EP2856390A1 - Verfahren und vorrichtung zur verarbeitung stereoskopischer daten - Google Patents
Verfahren und vorrichtung zur verarbeitung stereoskopischer datenInfo
- Publication number
- EP2856390A1 EP2856390A1 EP13718581.5A EP13718581A EP2856390A1 EP 2856390 A1 EP2856390 A1 EP 2856390A1 EP 13718581 A EP13718581 A EP 13718581A EP 2856390 A1 EP2856390 A1 EP 2856390A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- disparity
- points
- sensor system
- stereo
- change
- 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.)
- Ceased
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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
- H04N13/128—Adjusting depth or disparity
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/002—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles specially adapted for covering the peripheral part of the vehicle, e.g. for viewing tyres, bumpers or the like
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- 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
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- 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
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/107—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using stereoscopic cameras
-
- 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
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
- B60R2300/303—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing using joined images, e.g. multiple camera images
-
- 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
- B60R2300/8093—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 obstacle warning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N2013/0074—Stereoscopic image analysis
- H04N2013/0081—Depth or disparity estimation from stereoscopic image signals
Definitions
- the invention relates to a method and an apparatus for processing or sensor data of a stereo sensor system for a stereoscopic detection of an environment of the stereo sensor system.
- the invention further relates to an object recognition system and a computer program.
- Driver assistance systems usually require sensors for detecting obstacles and for determining an open space in the vehicle environment.
- this stereo cameras are used, which include two horizontally offset video cameras.
- objects are also observed to be horizontally offset in the camera images, with the offset, the so-called disparity, becoming smaller for distant objects and for objects in the vicinity in relation to the cameras. From the disparity, therefore, its distance from the observer, in this case the stereo camera, can be determined for each object.
- the published patent application DE 2009 003 1 10 A1 discloses a method for determining the disparities of the two camera images, the so-called disparity card.
- the published patent application EP 2 136 333 A2 discloses a method for determining a passable area and for detecting obstacles from the disparity map.
- the object underlying the invention can be seen to provide a method which allows a simple classification of objects of an environment of a stereo sensor system.
- the object underlying the invention can also be seen to provide a corresponding device.
- the object underlying the invention can also be seen to provide a corresponding object recognition system.
- a method of processing sensor data of a stereo sensor system for stereoscopically sensing an environment of the stereo sensor system for stereoscopically sensing an environment of the stereo sensor system.
- a disparity map is formed based on the sensor data of the stereo sensor system. It is provided that a disparity change is determined between two disparity points of the disparity map formed at a distance from one another, wherein at least one of the two disparity points is classified according to the disparity change of an object.
- an apparatus for processing sensor data of a stereo sensor system for a stereoscopic detection of an environment of the stereo sensor system includes disparity means for forming a disparity map based on the sensor data of the stereo sensor system. Furthermore, a determination device is provided for determining a disparity change between two disparity points of the disparity map formed at a distance from each other. In addition, the device comprises a classification direction for classifying at least one of the two disparity points corresponding to an object depending on the disparity change.
- an object recognition system comprising a stereo sensor system for stereoscopically detecting an environment of the stereo sensor system and a device for processing sensor data of a stereo sensor system for stereoscopically detecting an environment of the stereo sensor system.
- a computer program comprising program code for executing the method of processing sensor data of a stereo sensor system for stereoscopically detecting an environment of the stereo sensor system when the computer program is executed in a computer.
- the invention has the advantage that it has substantially no size dependency of objects in the environment. Only a minimum height should have the objects.
- a stereo sensor system according to the present invention is particularly adapted to stereoscopically to an environment of the stereo sensor system to capture. This means, in particular, that two sensor images of the environment are formed, wherein the two sensor images are taken from each other horizontally offset perspectives. This leads, as mentioned above, to an offset of objects in the two sensor images.
- the sensor data of the stereo sensor system correspond to the two sensor images.
- Disparity in the sense of the present invention thus refers in particular to the resulting offset from a pixel of the first sensor image to the corresponding pixel of the second sensor image.
- the pixels correspond to world points that are associated with a real object in the vicinity of the stereo sensor system.
- the pixels thus result from a mapping of the world points on one or more sensors of the stereo sensor system.
