公开(公告)号：EP3721382B1

公开(公告)日：2022-10-12

申请号：EP18880069.2

申请日：2018-12-31

Inventor： XUN, Xu ,  RUXIAO, Bao

IPC: G06V10/26 ,  G06V10/44 ,  G06V10/82 ,  G06V20/56

公开(公告)号：EP3832595B1

公开(公告)日：2022-07-13

申请号：EP20208588.2

申请日：2014-02-12

Inventor： HAN, Xiao

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/12 ,  G06T7/143 ,  G06T7/174 ,  G06K9/62 ,  G06V10/26

公开(公告)号：EP4002294A1

公开(公告)日：2022-05-25

申请号：EP21207692.1

申请日：2021-11-11

Applicant: Corning Research & Development Corporation

Inventor： KLARES, Robert

IPC: G06V10/56 ,  G06K9/62 ,  G06V10/26 ,  G06V20/52

Abstract: A system (100) for the identification of the formation of a burning droplet (9) of a material of a fiber optic cable (3) during cable burn testing comprises a data processing device (11) for processing respective image data of a plurality of image samples of an image stream. The data processing device (11) is configured to execute at least a processing step of preprocessing each of the recorded image samples of the image stream to generate a respective preprocessed image sample for each of the recorded image samples such that areas of the recorded image samples disturbing the identification of burning droplets (9) are masked out in the respective preprocessed image sample, and a step of identifying a burning droplet (9) in each of the preprocessed image samples by evaluating a pixel color property of a pixel of each preprocessed image sample.

公开(公告)号：EP4485390A1

公开(公告)日：2025-01-01

申请号：EP22926881.8

申请日：2022-12-19

Applicant: Jingdong Kunpeng (Jiangsu) Technology Co., Ltd.

Inventor： LIU, Hao ,  ZHANG, Baofeng

IPC: G06V20/56 ,  G06V10/22 ,  G06V10/24 ,  G06V10/26 ,  G06V10/44 ,  G06V10/764

Abstract: The disclosure, which provides an image detection method and apparatus, relates to the technical field of computer vision. A specific implementation scheme of the method comprises: performing instance segmentation on an image to be detected using an image instance segmentation model so as to obtain respective instances in the image to be detected; calculating preliminary centers of the respective instances based on point cloud data and the respective instances; correcting the preliminary centers of the respective instances using an instance center correction model so as to obtain corrected centers of the respective instances; and inputting the corrected centers of the respective instances into a target detection model so as to output frames and categories of the respective instances. The implementation scheme can solve a technical problem of a comparatively poor image detection performance.

公开(公告)号：EP4485367A1

公开(公告)日：2025-01-01

申请号：EP24180426.9

申请日：2024-06-06

Applicant: AIRBUS OPERATIONS (SAS)

Inventor： FAURE, Louise ,  SAMMOUR SAWAYA, Thierry

IPC: G06V10/26 ,  G06V10/50 ,  G06V20/17 ,  G06V20/56

Abstract: - Procédé et système de détection d'au moins un élément de marquage au sol d'au moins une piste d'atterrissage par vision par ordinateur et par l'intermédiaire de techniques de traitement du signal.
- Le système de détection (S) comprend au moins une unité de collecte d'images (10), une unité de découpage (11) pour découper l'image (I) en bandes (ST1), une unité de détermination (12) pour déterminer au moins une courbe d'intensité moyenne (C) pour au moins une bande (ST1), une unité de reconnaissance (13) pour reconnaître dans la courbe d'intensité moyenne (C) au moins un élément de marquage au sol (100) de la piste d'atterrissage (T), une unité de détection (2) pour détecter une position d'au moins un élément de marquage au sol d'au moins une piste d'atterrissage (T) dans l'images (I). Grâce à la détermination des courbes d'intensité moyenne, la détection des éléments de marquage au sol demande peu de ressource de calcul.

