzeugs - Google Patents
Verfahren und system zur bestimmung von informationen bezüglich der eigenbewegung eines fahrzeugsInfo
- Publication number
- EP4315275A1 EP4315275A1 EP22714211.4A EP22714211A EP4315275A1 EP 4315275 A1 EP4315275 A1 EP 4315275A1 EP 22714211 A EP22714211 A EP 22714211A EP 4315275 A1 EP4315275 A1 EP 4315275A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- information
- vehicle
- neural network
- movement
- cameras
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
Definitions
- the invention relates to a method and a system for determining information about a vehicle's own movement, and to a vehicle with such a system.
- the odometry unit receives measurement information from different sensors, for example wheel rotation sensors, yaw rate sensors, steering angle sensors and/or GPS sensors, and determines information on the basis of this
- Vehicle position can only be insufficiently detected, which is particularly disadvantageous for autonomous driving functions.
- the invention relates to a method for determining information on the movement of a vehicle.
- the vehicle has a stereo camera system with at least two cameras for capturing stereo images of the area surrounding the vehicle and an artificial neural network for processing the image information provided by the stereo camera system.
- the stereo camera system uses the at least two cameras to capture image sequences that contain a plurality of pieces of image information at different points in time.
- a pair of images which includes image information from a first and a second camera, is captured at successive points in time. The chronologically consecutive image pairs form the image sequences.
- the artificial neural network receives the image information and based on this generates stereo images with distance information.
- the stereo images have color information (e.g. RGB values or gray values) and pixel-related distance information for each pixel.
- the distance information indicates how far away the area of the scene that is imaged by the pixel is from the vehicle or from the stereo camera system.
- the artificial neural network Based on the image information from the stereo camera system, the artificial neural network provides information regarding the vehicle's own movement at an output interface.
- the movement of the vehicle itself is estimated by the neural network from the change over time in the image information provided by the cameras, and this is estimated Proper motion information is output in addition to the stereo images.
- the technical advantage of the proposed method is that the vehicle's own movement can be determined with a very high level of accuracy by evaluating the image information from the cameras of the stereo camera system, since a shift in the image information by one or a few pixels can already be converted into own movement information.
- the determination of one's own motion by the proposed method is in particular significantly more precise than the determination of one's own motion by known odometry units.
- This method is also clearly superior to the optical flow with a mono camera because of the significantly better signal-to-noise ratio due to the non-linear correlation of the artificial neural network.
- the artificial neural network analyzes the change over time in the image information in the image sequences and, based on this, generates information relating to the vehicle's own movement.
- the artificial neural network analyzes the change over time in the image information in the image sequences and, based on this, generates information relating to the vehicle's own movement.
- conclusions are drawn about the individual's own movement. Due to the high resolution of image information and the typically large distances between the scene represented in the image information and the vehicle, even very small changes in the vehicle position or vehicle orientation can be detected. This creates a very high level of accuracy in the determination of the self-motion information.
- the information relating to the vehicle's own movement comprises information relating to the translational movement of the vehicle along three axes of a Cartesian coordinate system.
- the self-movement information is speed information indicating the speed at which the vehicle is moving in the direction of the respective axes.
- the information about one's own movement is, for example, longitudinal, vertical, and transverse speed information.
- the information relating to the vehicle's own movement includes information relating to a rotational movement of the vehicle around the three axes of a Cartesian coordinate system.
- the self-motion information is rotational speed information or angular speed information that indicates the speed at which the vehicle is rotating about the respective axes.
- the self-motion information includes pitch, yaw, and roll rate information, for example.
- the artificial neural network compensates for changes in calibration parameters of the stereo camera system.
- the artificial neural network uses a non-linear correlation of the image information to compensate for the calibration inaccuracies.
- the artificial neural network is preferably trained to recognize and compensate for the calibration of the cameras of the stereo camera system from the recognized disparity.
- the neural network is supplied with image sequences that are recorded from different viewing directions and are suitably labeled, ie disparity information and/or distance information is available for the individual pixels.
- the training data preferably also has calibration information. This calibration information is uniquely assigned to the image information.
- the neural network can use this calibration information from the training data learn how stereo images change depending on the calibration of the cameras.
- the weighting factors of the neural network can thus be selected in such a way that the error between the detected disparity and the disparity specified by the training data or the error between the distance information determined by the neural network and the distance information of the training data is minimized.
- the cameras of the stereo camera system have inertial sensors that determine changes in the movement of the cameras.
