-
1.发明公开公开(公告)号：US20240062525A1
公开(公告)日：2024-02-22
申请号：US18270764
申请日：2021-12-03
Applicant: NEC Corporation
Inventor： Tsenjung TAI , Masato TODA , Eiji KANEKO , Kazutoshi SAGI
IPC: G06V10/774 , G06V10/764 , G06V10/77 , G06V10/776
CPC classification number: G06V10/774 , G06V10/764 , G06V10/7715 , G06V10/776 , G06V10/82
Abstract: To provide an efficient training process even in a case where training images having a limited variation of shooting angles are available.
Solution to Problem
A training apparatus (10) comprises: feature extraction section (11) for extracting source domain feature values from input source domain image data and for extracting target domain feature values from input target domain image data; angle conversion section (12) for generating converted source domain feature values by converting the source domain feature values as if the converted source domain feature values are extracted from source domain image data having different angles from the input source domain image data, and generating converted target domain feature values by converting the target domain feature values as if the converted target domain feature values are extracted from target domain image data having different angles from the input target domain image data; class prediction section(13) for predicting source domain class prediction values from the source domain feature values and the converted source domain feature values, and predicting target domain class prediction values from the target domain feature values and the converted target domain feature values; and updating section (14) for updating at least one of (i) the feature extraction section, (ii) the angle conversion section, and (iii) the class prediction section.-
2.发明申请公开(公告)号：US20220172378A1
公开(公告)日：2022-06-02
申请号：US17600288
申请日：2019-04-03
Applicant: NEC Corporation
Inventor： Shreya SHARMA , Masato TODA
IPC: G06T7/246
Abstract: An object is to provide an image processing apparatus capable of appropriately detecting changes of a target object. An image processing apparatus may include: object-driven feature extractor means to extract relevant features of target object from input images; a feature merger means to merge the features extracted from the input images into a merged feature; a change classifier means to predict a probability of each change class based on the merged feature; an object classifier means to predict a probability of each object class based on the extracted features of each image; a multi-loss calculator means to calculate a combined loss from a change classification loss and an object classification loss; and a parameter updater means to update the parameters of the object-driven feature extractor means.
-
公开(公告)号：US20250022164A1
公开(公告)日：2025-01-16
申请号：US18712816
申请日：2021-11-30
Applicant: NEC Corporation
Inventor： Tsenjung TAI , Masato TODA
IPC: G06T7/73 , G06V10/774
Abstract: The feature extraction section extracts source domain structural features from input source domain image data and, extracting target domain structural features from input target domain image data. The rigid transformation section generates transformed structural features by rigid transforming the structural features with reference to conversion parameters. The relighting section generates new view features with reference to the transformed structural features and the conversion parameters in a way that new view features approximate the structural features which are extracted from input image data at the views indicated by the conversion parameters. The class prediction section predicts source domain class predictions from the source domain structural features and the source domain new view features, and predicting target domain class predictions from the target domain structural features and the target domain new view features. The updating section updates at least one of the feature extraction section, the relighting extraction section, and the class prediction extraction section.
-
公开(公告)号：US20210383546A1
公开(公告)日：2021-12-09
申请号：US17281305
申请日：2018-10-04
Applicant: NEC Corporation
Inventor： Eiji KANEKO , Masato TODA
Abstract: A learning device 10 includes a learning means 11 that, by using learning data including at least a set of image areas representing a periodic change of a predetermined object among changes between a plurality of images and a set of image areas representing a change other than the periodic change among the changes between the plurality of images, causes a detector to learn a process for detecting a change other than the periodic change among the changes between the plurality of images.
-
5.发明申请公开(公告)号：US20210312327A1
公开(公告)日：2021-10-07
申请号：US17057916
申请日：2018-05-28
Applicant: NEC Corporation
Inventor： Eiji KANEKO , Takahiro TOIZUMI , Kazutoshi SAGI , Masato TODA
Abstract: Provided is to generate learning data set for learning a cloud correction processing method. A device includes: synthesis unit configured to have a more cloud image and a less cloud image including a same observation object as a set, and receive a first thick cloud area indicating a thick cloud in the more cloud image and a second thick cloud area indicating the thick cloud in the less cloud image; execute a first operation for the first and/or second thick cloud area to generate a first mask in the less cloud image; execute a second operation for the first and/or second thick cloud area to generate a second mask in the more cloud image; and adopt, as learning data, the set including data including the generated first mask and the more cloud image and data including the generated second mask and the less cloud image.
