公开(公告)号：US11586856B2

公开(公告)日：2023-02-21

申请号：US17287182

申请日：2019-09-13

Applicant: NEC Corporation

Inventor： Yasunori Futatsugi ,  Yoshihiro Mishima ,  Atsushi Fukuzato ,  Jun Nakayamada ,  Kenji Sobata

IPC: G06K9/62 ,  G06V20/58 ,  G01S7/41 ,  G01S13/931 ,  G06V10/774 ,  G01S17/931 ,  G06V10/778 ,  G06N20/20 ,  G06N3/04

Abstract: An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

公开(公告)号：US20240312220A1

公开(公告)日：2024-09-19

申请号：US18273258

申请日：2021-03-30

Applicant: NEC CORPORATION

Inventor： Yoshihiro Mishima

IPC: G06V20/58 ,  G06T7/55 ,  G06T7/60 ,  G06T7/73 ,  G06V10/764 ,  G06V20/56

CPC classification number: G06V20/58 ,  G06T7/55 ,  G06T7/60 ,  G06T7/74 ,  G06V10/764 ,  G06V20/588 ,  G06T2207/30256 ,  G06V2201/08

Abstract: Among multiple different area classes designated regarding photographic subjects, to which area class a photographic subject of each pixel in a captured image that has been acquired belongs is recognized. From depth map information corresponding to the captured image, range information of each pixel in an area in the captured image representing a vehicle area class among the multiple different area classes is acquired, and a position at which the range information is discontinuous is determined to be a boundary between different vehicles.

公开(公告)号：US12194987B2

公开(公告)日：2025-01-14

申请号：US17293564

申请日：2019-09-13

Applicant: NEC Corporation

Inventor： Yasunori Futatsugi ,  Yoshihiro Mishima ,  Atsushi Fukuzato ,  Jun Nakayamada ,  Kenji Sobata ,  Yuki Chiba

IPC: B60W30/08 ,  G06N3/08 ,  G06V20/56

Abstract: A dangerous scene prediction device 80 for predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unit 81 and a dangerous scene prediction unit 82. The learning model selection/synthesis unit 81 selects, from two or more learning models, a learning model used for predicting the dangerous scene, depending on a scene determined based on information obtained during the driving of the vehicle. The dangerous scene prediction unit 82 predicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

公开(公告)号：US20240095946A1

公开(公告)日：2024-03-21

申请号：US18039625

申请日：2020-12-03

Applicant: NEC Corporation

Inventor： Wenjing Cui ,  Yoshihiro Mishima

IPC: G06T7/73 ,  G06V20/56

CPC classification number: G06T7/73 ,  G06V20/588 ,  G06T2207/30256

Abstract: The area recognition image generation means 81 generates an area recognition image including a road area from an area recognition image which is a captured image of the front of a vehicle. The overhead view image generation means 82 generates a first overhead view image obtained by converting the generated area recognition image into an overhead view image. The line position estimation means 83 estimates a position of line marked on a road surface from the road area identified by the generated first overhead view image, based on a principle of lane boundaries.

公开(公告)号：US20240062505A1

公开(公告)日：2024-02-22

申请号：US18270674

申请日：2021-03-30

Applicant: NEC Corporation

Inventor： Yoshihiro Mishima ,  Naoko Asano ,  Erina Kitahara

IPC: G06V10/25 ,  G06V10/764 ,  G06V20/64 ,  G06V20/58 ,  G06V20/56

CPC classification number: G06V10/25 ,  G06V10/764 ,  G06V20/64 ,  G06V20/58 ,  G06V20/588 ,  G06V2201/08

Abstract: Among multiple different area classes designated regarding objects appearing in a captured image that has been acquired, to which area class each pixel in the captured image belongs is recognized. An unrecognized-class area not belonging to any of the multiple area classes in an area in the captured image representing a prescribed area class among the multiple different area classes is identified as an area-of-interest candidate. A determination is made regarding whether the area-of-interest candidate is a prescribed desired area.

公开(公告)号：US11783602B2

公开(公告)日：2023-10-10

申请号：US17288607

申请日：2019-09-17

Applicant: NEC Corporation

Inventor： Yasunori Futatsugi ,  Yoshihiro Mishima ,  Atsushi Fukuzato ,  Jun Nakayamada ,  Kenji Sobata

IPC: G06V20/64 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2431 ,  G06V20/56

CPC classification number: G06V20/64 ,  G06F18/217 ,  G06F18/2148 ,  G06F18/2431 ,  G06V20/56

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.