-
公开(公告)号：US20190147360A1
公开(公告)日：2019-05-16
申请号：US16097998
申请日：2017-12-11
Inventor： Yuichi MATSUMOTO , Masataka SUGIURA
Abstract: Learned model providing system is configured of learned model providing device in which a plurality of learned models are saved in advance and user side device that receive the learned model from learned model providing device. Since learned model providing device can select a learned model to be provided to user side device from the plurality of learned models saved in learned model database based on needs information acquired from user side device, it is possible to select the learned model suitable for the user side needs.
-
2.发明申请公开(公告)号：US20190019285A1
公开(公告)日：2019-01-17
申请号：US16080345
申请日：2017-02-15
Inventor： Yuichi MATSUMOTO , Kazuma YOSHIDA
CPC classification number: G06T7/0008 , G06Q10/08 , G06Q10/0833 , G06Q10/087 , G06T11/60 , G06T2207/10016 , G06T2207/30232
Abstract: A commodity monitoring device includes: an image acquisition unit (51) that sequentially acquires a sales floor image with the lapse of time; a shortage state detector (52) that detects a shortage state of commodities displayed on a sales floor based on the sales floor image, every time the image acquisition unit acquires the sales floor image; a duration acquisition unit (53) that acquires duration of the shortage state in a case where the shortage state of the commodities is detected by the shortage state detector; and a screen generator (54) that generates a state display image whose display form changes according to a length of the duration based on an output result of the duration acquisition unit to generate a monitoring screen including an image area in which the state display image is superimposed on the sales floor image.
-
公开(公告)号：US20210264210A1
公开(公告)日：2021-08-26
申请号：US17256871
申请日：2019-04-23
Inventor： Daisuke UETA , Makoto SHINZAKI , Yuichi MATSUMOTO
Abstract: In collection of training data for image recognition, in order to support a reduction in collection of improper images which are not suitable as training data, a learning data collection device 3 includes a processor 51 which is configured to acquire a captured image from an image capturing device 2, determine whether or not the captured image is suitable as training data, and when the captured image is determined to be not suitable as training data, perform a notification operation to prompt an image capturing person to reshoot a new image for the captured image.
-
4.发明申请公开(公告)号：US20190095757A1
公开(公告)日：2019-03-28
申请号：US16097968
申请日：2017-12-11
Inventor： Masataka SUGIURA , Yuichi MATSUMOTO
Abstract: Learned model providing system has a configuration including consent acquisition device that acquires use consent that an acquired image of visitor is to be used for generating a learned model from visitor, a plurality of cameras that image visitor, learned model generating device that generates the learned model by machine learning based on a captured image imaged by camera, server device that saves the learned model generated by learned model generating device, user side device that receives the learned model from server device, camera, and member database.
-
公开(公告)号：US20160323532A1
公开(公告)日：2016-11-03
申请号：US15025999
申请日：2015-07-22
Inventor： Youichi GOUDA , Yuichi MATSUMOTO , Hiroaki YOSHIO
CPC classification number: H04N5/45 , G06K9/00771 , G09G5/00 , G09G2340/045 , G09G2340/0464 , G09G2340/12 , G09G2340/14 , H04N5/272 , H04N7/181 , H04N7/183
Abstract: A monitoring device includes a process condition setter that sets a target area on the monitored moving image according to a user's operation input, a stay information acquirer that observes a staying situation of a moving object appearing on the monitored moving image and acquires stay information indicating the staying situation of the moving object, a sub-image generator that generates the sub-image, a sub-image arrangement controller that controls an arrangement position of the sub-image on the monitored moving image based on the stay information acquired by the stay information acquirer, and an output controller that generates the monitoring moving image in which the sub-image is composed on the monitored moving image based on the arrangement position of the sub-image determined by the sub-image arrangement controller and outputs the monitoring moving image on the display device.