- These sensors are in particular designed to detect the environment by sensors. For example, infrared sensors can be provided, which can still detect the environment in an advantageous manner even in the dark.
- Each pixel and / or each disparity is here in a unique relationship to a respective distance of the world point to the stereo sensor system. The further away an object is located in relation to the stereo sensor system in the environment, the lower the corresponding disparity compared to an object which is arranged closer to the stereo sensor system. From the disparity, therefore, for each object its distance from the stereo sensor system can be determined.
- the pixels of the sensor images can be described by X, Y coordinates, also referred to as image coordinates, of a Cartesian coordinate system.
- a sensor image line also referred to as image line or simply line, is defined in the direction of the abscissa, here the X axis, of the coordinate system.
- a sensor image column also referred to as image column or simply column, is defined in the direction of the ordinate, here the Y axis, of the coordinate system.
- the disparity can also be abbreviated as "d.”
- a set of all disparities d (X, Y) of two sensor images forms the disparity map.
- the stereo sensor system is formed as a stereo video camera. That is, that means that two horizontally offset video cameras are formed.
- the disparity can be related to a focal length of the cameras and in particular as a quotient of the offset of the pixels corresponding to a world point, expressed in image coordinates X, Y and the focal length of the cameras result.
- the disparity is preferably reciprocal to the distance of the world point from a reference such as a reference point, a reference surface, or a reference surface of the stereo.
- the quotient of disparity and camera focal length corresponds to the quotient of base distance and distance of the world point.
- the disparity d is therefore defined in particular as a one-dimensional displacement vector in the direction of the image line and, starting from a pixel Xi in the first sensor image, gives the corresponding pixel Xj in the second
- a disparity change in the sense of the present invention therefore in particular denotes a difference between a first disparity value, also referred to simply as disparity, at a first pixel (X1, Y1) and a second pixel
- Disparity value also referred to simply as disparity
- h d (X1, Y1) - d (X2, Y2)
- the disparity change means in particular that a predetermined threshold value, in particular a plurality of predetermined threshold values, is provided, the classification depending in particular being carried out by whether h is greater, equal, smaller, greater than or equal or less than the predetermined one Threshold, preferably equal to the plurality of predetermined thresholds, is. For example, it may be provided that if h is less than the threshold, the disparity point is classified as a first object, for example an obstacle, and if h is greater than the threshold, the disparity point is a second object, such as a drivable area , is classified.
- a classification or a classification or a classification in the sense of the present invention designates in particular an association or an association of the disparity points or the pixels corresponding to these disparity points in the sensor images to predetermined object classes or objects.
- an object class may be an obstacle.
- Another object class may be an open space or a drivable area. This means, in particular, that the individual pixels of the sensor images are classified, for example, as to whether it is an obstacle or an open space or a drivable area.
- the disparity points are based on the image points of the sensor images which correspond to world points or which world points are assigned, it is therefore advantageously possible to classify a real object in the surroundings of the stereosensor system.
- ⁇ denotes the horizontal distance, ie in the X direction, between the two disparity points.
- ⁇ denotes the vertical distance, ie in the Y-direction, between the two disparity points.
- the distance ⁇ between the two disparity points is selected as a function of a position of one of the two disparity points in the disparity map.
- a sensitivity adjustment with respect to the classification is made possible in an advantageous manner.
- the distance ⁇ between the two disparity points is selected as a function of a disparity noise, in particular of an expected disparity noise.
- a sensitivity adjustment with regard to the classification is likewise made possible in an advantageous manner, since individual differently rushing regions of the disparity card can thus be taken into account individually.
- the distance between the two disparity points is selected as a function of a height of an object to be expected, in particular of an obstacle.
- the distance is chosen differently for each disparity point of the disparity card.
- a sensitivity with regard to the detection and classification or classification can be effected in an advantageous manner.
- the distance for all disparity points of the disparity map is chosen to be constant. As a result, an arithmetic effort is advantageously further reduced.
- the disparity map is smoothed in the horizontal and / or vertical direction, ie in the column and / or line direction. This advantageously suppresses observation noise of the disparity card, resulting in an improved signal to noise ratio.
- the two disparity points are therefore arranged only vertically offset from each other, not even offset horizontally to each other.
