WO2022167120A1 - Verfahren und vorrichtung zur erkennung von beeinträchtigungen im optischen pfad einer stereokamera - Google Patents
Verfahren und vorrichtung zur erkennung von beeinträchtigungen im optischen pfad einer stereokamera Download PDFInfo
- Publication number
- WO2022167120A1 WO2022167120A1 PCT/EP2021/083795 EP2021083795W WO2022167120A1 WO 2022167120 A1 WO2022167120 A1 WO 2022167120A1 EP 2021083795 W EP2021083795 W EP 2021083795W WO 2022167120 A1 WO2022167120 A1 WO 2022167120A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- stereo camera
- optical path
- depth map
- gaps
- depth
- Prior art date
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000006735 deficit Effects 0.000 claims description 41
- 238000001514 detection method Methods 0.000 claims description 22
- 238000012790 confirmation Methods 0.000 claims description 6
- 230000032683 aging Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000005855 radiation Effects 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 230000005494 condensation Effects 0.000 description 2
- 238000009833 condensation Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000005357 flat glass Substances 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000004313 glare Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 238000001454 recorded image Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- 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
-
- 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
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
-
- 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
- H04N13/271—Image signal generators wherein the generated image signals comprise depth maps or disparity maps
-
- 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 for detecting impairments in the optical path of a stereo camera.
- the invention also relates to a device for detecting impairments in the optical path of a stereo camera.
- the invention also relates to a vehicle.
- DE 102016216 118 A1 discloses a spot detection method in an object detection device and an object detection device which is arranged in a vehicle and which uses recorded images from a stereo camera.
- the stereo camera includes two cameras, each of which captures an exterior of the vehicle from inside the vehicle through a portion of a window glass wiped by a wiper.
- the object detection device has a light source detector that can detect a light source in a captured image captured by one of the two cameras.
- the object detection device has an edge detector that can detect an edge that extends in a direction that crosses a wiping direction of the wiper in the image recorded by one of the two cameras.
- the object detection device includes a determiner that can determine that the window glass has a stain when the edge extending in the crossing direction from the light source is continuously detected for a certain period of time based on a detection result from the light source detector and a detection result from the edge detector .
- the invention is based on the object of specifying an improved method and an improved device for detecting impairments in the optical path of a stereo camera compared to the prior art. Furthermore, the invention is based on the object of specifying a new type of vehicle.
- the object is achieved according to the invention by a method which has the features specified in claim 1, by a device which has the features specified in claim 7, and by a vehicle which has the features specified in claim 8.
- a depth map also referred to as a disparity image or disparity map, of a detected environment is generated according to the invention using image data captured by the stereo camera. Furthermore, it is checked whether there are gaps without depth values in the depth map. If there are gaps in the depth map, an impairment in the optical path of the stereo camera is inferred.
- the optical path of a stereo camera can be affected by aging and environmental influences. For example, blurring can occur due to aging processes, blockages due to condensation, dirt, etc., dazzling effects due to solar radiation, etc. For reliable operation of functions that use image data captured by the stereo camera, rapid and robust detection of such impairments, also referred to as degradations, in the optical path of a stereo camera is very important.
- the method enables the detection of impairments in the optical path of a stereo camera even without any movement present in the image data recorded by the stereo camera. This means that the procedure enables impairments to be recognized even when the stereo camera is stationary and in static scenarios.
- the method for this recognition can be used as a so-called stand-alone solution or for the improvement and/or plausibility check of already existing algorithms.
- the method forms further recognition input to increase robustness and recognition speed.
- objects are detected in the depth map and a plausibility check of depth information in the depth map is carried out on the basis of a comparison of the detected objects with object information stored in a digital map.
- implausible depth information is evaluated as confirmation of an impairment in the optical path of the stereo camera.
- An error rate when detecting the impairments in the optical path can thus be reduced and the reliability and robustness of the method can be further increased.
- implausible depth information is also evaluated as confirmation of an impairment in the optical path of the stereo camera if there are no gaps in the depth map. Impairments in the optical path that are present on both camera units of the stereo camera and thus do not lead to gaps in the depth map can also be detected.
- the image data is captured by means of the stereo camera while the stereo camera is stationary relative to the captured surroundings.
