-
公开(公告)号：US10902268B2
公开(公告)日：2021-01-26
申请号：US16325619
申请日：2017-08-11
Applicant: OSRAM GMBH
Inventor： Herbert Kaestle , Fabio Galasso , Ling Wang , Michael Eschey , Meltem Demirkus Brandlmaier
IPC: G06K9/00 , G08B13/196 , G08B13/19 , H05B47/19 , H05B47/105 , G06K9/62 , H04N7/18
Abstract: The presence of a stationary object is to be reliably recognized. Thereto, a presence detection device for detecting a presence of an object in its environment is provided, which comprises a movement detection unit for detecting an initial movement of the object in the environment of the presence detection device and for outputting a movement signal depending on the detection as well as a control unit for generating an activation signal depending on the movement signal. Moreover, the presence detection device comprises a camera, which can be activated by the activation signal, for obtaining a video signal of the environment of the presence detection device and an evaluation unit for generating a presence signal relating to the presence of the object by evaluating the video signal.
-
公开(公告)号：US20190250702A1
公开(公告)日：2019-08-15
申请号：US16341467
申请日：2017-10-10
Applicant: OSRAM GmbH , Fondazione Istituto Italiano di Tecnologia , Università degli Studi di Verona
Inventor： Marco Cristani , Alessio Del Bue , Michael Eschey , Fabio Galasso , Irtiza Hasan , Herbert Kaestle , Francesco Setti , Theodore Tsesmelis
CPC classification number: G06F3/012 , G06F3/011 , G06T7/73 , G06T2207/30241
Abstract: An image signal indicative of the head pose of a person in a scene, as provided by a camera may be processed by estimating, as a function of the image signal received by the image sensor, the head pose of the person. A view frustum of the person may be generated from the estimated head pose. A visual frustum of attention or VFOA of the person may be generated from the view frustum. From the visual frustum, a predicted movement trajectory of the person or an estimated scene attention map as a function of the visual frustum of attention, preferably by identifying in the attention map at least one object to be controlled may be generated.
-
公开(公告)号：US11798286B2
公开(公告)日：2023-10-24
申请号：US17271608
申请日：2019-08-08
Applicant: OSRAM GmbH
Inventor： Alexander Faller , Fabio Galasso , Prasanth Kuncheerath Ramankutty , Meltem Demirkus Brandlmaier
CPC classification number: G06V20/53 , G06T7/292 , G06T2207/10016 , G06T2207/30232 , H04N7/181
Abstract: A tracking system for tracking objects within a field of view is disclosed. The field of view may include a first zone and an adjacent zone of interest where at least two gates are associated with respective sides of the first zone within the field of view. The first camera is configured to detect when an object crosses one of the at least two gates and track the object throughout the first zone and the zone of interest. The tracking system is configured to generate a first event message in response to the object being tracked from one of the gates into the zone of interest and subsequently leaving the first zone through a dedicated gate of the at least two gates.
-
Patent Agency Ranking
公开(公告)号：US11175733B2
公开(公告)日：2021-11-16
申请号：US16341467
申请日：2017-10-10
Applicant: OSRAM GmbH , Fondazione Istituto Italiano di Tecnologia , Università degli Studi di Verona
Inventor： Marco Cristani , Alessio Del Bue , Michael Eschey , Fabio Galasso , Irtiza Hasan , Herbert Kaestle , Francesco Setti , Theodore Tsesmelis
Abstract: An image signal indicative of the head pose of a person in a scene, as provided by a camera may be processed by estimating, as a function of the image signal received by the image sensor, the head pose of the person. A view frustum of the person may be generated from the estimated head pose. A visual frustum of attention or VFOA of the person may be generated from the view frustum. From the visual frustum, a predicted movement trajectory of the person or an estimated scene attention map as a function of the visual frustum of attention, preferably by identifying in the attention map at least one object to be controlled may be generated.
-
公开(公告)号：US20190130215A1
公开(公告)日：2019-05-02
申请号：US16094503
申请日：2017-03-23
Applicant: OSRAM GmbH
Inventor： Herbert Kaestle , Meltem Demirkus Brandlmaier , Michael Eschey , Fabio Galasso , Ling Wang
Abstract: A training method for object recognition, the training method comprising: providing at least one top-view training image; aligning a training object present in the training image along a pre-set direction; labelling at least one training object from the at least one training image using a pre-defined labelling scheme; extracting at least one feature vector for describing the content of the at least one labelled training object and at least one feature vector for describing at least one background scene; and training a classifier model based on the extracted feature vectors.
-
公开(公告)号：US10893594B2
公开(公告)日：2021-01-12
申请号：US16341465
申请日：2017-10-10
Applicant: OSRAM GmbH , Fondazione Istituto Italiano di Tecnologia , Università degli Studi di Verona
Inventor： Marco Cristani , Alessio Del Bue , Michael Eschey , Fabio Galasso , Irtiza Hasan , Herbert Kaestle , Theodore Tsesmelis
IPC: H05B47/105 , G06T7/00 , G01J1/02 , G01J1/42
Abstract: A lighting system including a set of lighting devices for lighting an environment that may be controlled by a method. The method may include receiving, from one or more image sensors (e.g. a RGB-D camera—W), an image signal including a sequence of images of the environment under different conditions of illumination and light reflection. The method may further include processing the image signal to provide a light source identification signal representative of light sources affecting the environment, and controlling the lighting devices as a function of the light source identification signal, and, possibly, of human occupancy and activity.
-
7.发明申请公开(公告)号：US20200250847A1
公开(公告)日：2020-08-06
申请号：US16637281
申请日：2018-07-31
Applicant: OSRAM GmbH
Inventor： Bernhard Siessegger , Fabio Galasso , Nicolau Leal Werneck , Herbert Kaestle
Abstract: A method for surface reconstruction may include illuminating at least one object simultaneously by light emitted by a plurality of luminaires spaced apart from another. The method may further include recording a photographic sequence comprising a plurality of individual images of the object(s). The method may further include reconstructing at least one visible object surface of the object by photometric stereo analysis.
-
公开(公告)号：US20190180597A1
公开(公告)日：2019-06-13
申请号：US16214167
申请日：2018-12-10
Applicant: OSRAM GmbH
Inventor： Ling Wang , Herbert Kaestle , Fabio Galasso , Yi Li
Abstract: A method for recognizing the presence of at least one person in a specified spatial region by way of at least one camera is provided. The method may include recording a sequence of images of the spatial region by way of the at least one camera, performing a person recognition on the basis of at least one image of the image sequence, and then classifying or remaining classified a person object recognized by way of the person recognition as a real person if it is possible to assign to the person object a movement that has been recognized by an image evaluation of a plurality of images of the image sequence.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.014 seconds)