-
Patent Agency Ranking
公开(公告)号：US20210003698A1
公开(公告)日：2021-01-07
申请号：US17040785
申请日：2019-03-18
Applicant: NEC CORPORATION
Inventor： Hisatoshi TORIYA , Masato TODA
Abstract: A radar image processing device includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: determine a search range based on a reference block and a layover direction, the reference block being set as an area of interest in a radar image generated from data obtained by an imaging radar, the layover direction being a direction in which layover occurs in the radar image and being estimated from an incident direction of an electromagnetic wave used for observation by the imaging radar; extract a similar block that is similar to the reference block and included in the search range by searching the search range; and perform filtering processing for reducing speckles generated in the radar image by using the reference block and the extracted similar block.
-
7.发明申请公开(公告)号：US20170308995A1
公开(公告)日：2017-10-26
申请号：US15521345
申请日：2015-11-06
Applicant: NEC Corporation
Inventor： Kenta SENZAKI , Masato TODA
CPC classification number: G06T5/002 , G06T5/10 , G06T7/11 , G06T7/168 , G06T2207/20024 , G06T2207/20064 , G06T2207/20182 , G06T2207/20192 , H04N1/409
Abstract: When performing noise removal of an image signal by applying the background art, there is a case where a filter coefficient that causes an edge constituting the image to become blurred against expectation due to the influence of noise in the image signal is set. The methods to solve this problem include a method for calculating a wide range of image feature values needed for correction of the filter coefficient, but this method has the problem that it requires a significant amount of calculation, thus increasing the calculation cost. To solve the above problem, the present invention is provided with an image signal input means, a wavelet transformation means, a first structure/texture separating means, a texture component degenerating means, a first combining means, an inverse wavelet transformation means, and a second structure/texture separating means. The present invention is further provided with a second texture component degenerating means, a second combining means, and an image signal output means.
-
公开(公告)号：US20220327813A1
公开(公告)日：2022-10-13
申请号：US17641913
申请日：2020-06-17
Inventor： Takashi SHIBATA , Hiroyoshi MIYANO , Eiji KANEKO , Masato TODA , Tsubasa MINEMATSU , Atsushi SHIMADA , Rin-ichiro TANIGUCHI
IPC: G06V10/774 , G06V10/22 , G06V20/70 , G06V10/762 , G06V10/764
Abstract: A learning apparatus (500) according to the present invention includes a detection unit (510) that detects, as a candidate region of a learning target, a region detected by one of first detection processing of detecting an object region from a predetermined image and second detection processing of detecting a change region from background image information and the image, and not detected by the other, an output unit (520) that outputs at least a part of the candidate region as a labeling target, and a learning unit (530) that learns a model for performing the first detection processing or a model for performing the second detection processing by using the labeled candidate region as learning data.
-
9.发明申请公开(公告)号：US20200043136A1
公开(公告)日：2020-02-06
申请号：US16052612
申请日：2018-08-02
Applicant: NEC Corporation
Inventor： Madhuri Mahendra NAGARE , Eiji KANEKO , Masato TODA , Masato TSUKADA
Abstract: An image processing system includes a storage device, and a processor coupled to the storage device and configured to extract, from an input image, an aerosol spectrum across a plurality of wavelength bands of the input image. The storage device contains therein a database storing a plurality of predetermined aerosol spectra, and a plurality of corresponding values associated with an aerosol optical property at the plurality of wavelength bands. The processor is further configured to retrieve, from the database, values associated with the aerosol optical property at the plurality of wavelength bands, the retrieved values corresponding to the extracted aerosol spectrum. The processor is further configured to correct the input image, by using the retrieved values associated with the aerosol optical property at the plurality of wavelength bands, to generate a corrected image.
-
公开(公告)号：US20170352133A1
公开(公告)日：2017-12-07
申请号：US15540330
申请日：2016-01-15
Applicant: NEC Corporation
Inventor： Masato TODA
CPC classification number: G06T5/002 , G06T5/40 , G06T5/50 , G06T2207/10024 , G06T2207/10048 , H04N5/332
Abstract: An image processing device includes: an estimation unit configured to estimate a spectral reflectance ratio at each pixel position in a visible light image and a near infrared image in which an object of photographing is photographed, the spectral reflectance ratio indicating a ratio of a spectral reflectance of a visible light wavelength region to a spectral reflectance of a near infrared light wavelength region; and a restoration unit configured to multiply an estimated spectral reflectance ratio by luminance of the near infrared image at each pixel position and generate a restored visible light image.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.019 seconds)
