-
Patent Agency Ranking
公开(公告)号：US20190066313A1
公开(公告)日：2019-02-28
申请号：US16171923
申请日：2018-10-26
Inventor： MIN YOUNG KIM , SOTARO TSUKIZAWA
Abstract: An object tracking method includes inputting, into a neural network, two or more chronologically consecutive images, and matching similarity by comparing features extracted by the neural network, namely features of each of the two or more input images, and thereby outputting, as an identification result, identification information and position information about one or more objects depicted in a chronologically later image than a chronologically earlier image, which match one or more objects which are tracking candidates depicted in the chronologically earlier image. The neural network includes two or more identical structures having zero or more fully-connected layers and one or more convolution layers, and shares parameters among corresponding layers across the identical structures.
-
公开(公告)号：US20160260014A1
公开(公告)日：2016-09-08
申请号：US15053642
申请日：2016-02-25
Inventor： REIKO HAGAWA , SOTARO TSUKIZAWA , YASUNORI ISHII
CPC classification number: G06N3/08 , G06K7/1482 , G06K9/4628 , G06K9/6267 , G06K9/6281 , G06K9/6282 , G06N3/02 , G06N3/0454 , G06T2207/20081
Abstract: Learning method includes performing a first process in which a coarse class classifier configured with a first neural network is made to classify a plurality of images given as a set of images each attached with a label indicating a detailed class into a plurality of coarse classes including a plurality of detailed classes and is then made to learn a first feature that is a feature common in each of the coarse classes, and performing a second process in which a detailed class classifier, configured with a second neural network that is the same in terms of layers other than the final layer as but different in terms of the final layer from the first neural network made to perform the learning in the first process, is made to classify the set of images into detailed classes and learn a second feature of each detailed class.
Abstract translation: 学习方法包括执行第一处理，其中配置有第一神经网络的粗类分类器被分类为以图像集合给出的多个图像，每个图像附加有指示详细类别的标签为多个粗类，包括 多个详细类，然后被做成学习作为每个粗类中共同的特征的第一特征，并且执行第二处理，其中配置有第二神经网络的详细类分类器在第 将最终层以外的层作为第一神经网络的最终层而不是第一神经网络，以在第一过程中执行学习进行分类，以将该组图像分类为详细类并学习每个详细类的第二特征 。
-
公开(公告)号：US20170220891A1
公开(公告)日：2017-08-03
申请号：US15485250
申请日：2017-04-12
Inventor： MIN YOUNG KIM , LUCA RIGAZIO , SOTARO TSUKIZAWA , KAZUKI KOZUKA
CPC classification number: G06K9/4628 , G06K9/6223 , G06K9/6255 , G06K9/6256 , G06K9/66 , G06N3/0454 , G06N3/082 , G06N7/005
Abstract: A determination method for determining the structure of a convolutional neural network includes acquiring N filters having the weights trained using a training image group as the initial values, where N is a natural number greater than or equal to 1, and increasing the number of the filters from N to M, where M is a natural number greater than or equal to 2 and is greater than N, by adding a filter obtained by performing a transformation used in image processing fields on at least one of the N filters.
-
4.发明申请公开(公告)号：US20190251383A1
公开(公告)日：2019-08-15
申请号：US16394062
申请日：2019-04-25
Inventor： GREGORY SENAY , SOTARO TSUKIZAWA , MIN YOUNG KIM , LUCA RIGAZIO
Abstract: Inputting an image to a neural network, performing convolution on a current frame included in the image to calculate a current feature map, which is a feature map at a present time, combining a past feature map, which is obtained by performing convolution on a past frame included in the image, and the current feature map, estimating an object candidate area using the combined past feature map and current feature map, estimating positional information and identification information regarding the one or more objects included in the current frame using the combined past feature map and current feature map and the estimated object candidate area, and outputting the positional information and the identification information regarding the one or more objects included in the current frame of the image estimated in the estimating as object detection results are included.
-
5.发明申请公开(公告)号：US20160259995A1
公开(公告)日：2016-09-08
申请号：US15049149
申请日：2016-02-22
Inventor： YASUNORI ISHII , SOTARO TSUKIZAWA , REIKO HAGAWA
CPC classification number: G06K9/6267 , G06K9/46 , G06K9/4628 , G06K9/6256 , G06K9/6274 , G06N3/0454 , G06N3/08
Abstract: An image recognition method includes: receiving an image; acquiring processing result information including values of processing results of convolution processing at positions of a plurality of pixels that constitute the image by performing the convolution processing on the image by using different convolution filters; determining 1 feature for each of the positions of the plurality of pixels on the basis of the values of the processing results of the convolution processing at the positions of the plurality of pixels included in the processing result information and outputting the determined feature for each of the positions of the plurality of pixels; performing recognition processing on the basis of the determined feature for each of the positions of the plurality of pixels; and outputting recognition processing result information obtained by performing the recognition processing.
Abstract translation: 一种图像识别方法，包括：接收图像; 通过使用不同的卷积滤波器对所述图像执行卷积处理来获取包括在构成图像的多个像素的位置处的卷积处理的处理结果的值的处理结果信息; 基于处理结果信息中包括的多个像素的位置处的卷积处理的处理结果的值，确定多个像素中的每个位置的1个特征，并输出所确定的特征 所述多个像素的位置; 基于针对所述多个像素的每个位置的所确定的特征执行识别处理; 并输出通过执行识别处理获得的识别处理结果信息。
-
-
-
-
Search Results
5
records
(took 0.012 seconds)
