-
1.
公开(公告)号:US20240153260A1
公开(公告)日:2024-05-09
申请号:US18280381
申请日:2021-03-09
Applicant: NEC Corporation
Inventor: Florian Beye , Yusuke Shinohara , Hayato Itsumi , Charvi Vitthal , Koichi Nihei , Takanori Iwai
IPC: G06V10/82 , G06V10/776
CPC classification number: G06V10/82 , G06V10/776
Abstract: A model learning device determines a first machine learning model so as to further increase a combined loss function obtained by combining: a first loss function indicating the level of change in the reliability of a second image feature in a feature region of a reconstructed image, from the reliability of a first image feature in a feature region of the original image; and a second loss function indicating the level of recognition error. In addition, the model learning device: determines, so as to further reduce the combined loss function, respective parameter sets for a second machine learning model used in the generation of compressed data, and a third machine learning model used in the generation of the reconstructed image from the compressed data; and determines a parameter set for the fourth machine learning model in common with that for the first machine learning model.
-
2.
公开(公告)号:US20240062507A1
公开(公告)日:2024-02-22
申请号:US18271642
申请日:2021-01-15
Applicant: NEC Corporation
Inventor: Florian Beye , Yusuke Shinohara , Hayato Itsumi , Koichi Nihei , Charvi Vitthal , Takanori Iwai
Abstract: An information processing device receives communication data based on feature data that indicates a feature of presented content of target data; restores the feature data on the basis of the received communication data; restores the target data on the basis of the restored feature data; performs a recognition process on the presented content of the target data on the basis of the restored feature data; and outputs information that indicates the presented content of the restored target data and a recognition result of the recognition process.
-
公开(公告)号:US20250166345A1
公开(公告)日:2025-05-22
申请号:US18841409
申请日:2022-03-02
Applicant: NEC Corporation
Inventor: Florian Beye , Hayato Itsumi , Charvi Vitthal , Koichi Nihei
IPC: G06V10/72 , G06V10/77 , G06V10/776 , G06V10/82 , H04N19/132 , H04N19/17 , H04N19/42
Abstract: A parameter set of a first machine learning model is determined such that a first loss function becomes larger. The first loss function indicates a degree of variation from a conditional confidence of a first image feature conditional on a third image feature to a conditional confidence of a second image feature conditional on the third image feature. The third image feature is an image feature for recognition of a subject extracted from an original image. The first image feature is discriminated in a specific region of the original image by using a first machine learning model. A parameter set of each of the second machine learning model and the third machine learning model are determined such that a second loss function becomes smaller.
-
公开(公告)号:US12087048B2
公开(公告)日:2024-09-10
申请号:US17765512
申请日:2019-10-07
Applicant: NEC Corporation
Inventor: Hayato Itsumi , Takanori Iwai , Florian Beye , Yusuke Shinohara
CPC classification number: G06V10/95 , G06T7/12 , G06V10/776 , G06V10/82 , G06V20/49 , G06V30/1916
Abstract: According to the present disclosure, a video analysis method and a video analysis system in which video analysis accuracy at a cloud server and an edge is improved is provided. The video analysis method includes a first image analysis step of analyzing an input image frame on the edge side, a difference value estimation step of estimating a difference value between an evaluation value of an analysis result in the first image analysis step and an evaluation value of an analysis result being predicted when the input image frame is analyzed by the cloud server, and a filtering step of determining whether to transmit the input image frame to the cloud server, based on the difference value.
-
公开(公告)号:US11470248B2
公开(公告)日:2022-10-11
申请号:US17131002
申请日:2020-12-22
Applicant: NEC CORPORATION
Inventor: Yusuke Shinohara , Takanori Iwai , Hayato Itsumi , Florian Beye
IPC: H04N5/232 , H04N7/18 , G06N20/00 , H04N19/103 , G06V20/52
Abstract: A data compression apparatus includes: a compression unit that performs a compression process on output data that is sequentially outputted as time series data by a monitoring apparatus for monitoring a monitoring target range; an output unit that outputs the output data on which the compression process is performed, to a data processing apparatus that performs an object detection process for detecting an object that exists in the monitoring target range by using the output data; and a setting unit that sets a compression ratio used in the compression unit, on the basis of an accuracy information indicating a relationship between a compression ratio at which the output data is compressed and a detection accuracy of the object by the object detection process performed by using the output data compressed at the compression ratio.
