公开(公告)号：US20250095171A1

公开(公告)日：2025-03-20

申请号：US18964079

申请日：2024-11-29

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Masaki FUKUDA ,  Toshiyasu SUGIO ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA ,  Kensho TERANISHI

IPC: G06T7/33 ,  G06T17/00 ,  G06T19/20

Abstract: An object amount calculation apparatus includes: a receiver configured to obtain a first three-dimensional model and a second three-dimensional model different from the first three-dimensional model, each of the first three-dimensional model and the second three-dimensional model representing a same space, each of the first three-dimensional model and the second three-dimensional model being constituted with regions having respective attributes; and a processor configured to: align the first three-dimensional model and the second three-dimensional model based on at least one attribute of the first three-dimensional model and the second three-dimensional model; calculate, for each of the attributes, a difference between the first three-dimensional model aligned and the second three-dimensional model aligned; and output (i) a total amount of differences corresponding to two or more attributes among the attributes and (ii) information on the two or more attributes.

公开(公告)号：US20230003506A1

公开(公告)日：2023-01-05

申请号：US17942548

申请日：2022-09-12

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Masaki FUKUDA ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA ,  Kensho TERANISHI

IPC: G01B11/02 ,  G06T7/62 ,  G06T7/12 ,  G06T7/13 ,  G06T17/00 ,  G06V10/44 ,  G06V10/74

Abstract: A dimension measurement method includes: extracting a plurality of lines from a plurality of images generated by shooting a target area from a plurality of viewpoints, and generating a line segment model which is a three-dimensional model of the target area that is expressed using the plurality of lines; calculating a dimension of a particular part inside the target area, using the line segment model; and outputting the dimension calculated.

公开(公告)号：US20210027496A1

公开(公告)日：2021-01-28

申请号：US17070290

申请日：2020-10-14

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Tatsuya KOYAMA ,  Masaki FUKUDA ,  Toshiyasu SUGIO ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA

IPC: G06T7/80 ,  G06T7/73 ,  G06T7/246 ,  H04N13/246

Abstract: A calibration apparatus calibrates parameters of imaging apparatuses which are disposed at different positions and image a common three-dimensional space. The calibration apparatus includes: an obtaining circuit which obtains videos captured by the imaging apparatuses and each including frames; an extraction circuit which extracts feature points from the frames included in the videos, the feature points including first feature points extracted from first frames included in the videos and second feature points extracted from areas containing an image of a moving object in second frames included in the videos and different from the first frames; a matching circuit which performs matching using the feature points, the matching including matching between the first feature points and matching between the second feature points; and a calibration circuit which calculates parameters of the imaging apparatuses based on first matching results obtained through the matching by the matching circuit.

公开(公告)号：US20200034989A1

公开(公告)日：2020-01-30

申请号：US16580185

申请日：2019-09-24

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Tatsuya KOYAMA ,  Toshiyasu SUGIO ,  Yoichi SUGINO ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA

IPC: G06T7/80 ,  G06T7/73 ,  H04N13/246 ,  H04N13/243 ,  G05D1/00 ,  B64D47/08 ,  B64C39/02

Abstract: A calibrator for cameras includes a controlling circuit, a photographing circuit, a calculating circuit, and an instructing circuit. The controlling circuit is configured to control a movable body in a shooting area of the cameras. A marker is provided on the movable body for calibration of the cameras. The photographing circuit is configured to control the cameras to photograph the marker at a first position at a first timing to generate first images. The photographing circuit is configured to control the cameras to photograph the marker at a second position at a second timing to generate second images. The calculating circuit is configured to calculate parameters of the cameras based on the first images and the second images. The instructing circuit is configured to transmit the parameters to the cameras to calibrate the cameras.

公开(公告)号：US20180184123A1

公开(公告)日：2018-06-28

申请号：US15735427

申请日：2016-03-18

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Kengo TERADA ,  Takahiro NISHI ,  Tadamasa TOMA ,  Satoshi YOSHIKAWA

IPC: H04N19/61 ,  H04N19/80

CPC classification number: H04N19/61 ,  G06T9/002 ,  H04N19/109 ,  H04N19/11 ,  H04N19/117 ,  H04N19/147 ,  H04N19/156 ,  H04N19/17 ,  H04N19/51 ,  H04N19/593 ,  H04N19/70 ,  H04N19/80 ,  H04N19/82 ,  H04N19/85

Abstract: The image encoding method includes: encoding an image including a block by performing, in at least one of intra prediction, inter prediction, and an in-loop filter, a non-linear process by which the input-output relationship becomes non-linear; and encoding an operation parameter of a non-linear filter to be used in the non-linear process.

公开(公告)号：US20180041767A1

公开(公告)日：2018-02-08

申请号：US15785756

申请日：2017-10-17

Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.