- the inertial sensors can, for example, detect translational movements of the camera in three spatial directions of a Cartesian coordinate system and rotational movements around the three spatial axes of the Cartesian coordinate system. In this way, absolute changes in position or orientation of the respective camera and changes in the relative position or orientation of the two cameras to one another (extrinsic calibration parameters) can be detected.
- the calibration parameters of the stereo camera system are adjusted using information provided by the inertial sensors of the cameras of the stereo camera system.
- the position or alignment changes of the cameras are preferably detected via the inertial sensors of the cameras during ongoing operation of the stereo camera system and calibration parameters of the stereo camera system are adjusted based thereon.
- information from the inertial sensors of the cameras is used to carry out an initial training of the neural network.
- the training data preferably includes inertial sensor information that contains position or Emulate orientation changes of the cameras. This allows the neural network to be trained to recognize and compensate for calibration inaccuracies.
- additional information provided by sensors is used to calculate the speed of the vehicle. According to one embodiment, additional information provided by sensors is used to calculate the speed of the vehicle.
- Detect and compensate for calibration changes For example, information from a temperature sensor can be used to compensate for temperature dependent calibration changes.
- the artificial neural network is a pre-trained neural network that is trained using training data in the form of stereo images of a scene and associated calibration parameters, the training data indicating how the stereo images change depending on modifications to the calibration parameters of the cameras of the stereo camera system.
- the neural network can be trained to compensate for calibration inaccuracies or calibration deviations of the cameras.
- the artificial neural network is retrained based on calibration information generated from information from the inertial sensors of the cameras. This allows the neural network to be adapted to the calibration changes in online training.
- the inertial sensors of the cameras can also be used to provide movement information from the cameras, which is used for initial training of the neural network.
- the invention relates to a system for determining information on a vehicle's own movement.
- the vehicle has a stereo camera system with at least two cameras Acquisition of stereo images of the area surrounding the vehicle and an artificial neural network for processing the image information provided by the stereo camera system.
- the stereo camera system is designed to use the at least two cameras to capture image sequences that contain multiple pieces of image information at different points in time while the vehicle is moving.
- the artificial neural network is designed to receive the image information and, based on this, generates stereo images with distance information.
- the artificial neural network has an output interface at which information regarding the
- Own motion of the vehicle are provided, which are calculated based on the image sequences by the artificial neural network.
- the artificial neural network is designed to analyze the change in the image information over time in the image sequences and, based on this, to generate information relating to the vehicle's own movement.
- conclusions are drawn about the individual's own movement. Due to the high resolution of image information and the typically large distances between the scene represented in the image information and the vehicle, even very small changes in the vehicle position or vehicle orientation can be detected. This creates a very high level of accuracy in the determination of the self-motion information.
- the artificial neural network for providing information about the translational movement of the vehicle along three axes of a Cartesian
- Coordinate system and information about a rotational movement of the vehicle around the three axes of the Cartesian coordinate system formed at the output interface is speed information that indicates the speed at which the vehicle is moving in the direction of the respective axes or the rotational speed at which the vehicle is rotating about one or more of these axes.
- the self-motion information is, for example, longitudinal, vertical, and lateral speed information and pitch, yaw, and roll speed information.
- the invention relates to a vehicle comprising an aforesaid system according to one of the exemplary embodiments.
- Fig. 1 an example of a schematic representation of a
- Stereo camera system equipped with an artificial neural network for providing stereo imagery and self-motion information of a vehicle is coupled;
- FIG. 2 shows, by way of example and schematically, a schematic representation of a stereo camera system that uses information from the inertial sensors to train the neural network
- FIG. 3 shows an example of a schematic representation of the method steps for determining information on the vehicle's own movement.
- FIG. 1 shows an example of a schematic block diagram of a system 1 for determining information on the movement of a vehicle.
- the system has a stereo camera system 2, which includes at least two cameras 2.1, 2.2.
- the stereo camera system 2 records image information of the vehicle surroundings, in particular an area in the forward direction of travel in front of the vehicle, as pairs of images, i.e. an image with the first camera 2.1 and an image with a second camera 2.2 are recorded at the same time, which show the same scene However, they show from different perspectives, since the cameras 2.1, 2.2 are arranged at different positions in the vehicle.
- the cameras 2.1, 2.2 can be installed in the headlights of the vehicle.
- the cameras 2.1, 2.2 can also be integrated in the front area of the vehicle or in the windshield.
- the cameras 2.1, 2.2 are preferably at a distance of more than 0.5 m from one another in order to have a high base width as possible
- the cameras 2.1, 2.2 take several image pairs one after the other, ie at different points in time, so that image sequences are created.