- the disparity card is thus evaluated in particular column by column.
- the disparity change in the vertical direction is considered.
- bridges or similar accessible objects can be detected in an advantageous manner.
- the points corresponding to the bridge have a greater disparity than the points below the bridge. In this respect, a disparity change will be negative.
- the disparity means may be formed as a disparity estimator configured to perform a disparity estimation based on the sensor data and to form the disparity map based on the disparity estimate. This can be formed quickly, without too much computational effort and efficiently a disparity card.
- the determination of the disparity change corresponds to a determination of a disparity gradient.
- the disparity change corresponds to a disparity gradient.
- the second disparity point in an environment of the first disparity point is therefore determined in particular from the first disparity point in such a way that the corresponding disparity change, which in fact corresponds to a slope of the disparity map, is maximal.
- a gradient at a point here the first disparity point, a scalar field, here the disparity map, a vector pointing from the point in the direction of maximum or steepest rise of the scalar field, a length of the gradient being a measure of the Slope or slope is.
- a vertical disparity gradient is determined. This means in particular that, starting from the first disparity point, the second disparity point is determined such that it has the same X coordinate but a different Y coordinate, the disparity change being maximal with respect to the set of disparity points having the same Y coordinate is.
- the proportion in the Y direction of the corresponding vector field is determined based on the disparities.
- Show here 1 is a flowchart of a method for operating sensor data of a stereo sensor system
- FIG. 2 shows an apparatus for processing or sensor data of a stereo sensor system
- FIG. 6 shows a flowchart of a further method for processing or sensor data of a stereo sensor system.
- FIG. 1 shows a flowchart of a method for processing sensor data of a stereo sensor system for a stereoscopic detection of an environment of the stereo sensor system.
- a disparity map is formed based on the sensor data of the stereo sensor system.
- a disparity change between two disparity points of the disparity map formed at a distance from one another is determined.
- at least one of the two disparity points is classified according to an object according to a step 105.
- an object assigned to the disparity point is classified. This means, for example, that the object is classified as an obstacle or as an open space or a drivable area or as an accessible object such as a bridge.
- FIG. 2 shows a device 201 for processing sensor data of a stereo sensor system (not shown) for a stereoscopic detection of an environment of the stereo sensor system.
- the device 201 includes a disparity device 203 for forming a disparity map based on the sensor data provided by the stereo sensor system.
- the disparity means 203 may be preferably formed as a disparity estimator configured to perform a disparity estimation based on the sensor data and to form the disparity map based thereon.
- the device 201 comprises a determination device 205 for determining a disparity change between two disparity points of the disparity map arranged at a distance from each other. Furthermore, the device 201 includes a classifier 207 for classifying at least one of the two disparity points corresponding to an object depending on the disparity change.
- 3 shows an object recognition system 301.
- the object recognition system 301 comprises a stereo sensor system 303 for a stereoscopic detection of an environment of the stereo sensor system and the device 201 according to FIG. 2.
- Fig. 4 shows two sensor images 401 and 403, which were formed by means of a stereo sensor system. Furthermore, a Cartesian X, Y, Z coordinate system 405 is shown. Furthermore, a pixel 407 with the coordinates Xi, Y in the sensor image 401 is shown for illustration. The pixel corresponding to the pixel 407 in the sensor image 403 is identified in the sensor image 403 by the reference numeral 409 and has the coordinates Xj, Y. Furthermore, the projected point 407 of the sensor image 401 is shown in the sensor image 403 as an unfilled circle.
- the individual disparity values d are then plotted in the Cartesian coordinate system 405 on the Z axis.
- FIG. 5 shows a disparity map 501.
- Two regions 503 and 509 are shown in the disparity map 501, which identify regions each having different disparities, wherein in the individual regions 503 and 509 the disparities are substantially constant or differ only by negligible amounts.
- all disparities in the area 505 may be smaller than the disparities in the area 503.
- the world points that underlie the area 505 are farther away than the world points that underlie the area 503.
- the objects corresponding to these world points are at different distances from the stereo sensor system.
- the objects corresponding to the region 505 are thus located farther away than the objects corresponding to the region 503 with respect to the stereo sensor system.