Inventor： Satoshi YOSHIKAWA ,  Hisao SASAI ,  Kengo TERADA

IPC: H04N19/50 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46

CPC classification number: H04N19/50 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46

Abstract: An image decoding device is provided for decoding a current block in a current coded picture using a coded bitstream. The image decoding device includes a processor and a memory coupled to the processor. The processor of the image decoding device performs operations, including decoding first motion information for the current block from the coded bitstream, and selecting second motion information from a decoded region adjacent to the current block. The processor also performs operations including decoding the current block using the decoded first motion information and the decoded second motion information, and generating a decoded picture using the decoded current block.

公开(公告)号：US20240362860A1

公开(公告)日：2024-10-31

申请号：US18764883

申请日：2024-07-05

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Kensho TERANISHI ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA

IPC: G06T17/00 ,  G06T7/11 ,  G06V10/764

CPC classification number: G06T17/00 ,  G06T7/11 ,  G06V10/764 ,  G06T2207/30201

Abstract: A calculation method according to one aspect of the present disclosure obtains three-dimensional points that represent an object in a space on a computer, each indicating a position on the object, classifies the three-dimensional points into groups based on the respective normal directions of the three-dimensional points, and calculates a first accuracy of each of the groups, the first accuracy increasing with an increase of a second accuracy of at least one three-dimensional point belonging to the group. The three-dimensional points are generated by a sensor detecting light from the object from different positions and in different directions. The normal direction of each three-dimensional point is determined based on the different directions used to generate the three-dimensional point.

公开(公告)号：US20230213371A1

公开(公告)日：2023-07-06

申请号：US18113223

申请日：2023-02-23

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Ukyou KATSURA ,  Toru MATSUNOBU ,  Satoshi YOSHIKAWA ,  Masaki FUKUDA ,  Kensho TERANISHI ,  Tomokazu ICHIRIKI ,  Masanori KIMURA ,  Toshiyasu SUGIO

IPC: G01F23/284 ,  G06T7/62

CPC classification number: G01F23/2845 ,  G06T7/62

Abstract: A filling rate measurement method includes: obtaining a space three-dimensional model generated by measuring a storage through an opening of the storage using a range sensor facing the storage; obtaining a storage three-dimensional model that is a three-dimensional model of the storage; extracting a target part that is a part of a measurement target in the space three-dimensional model; identifying a line segment indicating a shape of the opening on a two-dimensional image of the opening which is generated; estimating a target three-dimensional model that is a three-dimensional model of the measurement target based on the target part and a three-dimensional coordinate system with respect to the position of the opening on a three-dimensional space identified based on the position of the range sensor, the specific direction, and the shape of the opening; and calculating a filling rate of the measurement target with respect to the storage space.

公开(公告)号：US20220284672A1

公开(公告)日：2022-09-08

申请号：US17748331

申请日：2022-05-19

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Kensho TERANISHI ,  Satoshi YOSHIKAWA ,  Toru MATSUNOBU ,  Masaki FUKUDA

IPC: G06T17/05 ,  G06T7/55 ,  G06T7/80

Abstract: A three-dimensional model generation method includes: obtaining map information generated by camera calibration executed by controlling one or more cameras to shoot a subject from a plurality of viewpoints, the map information including three-dimensional points each indicating a position on the subject in a three-dimensional space; obtaining a first image from a first view point and a second image from a second viewpoint; determining a search range in the three-dimensional space, based on the map information, the search range including a first three-dimensional point on the subject, the first three-dimensional point corresponding to a first point in the first image; searching for a similar point that is similar to the first point, in a range in the second image which corresponds to the search range; and generating a three-dimensional model using a search result in the searching.

公开(公告)号：US20210235087A1

公开(公告)日：2021-07-29

申请号：US17231167

申请日：2021-04-15

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Satoshi YOSHIKAWA ,  Takahiro NISHI ,  Kengo TERADA

IPC: H04N19/124 ,  H04N19/176 ,  H04N19/126 ,  H04N19/154 ,  H04N19/159 ,  H04N19/46 ,  H04N19/136

Abstract: An encoding method which allows reduction in the amount of codes is provided. The encoding method includes: setting step S11 for setting a quantization matrix set; quantization step S12 for performing quantization on a target block using the selected quantization matrix; and encoding step S13 for encoding, in a mutually associated manner, the target block which has been subjected to the quantization and identification information for identifying the quantization matrix set which has been set. In setting step S11, a quantization matrix set selected from a plurality of quantization matrix sets is set as the quantization matrix set to be used to perform the quantization on the target block, the plurality of quantization matrix sets including a custom quantization matrix set which is arbitrarily specified and a plurality of defined quantization matrix sets which have been respectively defined in advance.