-
公开(公告)号：US20240428172A1
公开(公告)日：2024-12-26
申请号：US18823886
申请日：2024-09-04
Inventor： Risako TANIGAWA , Yasunori Ishii , Kazuki Kozuka , Tatsumi Nagashima
Abstract: A work estimation method includes: obtaining first sound information related to a reflected sound that is a sound obtained by reflection of an emission sound in an inaudible frequency range and second sound information related to a work sound generated by a work performed by the person; outputting image information that indicates a work area of the person by inputting the first sound information to a first trained model; outputting tool information that indicates a tool that is being used by the person, by inputting the second sound information to a second trained model; and outputting work information that indicates the content of the work, by inputting the image information and the tool information to a third trained model.
-
公开(公告)号：US10248873B2
公开(公告)日：2019-04-02
申请号：US15437874
申请日：2017-02-21
Inventor： Kazuki Kozuka , Ryota Fujimura , Tetsuji Fuchikami
IPC: G06K9/00 , B60R1/00 , G05D1/00 , G05D1/02 , G08G1/16 , B60W50/14 , B60Q1/00 , B60K35/00 , B60Q1/26 , B60Q1/50 , B60Q1/52 , B60Q5/00 , B60Q9/00 , B60W40/00 , B60W40/04 , G08G1/005
Abstract: There are provided an apparatus, a method, and an autonomous moving body which allow a recognition target to be notified with certainty that the recognition target is recognized by an autonomous moving body. A recognition result presenting apparatus according to an embodiment of the present disclosure detects a recognition target (person) present within a predetermined range from an automatic driving vehicle and presents, to the detected recognition target (person), the result of recognition indicating that the automatic driving vehicle recognizes the recognition target (person).
-
公开(公告)号：US10338589B2
公开(公告)日：2019-07-02
申请号：US15462098
申请日：2017-03-17
Inventor： Ryota Fujimura , Kazuki Kozuka , Tetsuji Fuchikami
IPC: G05D1/00 , G06K9/00 , B62D15/02 , G05D1/02 , G08G1/0962 , B60W10/184 , B60W10/20 , B60W30/09
Abstract: A controller that controls driving of an autonomously moving vehicle includes a first sensor that detects an obstacle and a direction of travel of the vehicle, and a processor that sets a virtual region surrounding the vehicle. Processor stops the vehicle when the obstacle is detected therein, determines whether the obstacle is present in the direction of travel, determines whether the vehicle has been stopped for a predetermined amount of time when the obstacle is present, reduces a length of the virtual region in the direction of travel to provide an adjusted virtual region when the vehicle is determined to have been stopped for the predetermined amount of time, causes the vehicle to drive when the obstacle is not detected within the adjusted virtual region, and stops the vehicle when the obstacle is detected within the adjusted virtual region.
-
公开(公告)号：US10019004B2
公开(公告)日：2018-07-10
申请号：US15462048
申请日：2017-03-17
Inventor： Masaki Takahashi , Yasunori Ishii , Kazuki Kozuka
CPC classification number: G05D1/0077 , G05D1/0246 , G06F9/4881 , G06F11/0796 , G06K9/00791 , G06K9/00973 , G06N3/08 , G07C5/0808
Abstract: A device that detects an object includes a receiver that receives information about the object detected by a sensor, multiple circuits that detect the object by performing different detection processes, and a control circuit that controls the circuits. The control circuit detects whether the detection circuits are in an abnormal state, based on a change in a state of the circuits, when the control circuit detects that a first circuit of the circuits is in an abnormal state, the control circuit causes the first circuit to stop a detection process being performed by the first circuit and causes one or more circuits, other than the first circuit, to detect the object by causing the one or more circuits to stop performing detection processes performed by the one or more circuits, and to perform detection processes different from the detection processes being performed by the one or more circuits.
-
公开(公告)号：US20240412112A1
公开(公告)日：2024-12-12
申请号：US18808592
申请日：2024-08-19
Inventor： Yasunori ISHII , Kazuki Kozuka , Hironobu Fujiyoshi , Takayoshi Yamashita , Tsubasa Hirakawa
IPC: G06N20/00
Abstract: A training data generation method for generating training data for training a recognition model that is input with image data and outputs one of a plurality of classes as a class of an object present in the image data, the training data generation method including: selecting a first class from the plurality of classes based on a recognition accuracy of the recognition model; calculating an inter-class distance that is a distance between the first class and each of two or more other classes among the plurality of classes; selecting a second class for generating the training data from the two or more other classes, based on the inter-class distance; and generating the training data by mixing image data and labels of each of the first class selected and the second class selected.
