Patents by Inventor Tomoya SAWADA
Tomoya SAWADA has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240362901Abstract: An image signal indicating an inference target image in which a detection target appears is acquired when a domain of the inference target image is different from a domain of a training image or a recognition task of the inference target image is different from a pre-learned task. The image signal is provided to a trained learning model, and from the learning model, an inference time feature amount obtained by combining feature amounts of the detection target in the inference target image after the feature amounts is blurred is acquired. The detection target in the inference target image is recognized on the basis of a representative feature amount that is a registered feature amount of the detection target in an image for conversion in which a domain and a recognition task of the image are the same as those of the inference target image, and the inference time feature amount.Type: ApplicationFiled: August 2, 2022Publication date: October 31, 2024Applicant: Mitsubishi Electric CorporationInventor: Tomoya SAWADA
-
Publication number: 20240249178Abstract: A trained model generation system that generates a trained model includes: an estimation unit configured to perform estimation on learning data; a loss gradient calculating unit configured to calculate a gradient of loss for a result of estimation from the estimation unit; and an optimizer unit configured to calculate a plurality of parameters constituting the trained model on the basis of the gradient of loss. The optimizer unit uses an expression including a first factor of which an absolute value becomes greater than 1 to achieve an effect of increasing a learning rate when learning stagnates and in which the effect of increasing the learning rate when the learning stagnates increases as the number of epochs increases as an expression for calculating the learning rate used to calculate the plurality of parameters. Accordingly, it is possible to enable learning to exit from a state in which the learning stagnates.Type: ApplicationFiled: December 3, 2021Publication date: July 25, 2024Applicant: MITSUBISHI ELECTRIC CORPORATIONInventor: Tomoya SAWADA
-
Publication number: 20240046512Abstract: An image signal indicating a target image is acquired when a domain of the target image is different from that of a training image or a recognition task of the target image is different from a pre-learned task. The image signal is provided to a trained learning model. An inference time feature amount obtained by combining feature amounts of the detection target after the feature amounts are blurred is acquired from the learning model. A three-dimensional position of the detection target is estimated on the basis of a representative feature amount being a registered feature amount of the detection target appearing in an image for conversion whose domain and recognition task of the image are the same as those of the target image, and the inference time feature amount. A temporal positional change of the detection target in the target image is analyzed on the basis of the estimated position.Type: ApplicationFiled: August 2, 2022Publication date: February 8, 2024Applicant: Mitsubishi Electric CorporationInventor: Tomoya SAWADA
-
Publication number: 20230410532Abstract: An object detection device includes an image data acquiring unit that acquires image data indicating an image captured by a camera, a first feature amount extracting unit that generates a first feature map using the image data, a second feature amount extracting unit that generates a second feature map using the image data, and generates a third feature map by performing addition or multiplication of the second feature map using the first feature map and weighting the second feature map, and the object detection unit that detects an object in the captured image using the third feature map. A first feature amount in the first feature map uses a mid-level feature corresponding to objectness, and a second feature amount in the second feature map uses a high-level feature.Type: ApplicationFiled: December 25, 2020Publication date: December 21, 2023Applicant: Mitsubishi Electric CorporationInventors: Tomoya SAWADA, Ken FUKUCHI
-
Publication number: 20230394807Abstract: A learning device according to the present disclosed technology is a learning device including a coupled mathematical model capable of machine learning and learning a data set of a target domain from a data set of an original domain for a teacher, in which a pre-stage part of the coupled mathematical model generates a plurality of low-level feature maps from input image data, compares the low-level feature maps of data sets belonging to the same type of learning target for the original domain and the target domain in the image data, and calculates domain-shared features, and calculates domain relaxation learning information for each space of {1} color, {2} illumination, {3} low frequency component, and {4} high frequency component among the domain-shared features.Type: ApplicationFiled: August 18, 2023Publication date: December 7, 2023Applicant: Mitsubishi Electric CorporationInventor: Tomoya SAWADA