- a lane detection, a traffic sign detection, a detection of mobile surrounding objects and/or a detection of immobile surrounding objects are or will be carried out in the object recognition. This enables a large number of objects present in the environment and in the digital map to be compared and thus leads to a further improved plausibility check.
- the device for detecting impairments in the optical path of a stereo camera is characterized by a processing device which is designed to generate a depth map of a detected environment on the basis of image data captured by means of the stereo camera, to check whether there are gaps without depth values in the depth map, and, in the presence of gaps in the depth map, to infer an impairment in the optical path of the stereo camera.
- the device In contrast to devices known from the prior art, the device enables the detection of impairments in the optical path of a Stereo camera even with no motion present in image data captured by the stereo camera. This means that the device enables impairments to be recognized even when the stereo camera is stationary and in static scenarios.
- the device for this recognition can be used as a so-called stand-alone solution or to improve and/or check existing algorithms for plausibility.
- the device generates further recognition input to increase robustness and recognition speed.
- the vehicle according to the invention comprises an aforementioned device.
- the reliability of the operation of vehicle functions for example driver assistance functions that use image data captured by the stereo camera, can thus be significantly increased. Traffic safety can thus be increased.
- the vehicle In one possible configuration of the vehicle, it is designed for automated, in particular highly automated or autonomous, ferry operation.
- the device enables a particularly reliable automated ferry operation, since driving functions have increased reliability and increased availability due to the use of the device. Traffic safety can also be increased as a result, and vehicle drivers can be better supported in the driving task.
- FIG. 1 shows a schematic of a device for detecting impairments in the optical path of a stereo camera.
- FIG. 1 A possible exemplary embodiment of a device 1 for detecting impairments D in the optical path of a stereo camera is shown schematically in FIG.
- the device 1 comprises a processing device 2 for this recognition.
- the device 1 is, for example, part of a vehicle that is not shown in detail.
- the vehicle is designed, for example, for an automated, in particular highly automated or autonomous, ferry operation, using the Stereo camera captured image data B are used to carry out the automated ferry operation. This requires reliable operation of the stereo camera.
- An optical path of a stereo camera can be affected by aging and environmental influences. For example, blurring can occur due to aging processes, blockages due to condensation, dirt, etc., dazzling effects due to solar radiation, etc. Rapid and robust detection of such impairments D, also known as degradations, in the optical path of a stereo camera is very important for reliable operation of the stereo camera and of functions that use image data B captured by means of the stereo camera.
- Impairments D in the optical path of the stereo camera are reflected directly in the depth map in the form of gaps without depth values and thus indicate such an impairment D.
- a depth map T also known as a disparity image or disparity map, of a detected environment is generated by the processing device 2 in a first module 2.1 using image data B captured by the stereo camera.
- the recording of the image data B by means of the stereo camera can also be carried out while the stereo camera is stationary relative to the recorded surroundings, ie when the vehicle is stationary.
- a second module 2.2 then checks whether there are gaps without depth values in the depth map T.
- potential candidates for an impairment D in the optical path of the stereo camera are determined. If there are gaps in the depth map T, an impairment D in the optical path of the stereo camera is inferred.
- objects are detected in the depth map T and detected using a comparison of the detected objects with object information stored in a digital map 3 and/or using additional sensors 4 Object information carried out a plausibility check of depth information of the depth map T.
- the object detection in the depth map T is camera-based, for example, and includes, for example, a detection 5 of mobile and/or immobile surrounding objects, a lane detection 6 and a traffic sign detection 7.
- Implausible depth information is also evaluated as confirmation of an impairment D in the optical path of the stereo camera if there are no gaps in the depth map T. This is the case, for example, when impairments D are present on both camera units of the stereo camera.
- one of two optical camera lenses of a stereo camera is degraded. If so-called vertical lightsabers occur on the camera lens due to reflections from solar radiation, these lead to vertical gaps in the depth map T.
- a fogging of the camera lens leads to large-area gaps or implausible stereo information. Dirt leads to individual gaps in the depth map. Glare or exposure effects, which result from a low-lying sun, for example, lead to effects similar to fogging.
- a type of impairment D can be inferred.
- both camera lenses are degraded.
- the examples of gaps in a depth map T mentioned in the first application example can also occur if an impairment D is present on both camera lenses at the same time. je depending on the position of the respective impairment D on the camera lenses, a stereo matching can take place under certain circumstances, so that there are no gaps in the depth map T.
