公开(公告)号：US20240296663A1

公开(公告)日：2024-09-05

申请号：US18273943

申请日：2022-01-14

Applicant: NEC Corporation

Inventor： Kenta Senzaki ,  Kyoko Murozono ,  Shogo Sato

IPC: G06V10/776 ,  G06T7/73 ,  G06V10/74 ,  G06V10/774

CPC classification number: G06V10/776 ,  G06T7/74 ,  G06V10/761 ,  G06V10/774 ,  G06T2207/20081

Abstract: An estimation unit estimates attitude parameters, which are parameters representing an attitude of an object in a target image based on the target image, which is an image in which the object whose attitude is to be estimated has been taken, using an attitude estimation model learned using one or more teacher data including a teacher image, which is an image in which the object has been taken, and the attitude parameters of the object in the teacher image. An acquisition unit acquires a teacher image whose attitude similarity, which is a degree of similarity between the estimated attitude parameters and the attitude parameters related to the teacher image, is the largest among one or more teacher images included in the one or more teacher data. A first computation unit computes an image similarity, which is a degree of similarity between the target image and the acquired teacher image.

公开(公告)号：US12038502B2

公开(公告)日：2024-07-16

申请号：US17427991

申请日：2019-02-06

Applicant: NEC Corporation

Inventor： Kenta Senzaki

IPC: G01S13/90 ,  G08G3/00

CPC classification number: G01S13/9029 ,  G01S13/9027 ,  G08G3/00

Abstract: An object of an example embodiment of the present disclosure is to stably estimate a navigation status of a target ship at a predetermined time from time-series position information of the ship. A ship behavior analyzing device according to the example embodiment of the present disclosure includes a ship detection means for detecting a ship from synthetic aperture radar (SAR) data, a wake extraction means for extracting a wake of the detected ship, a wake pattern generation means for generating a wake pattern image by using the extracted wake, and a navigation status estimation means for estimating a navigation status of the target ship by using the generated wake pattern image.

公开(公告)号：US11647205B2

公开(公告)日：2023-05-09

申请号：US17685579

申请日：2022-03-03

Applicant: NEC Corporation

Inventor： Kenta Senzaki ,  Yuzo Senda ,  Keiichi Chono ,  Hirofumi Aoki

IPC: H04N11/02 ,  H04N19/139 ,  H04N19/61 ,  H04N19/109 ,  H04N19/119 ,  H04N19/176 ,  H04N19/46 ,  H04N19/51 ,  H04N19/147 ,  H04N19/70 ,  H04N19/91 ,  H04N19/65

CPC classification number: H04N19/139 ,  H04N19/109 ,  H04N19/119 ,  H04N19/147 ,  H04N19/176 ,  H04N19/46 ,  H04N19/51 ,  H04N19/61 ,  H04N19/70 ,  H04N19/65 ,  H04N19/91

Abstract: A video encoding device includes encoding control means 11 for controlling an inter-PU partition type of a CU to be encoded, based on the maximum number (PA) of motion vectors allowed for an image block having a predetermined area and the number (PB) of motion vectors of an encoded image block contained in the image block having the predetermined area. A video decoding device includes decoding control means for controlling an inter-PU partition type of a CU to be decoded, based on the maximum number (PA) of motion vectors allowed for an image block having a predetermined area and the number (PB) of motion vectors of a decoded image block contained in the image block having the predetermined area.

公开(公告)号：US11496749B2

公开(公告)日：2022-11-08

申请号：US16984957

申请日：2020-08-04

Applicant: NEC CORPORATION

Inventor： Hirofumi Aoki ,  Keiichi Chono ,  Yuzo Senda ,  Kenta Senzaki

IPC: H04N7/12 ,  H04N19/159 ,  H04N19/196 ,  H04N19/593 ,  H04N19/124 ,  H04N19/157

Abstract: In a video decoding device, a quantization step size decoding unit calculates a quantization step size that controls a granularity of the inverse quantization by, based on an image prediction, selectively using a mean value of at least a quantization step size assigned to a leftwardly adjacent neighboring image block already decoded and a quantization step size assigned to a upwardly adjacent neighboring image block already decoded or a quantization step size assigned to an image block decoded immediately before.