- disparity point 507 is drawn in the disparity map 501, the disparity point 507 being in the area 503.
- Disparity point 509 is in region 505.
- Disparity point 51 1 lies outside of both regions 503 and 505 and within disparity map 501.
- the disparity point 513 is also located outside the two regions 503 and 505 but within the disparity map 501.
- a distance between the two disparity points 507 and 509 is indicated by ⁇ 1.
- a distance between the disparity point 507 and the disparity point 51 1 is indicated by ⁇ 2.
- a distance between the disparity point 507 and the disparity point 513 is ⁇ 3 .
- the two disparity points 507 and 505 have different X coordinates but the same Y coordinate.
- the two disparity points 507 and 51 1 have the same X coordinate but different Y coordinates.
- the two disparity points 507, 513 each have different X and Y coordinates.
- the disparity change between the two disparity points 507 and 51 1 may also be referred to as a vertical disparity change.
- the disparity map 501 is evaluated column by column. This means, in particular, that the disparity change in the column direction of the disparity map 501 is used as a measure of the classification.
- h (X, Y) d (X, Y) -d (X, Y + ⁇ 2), where d is the disparity.
- a predetermined threshold is provided, wherein, depending on whether h (X, Y) is less than or equal to or greater than or equal to the predetermined threshold, the corresponding disparity points and thus indirectly classifies the objects underlying the disparity points in the environment be, for example, as an obstacle, as an open space or drivable area or as an accessible area such as a bridge.
- FIG. 6 shows a flow chart of another method for processing sensor data of a stereo sensor system 601.
- the stereo sensor system 601 comprises two video cameras 603 and 605, which are arranged horizontally offset from one another.
- the respective sensor data of the two video cameras 603, 605, each corresponding to a sensor image, are used in a step 607 to form a disparity map 609.
- a step 61 1 it is provided to smooth the disparity map 609 in the vertical and / or horizontal direction in order to advantageously suppress observation noise in the disparity map 609.
- a disparity change between two spaced disparity points of the disparity map 609 is determined.
- the disparity change in the column direction of the disparity card 609 is determined.
- a classification then takes place in step 615 to classify at least one of the disparity points.
- a classification may be made such that the object underlying the disparity points is classified as an obstacle 617 or as an open space 619.
- This classification according to the step 615 is carried out in particular as a function of the disparity change according to the step 613.
- a threshold value is provided, wherein preferably in the case of a disparity change which is smaller or smaller than or equal to the predetermined threshold value, the corresponding disparity points are classified as free area 619. If the disparity change is greater than or equal to the predetermined threshold, the corresponding disparity points are classified as an obstacle 617.
- the invention in particular includes the idea of performing a detection of obstacles and a determination of accessible open spaces on the basis of a disparity card of a stereo sensor system, in particular a stereo video sensor system.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102012209316A DE102012209316A1 (de) | 2012-06-01 | 2012-06-01 | Verfahren und Vorrichtung zum Verarbeiten von Sensordaten eines Stereosensorsystems |