-
公开(公告)号:US11620812B2
公开(公告)日:2023-04-04
申请号:US17131045
申请日:2020-12-22
Applicant: NEC CORPORATION
Inventor: Hayato Itsumi , Florian Beye , Yusuke Shinohara , Takanori Iwai
IPC: G06V10/764 , G06V10/98 , G06V10/96 , G06V10/82
Abstract: The image analysis apparatus includes: a first analysis unit that analyzes image frames by using a first image analysis model; a second analysis unit that can analyze the image frames by using a second image analysis model an analysis accuracy of which is lower; a storage unit that stores therein analyzed frames, which are already analyzed by using the first and second image analysis models, in association with an evaluation value for evaluating a result of an analysis performed with the second image analysis model; an extraction unit that extracts an analyzed frame that satisfies an extraction condition based on the evaluation value; and an update unit that updates the second image analysis model by using a result of an analysis performed with the first image analysis model on the extracted analyzed frame, and a result of an analysis performed with the first image analysis model on a new frame.
-
公开(公告)号:US10230581B2
公开(公告)日:2019-03-12
申请号:US15117179
申请日:2015-02-05
Applicant: NEC Corporation
Inventor: Hayato Itsumi
IPC: H04L12/24 , H04L12/46 , H04L12/715
Abstract: A management method and apparatus which allows easy management of virtual network function deployment on a network are provided. A network management apparatus generates an extended topology in which a virtual network function that can be deployed on a server is added as an extended node ((VNF(A), VNF(B)) to a topology of the network; and displays an optimum path (RP1, RP2, RP3) in the extended topology on display means (400b) when a requirement of at least one virtual network function and endpoint nodes involved in the requirement are input through an input means (401, 402), wherein the optimum path is obtained based on network resource information of the network and computing resource information of servers on which at least one virtual network function can be deployed.
-
8.
公开(公告)号:US09904566B2
公开(公告)日:2018-02-27
申请号:US14392305
申请日:2014-06-26
Applicant: NEC Corporation
Inventor: Hayato Itsumi , Yasunobu Chiba , Yusuke Shinohara
CPC classification number: G06F9/45558 , G06F9/5083 , G06F2009/4557 , G06F2009/45595 , G06F2209/5019 , H04L67/101
Abstract: An apparatus includes an input unit that receives a requested resource, and a VM arrangement destination computation unit that predicts traffic volume flowing through a network with the physical machines connected thereto in a case wherein the virtual machine is arranged on the physical machine that conform to a condition specified by the requested resource, and based on the predicted traffic volume, and selects the physical machine that balances a link utilization of the network as an arrangement destination of the virtual machine.
-
9.
公开(公告)号:US12283110B2
公开(公告)日:2025-04-22
申请号:US18028486
申请日:2020-10-05
Applicant: NEC Corporation
Inventor: Hayato Itsumi , Yusuke Shinohara , Koichi Nihei , Takanori Iwai , Florian Beye , Charvi Vitthal
Abstract: An information processing device includes: an image acquisition unit configured to acquire an image captured by an imaging unit mounted on a vehicle; a target detection unit configured to detect a target region including a target in the acquired image; a classification identification unit configured to identify classification including a type of the detected target and a size of the detected target region; and a region determination unit configured to determine a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region.
-
公开(公告)号:US20240331385A1
公开(公告)日:2024-10-03
申请号:US18291374
申请日:2021-07-29
Applicant: NEC Corporation
Inventor: Hayato Itsumi , Koichi Nihei , Yusuke Shinohara , Takao Onomura , Yutaka Takei
Abstract: A state analysis unit analyzes the state of each of a plurality of monitoring targets based on sensor data received from the plurality of monitoring targets, and determines whether or not a predetermined event has occurred in each of the monitoring targets. A surveillant allocation unit determines one of the plurality of surveillants who is responsible for work of monitoring the monitoring target where it has been determined that the predetermined event has occurred based on the predetermined event that has occurred and a load index indicating the monitoring work by the surveillant.
-
-
-
-
-
-
-
-
-