- the image information changes as a result of vehicle movement, since the image pairs are recorded at different vehicle positions in space.
- the system also has an artificial neural network 3 that is pre-trained by initial training and is designed to process the image information provided by the stereo camera system 2 .
- the artificial neural network 3 can be, for example, a deep neural network, in particular a convolutional neural network (CNN).
- CNN convolutional neural network
- the neural network 3 receives the image information provided by the stereo camera system 2 and estimates disparity information for this image information.
- the disparity information indicates how high the lateral offset is between the individual pixels of the image information of an image pair.
- This lateral offset is a measure of the distance that the scene area represented by the pixel has from the vehicle or from the stereo camera system 2 .
- Distance information can thus be obtained from the disparity information, which indicates how far away a scene area represented by a pixel is from the vehicle or from the stereo camera system 2 .
- the neural network 3 can provide stereo images which, in addition to two-dimensional image information in the form of pixel-related color values, also contain distance information for each pixel.
- the artificial neural network 3 is also designed to estimate the vehicle's own movement based on the image information provided by the cameras 2.1, 2.2.
- position changes of the pixels arise due to the vehicle movement, ie due to the vehicle movement a region of a scene appears in a subsequent image of the image sequence at a different position than in a preceding image of the image sequence.
- the neural network is trained to estimate information on the vehicle's own movement, also referred to below as odometry data, based on these position changes.
- the neural network has an output interface at which the vehicle's odometry data are output.
- information about the translatory movement of the vehicle along three spatial axes of a Cartesian coordinate system is output.
- this is speed information, i.e. the longitudinal, vertical and lateral speed of the vehicle.
- information about the rotational movement of the vehicle around the three spatial axes of the Cartesian coordinate system is preferably output.
- this is rotational speed information, i.e. the pitch, yaw and roll speed of the vehicle.
- the high resolution of the image information results in a high resolution of the vehicle's own motion information. In particular, these are higher than the information provided by an odometry unit of the vehicle.
- the self-motion information provided by the neural network 3 is preferably used to modify the information provided by an odometry unit of the vehicle.
- modified odometry information can be obtained by merging the ego-motion information of the neural network 3 and the information of the odometry unit be created that allow a more accurate position determination of the vehicle.
- FIG. 2 shows an embodiment of a stereo camera system 2 in which the cameras 2.1, 2.2 have inertial sensors.
- the inertial sensors are designed to detect changes in the movement of the cameras and the vehicle. In particular, this can be translational changes in movement along three axes of a Cartesian coordinate system and rotary changes in movement around these three axes of the Cartesian coordinate system.
- the inertial sensors make it possible to detect the absolute change in movement of the camera 2.1, 2.2 and thus an absolute change in the position of this camera 2.1, 2.2.
- the information from the inertial sensors or information derived therefrom is preferably transmitted to the neural network 3, so that the weighting factors of the neural network 3 can be adapted as a function of this information from the inertial sensors.
- the calculation of the stereo images by the neural network 3 can be adapted to the changed camera positioning and the calibration changes associated therewith.
- the neural network 3 is preferably designed to estimate disparity information and to compensate for calibration inaccuracies that arise as a result of a change in the extrinsic parameters of the stereo camera system 2 .
- the neural network 3 is trained using training data in which the distance of all pixels from the stereo camera system is known, and the neural network 3 is optimized for recognizing the disparity.
- the neural network 3 preferably uses a non-linear correlator in order to determine the disparity information.
- the information from the inertial sensors of the cameras 2.1, 2.2 can be used as training data in order to suitably adjust the weighting factors of the neural network.
- the neural network 3 can be trained using training data, i.e. the weighting factors of the neural network 3 are adapted by a training phase in such a way that the neural network 3 provides disparity information and/or distance information for the image information recorded by the stereo camera system 2.
- the training data (also referred to as ground truth information) has pairs of images that represent the same scene with different positions and orientations of the cameras 2.1, 2.2.
- the training data also has distance information for each image pixel, so that the error between the calculation result of the neural network 3 and the training data can be determined based on the training data and the weighting factors of the neural network 3 are successively adjusted in such a way that the error is reduced .
- the training data can have information about the vehicle's own movement, which is assigned to the respective image pairs (ie a self-movement labeling), so that the neural network 3 learns during the training how the image information of image pairs of an image sequence changes over time when the vehicle own movement.
- the information about the vehicle's own movement in the training data can preferably contain information about the translatory movement of the vehicle along three spatial axes of a Cartesian coordinate system, ie in particular the longitudinal, vertical and lateral speeds of the vehicle.