PCT/EP2013/058476 WO2013178407A1 (de) | 2012-06-01 | 2013-04-24 | Verfahren und vorrichtung zur verarbeitung stereoskopischer daten |
Publications (1)
Publication Number | Publication Date |
---|---|
EP2856390A1 true EP2856390A1 (de) | 2015-04-08 |
Family
ID=48184204
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP13718581.5A Ceased EP2856390A1 (de) | 2012-06-01 | 2013-04-24 | Verfahren und vorrichtung zur verarbeitung stereoskopischer daten |
Country Status (5)
Country | Link |
---|---|
US (1) | US10165246B2 (de) |
EP (1) | EP2856390A1 (de) |
CN (1) | CN104364796A (de) |
DE (1) | DE102012209316A1 (de) |
WO (1) | WO2013178407A1 (de) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015209550A1 (de) * | 2015-05-26 | 2016-12-01 | Conti Temic Microelectronic Gmbh | Verfahren und vorrichtung zur erkennung von objekten in einer fahrzeugumgebung eines fahrzeugs |
CN106254888B (zh) * | 2015-06-09 | 2020-06-02 | 同济大学 | 一种图像编码及解码方法、图像处理设备 |
CN106489062B (zh) * | 2015-06-26 | 2019-06-28 | 深圳市大疆创新科技有限公司 | 用于测量移动平台的位移的系统和方法 |
EP3497618B1 (de) * | 2016-08-12 | 2023-08-02 | 3M Innovative Properties Company | Unabhängige verarbeitung mehrerer regionen von interesse |
US11450140B2 (en) | 2016-08-12 | 2022-09-20 | 3M Innovative Properties Company | Independently processing plurality of regions of interest |
EP3306521B1 (de) * | 2016-10-07 | 2021-12-08 | Veoneer Sweden AB | Stereosichtsystem und -verfahren für ein kraftfahrzeug |
US11202055B2 (en) * | 2018-02-28 | 2021-12-14 | Blackberry Limited | Rapid ground-plane discrimination in stereoscopic images |
CN108647579B (zh) * | 2018-04-12 | 2022-02-25 | 海信集团有限公司 | 一种障碍物检测方法、装置及终端 |
US20200077073A1 (en) * | 2018-08-28 | 2020-03-05 | Qualcomm Incorporated | Real-time stereo calibration by direct disparity minimization and keypoint accumulation |
CN111898396B (zh) * | 2019-05-06 | 2024-08-09 | 北京四维图新科技股份有限公司 | 障碍物检测方法和装置 |
DE102023201888A1 (de) | 2023-03-02 | 2024-09-05 | Zf Friedrichshafen Ag | Verfahren und Steuereinrichtung zum Steuern eines Fahrzeugs abseits der Straße |
Family Cites Families (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1574079B1 (de) * | 2002-10-23 | 2013-03-13 | Koninklijke Philips Electronics N.V. | Verfahren zur nachverarbeitung eines 3d digitalen video signals |
US6956469B2 (en) * | 2003-06-13 | 2005-10-18 | Sarnoff Corporation | Method and apparatus for pedestrian detection |
US7366325B2 (en) * | 2003-10-09 | 2008-04-29 | Honda Motor Co., Ltd. | Moving object detection using low illumination depth capable computer vision |
US7324687B2 (en) * | 2004-06-28 | 2008-01-29 | Microsoft Corporation | Color segmentation-based stereo 3D reconstruction system and process |
GB2418314A (en) * | 2004-09-16 | 2006-03-22 | Sharp Kk | A system for combining multiple disparity maps |
WO2006106522A2 (en) * | 2005-04-07 | 2006-10-12 | Visionsense Ltd. | Method for reconstructing a three- dimensional surface of an object |
AU2006295455A1 (en) * | 2005-09-22 | 2007-04-05 | 3M Innovative Properties Company | Artifact mitigation in three-dimensional imaging |
WO2007110000A1 (en) * | 2006-03-29 | 2007-10-04 | Huawei Technologies Co., Ltd. | A method and device of obtaining disparity vector and its multi-view encoding-decoding |
KR100902343B1 (ko) * | 2007-11-08 | 2009-06-12 | 한국전자통신연구원 | 로봇 영상 시스템 및 검출 방법 |
US8411934B2 (en) * | 2007-11-09 | 2013-04-02 | Thomson Licensing | System and method for depth map extraction using region-based filtering |
US9137518B2 (en) * | 2008-01-29 | 2015-09-15 | Thomson Licensing | Method and system for converting 2D image data to stereoscopic image data |
