-
公开(公告)号：EP3098755B1
公开(公告)日：2021-10-20
申请号：EP16171900.0
申请日：2016-05-30
-
72.发明公开
公开(公告)号：EP3886045A1
公开(公告)日：2021-09-29
申请号：EP20215968.7
申请日：2020-12-21
发明人： CAI, Yuzhan , ZHENG, Chao , YAN, CHAO , ZHANG, Hantian
摘要： The disclosure provides a 3-dimensional reconstruction method, an electronic device and a storage medium. The method includes: obtaining an image sequence pre-collected by a camera; obtaining nominal intrinsic parameters of the camera, and preset initial values of distortion coefficients of the camera, the camera being a camera for collecting the image sequence; calculating fluctuation ranges of the distortion coefficients; performing the 3D reconstruction on the image sequence based on the nominal intrinsic parameters, the initial values of the distortion coefficients, and the fluctuation ranges of the distortion coefficients; and during the 3D reconstruction, optimizing an obtained visual point cloud and a camera pose.
-
公开(公告)号：EP3547260B1
公开(公告)日：2021-09-15
申请号：EP19165298.1
申请日：2019-03-26
-
公开(公告)号：EP3876141A1
公开(公告)日：2021-09-08
申请号：EP19886206.2
申请日：2019-06-11
发明人： FANG, Minquan , LI, Yueliang , LI, Huaizhou
摘要： Embodiments of the present invention disclose an object detection method, including: A computing device obtains two-dimensional coordinates of m pixel pairs from an object region of binocular image, where the binocular images include a first image and a second image that are captured by using a dual-lens camera, and one pixel in each pixel pair is from the first image, and the other pixel in each pixel pair is from the second image, and pixels in each pixel pair respectively correspond to a same feature of the object region in each of the first image and the second image; determines three-dimensional coordinates of the to-be-detected object in a camera coordinate system based on the two-dimensional coordinates of the m pixel pairs; converts the three-dimensional coordinates into data in a coordinate system in which laser point cloud data of the to-be-detected object is located, and merges the data and the laser point cloud data into merged point cloud data; and further determines the to be detected object based on the merged point cloud data. By implementing the embodiments of the present invention, problems in the prior art such as low accuracy of object detection or difficulty in implementing object detection can be resolved.
-
公开(公告)号：EP3865981A1
公开(公告)日：2021-08-18
申请号：EP20156794.8
申请日：2020-02-12
发明人： PUTZ, Thomas , FALTINATH, Andreas
摘要： Die Erfindung betrifft Verfahren und eine zu dessen Ausführung eingerichtete Vorrichtung zum Kalibrieren eines 3D-Bildsensors. Das Verfahren weist auf: für jeden einer Mehrzahl von verschiedenen vorbestimmten Raumpunkten auf einer Strahlungsreflektionsfläche, insbesondere Oberfläche, zumindest einer körperlichen Struktur im Sichtfeld eines 3D-Bildsensors, wobei die Position der Raumpunkte im Sichtfeld des 3D-Bildsensors jeweils fixiert ist: Veranlassen der Messung einer Distanz des jeweiligen Raumpunktes vom 3D-Bildsensor und Empfangen eines Werts für die dabei jeweils gemessene Distanz; und Ermitteln einer Distanzabweichung der jeweiligen gemessenen Distanz von einer als Maß für eine tatsächliche Distanz des jeweiligen Raumpunkts von dem 3D-Bildsensor vorab bestimmten jeweiligen Referenzdistanz. Das Verfahren weist weiter auf: Bestimmen eines Distanzkorrekturwerts in Abhängigkeit von den für zumindest zwei der Raumpunkte jeweils ermittelten Distanzabweichungen, so dass der Distanzkorrekturwert in dem durch diese Distanzabweichungen aufgespannten Distanzintervall liegt; und Berücksichtigen des Distanzkorrekturwerts im Rahmen einer Korrektur des Messergebnisses für zumindest eine bei einer nachfolgenden weiteren Distanzmessung mittels des 3D-Bildsensors gemessenen Distanz. Die Erfindung betrifft zudem ein zur Ausführung des Verfahrens konfiguriertes Computerprogramm sowie ein System zur Gestenerkennung, insbesondere zur Gestenerkennung in einem Fahrzeug, das die genannte Kalibriervorrichtung aufweist.
-
76.发明公开
公开(公告)号：EP3859298A1
公开(公告)日：2021-08-04
申请号：EP19902819.2
申请日：2019-12-26
发明人： SU, Yixiong
IPC分类号： G01M17/013 , G06T7/80
摘要： The present invention relates to the technical field of automobile calibrations, and discloses a method for aligning a calibration device with a vehicle based on a wheel aligner and a calibration system. The wheel aligner includes an image sensor and a computer. The method includes: controlling, by the computer, at least one image sensor to image a vehicle-mounted object on a vehicle and process the obtained image, to determine a position of the vehicle; controlling, by the computer, the at least one image sensor to image a reference object on a calibration device and process the obtained image, to determine a position of the calibration device; and determining, by the computer, an adjusting mode of the calibration device according to the position of the vehicle and the position of the calibration device, so that the calibration device is aligned with the vehicle according to an anticipated position or direction. In the method, the position of the vehicle and the position of the calibration device are determined by using the wheel aligner, and the computer determines the adjusting mode of the calibration device according to the position of the vehicle and the position of the calibration device and guides an operator to accurately align the calibration device with the vehicle.
-
77.发明授权
-
78.发明授权
-
公开(公告)号：EP3845922A1
公开(公告)日：2021-07-07
申请号：EP21150186.1
申请日：2021-01-05
申请人： Outsight
发明人： BRAVO ORELLANA, Raul
IPC分类号： G01S7/497 , G01S17/42 , G06T7/593 , G06T7/80 , H04N13/271 , H04N13/254
摘要： We disclose sensor systems, and associated calibration systems and methods, that provide efficient and reliable depth and texture fusion. One disclosed method includes transmitting a first light beam from a first perspective, transmitting a second light beam from a second perspective, aligning a visible light photodetector with the second perspective, aligning a depth sensor with the first perspective, and mutually registering the visible light photodetector and the depth sensor using a return of the first light beam, a return of the second light beam, and a reference map. The reference map can include a transform from a reference frame based on the first perspective and a reference frame based on the second perspective.
-
公开(公告)号：EP3834997A1
公开(公告)日：2021-06-16
申请号：EP19215106.6
申请日：2019-12-11
摘要： The invention relates to a method and device for calibrating calibrating at least one image capturing unit (2a, 2b, 2c, ..., 2n) of a machine vision device for position determination, wherein an optically recordable calibration element (8) is moved into a plurality of positions within a measurement volume (3) of the at least one image capturing unit (2a, 2b, 2c, ..., 2n), wherein a first set of positions is provided by determining the position of the calibration element in each of the positions, wherein a further set of positions is provided by determining the position of the calibration element (8) by a further position determining device, wherein at least one calibration parameter of the at least one image capturing unit (2a, 2b, 2c, ..., 2n) is determined depending on the first and the further set of positions.
-
-
-
-
-
-
-
-
-
搜索结果
764 条记录 (耗时 0.058 秒)
