公开(公告)号：EP4390689A1

公开(公告)日：2024-06-26

申请号：EP22216256.2

申请日：2022-12-22

申请人： NOS Inovação, S.A.

发明人： PINTO SEQUEIRA DOS SANTOS GRAÇA, Jorge Filipe ,  NUNES FERREIRA, João Miguel ,  FERREIRA MARTINS, Carlos Manuel ,  DAVID RECHENA, Pedro Miguel ,  PIMENTEL FERNANDES MAIO, Carolina ,  PRETO XAVIER, Tiago Francisco ,  SOARES CAPITÃO, Pedro Miguel ,  RODRIGUES FERREIRA MELO, Orlando Duarte ,  SOUSA ROSA DA CRUZ FERNANDES, Bruno de

IPC分类号： G06F9/54 ,  G06V10/00

CPC分类号： G06F9/541 ,  G06V10/00 ,  G06N20/00

摘要： The present application describes a machine learning framework (1) for generic object detection, comprising processing means adapted to implement a framework front-end service (1.1) configured to provide and implement a user interface (4), and a framework back-end service (2.1) configured to provide an interface to a cloud computing platform (2) containing a machine learning module (2.2). The framework front-end service (1.1) being configured to receive an image data containing at least one embedded detectable object and the machine learning module (2.2) being adapted to detect at least one object embedded in the received image data. The developed solution offers a simple, no code, intuitive and fully Web environment for the development of object detection machine learning models.

公开(公告)号：EP4376432A1

公开(公告)日：2024-05-29

申请号：EP23211625.1

申请日：2023-11-23

申请人： Ubotica Technologies Ltd.

发明人： Vállez Enano, Noelia ,  Dunne, Aubrey ,  Espinosa Aranda, José Luis

IPC分类号： H04N23/61 ,  H04N23/617 ,  H04N23/73 ,  H04N23/75 ,  H04N23/76 ,  G06T7/00 ,  G06V10/00

CPC分类号： H04N23/61 ,  H04N23/617 ,  H04N23/73 ,  H04N23/75 ,  H04N23/76 ,  G06T7/00 ,  G06V10/00

摘要： The system and methods of the various embodiments enable better capturing of images of objects that are moving relative to a camera. A computing system may be configured to capture a frame containing a target object, generate at least two candidate object bounding boxes for the target object, and determine a candidate object feature vector for the part of the frame contained within each candidate object bounding box. The computing system may compute the distance between each candidate object feature vector and a target object feature vector, selecting the candidate object bounding box associated with the candidate object feature vector that is closest to the target object feature vector, generate partial image statistics on the part of the frame contained within the selected candidate object bounding box, and provide the partial image statistics as input to an AX algorithm that controls the camera.