-
21.
公开(公告)号:US11748970B2
公开(公告)日:2023-09-05
申请号:US17794110
申请日:2020-11-16
发明人: Qichun Cao , Yaqian Zhao , Gang Dong , Lingyan Liang , Wenfeng Yin
CPC分类号: G06V10/28
摘要: A hardware environment-based data quantization method includes: parsing a model file under a current deep learning framework to obtain intermediate computational graph data and weight data that are independent of a hardware environment; performing calculation on image data in an input data set through a process indicated by an intermediate computational graph to obtain feature map data; separately performing uniform quantization on the weight data and the feature map data of each layer according to a preset linear quantization method, and calculating a weight quantization factor and a feature map quantization factor (S103); combining the weight quantization factor and the feature map quantization factor to obtain a quantization parameter that makes hardware use shift instead of division; and finally, writing the quantization parameter and the quantized weight data to a bin file according to a hardware requirement so as to generate quantized file data (S105).
-
公开(公告)号:US11748881B2
公开(公告)日:2023-09-05
申请号:US17847326
申请日:2022-06-23
发明人: Elad Arbel , Itay Remer , Amir Ben-Dor
IPC分类号: G06T7/00 , G06T7/10 , G06T7/187 , G06T7/11 , G06T7/174 , G06N20/00 , G06F3/0482 , G06F3/0486 , G06N3/08 , G06F18/2431 , G06V10/764 , G06V10/774 , G06V10/80 , G06V10/82 , G06V10/26 , G06V10/28 , G06V20/69 , G06V10/94 , G06V10/24
CPC分类号: G06T7/0012 , G06F3/0482 , G06F3/0486 , G06F18/2431 , G06N3/08 , G06N20/00 , G06T7/0014 , G06T7/10 , G06T7/11 , G06T7/174 , G06T7/187 , G06V10/267 , G06V10/28 , G06V10/764 , G06V10/7753 , G06V10/809 , G06V10/82 , G06V10/945 , G06V20/695 , G06V20/698 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084 , G06T2207/20104 , G06T2207/30024 , G06T2207/30096 , G06V10/247
摘要: Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation and/or implementing instance segmentation based on partial annotations. In various embodiments, a computing system might receive first and second images, the first image comprising a field of view of a biological sample, while the second image comprises labeling of objects of interest in the biological sample. The computing system might encode, using an encoder, the second image to generate third and fourth encoded images (different from each other) that comprise proximity scores or maps. The computing system might train an AI system to predict objects of interest based at least in part on the third and fourth encoded images. The computing system might generate (using regression) and decode (using a decoder) two or more images based on a new image of a biological sample to predict labeling of objects in the new image.
-
23.
公开(公告)号:US20230260162A1
公开(公告)日:2023-08-17
申请号:US18302834
申请日:2023-04-19
申请人: FUJITSU LIMITED
发明人: Tomonori KUBOTA , Takanori NAKAO
摘要: An encoding system includes: a memory; and a processor coupled to the memory and configured to: calculate, for each area, for a first image, a quantization value that has a compression ratio according to a degree of influence on recognition accuracy during recognition processing; set, when setting the quantization value calculated for each area, for each area of a second image that is acquired after the first image, a quantization value that has a compression ratio lower than the compression ratio, for a specific area other than an area that corresponds to an area of an object to be recognized included in the first image; and encode the second image, using the quantization value.
-
公开(公告)号:US11710344B2
公开(公告)日:2023-07-25
申请号:US16859836
申请日:2020-04-27
CPC分类号: G06V40/168 , G06N3/08 , G06V10/28 , G06V10/454 , G06V10/764 , G06V10/82
摘要: A method is presented. The method includes determining a number of landmarks in an image comprising multiple pixels. The method also includes determining a number of channels for the image based on a function of the number of landmarks. The method further includes determining, for each one of the number of channels, a confidence of each pixel of the multiple pixels corresponding to a landmark. The method still further includes identifying the landmark in the image based on the confidence.
-
公开(公告)号:US20230222753A1
公开(公告)日:2023-07-13
申请号:US17928992
申请日:2021-06-14
IPC分类号: G06V10/143 , G06T7/70 , G06V10/28 , G06V10/60
CPC分类号: G06V10/143 , G06T7/70 , G06V10/28 , G06V10/60 , G06T2207/10152
摘要: In a sample observation device, an image acquisition unit 6 acquires a plurality of pieces of image data of a sample in a Y-axis direction, and an image generation unit generates luminance image data on luminance of the sample on the basis of the plurality of pieces of image data, binarizes luminance values of each of the plurality of pieces of image data to generate a plurality of pieces of binarized image data, and generates area image data on an existing area of the sample on the basis of the plurality of pieces of binarized image data.
-
公开(公告)号:US11694456B2
公开(公告)日:2023-07-04
申请号:US17348617
申请日:2021-06-15
申请人: Kofax, Inc.