- this abnormality can be detected by means of the described plausibility check based on the object recognition and the comparison with the object information stored in the digital map and can therefore be recognized as an impairment D.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Traffic Control Systems (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180092644.6A CN116965016A (zh) | 2021-02-05 | 2021-12-01 | 用于识别立体相机光路缺损的方法和装置 |
US18/275,828 US20240129452A1 (en) | 2021-02-05 | 2021-12-01 | Method and device for recognising impairments in the optical path of a stereo camera |
JP2023547432A JP2024507102A (ja) | 2021-02-05 | 2021-12-01 | ステレオカメラの光路における障害を認識するための方法及び装置 |
KR1020237025190A KR20230124053A (ko) | 2021-02-05 | 2021-12-01 | 스테레오 카메라의 광로의 저하를 감지하는 방법 및장치 |
EP21824340.0A EP4289133A1 (de) | 2021-02-05 | 2021-12-01 | Verfahren und vorrichtung zur erkennung von beeinträchtigungen im optischen pfad einer stereokamera |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021000600.3A DE102021000600A1 (de) | 2021-02-05 | 2021-02-05 | Verfahren und Vorrichtung zur Erkennung von Beeinträchtigungen im optischen Pfad einer Stereokamera |
DE102021000600.3 | 2021-02-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022167120A1 true WO2022167120A1 (de) | 2022-08-11 |
Family
ID=78851301
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2021/083795 WO2022167120A1 (de) | 2021-02-05 | 2021-12-01 | Verfahren und vorrichtung zur erkennung von beeinträchtigungen im optischen pfad einer stereokamera |
Country Status (7)
Country | Link |
---|---|
US (1) | US20240129452A1 (de) |
EP (1) | EP4289133A1 (de) |
JP (1) | JP2024507102A (de) |
KR (1) | KR20230124053A (de) |
CN (1) | CN116965016A (de) |
DE (1) | DE102021000600A1 (de) |
WO (1) | WO2022167120A1 (de) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016216118A1 (de) | 2015-09-16 | 2017-03-16 | Toyota Jidosha Kabushiki Kaisha | Objekterkennungsvorrichtung und Fleckerkennungsverfahren |
EP3496398A1 (de) * | 2017-12-11 | 2019-06-12 | Sick AG | Sichere stereokamera und verfahren zum prüfen der funktionsfähigkeit der bildsensoren |
US20190230347A1 (en) * | 2016-08-29 | 2019-07-25 | Hitachi, Ltd. | Photographing Device and Photographing Method |
US20200236338A1 (en) * | 2017-09-28 | 2020-07-23 | Koito Manufacturing Co., Ltd. | Sensor system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2275990B1 (de) | 2009-07-06 | 2012-09-26 | Sick Ag | 3D-Sensor |
GB2502213A (en) | 2010-12-30 | 2013-11-20 | Irobot Corp | Mobile Human Interface Robot |
US10466714B2 (en) | 2016-09-01 | 2019-11-05 | Ford Global Technologies, Llc | Depth map estimation with stereo images |
-
2021
- 2021-02-05 DE DE102021000600.3A patent/DE102021000600A1/de not_active Ceased
- 2021-12-01 EP EP21824340.0A patent/EP4289133A1/de active Pending
- 2021-12-01 KR KR1020237025190A patent/KR20230124053A/ko not_active Application Discontinuation
- 2021-12-01 CN CN202180092644.6A patent/CN116965016A/zh active Pending
- 2021-12-01 US US18/275,828 patent/US20240129452A1/en active Pending
- 2021-12-01 JP JP2023547432A patent/JP2024507102A/ja active Pending
- 2021-12-01 WO PCT/EP2021/083795 patent/WO2022167120A1/de active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016216118A1 (de) | 2015-09-16 | 2017-03-16 | Toyota Jidosha Kabushiki Kaisha | Objekterkennungsvorrichtung und Fleckerkennungsverfahren |
US20190230347A1 (en) * | 2016-08-29 | 2019-07-25 | Hitachi, Ltd. | Photographing Device and Photographing Method |
US20200236338A1 (en) * | 2017-09-28 | 2020-07-23 | Koito Manufacturing Co., Ltd. | Sensor system |
EP3496398A1 (de) * | 2017-12-11 | 2019-06-12 | Sick AG | Sichere stereokamera und verfahren zum prüfen der funktionsfähigkeit der bildsensoren |
