公开(公告)号：US20190080604A1

公开(公告)日：2019-03-14

申请号：US16113043

申请日：2018-08-27

Applicant: Connaught Electronics Ltd.

Inventor： Senthil Kumar Yogamani ,  Sunil Chandra

IPC: G08G1/14 ,  G06N3/08 ,  G08G1/04 ,  G06K9/00 ,  G06K9/66

Abstract: The invention relates to a method for operating a driver assistance system (2) of a motor vehicle (1), including a) Capturing an environment (4) of the motor vehicle (1) by a capturing device (3) of the driver assistance system (2); b) Detecting an accessible freespace (6) in the captured environment (4) by a computing device (5) of the driver assistance system (2); c) Detecting and Classifying at least one object (7a-7e) in the captured environment (4) that is located at a border (8) of the freespace (6) by a neural network (9) of the driver assistance system (2); d) Assigning a part (10a-10e) of the border (8) of the freespace (6) to the detected and classified object (7a-7e); and e) Categorizing a part (11a-11e) of the freespace (6) adjacent to the part (10a-10e) of the border (8) that is assigned to the detected and classified object (7a-7e) in dependence upon the class of that classified object (7a-7e), so as to enable improved safety in driving.

公开(公告)号：US10950127B2

公开(公告)日：2021-03-16

申请号：US16113043

申请日：2018-08-27

Applicant: Connaught Electronics Ltd.

Inventor： Senthil Kumar Yogamani ,  Sunil Chandra

IPC: G08G1/14 ,  G06K9/00 ,  G06K9/62 ,  G06K9/66 ,  G06N3/08 ,  G08G1/04

Abstract: The invention relates to a method for operating a driver assistance system (2) of a motor vehicle (1), including a) Capturing an environment (4) of the motor vehicle (1) by a capturing device (3) of the driver assistance system (2); b) Detecting an accessible freespace (6) in the captured environment (4) by a computing device (5) of the driver assistance system (2); c) Detecting and Classifying at least one object (7a-7e) in the captured environment (4) that is located at a border (8) of the freespace (6) by a neural network (9) of the driver assistance system (2); d) Assigning a part (10a-10e) of the border (8) of the freespace (6) to the detected and classified object (7a-7e); and e) Categorizing a part (11a-11e) of the freespace (6) adjacent to the part (10a-10e) of the border (8) that is assigned to the detected and classified object (7a-7e) in dependence upon the class of that classified object (7a-7e), so as to enable improved safety in driving.

公开(公告)号：US20240312226A1

公开(公告)日：2024-09-19

申请号：US18576750

申请日：2022-07-05

Applicant: CONNAUGHT ELECTRONICS Ltd.

Inventor： Akhilesh Kumar Malviya ,  Arindam Das ,  Senthil Kumar Yogamani

IPC: G06V20/56 ,  G01C21/36 ,  G06T7/62 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V20/588 ,  G01C21/3602 ,  G06T7/62 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20076 ,  G06T2207/20084 ,  G06T2207/30252

Abstract: A computer-implemented method for analyzing a roundabout in an environment for a vehicle is disclosed. The method includes generating at least one initial feature map by applying a feature encoder module of a trained neural network to an input image. The input image depicts the roundabout. The method includes next applying a classificator module of the trained neural network to the initial feature map. An output of the classificator module represents a road region on the input image. The method includes next applying a radius estimation module of the trained neural network to the initial feature map. An output of the radius estimation module depends on an inner radius of the roundabout and an outer radius of the roundabout. The method includes finally determining an entry point and an exit point of the roundabout depending on the output of the classificator module and depending on the output of the radius estimation module.