公开(公告)号：US11323720B2

公开(公告)日：2022-05-03

申请号：US17060828

申请日：2020-10-01

Applicant: NEC CORPORATION

Inventor： Kenta Senzaki ,  Yuzo Senda ,  Keiichi Chono ,  Hirofumi Aoki

IPC: H04N11/02 ,  H04N19/139 ,  H04N19/61 ,  H04N19/109 ,  H04N19/119 ,  H04N19/176 ,  H04N19/46 ,  H04N19/51 ,  H04N19/147 ,  H04N19/70 ,  H04N19/91 ,  H04N19/65

Abstract: A video encoding device includes encoding control means 11 for controlling an inter-PU partition type of a CU to be encoded, based on the maximum number (PA) of motion vectors allowed for an image block having a predetermined area and the number (PB) of motion vectors of an encoded image block contained in the image block having the predetermined area. A video decoding device includes decoding control means for controlling an inter-PU partition type of a CU to be decoded, based on the maximum number (PA) of motion vectors allowed for an image block having a predetermined area and the number (PB) of motion vectors of a decoded image block contained in the image block having the predetermined area.

公开(公告)号：US11310510B2

公开(公告)日：2022-04-19

申请号：US16910288

申请日：2020-06-24

Applicant: NEC CORPORATION

Inventor： Keiichi Chono ,  Yuzo Senda ,  Junji Tajime ,  Hirofumi Aoki ,  Kenta Senzaki

IPC: H04N19/156 ,  H04N19/503 ,  H04N19/176 ,  H04N19/46 ,  H04N19/61 ,  H04N19/593 ,  H04N19/12 ,  H04N19/172 ,  H04N19/184

Abstract: A video decoding device and method, including extracting PCM block size information including a threshold, from a bitstream, determining the threshold based on the extracted PCM block size information; parsing a PCM header from the bitstream with respect to an encoded block, only when said encoded block is prediction mode of intra prediction and a block size of said encoded block is equal to or greater than the determined threshold, controlling an entropy decoding process and a PCM decoding process based on the parsed PCM header; parsing transformed data of a prediction error data of an image in the bitstream; and PCM-decoding PCM data of the image in the bitstream, wherein the decoding performs the decoding operation based on the prediction mode being intra prediction and based on the block size of the encoded block being equal to or greater than the determined threshold.

公开(公告)号：US09542617B2

公开(公告)日：2017-01-10

申请号：US14762889

申请日：2014-02-26

Applicant: NEC Corporation

Inventor： Kenta Senzaki ,  Masato Tsukada ,  Hiroaki Kawaguchi

IPC: G06K9/40 ,  G06K9/52 ,  H04N1/409 ,  H04N5/14 ,  G06T5/00 ,  G06K9/46

CPC classification number: G06K9/52 ,  G06K9/46 ,  G06K9/4604 ,  G06K9/4661 ,  G06K2009/4666 ,  G06T5/00 ,  G06T5/002 ,  G06T2207/20016 ,  G06T2207/20192 ,  H04N1/409 ,  H04N5/14

Abstract: The present invention is directed to an image processing method, comprising: deriving a pixel statistical value of pixels and edge information for each of regions in a plurality of layers, the regions including attention pixels and having ranges that are successively narrower; correcting differential information between a pixel statistical value for a region in an attention layer and a pixel statistical value for a region in a layer wider than the region in the attention layer by using the edge information; correcting the pixel statistical value for the region in the attention layer by using the corrected differential information and the pixel statistical value for the region wider than the region in the attention layer; re-correcting the corrected pixel statistical value for the region in the attention layer by using a pixel statistical value for a region equal to or wider than a region in each of the layers and differential information between the uncorrected pixel statistical value for the region in the attention layer and the corrected pixel statistical value for the region in the attention layer; and correcting the attention pixel by repeating the correcting and the re-correcting the pixel statistical value for the region in the attention layer sequentially in the respective layers until the region is reduced from a maximum range to a minimum range.