Also Published As
Publication number | Publication date |
---|---|
KR20230124053A (ko) | 2023-08-24 |
EP4289133A1 (de) | 2023-12-13 |
CN116965016A (zh) | 2023-10-27 |
JP2024507102A (ja) | 2024-02-16 |
US20240129452A1 (en) | 2024-04-18 |
DE102021000600A1 (de) | 2022-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102016216118B4 (de) | Objekterkennungsvorrichtung und Fleckerkennungsverfahren | |
DE60208894T2 (de) | Regensensor mit stereoscopischem abbildungssystem | |
EP2558336B1 (de) | Verfahren und vorrichtung zur fahrerunterstützung beim fahren eines fahrzeugs durch detektion von wetterbedingten sichteinschränkungen | |
DE102014209197A1 (de) | Vorrichtung und Verfahren zum Erkennen von Niederschlag für ein Kraftfahrzeug | |
DE102008001679A1 (de) | Verfahren und Vorrichtung zur Verarbeitung von aufgenommenen Bildinformationen aus einem Fahrzeug | |
EP1053140A1 (de) | Verfahren zum detektieren von auf einer lichtdurchlässigen scheibe befindlichen objekten sowie vorrichtung | |
DE102016206493A1 (de) | Verfahren und Kamerasystem zur Entfernungsbestimmung von Objekten zu einem Fahrzeug | |
DE102014201158A1 (de) | Verfahren und Vorrichtung zum Überprüfen eines von einer Objekterkennung erkannten relevanten Objekts | |
DE102020215860A1 (de) | Korrektur von Bildern eines Rundumsichtkamerasystems bei Regen, Lichteinfall und Verschmutzung | |
DE102005004513A1 (de) | Detektion von Niederschlägen auf Oberflächen, insbesondere auf der Oberfläche der Windschutzscheibe eines Kraftfahrzeuges | |
DE102012015282B4 (de) | Verfahren zur Detektion eines verdeckten Zustands einer Bilderfassungseinrichtung eines Kraftfahrzeugs, Kamerasystem und Kraftfahrzeug | |
WO2020020654A1 (de) | Verfahren zum betreiben eines fahrerassistenzsystems mit zwei erfassungseinrichtungen | |
WO2019238319A1 (de) | Verfahren und vorrichtung zum erfassen einer umgebung, sowie fahrzeug mit einer solchen vorrichtung | |
DE102013222304A1 (de) | Verfahren zur Bestimmung von Objektentfernungen mit einer in einem Kraftfahrzeug verbauten Kamera | |
WO2022167120A1 (de) | Verfahren und vorrichtung zur erkennung von beeinträchtigungen im optischen pfad einer stereokamera | |
DE102014205204B3 (de) | Kamerabasiertes Fahrerassistenzsystem zur Detektion des Zustandes einer Fahrbahnoberfläche | |
DE102021004337A1 (de) | Vorrichtung und Verfahren zur Filterung von Spiegelungen in Bilddaten | |
DE102017221381A1 (de) | Verfahren, Vorrichtung und Computerprogramm zum Ermitteln eines Abstandes zu einem Objekt | |
DE102004053416A1 (de) | Konzeption einer Kamera mit Spiegeln zur Erzeugung eines Stereobildpaares | |
WO2022128013A1 (de) | Korrektur von bildern einer kamera bei regen, lichteinfall und verschmutzung | |
DE102018205144B3 (de) | Testverfahren zur Erkennung von Fehler-Frames bei hochauflösenden Scheinwerfern | |
DE102016205471A1 (de) | Stereokameravorrichtung sowie ein Verfahren zum Betrieb der Stereokameravorrichtung | |
DE102019003562A1 (de) | Verfahren zur Auswertung von mittels einer Kamera eines Fahrzeugs erfassten Bildern | |
EP1962245B1 (de) | Verfahren und Vorrichtung zum Ermitteln des Bewegungszustands von Objekten | |
DE102013210591A1 (de) | Bewegungserkennung eines fahrzeugs mittels mehrerer kameras |
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: 21824340 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20237025190 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180092644.6 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18275828 Country of ref document: US Ref document number: 2023547432 Country of ref document: JP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021824340 Country of ref document: EP Effective date: 20230905 |