JP4871909B2 (ja) * | 2008-04-25 | 2012-02-08 | 日立オートモティブシステムズ株式会社 | 物体認識装置、および物体認識方法 |
DE102008002567A1 (de) | 2008-06-20 | 2009-12-24 | Robert Bosch Gmbh | Bilddatenverarbeitungsverfahren |
US8300089B2 (en) * | 2008-08-14 | 2012-10-30 | Reald Inc. | Stereoscopic depth mapping |
US8233664B2 (en) * | 2008-11-12 | 2012-07-31 | Eastman Kodak Company | Determining relative depth of points in multiple videos |
KR20100072772A (ko) * | 2008-12-22 | 2010-07-01 | 한국전자통신연구원 | 스테레오 비전을 이용한 실시간 얼굴 검출 시스템 및 그 방법 |
US8326036B2 (en) * | 2009-02-20 | 2012-12-04 | Qylur Security Systems, Inc. | Automated image separation method |
EP2246806B1 (de) * | 2009-04-29 | 2014-04-02 | Autoliv Development AB | Sichtverfahren und -system zur automatischen Erkennung von Objekten vor einem Kraftfahrzeug |
DE102009003110A1 (de) | 2009-05-14 | 2010-11-18 | Robert Bosch Gmbh | Bildverarbeitungsverfahren zur Bestimmung von Tiefeninformation aus wenigstens zwei mittels eines Stereokamerasystems aufgenommenen Eingangsbildern |
DE102009035755A1 (de) * | 2009-07-24 | 2011-01-27 | Pilz Gmbh & Co. Kg | Verfahren und Vorrichtung zum Überwachen eines Raumbereichs |
US20110032341A1 (en) * | 2009-08-04 | 2011-02-10 | Ignatov Artem Konstantinovich | Method and system to transform stereo content |
CN101701818B (zh) | 2009-11-05 | 2011-03-30 | 上海交通大学 | 远距离障碍的检测方法 |
CN101701828B (zh) | 2009-11-23 | 2012-10-03 | 常州超媒体与感知技术研究所有限公司 | 基于立体视觉和信息融合的盲人自主导航方法 |
KR101813299B1 (ko) * | 2010-04-01 | 2017-12-28 | 톰슨 라이센싱 | 3차원(3d) 표시에 있어서 플로팅 윈도우를 사용하는 방법과 시스템 |
FR2958767B1 (fr) * | 2010-04-09 | 2016-11-11 | Commissariat Energie Atomique | Procede de detection de cibles dans des images stereoscopiques. |
WO2012017650A1 (ja) * | 2010-08-03 | 2012-02-09 | パナソニック株式会社 | 物体検出装置、物体検出方法及びプログラム |
US9294755B2 (en) * | 2010-10-20 | 2016-03-22 | Raytheon Company | Correcting frame-to-frame image changes due to motion for three dimensional (3-D) persistent observations |
CN101999972B (zh) * | 2010-11-24 | 2013-07-03 | 上海理工大学 | 一种基于立体视觉的盲人辅助行走装置及其辅助方法 |
WO2012092246A2 (en) * | 2010-12-27 | 2012-07-05 | 3Dmedia Corporation | Methods, systems, and computer-readable storage media for identifying a rough depth map in a scene and for determining a stereo-base distance for three-dimensional (3d) content creation |
CN102313536B (zh) * | 2011-07-21 | 2014-02-19 | 清华大学 | 基于机载双目视觉的障碍物感知方法 |
US20130063560A1 (en) * | 2011-09-12 | 2013-03-14 | Palo Alto Research Center Incorporated | Combined stereo camera and stereo display interaction |
CN102390370B (zh) | 2011-10-25 | 2013-07-03 | 河海大学 | 一种基于立体视觉的车辆行驶应急处理装置及方法 |
US8837815B2 (en) * | 2011-12-14 | 2014-09-16 | Thomson Licensing | Method of filtering a disparity mesh obtained from pixel images |
US9237330B2 (en) * | 2012-02-21 | 2016-01-12 | Intellectual Ventures Fund 83 Llc | Forming a stereoscopic video |
-
2012
- 2012-06-01 DE DE102012209316A patent/DE102012209316A1/de active Pending
-
2013
- 2013-04-24 US US14/404,799 patent/US10165246B2/en active Active
- 2013-04-24 CN CN201380028624.8A patent/CN104364796A/zh active Pending
- 2013-04-24 WO PCT/EP2013/058476 patent/WO2013178407A1/de active Application Filing
- 2013-04-24 EP EP13718581.5A patent/EP2856390A1/de not_active Ceased
Non-Patent Citations (2)
Title |
---|
None * |
See also references of WO2013178407A1 * |
Also Published As
Publication number | Publication date |
---|---|
DE102012209316A1 (de) | 2013-12-05 |
WO2013178407A1 (de) | 2013-12-05 |
US10165246B2 (en) | 2018-12-25 |
CN104364796A (zh) | 2015-02-18 |
