-
1.发明公开
公开(公告)号：EP3869392A1
公开(公告)日：2021-08-25
申请号：EP20158613.8
申请日：2020-02-20
申请人： TOYOTA JIDOSHA KABUSHIKI KAISHA , Katholieke Universiteit Leuven KU Leuven Research & Development
发明人： ABBELOOS, Wim , OLMEDA REINO, Daniel , ABDELKAWY, Hazem , HEYLEN, Jonas , DE WOLF, Mark , DAWAGNE, Bruno , BARNES, Michael , LEMKENS, Wim , PROESMANS, Marc , VAN GOOL, Luc
摘要： A method for processing at least one image comprising inputting the image to at least one neural network (ANN1, ANN2), the at least one network being configured to deliver, for each pixel of a group of pixels belonging to an object of a given type visible on the image, an estimation of parameters of the object,
the method further comprising processing the estimations of the parameters of the object using an instance segmentation mask identifying instances of objects having the given type.-
公开(公告)号：EP4456012A1
公开(公告)日：2024-10-30
申请号：EP23170426.3
申请日：2023-04-27
摘要： A computer-implemented method for determining whether an apparatus is ready to move, the computer-implemented method comprising:
- obtaining (10) a sequence of images relating to the apparatus;
- extracting (12) motion information from the sequence of images, wherein the motion information comprises information about motion of at least one object in the sequence of images;
- determining (28) whether the apparatus is ready to move based on the motion information.-
公开(公告)号：EP4375953A1
公开(公告)日：2024-05-29
申请号：EP22208898.1
申请日：2022-11-22
摘要： A method for determining a perceptual load ( PLscenepred) of a person facing a scene, comprising:
S20) updating a scene graph (sg) of the scene (s), updating the scene graph including detecting objects present in the scene, and determining their positions (pi);
the scene graph (sg) comprising a node (ri) for each detected object (oi), the node (ri) comprising a position (pi) of the object (oi);
S30) by passing the scene graph (sg) through a perceptual load determination module (PLDM), determining the global perceptual load value ( PLscenepred), the perceptual load determination module (PLDM) being a convolutional neural network trained to determine the global perceptual load value ( PLscenepred) on the basis of the scene graph (sg).
A perceptual load determination system for implementing the method.-
公开(公告)号：EP4456017A1
公开(公告)日：2024-10-30
申请号：EP23170430.5
申请日：2023-04-27
发明人： VAN LOOCK, Mark , ABDELKAWY, Hazem , SUNDRAM, Jugesh , FRANCESCA, Gianpiero , MEIER, Sven , DESPINOY, Fabien , KNAPP, Jakob , ACCAD, Dimitri
摘要： A computer-implemented method for assisting opening or closing of a door, comprising:
- obtaining at least one image showing at least one region of interest, the at least one region of interest comprising a door operating area or an area adjacent the door operating area;
- detecting, in the at least one image, whether at least one object is present in the region of interest;
- determining, based on the detection, at least one interference indicator for opening or closing the door.-
5.发明公开
公开(公告)号：EP4375156A1
公开(公告)日：2024-05-29
申请号：EP22208889.0
申请日：2022-11-22
CPC分类号： G06F2203/01120130101 , B60W40/02 , G06V40/174 , G06V20/597 , G06V10/84 , G06V10/803
摘要： A computer-implemented method for controlling a device, said method comprising:
• obtaining (S10), using sensors (SR), data (DT) representative of said user (Us) and of an environment (Env);
• determining (S20), based on said data, indicators (Em_I) of states of said user and at least one event indicator (Ev_I);
• determining (S30), based on said state indicators and said data, using a Bayesian inference model (BIM), probabilities (Em_P) of states of said user (Us); and
• determining (S40), based on said probabilities and said at least one event indicator, at least one state (Em_S) of said user and at least one event (Ev_C) causing the user to be in said at least one state;
• determining (S50), based on said at least one state and event, a control action (Ac) of said device.-
6.发明公开
公开(公告)号：EP4015311A1
公开(公告)日：2022-06-22
申请号：EP20216213.7
申请日：2020-12-21
申请人： TOYOTA JIDOSHA KABUSHIKI KAISHA , Stichting Nederlandse Wetenschappelijk Onderzoek Instituten met haar Instituut Centrum Wiskunde & Informatica
发明人： DE WESER, Marleen , ABDELKAWY, Hazem , GHOSH, Surjya , PONS RODRIGUEZ, Gerard , EL ALI, Abdallah , CESAR, Pablo
摘要： A vehicle driver assistance system (100) comprises
a gesture detection unit (A) which, based on images (I) of a scene around a vehicle (1), detects that a human being (P) in a vicinity of the vehicle has made a predetermined gesture;
a driver emotion determination unit (B) which, based on the images (II) of the driver (D), determines an affective state (Ar,Va) of the driver; and
a vehicle control unit (C).
When the gesture detection unit (A) has detected that a human being (P) has made the predetermined gesture, and the driver emotion determination unit (B) has determined that the affective state of the driver or a change thereof has reached a predetermined range in a certain response time after the human being (P) made the predetermined gesture, the vehicle control unit (C) adapts a control of the vehicle (1).
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.014 秒)