- the information about the vehicle's own movement in the training data can contain information about the rotational movement of the vehicle around the three spatial axes of the Cartesian coordinate system, for example the pitch, yaw and roll speed of the vehicle.
- the neural network 3 has an output interface at which the vehicle's own movement information is provided.
- this intrinsic movement information estimated by the neural network 3 is compared with the intrinsic movement information of the training data.
- the weighting factors of the neural network 3 are then adjusted in such a way that the error between the information on the patient's own motion estimated by the neural network 3 and the information on the patient's motion in the training data is minimized.
- the movement information of the vehicle and/or the cameras 2.1, 2.2 contained in the training data can be provided by the inertial sensors of the cameras 2.1, 2.2, for example. Alternatively or additionally movement information from an odometry unit of the vehicle can also be used.
- the neural network 3 can be processed in a control unit of the stereo camera system 2, for example. Alternatively, the neural network 3 can also be operated in a control device that is provided separately from the stereo camera system 2 .
- FIG. 3 shows a block diagram illustrating the steps of a method for determining the own motion information of a vehicle using a neural network.
- image information is recorded by the cameras 2.1, 2.2 of the stereo camera system 2 (S10).
- the image information is image pairs, with the images of an image pair being recorded at the same point in time, specifically a first image from the first camera 2.1 and a second image from the second camera 2.2. Several such pairs of images are recorded one after the other, resulting in an image sequence.
- the neural network then obtains stereo images of the area surrounding the vehicle (S11). In addition to pixel-related color values, these also contain pixel-related distance information
- the neural network 3 also provides self-motion information of the vehicle (S12). These are determined based on the image information from the stereo camera system, specifically based on the change in position of areas of the scene represented in the image information over time. In particular, this can be the position changes of individual pixels or groups of pixels over time, which result from the vehicle's own movement in space.
- S12 self-motion information of the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102021106988.2A DE102021106988A1 (de) | 2021-03-22 | 2021-03-22 | Verfahren und System zur Bestimmung von Eigenbewegungsinformationen eines Fahrzeugs |
| PCT/EP2022/057203 WO2022200222A1 (de) | 2021-03-22 | 2022-03-18 | Verfahren und system zur bestimmung von informationen bezüglich der eigenbewegung eines fahrzeugs |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4315275A1 true EP4315275A1 (de) | 2024-02-07 |
Family
ID=81074249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP22714211.4A Pending EP4315275A1 (de) | 2021-03-22 | 2022-03-18 | Verfahren und system zur bestimmung von informationen bezüglich der eigenbewegung eines fahrzeugs |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20240174260A1 (de) |
| EP (1) | EP4315275A1 (de) |
| CN (1) | CN117136388A (de) |
| DE (1) | DE102021106988A1 (de) |
| WO (1) | WO2022200222A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL2028357B1 (en) * | 2021-06-01 | 2022-12-13 | Cyclomedia Tech B V | Method for training a neural network |
| DE102023130929B3 (de) * | 2023-11-08 | 2025-02-06 | Daimler Truck AG | Verfahren zum Fusionieren von Kamerabildern sowie Fahrzeug |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3438776B1 (de) * | 2017-08-04 | 2022-09-07 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren, vorrichtung und computerprogramm für ein fahrzeug |
| DE102017222600B3 (de) | 2017-12-13 | 2018-12-27 | Audi Ag | Optische Positionsermittlung eines Fahrzeugs mittels eines Convolutional Autoencoders und/oder eines tiefen neuronalen Netzes |
| CN108230437B (zh) * | 2017-12-15 | 2021-11-09 | 深圳市商汤科技有限公司 | 场景重建方法和装置、电子设备、程序和介质 |
| CN111788102B (zh) * | 2018-03-07 | 2024-04-30 | 罗伯特·博世有限公司 | 用于跟踪交通灯的里程计系统和方法 |