-
Publication number: 20220366676Abstract: A labeling device includes: an image-signal acquisition unit that acquires an image signal indicating an image captured by a camera; an image recognition unit that has learned by machine learning and performs image recognition on the captured image; and a learning-data-set generation unit that generates, by performing labeling on each object included in the captured image on the basis of a result of image recognition, a learning data set including image data corresponding to each object and label data corresponding to each object.Type: ApplicationFiled: August 2, 2022Publication date: November 17, 2022Applicant: Mitsubishi Electric CorporationInventors: Tomoya SAWADA, Ken FUKUCHI, Yoshimi MORIYA
-
Patent number: 10943141Abstract: An image feature map generating unit (3) generates, on the basis of feature amounts extracted from a plurality of images successively captured by a camera (109), an image feature map which is an estimated distribution of the object likelihood on each of the images. An object detecting unit (4) detects an object on the basis of the image feature map generated by the image feature map generating unit (3).Type: GrantFiled: September 15, 2016Date of Patent: March 9, 2021Assignee: MITSUBISHI ELECTRIC CORPORATIONInventors: Tomoya Sawada, Hidetoshi Mishima, Hideaki Maehara, Yoshimi Moriya, Kazuyuki Miyazawa, Akira Minezawa, Momoyo Hino, Mengxiong Wang, Naohiro Shibuya
-
Patent number: 10643338Abstract: An object detection device includes: an optical flow calculator to calculate an optical flow between images captured by the image capturer at different times; an evaluation value calculator to divide the image captured by the image capturer into areas, and calculate, for each divided area, an evaluation value by using the optical flows of pixels belonging to the divided area, the evaluation value indicating a measure of a possibility that the divided area is an object area representing part or whole of the object to be detected; and an area determinator to determine an area in an image, in which the object to be detected exists, by comparing the evaluation value of each divided area calculated by the evaluation value calculator with a threshold value.Type: GrantFiled: December 2, 2015Date of Patent: May 5, 2020Assignee: MITSUBISHI ELECTRIC CORPORATIONInventors: Kazuyuki Miyazawa, Shunichi Sekiguchi, Hideaki Maehara, Yoshimi Moriya, Akira Minezawa, Ryoji Hattori, Momoyo Nagase, Tomoya Sawada
-
Publication number: 20190197345Abstract: An image feature map generating unit (3) generates, on the basis of feature amounts extracted from a plurality of images successively captured by a camera (109), an image feature map which is an estimated distribution of the object likelihood on each of the images. An object detecting unit (4) detects an object on the basis of the image feature map generated by the image feature map generating unit (3).Type: ApplicationFiled: September 15, 2016Publication date: June 27, 2019Applicant: Mitsubishi Electric CorporationInventors: Tomoya SAWADA, Hidetoshi MISHIMA, Hideaki MAEHARA, Yoshimi MORIYA, Kazuyuki MIYAZAWA, Akira MINEZAWA, Momoyo HINO, Mengxiong WANG, Naohiro SHIBUYA
-
Publication number: 20190193659Abstract: An information processing unit (32) collects accident information from a vehicle-mounted device (2) existing in a periphery of a site of an accident indicated by accident information stored in a storage unit (31), by controlling a communication unit (30).Type: ApplicationFiled: July 7, 2016Publication date: June 27, 2019Applicant: Mitsubishi Electric CorporationInventors: Kazuyuki MIYAZAWA, Shunichi SEKIGUCHI, Hideaki MAEHARA, Yoshimi MORIYA, Akira MINEZAWA, Ryoji HATTORI, Momoyo HINO, Tomoya SAWADA, Naohiro SHIBUYA
-
Publication number: 20180204333Abstract: An object detection device includes: an optical flow calculator to calculate an optical flow between images captured by the image capturer at different times; an evaluation value calculator to divide the image captured by the image capturer into areas, and calculate, for each divided area, an evaluation value by using the optical flows of pixels belonging to the divided area, the evaluation value indicating a measure of a possibility that the divided area is an object area representing part or whole of the object to be detected; and an area determinator to determine an area in an image, in which the object to be detected exists, by comparing the evaluation value of each divided area calculated by the evaluation value calculator with a threshold value.Type: ApplicationFiled: December 2, 2015Publication date: July 19, 2018Applicant: MITSUBISHI ELECTRIC CORPORATIONInventors: Kazuyuki MIYAZAWA, Shunichi SEKIGUCHI, Hideaki MAEHARA, Yoshimi MORIYA, Akira MINEZAWA, Ryoji HATTORI, Momoyo NAGASE, Tomoya SAWADA