公开(公告)号：EP4485366A1

公开(公告)日：2025-01-01

申请号：EP24159606.3

申请日：2024-02-26

Applicant: Elektrobit Automotive GmbH

Inventor： Rodrigues, Sandy ,  Shetty, Pavithree ,  Balakrishna, Akshatha ,  George, Anoop ,  Nourbakhsh, Seyed Hami ,  Kleinhenz, Thomas

IPC: G06V10/26 ,  G06V10/764 ,  G06V10/766 ,  G06V10/82 ,  G06V20/56

Abstract: Embodiments of the present disclosure relate to a vehicle, an apparatus, a method for training a regression model, and a method for processing sensor data of a vehicle. The method for processing sensor data obtaining sensor data of an environment and applying a segmentation model to the sensor data to obtain segmented sensor data of an object in the environment. Further, the method comprises applying a regression model to the segmented sensor data to determine a steering angle for the vehicle.

公开(公告)号：EP3926537B1

公开(公告)日：2025-01-01

申请号：EP20755319.9

申请日：2020-02-11

Inventor： WANG, Liang ,  ZHANG, Jun

IPC: G06T7/11 ,  G06T7/149 ,  G06V10/26 ,  G06V10/774 ,  G06V20/64

公开(公告)号：EP4471728A1

公开(公告)日：2024-12-04

申请号：EP24178352.1

申请日：2024-05-28

Applicant: Xeos Imaging Inc.

Inventor： NGUYEN, Van Tho ,  ST-PIERRE, Tony ,  CLABAUT, Etienne

IPC: G06V10/26 ,  G06V10/764 ,  G06V10/82 ,  G06V20/17 ,  G06V20/56 ,  G06V20/64 ,  G06V20/70 ,  G06V10/774 ,  G06V10/80

Abstract: Systems and methods for performing semantic segmentation of LiDAR point clouds are provided. LiDAR point data are generated using aerial vehicles equipped with LiDAR transceivers. Tiles representing sampled areas of the point cloud are augmented by rotation or division, allowing for multiple semantic segmentation by a neural network, resulting in a smoother segmentation with an increased quality. To increase the quality further, buffers can be used around tiles, the scan angle of each LiDAR point can be used as input to the neural network, and points of an object can be segmented into different classes. The resulting segmentations are then aggregated to provide a final semantic segmentation, which can be used to create a digital terrain map, a building footprint or a vegetation map.

公开(公告)号：EP4465257A1

公开(公告)日：2024-11-20

申请号：EP23174323.8

申请日：2023-05-19

Applicant: Aptiv Technologies AG

Inventor： ZHANG, Xuebing ,  REHFELD, Timo ,  OSAMA, Muhammad

IPC: G06V20/59 ,  B60R21/015 ,  G06V40/10 ,  G06F18/2413 ,  G06V10/25 ,  G06V10/20 ,  G06V10/26 ,  G06F18/25 ,  G06V10/80 ,  B60R21/01

Abstract: A computerized method of controlling one or more vehicle safety measures by determining the height of a person sitting on a seat in a vehicle cabin is provided. The method comprises determining, based on one or more images showing the person on a vehicle seat, a height of the person by determining a set of body characteristics of the person, comparing the set of determined body characteristics with a corresponding set of reference characteristics, and determining the height of the person based on the comparison. The method further comprises outputting a control signal to the one or more vehicle safety measures based at least partially on the determined height.

公开(公告)号：EP4465254A1

公开(公告)日：2024-11-20

申请号：EP23195377.9

申请日：2023-09-05

Applicant: Xiaomi EV Technology Co., Ltd.

Inventor： WAN, Shaohua

IPC: G06V20/58 ,  G06V20/56 ,  G06V10/25 ,  G06V10/26

Abstract: A three-dimensional target detection method includes: acquiring (101) a surrounding image of a vehicle; inputting (102) the surrounding image of the vehicle into a preset target detection model, and acquiring (102) three-dimensional detection framework information of a target vehicle output by the target detection model; obtaining (101) auxiliary detection information of the target vehicle by performing at least one of a grounding line detection, an in-garage location detection and an occlusion rate detection on the surrounding image of the vehicle; and obtaining (104) corrected three-dimensional detection framework information of the target vehicle by correcting the three-dimensional detection framework information of the target vehicle according to the auxiliary detection information of the target vehicle.