| US12122420B2 (en) | 2018-08-29 | 2024-10-22 | Intel Corporation | Computer vision system |
| US11670088B2 (en) * | 2020-12-07 | 2023-06-06 | Ford Global Technologies, Llc | Vehicle neural network localization |
| DE102020215860A1 (de) * | 2020-12-15 | 2022-06-15 | Conti Temic Microelectronic Gmbh | Korrektur von Bildern eines Rundumsichtkamerasystems bei Regen, Lichteinfall und Verschmutzung |
-
2021
- 2021-03-22 DE DE102021106988.2A patent/DE102021106988A1/de active Pending
-
2022
- 2022-03-18 WO PCT/EP2022/057203 patent/WO2022200222A1/de not_active Ceased
- 2022-03-18 CN CN202280022395.8A patent/CN117136388A/zh active Pending
- 2022-03-18 EP EP22714211.4A patent/EP4315275A1/de active Pending
- 2022-03-18 US US18/551,589 patent/US20240174260A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022200222A1 (de) | 2022-09-29 |
| US20240174260A1 (en) | 2024-05-30 |
| DE102021106988A1 (de) | 2022-09-22 |
| CN117136388A (zh) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102014209137A1 (de) | Verfahren und Vorrichtung zur Kalibrierung eines Kamerasystems eines Kraftfahrzeugs | |
| DE102015107390B4 (de) | Verfahren und Vorrichtung zum automatischen Kalibrieren von Rundumsichtsystemen | |
| DE102009005861A1 (de) | Fahrzeugumgebungs-Erkennungssystem | |
| DE112014007047B4 (de) | Fahrzeugkamera-Steuervorrichtung | |
| DE102014201271A1 (de) | Verfahren und Steuergerät zum Erkennen einer Veränderung eines relativen Gierwinkels innerhalb eines Stereo-Video-Systems für ein Fahrzeug | |
| DE102004048400A1 (de) | Verfahren für die Erfassung einer optischen Struktur | |
| EP2736017A2 (de) | Verfahren zur Ermittlung der Bewegung eines Kraftfahrzeugs | |
| EP4315275A1 (de) | Verfahren und system zur bestimmung von informationen bezüglich der eigenbewegung eines fahrzeugs | |
| EP4068223A1 (de) | Verfahren und system zur bestimmung der bodenebene mit einem künstlichen neuronalen netz | |
| EP4198894A1 (de) | Kamerabasierte fahrzeugkonturerfassung für fahrzeugbehandlungsanlagen | |
| DE102011076795A1 (de) | Verfahren zum Bestimmen einer Nickbewegung einer in einem Fahrzeug verbauten Kamera und Verfahren zur Steuerung einer Lichtaussendung zumindest eines Frontscheinwerfers eines Fahrzeugs | |
| WO2014009406A1 (de) | VERFAHREN UND VORRICHTUNG ZUM BERECHNEN EINER VERÄNDERUNG EINES ABBILDUNGSMAßSTABS EINES OBJEKTS | |
| EP2630632A1 (de) | Bestimmung der basisbreite eines stereobild-erfassungssystems | |
| DE102009007412A1 (de) | Verfahren zur Verfolgung wenigstens eines Objekts | |
| DE102021113111B4 (de) | Verfahren zur Kalibrierung von Sensorinformationen eines Fahrzeugs sowie Fahrassistenzsystem | |
| EP2192550A1 (de) | Verfahren zum Ermitteln der Lageänderung eines Kamerasystems und Vorrichtung zum Erfassen und Verarbeiten von Bildern | |
| DE102009017135A1 (de) | Verfahren, Vorrichtung und Computerprogramm zur Videodatenanalyse | |
| DE102021101593B3 (de) | Verfahren zum Betrieb von Umfeldsensoren in einem Kraftfahrzeug und Kraftfahrzeug | |
| EP4381465A1 (de) | Verfahren und kartenerzeugungseinrichtung für ein fahrzeug zur erzeugung einer hochauflösenden karte einer bodenfläche in einem fahrzeugumfeld | |
| DE102020201505A1 (de) | Verfahren und Vorrichtung zum kamerabasierten Ermitteln einer Geschwindigkeit eines Fortbewegungsmittels | |
| DE102023116272A1 (de) | Verfahren und System zur Detektion eines Objekts | |
| DE102019113962A1 (de) | Abbilden eines Umfelds | |
| DE102019209849B4 (de) | Verfahren und Steuergerät zur abstandsmessenden Bildverarbeitung für eine Stereokameraeinrichtung für ein Fahrzeug und Stereokamerasystem mit einer Stereokameraeinrichtung und einem Steuergerät | |
| DE102023203531A1 (de) | Verfahren und Vorrichtungen zum Positionieren einer Kalibriervorrichtung vor einem Kraftfahrzeug | |
| DE112023002835T5 (de) | Verbesserter Prozess zum Detektieren von Objekten mittels eines neuronalen Netzwerks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230928 |
|
| 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 |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20250604 |
|
| RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: AUMOVIO AUTONOMOUS MOBILITY GERMANY GMBH Owner name: VOLKSWAGEN AG |