Abstract translation: 本发明涉及一种图像处理方法，包括：针对多个层中的每个区域，导出像素的像素统计值和边缘信息，所述区域包括关注像素并且具有相继变窄的范围; 通过使用所述边缘信息来校正所述关注层中的区域的像素统计值与所述关注层中的所述区域之外的区域的像素统计值的差分信息; 通过使用校正后的差分信息和比关注层中的区域宽的区域的像素统计值来校正注意层中的区域的像素统计值; 通过使用等于或大于每个层中的区域的区域的像素统计值和在该层中的区域的未校正像素统计值之间的差分信息来重新校正注意层中的区域的校正像素统计值 注意层和注意层区域的校正像素统计值; 以及通过重复在各层中顺序地对关注层中的区域进行像素统计值的校正和重新校正，直到该区域从最大范围减小到最小范围来校正关注像素。

公开(公告)号：US09519958B2

公开(公告)日：2016-12-13

申请号：US14396061

申请日：2013-04-24

Applicant: NEC Corporation

Inventor： Kenta Senzaki ,  Masato Tsukada ,  Hiroaki Kawaguchi

IPC: G06K9/40 ,  G06T5/00 ,  G09G1/14 ,  G09G3/28 ,  G09G3/30 ,  G09G5/00 ,  G09G5/02 ,  G09G5/10 ,  G06T5/20 ,  H04N5/217 ,  H04N5/357

CPC classification number: G06T5/20 ,  G06T5/002 ,  G06T2207/20016 ,  G06T2207/20076 ,  H04N5/2173 ,  H04N5/357

Abstract: A method includes: calculating a pixel statistical value and edge of pixels for each of areas of a multi-layer, the areas each containing a target pixel and having a successively decreased range; correcting the edge based on a pixel statistical value of an area that is wider than a specific area; correcting difference between a pixel statistical value of the specific area and the pixel statistical value of the area that is wider than the specific area using the post-correction edge; correcting the pixel statistical value of the specific area using post-correction difference and the pixel statistical value of the area that is wider than the specific area; and correcting the target pixel by repeating correction of the pixel statistical value of the specific area successively in each area until the area reduces its range from the maximum range to the minimum range.

Abstract translation: 一种方法包括：计算多层的每个区域的像素统计值和像素边缘，每个区域包含目标像素并具有连续减小的范围; 基于比特定区域宽的区域的像素统计值来校正边缘; 使用所述校正后边缘来校正所述特定区域的像素统计值和比所述特定区域宽的区域的像素统计值之间的差异; 使用校正后差异以及比特定区域宽的区域的像素统计值来校正特定区域的像素统计值; 并且通过在每个区域中连续地重复校正特定区域的像素统计值来校正目标像素，直到该区域将其范围从最大范围减小到最小范围。

公开(公告)号：US11582461B2

公开(公告)日：2023-02-14

申请号：US17066136

申请日：2020-10-08

Applicant: NEC CORPORATION

Inventor： Kenta Senzaki ,  Yuzo Senda ,  Keiichi Chono ,  Hirofumi Aoki

IPC: H04N19/103 ,  H04N19/147 ,  H04N19/503 ,  H04N19/176 ,  H04N19/70 ,  H04N19/119 ,  H04N19/46 ,  H04N19/61 ,  H04N19/109 ,  H04N19/157 ,  H04N19/44 ,  H04N19/91 ,  H04N19/65

Abstract: A video encoding device for encoding video using inter prediction includes encoding control means 11 for controlling an inter-PU partition type of a CU to be encoded, based on a minimum inter-PU size (PA) and a CU size (PB) of the CU to be encoded. A video decoding device includes decoding control means for controlling an inter-PU partition of a CU to be decoded, based on the minimum inter-PU size (PA) and the size (PB) of the CU to be decoded.

公开(公告)号：US20220317314A1

公开(公告)日：2022-10-06

申请号：US17702009

申请日：2022-03-23

Applicant: NEC Corporation

Inventor： Chika UMEGAKI ,  Kenta Senzaki ,  Katsuya Odaka ,  Hironobu Mori ,  Kyoko Murozono

IPC: G01S19/40 ,  G01C21/24 ,  G01C21/02 ,  G01S19/48

Abstract: A satellite attitude estimation system 20 includes a determination unit 21 which determines the maximum pixel, which is a pixel with the largest luminance, and the minimum pixel, which is a pixel with the smallest luminance, respectively, in an infrared image, which is an image taken by an infrared sensor of a target satellite that is a satellite whose attitude is to be estimated, an association unit 22 which associates the determined maximum and minimum pixels with coordinates on the 3D structure of the target satellite, respectively, a computation unit 23 which computes normal vectors for a surface including the coordinates associated with the pixel, respectively, over the coordinates associated with each pixel, and a sun direction estimation unit 24 which estimates the direction of the sun relative to the target satellite before the infrared image is taken using the computed normal vectors.