发明人: Jiyong Ma , Stephen M. Thompson , Jan W. Amtrup
IPC分类号: G06K9/00 , G06V30/146 , G06T7/90 , G06T7/13 , G06T7/194 , G06T7/70 , G06T7/12 , G06V10/44 , G06V20/40 , G06F18/20 , G06F18/21 , G06V30/162 , G06V30/18 , G06V30/19 , G06V10/762 , G06V10/80 , G06V30/413 , G06T7/11 , G06N20/00 , G06N7/00 , G06T7/00 , G06V30/224 , G06V30/10 , G06V10/28
CPC分类号: G06V30/147 , G06F18/217 , G06F18/285 , G06N7/00 , G06N20/00 , G06T7/0002 , G06T7/11 , G06T7/12 , G06T7/13 , G06T7/194 , G06T7/70 , G06T7/90 , G06V10/44 , G06V10/762 , G06V10/809 , G06V20/40 , G06V30/162 , G06V30/18105 , G06V30/19147 , G06V30/19173 , G06V30/413 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/30176 , G06V10/28 , G06V30/10 , G06V30/2253
摘要: Systems, methods and computer program products for detecting objects using a multi-detector are disclosed, according to various embodiments. In one aspect, a computer-implemented method includes defining an analysis profile comprising an initial number of analysis cycles dedicated to each of a plurality of detectors, where each detector is independently configured to detect objects according to a unique set of analysis parameters and/or a unique detector algorithm. The method also includes: receiving digital video data that depicts at least one object; analyzing the digital video data using some or all of the detectors in accordance with the analysis profile, where the analyzing produces an analysis result for each detector used in the analysis. Further, the method includes updating the analysis profile by adjusting the number of analysis cycles dedicated to at least one of the detectors based on the analysis results.
-
27.
公开(公告)号:US20230196711A1
公开(公告)日:2023-06-22
申请号:US17936436
申请日:2022-09-29
申请人: Shinya Itoh , Hiroyuki Sakuyama
发明人: Shinya Itoh , Hiroyuki Sakuyama
IPC分类号: G06V10/28 , G06T3/40 , G06V10/764 , G06V10/82
CPC分类号: G06V10/28 , G06T3/40 , G06V10/764 , G06V10/82
摘要: An image forming apparatus includes circuitry. The circuitry generates a binary image having area gradation or a scaled image having area gradation from an image read by a scanner. The circuitry outputs classification of the binary image or the scaled image according to a neural network model learned in advance.
-
公开(公告)号:US20230162323A1
公开(公告)日:2023-05-25
申请号:US18151588
申请日:2023-01-09
CPC分类号: G06T3/4053 , G06T7/0002 , G06V10/28 , G06T2207/10016 , G06T2207/20084 , G06T2207/30168
摘要: This application provides an image frame super-resolution implementation method and apparatus, the method includes: obtaining super-resolution reference information including a quantization parameter and an image quality score set, and the image quality score set includes image quality scores of a plurality of image frames; selecting M image frames from the plurality of image frames based on the image quality score set, where M is greater than or equal to 1; obtaining a video super-resolution network corresponding to the quantization parameter, where the video super-resolution network has a super-resolution function; and inputting the M image frames and a first image frame into the video super-resolution network, where the video super-resolution network is configured to perform super-resolution processing on the first image frame based on the M image frames to obtain a second image frame, and resolution of the second image frame is higher than resolution of the first image frame.
-
公开(公告)号:US20230144795A1
公开(公告)日:2023-05-11
申请号:US18089739
申请日:2022-12-28
发明人: Zhiyuan WANG , Liang FENG , Guangzhi LIU , Yundai CHEN
CPC分类号: G06T7/0012 , G06T15/00 , G06T5/40 , G06V10/28 , G06T2207/10081 , G06T2207/30012 , G06T2207/30048 , G06T2207/30101 , G06T2207/30172
摘要: The present application provides a method and system for acquiring centerline of aorta based on CT sequence images. The method comprises: acquiring three-dimensional data of CT sequence images; acquiring a gravity center of heart and a gravity center of spine based on the three-dimensional data; filtering impurity data from the three-dimensional data of CT sequence images to obtain an image containing left atrium, left ventricle and without interfering coronary artery tree; layered slicing to obtain a group of binarized images; obtaining a circle center and an radius from each layer of slice in the group of binarized images, to generate a point list and an radius list; and mapping one or more pixel points in the point list and the radius list to the image to obtain a centerline of aorta.
-
公开(公告)号:US12111381B2
公开(公告)日:2024-10-08
申请号:US17655780
申请日:2022-03-21
申请人: NVIDIA CORPORATION
发明人: Niharika Arora
IPC分类号: G01S13/04 , B60W40/10 , B60W40/12 , B60W60/00 , G01S7/00 , G01S7/40 , G01S13/86 , G01S13/89 , G01S13/931 , G01S17/04 , G01S17/931 , G06T7/73 , G06V10/26 , G06V10/28
CPC分类号: G01S13/04 , B60W40/10 , B60W40/12 , B60W60/001 , G01S7/003 , G01S7/40 , G01S13/86 , G01S13/89 , G01S13/931 , G01S17/04 , G01S17/931 , G06T7/73 , G06V10/26 , G06V10/28 , B60W2420/408 , G01S2013/9316 , G06T2207/10044 , G06T2207/30252
摘要: One or more embodiments of the present disclosure may relate to communicating RADAR (RAdio Detection And Ranging) data to a distributed map system that is configured to generate map data based on the RADAR data. In these or other embodiments, certain compression operations may be performed on the RADAR data to reduce the amount of data that is communicated from the ego-machines to the map system.
-
-
-
-
-
-
-
-
-