US20150156471A1 (en) | 2015-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2013178407A1 (de) | Verfahren und vorrichtung zur verarbeitung stereoskopischer daten | |
DE102018116111B4 (de) | Ein einheitliches tiefes faltendes neuronales Netzwerk für die Abschätzung von Freiraum, die Abschätzung der Objekterkennung und die der Objektstellung | |
DE112010002047B4 (de) | Objekterfassungsvorrichtung | |
DE102014209137B4 (de) | Verfahren und Vorrichtung zur Kalibrierung eines Kamerasystems eines Kraftfahrzeugs | |
DE102005056645B4 (de) | Fahrzeugumgebungsüberwachungsvorrichtung | |
DE102014221144A1 (de) | Zielerfassungsvorrichtung | |
DE102017218366A1 (de) | Verfahren und system zur fussgängererfassung in einem fahrzeug | |
DE102016216294B4 (de) | Einrichtung zum Erkennen eines Hindernisses um ein Fahrzeug herum und Verfahren dafür | |
DE112018007485T5 (de) | Straßenoberflächen-Detektionsvorrichtung, Bildanzeige-Vorrichtung unter Verwendung einer Straßenoberflächen-Detektionsvorrichtung, Hindernis-Detektionsvorrichtung unter Nutzung einer Straßenoberflächen-Detektionsvorrichtung, Straßenoberflächen-Detektionsverfahren, Bildanzeige-Verfahren unter Verwendung eines Straßenoberflächen-Detektionsverfahrens, und Hindernis-Detektionsverfahren unter Nutzung eines Straßenoberflächen-Detektionsverfahrens | |
DE102011087797A1 (de) | Verfahren und Vorrichtung zur Lokalisation einer vordefinierten Parkposition | |
DE102013012930A1 (de) | Verfahren zum Bestimmen eines aktuellen Abstands und/oder einer aktuellen Geschwindigkeit eines Zielobjekts anhand eines Referenzpunkts in einem Kamerabild, Kamerasystem und Kraftfahrzeug | |
DE112021004200T5 (de) | Objekterkennungsvorrichtung | |
DE102012024878A1 (de) | Verfahren zum Detektieren eines Zielobjekts anhand eines Kamerabilds durch Clusterbildung aus mehreren benachbarten Bildzellen, Kameraeinrichtung und Kraftfahrzeug | |
DE112020005547T5 (de) | Verarbeitungsvorrichtung | |
DE102018113559A1 (de) | Verfahren zum Erkennen einer Fahrbahnmarkierung durch Validieren anhand der Linienbreite; Steuereinrichtung; Stellplatzerkennungssystem; sowie Fahrerassistenzsystem | |
DE112021002598T5 (de) | Bildverarbeitungsvorrichtung | |
EP1944212B1 (de) | Verfahren und Vorrichtung zum Ermitteln potentiell gefährdender Objekte für ein Fahrzeug | |
DE102012211961A1 (de) | Verfahren und Vorrichtung zum Berechnen einer Veränderung eines Abbildungsmaßstabs eines Objekts | |
DE102016216962B3 (de) | Verfahren und Steuerungseinheit zur Nachführung eines Bildausschnitts | |
DE102017217140B4 (de) | Verfahren und Vorrichtung zur Ansteuerung eines Fahrerassistenzsystems unter Verwendung eines Stereokamerasystems mit einer ersten und einer zweiten Kamera | |
DE102018121158A1 (de) | Verfahren zum Erfassen von Bodenabtastpunkten und Fahrerunterstützungssystem, das dafür konfiguriert ist, ein derartiges Verfahren auszuführen | |
DE102018202753A1 (de) | Verfahren zur Ermittlung einer Entfernung zwischen einem Kraftfahrzeug und einem Objekt | |
EP3663800B1 (de) | Verfahren zur objekterfassung mit einer 3d-kamera | |
DE102011111856B4 (de) | Verfahren und Vorrichtung zur Detektion mindestens einer Fahrspur in einem Fahrzeugumfeld | |
DE102014017904A1 (de) | Verfahren und Vorrichtung zur Detektion erhabener Objekte und Verfahren zur Unterstützung eines Fahrers beim Führen eines Fahrzeugs |
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: 20150105 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
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: 20170720 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: ROBERT BOSCH GMBH |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20201127 |