-
Patent Agency Ranking
公开(公告)号：US20240095906A1
公开(公告)日：2024-03-21
申请号：US18511337
申请日：2023-11-16
Inventor： Denis Gudovskiy , Shun Ishizaka , Kazuki Kozuka
IPC: G06T7/00 , G06N3/0464 , G06V10/44
CPC classification number: G06T7/001 , G06N3/0464 , G06V10/454 , G06T2207/20084
Abstract: An anomaly detection method by which a computer performs anomaly detection includes: obtaining first feature data outputted through N (N is an integer not less than 1) convolutional layers of a convolutional neural network configured as an encoder when an image is inputted to the convolutional neural network; obtaining second feature data outputted through M (M is an integer not less than 1, and M≠N) convolutional layers of the convolutional neural network and different in size from the first feature data; and performing anomaly detection on the image by using features indicated by the first feature data and the second feature data that are different in size.
-
公开(公告)号：US10282634B2
公开(公告)日：2019-05-07
申请号：US15450383
申请日：2017-03-06
Inventor： Kazuki Kozuka , Toru Tanigawa , Masahiko Saito
Abstract: An image processing method includes acquiring consecutive time-series images captured by an onboard camera of a vehicle, having a first annotation indicating two or more first regions, and at least including one or more images in which the two or more first regions are on a path of the vehicle and a distance therebetween is smaller than or equal to a threshold; determining, in reverse chronological order from an image of the last time point, positions of the two or more regions in each consecutive time-series image; identifying, from among the consecutive time-series images, the first image of a first time point in which none of the two or more first regions are located on the path, and setting, as a second region, a region between the two or more first regions in the identified first image; and attaching a second annotation to the first image corresponding to the first time point, the second annotation indicating the second region.
-
公开(公告)号：US10210420B2
公开(公告)日：2019-02-19
申请号：US15450360
申请日：2017-03-06
Inventor： Kazuki Kozuka , Toru Tanigawa , Masahiko Saito
Abstract: An image processing method includes acquiring consecutive time-series images captured by an onboard camera and including at least one image having a first annotation indicating a first region; determining, for each of the images, in reverse chronological order from an image of the last time point, whether the first region exists in the image based on whether the first annotation is attached; identifying the first image of a first time point for which the first region is determined not to exist, and setting a second region including a partial region of an object in the identified first image, indicating the moving object that is obstructed by the object before appearing on the path, and having dimensions based on dimensions of the first region in an image of a second time point immediately after the first time point; and attaching a second annotation to the image corresponding to the second time point, the second annotation indicating the second region.
-
9.发明公开公开(公告)号：US20240086774A1
公开(公告)日：2024-03-14
申请号：US18504300
申请日：2023-11-08
Inventor： Konstantinos Karras Kallidromitis , Denis Gudovskiy , Iku Ohama , Kazuki Kozuka
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A training method performed through batch learning by a computer includes: obtaining training data including first time-series data and second time-series data different from the first time-series data; performing first training processing of training a neural process (NP) model, which outputs, using a stochastic process, a prediction result that takes uncertainty into account, to predict first and second time-series data distributions, based on the first time-series data and second time-series data; and performing, using a contrastive learning algorithm, second training processing of (i) training the NP model to bring close to each other first sampling data items generated by sampling from the first time-series data distribution, (ii) training the NP model to bring close to each other second sampling data items generated by sampling from the second time-series data distribution, and (iii) training the NP model to push away the first and second sampling data items far from each other.
-
公开(公告)号：US10528827B2
公开(公告)日：2020-01-07
申请号：US16256118
申请日：2019-01-24
Inventor： Kazuki Kozuka , Ryota Fujimura , Tetsuji Fuchikami
IPC: G06K9/00 , B60W50/14 , B60K35/00 , B60Q1/50 , B60Q5/00 , B60W40/00 , B60W40/04 , G08G1/005 , B60R1/00 , G05D1/00 , G05D1/02 , G08G1/16 , B60Q1/00 , B60Q1/26 , B60Q1/52 , B60Q9/00
Abstract: There are provided an apparatus, a method, and an autonomous moving body which allow a recognition target to be notified with certainty that the recognition target is recognized by an autonomous moving body. A recognition result presenting apparatus according to an embodiment of the present disclosure detects a recognition target (person) present within a predetermined range from an automatic driving vehicle and presents, to the detected recognition target (person), the result of recognition indicating that the automatic driving vehicle recognizes the recognition target (person).
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.027 seconds)