Abstract translation: 监视装置包括：处理条件设定器，其根据用户的操作输入设定所监视的运动图像上的目标区域;停留信息获取部，其观察出现在所监视的运动图像上的运动对象的停留状况，并获取表示 基于由停留信息获取的停留信息，生成子图像的子图像生成器，子图像排列控制器，控制子图像在监视的运动图像上的排列位置; 以及输出控制器，其基于由副图像配置控制器确定的子图像的配置位置，在监视的运动图像上生成其中构成子图像的监视运动图像，并输出监视运动图像 显示设备。
-
Patent Agency Ranking
6.发明申请ACTIVITY SITUATION ANALYSIS APPARATUS, ACTIVITY SITUATION ANALYSIS SYSTEM, AND ACTIVITY SITUATION ANALYSIS METHOD 审中-公开活动情况分析装置，活动情况分析系统和活动情况分析方法公开(公告)号：US20160104174A1
公开(公告)日：2016-04-14
申请号：US14817598
申请日：2015-08-04
Inventor： Yuichi MATSUMOTO , Kazuma YOSHIDA
CPC classification number: G06Q30/0201 , G06K9/00778 , G06Q10/10
Abstract: Position information on every moving object is acquired from a moving image of a monitoring area, and activity information during every unit time is acquired from the position information on every moving object. Conditions of an observation period of time are set according to a user input operation, the observation period of time is controlled in accordance with the conditions of the observation period of time, and the activity information during every unit time is aggregated during the observation period of time to acquire the activity information during the observation period of time. An activity map image is generated from the activity information during the observation period of time, and the activity map image and the moving image of the monitoring area are generated and output at every predetermined point in time.
Abstract translation: 从监视区域的运动图像获取关于每个移动物体的位置信息，并且从每个移动物体的位置信息中获取每个单位时间内的活动信息。 根据用户输入操作设定观察期间的条件，根据观察期间的条件来控制观察时间，并且在每个单位时间内的活动信息在观察期间的观察期间 在观察期间获取活动信息的时间。 在观察期间，从活动信息生成活动地图图像，并且在每个预定时间点生成和输出活动地图图像和监视区域的运动图像。
-
公开(公告)号：US20160026875A1
公开(公告)日：2016-01-28
申请号：US14808236
申请日：2015-07-24
Inventor： Yuichi MATSUMOTO , Kazuma YOSHIDA
CPC classification number: G06K9/00771 , G06Q30/02 , G08B13/19686 , H04N5/23229 , H04N5/247 , H04N21/21805 , H04N21/23418 , H04N21/2343 , H04N21/25866 , H04N21/25875 , H04N21/4545
Abstract: A monitoring device according to an embodiment of the present invention controls a moving image processor and a moving image outputter according to the use purpose of a user, and outputs one of an original video and a mask processing image. A controller causes the moving image processor to perform a prescribed preprocessing according to a prescribed start event generated in advance of a use purpose input operation which is performed by the user.
Abstract translation: 根据本发明的实施例的监视装置根据用户的用途控制运动图像处理器和运动图像输出器，并输出原始视频和掩码处理图像之一。 控制器使得运动图像处理器根据由用户执行的使用目的输入操作之前产生的规定的开始事件来执行规定的预处理。
-
公开(公告)号：US20220343635A1
公开(公告)日：2022-10-27
申请号：US17763752
申请日：2020-09-10
Inventor： Makoto SHINZAKI , Yuichi MATSUMOTO
IPC: G06V10/774 , G06V10/778 , G06V10/26
Abstract: Provided is a method for performing accurate object recognition in a stable manner in consideration of changes in a shooting environment. In such a method, a camera captures an image of a shooting location where an object is to be placed and an object included in an image of the shooting location is recognized utilizing a machine learning model for object recognition. The method further involves: determining necessity of an update operation on the machine learning model for object recognition at a predetermined time; when the update operation is necessary, causing the camera to capture an image of the shooting location where no object is placed to thereby re-acquire a background image for training; and causing the machine learning model to be trained using a composite image of a backgroundless object image and the re-acquired background image for training as training data.
-
公开(公告)号：US20210158101A1
公开(公告)日：2021-05-27
申请号：US17256829
申请日：2019-04-23
Inventor： Makoto SHINZAKI , Daisuke UETA , Yuichi MATSUMOTO
IPC: G06K9/62
Abstract: In generation of training data for image recognition, in order to reduce a user's workload of assigning a label to a captured image, a learning device includes a processor for performing operations to generate training data and a display device, wherein the processor is configured to acquire a captured image from an image capturing device; acquire one or more candidate objects recognized based on an identification model for a recognition target included in the captured image; and display, on the display device, information on the candidate objects as respective label candidates for the captured image.
-
公开(公告)号：US20190147361A1
公开(公告)日：2019-05-16
申请号：US16098023
申请日：2017-12-11
Inventor： Yuichi MATSUMOTO , Masataka SUGIURA
Abstract: Learned model providing system is configured of learned model providing device in which a plurality of learned models are saved in advance and user side device that receives the learned model from learned model providing device. Learned model providing device can select the learned model to be provided from a plurality of learned models saved in learned model database to user side device based on the performance calculated using test data acquired from user side device. Accordingly, it is possible to select and provide the learned model optimal for use by user side device from the plurality of learned models saved in database in advance.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.018 seconds)
