公开(公告)号：US20210390283A1

公开(公告)日：2021-12-16

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: G06K9/00 ,  G06K9/62

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.

公开(公告)号：US20240071034A1

公开(公告)日：2024-02-29

申请号：US18273182

申请日：2021-03-30

Applicant: NEC Corporation

Inventor： Yoshihiro MISHIMA

IPC: G06V10/26 ,  G06T5/50 ,  G06T7/70 ,  G06V10/22 ,  G06V10/764 ,  G06V20/56 ,  G08G1/04

CPC classification number: G06V10/26 ,  G06T5/50 ,  G06T7/70 ,  G06V10/22 ,  G06V10/764 ,  G06V20/588 ,  G08G1/04 ,  G06T2207/20212 ,  G06T2207/30256

Abstract: Captured images generated by repeated image capture over time by an image capture device provided on a moving body are acquired, and for each pixel in each of said captured images, a probability indicating to which of multiple different area classes, which have been designated regarding multiple targets appearing in the captured images, the pixel belongs is calculated. Among divisional areas obtained by multiply dividing the captured images in a horizontal direction, a divisional area in which a clarity of a prescribed target among the multiple targets is high, where the probability of belonging to the area class of the prescribed target is equal to or higher than a threshold value, is identified. A clear image is generated by combining the divisional areas in which a display clarity regarding the prescribed target in the captured images is high.

公开(公告)号：US20230075659A1

公开(公告)日：2023-03-09

申请号：US17798360

申请日：2021-02-09

Applicant: NEC Corporation

Inventor： Yasunori FUTATSUGI ,  Yoshihiro MISHIMA

IPC: G06T7/55 ,  G06V20/58 ,  G06T7/521 ,  G06T7/70 ,  G01C3/08

Abstract: An object recognition unit recognizes an object included in an image captured by a camera mounted on a vehicle. A first distance estimation unit estimates a distance between the vehicle and the recognized object based on the image. A second distance estimation unit estimates the distance between the vehicle and the recognized object based on the image by using an estimation method different from that of the first distance estimation unit. A combining unit combines a result of estimating the distance obtained by the first distance estimation unit and a result of estimating the distance obtained by the second distance estimation unit based on at least one of an amount of change in the distance estimated by the second distance estimation unit, a steering wheel angle of the vehicle, and information about an acceleration in an up-down direction, and outputs a result of the combination as a ranging result.

公开(公告)号：US20220001858A1

公开(公告)日：2022-01-06

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 ,  G06K9/00 ,  G06N3/08

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：US20210390353A1

公开(公告)日：2021-12-16

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 ,  G06K9/00

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.