专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20230128420A1 RAPID IMAGE STITCHING WITH PREVIEW CAPABILITIES 有权
公开(公告)号：US20230128420A1
公开(公告)日：2023-04-27
申请号：US18048695
申请日：2022-10-21
申请人： Translucence Biosystems, Inc.
发明人： Ricardo R Azevedo , Jack Zeitoun , Anthony Reksoatmodjo
IPC分类号： G06T5/50 , G06T1/20 , G06T3/40
摘要： Multiple digital image tiles are stitched together into a single digital image through use of reactive alpha mask generation, allowing for efficient tile rearrangement and preview capabilities. The present invention features a method for stitching a first image tile and a second image tile to display a preview of a stitched image through use of alpha masking. The method may comprise arranging the first image tile and the second image tile into an initial image display, aligning the first image tile and the second image tile of the initial image display such that shared pixel regions of the first image tile overlap those of the second image tile, stitching the aligned first image tile to the aligned second image tile, applying the alpha blending mask of the stitched image to the initial image display, and displaying the initial image display with the alpha blending mask applied.

12. 发明授权

US11636708B2 Face detection in spherical images 有权
公开(公告)号：US11636708B2
公开(公告)日：2023-04-25
申请号：US17420741
申请日：2020-01-02
申请人： GoPro, Inc.
发明人： Thomas Armel Derbanne , Bruno César Douady , Maxim Karpushin
IPC分类号： G06V40/16 , G06T3/40 , H04N13/156 , G06V10/10 , G06V10/147 , G06T3/00 , H04N5/232
摘要： A face located along a stitch line in a spherical image is detected by rendering views of regions of the spherical image along the stitch line. The spherical image may be produced by combining first and second images. A first view of a projection of the spherical image is rendered. A scaling factor for rendering a second view of the projection is determined based characteristics of the first portion of the face. The second view is then rendered according to the scaling factor. The use of the scaling factor to render the second view causes a change in the depiction of the second portion of the face. For example, the scaling factor can indicate to change the resolution or expected size of the second portion of the face when rendering the second view. A face is then detected within the spherical image based on the rendered first and second views.

13. 发明授权

US11636685B1 Multi-resolution top-down segmentation 有权
公开(公告)号：US11636685B1
公开(公告)日：2023-04-25
申请号：US17127196
申请日：2020-12-18
申请人： Zoox, Inc.
发明人： Stanley L. Volta , Allan Zelener
IPC分类号： G06V20/56 , G06T3/40 , G06T7/11 , G05D1/00 , G05D1/02 , G06K9/62
摘要： Techniques for segmenting sensor data are discussed herein. Data can be represented in individual levels in a multi-resolution voxel space. A first level can correspond to a first region of an environment and a second level can correspond to a second region of an environment that is a subset of the first region. In some examples, the levels can comprise a same number of voxels, such that the first level covers a large, low-resolution region, while the second level covers a smaller, higher-resolution region, though more levels are contemplated. Operations may include analyzing sensor data represented in the voxel space from a perspective, such as a top-down perspective. From this perspective, techniques may generate masks that represent objects in the voxel space. Additionally, techniques may generate segmentation data to verify and/or generate the masks, or otherwise cluster the sensor data.

14. 发明授权

US11636595B2 Bovine embryo evaluation using AI/ML analysis of real-time frame speed video for predicting female-sex offspring 有权
公开(公告)号：US11636595B2
公开(公告)日：2023-04-25
申请号：US17903660
申请日：2022-09-06
申请人： Emgenisys, Inc.
发明人： Cara Elizabeth Wessels Wells , Russell Killingsworth
IPC分类号： G06K9/00 , G06T7/00 , G06T3/40 , G06T7/20 , G06N3/02 , G16H30/20 , G16H50/20 , H04N5/77 , G16H50/30 , G16H30/40
摘要： A computer-implemented system and method for predicting female sex bovine offspring to result from a bovine embryo by processing video image data of the embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data.

15. 发明申请

US20230124618A1 IMAGE PROCESSING DEVICE INCLUDING NEURAL NETWORK PROCESSOR AND OPERATING METHOD THEREOF 有权
公开(公告)号：US20230124618A1
公开(公告)日：2023-04-20
申请号：US18068113
申请日：2022-12-19
申请人： Samsung Electronics Co., Ltd.
发明人： Irina KIM , Seongwook SONG
IPC分类号： H04N25/13 , G06T3/40 , H04N23/80 , H04N23/65 , H04N23/667
摘要： An image processing device includes: an image sensor configured to generate first image data by using a color filter array; and processing circuitry configured to select a processing mode from a plurality of processing modes for the first image data, the selecting being based on information about the first image data; generate second image data by reconstructing the first image data using a neural network processor based on the processing mode; and generate third image data by post-processing the second image data apart from the neural network processor based on the processing mode.

16. 发明申请

US20230124391A1 PROCESSING PATHOLOGY IMAGES 有权
公开(公告)号：US20230124391A1
公开(公告)日：2023-04-20
申请号：US18067507
申请日：2022-12-16
申请人： AIFORIA TECHNOLOGIES OYJ
发明人： Juha Reunanen
IPC分类号： G06T7/00 , G06T3/40
摘要： A method of facilitating processing of pathology images involves receiving pathology image data representing a pathology image having a plurality of image regions, wherein the pathology image data includes, for each of the plurality of image regions, a respective plurality of representations of the image region including a first representation and a second representation, the second representation having a smaller data size than the first representation. The method involves, for each of the plurality of image regions: determining, based at least in part on the first representation of the image region, a first set of image properties, determining whether the first set of image properties meets first image property criteria, and, if the first set of image properties meets the first image property criteria, producing signals for causing the second representation to be used in place of the first representation. Other methods, systems, and computer-readable media are disclosed.

17. 发明申请

US20230124329A1 Method to Generate Additional Level of Detail When Zooming In On an Image 有权
公开(公告)号：US20230124329A1
公开(公告)日：2023-04-20
申请号：US17977616
申请日：2022-10-31
申请人： Comcast Cable Communications, LLC
发明人： Michael Chen
IPC分类号： G06T3/40 , G06T11/00
摘要： A viewer may zoom in on an image to see a portion of the image. The image may be analyzed to determine if zoom enhancement is necessary. The zoomed region may be matched to a replacement texture. The replacement texture may be used to enhance the image by replacing some or all of the image data.

18. 发明申请

US20230124286A1 SYSTEMS AND METHODS FOR DIGITAL IMAGING USING COMPUTATIONAL PIXEL IMAGERS WITH MULTIPLE IN-PIXEL COUNTERS 有权
公开(公告)号：US20230124286A1
公开(公告)日：2023-04-20
申请号：US18083794
申请日：2022-12-19
申请人： Anduril Industries, Inc.
发明人： Michael W. Kelly , Curtis Colonero , Christopher David , Joseph Bari , William Ross
IPC分类号： H04N23/741 , G06T7/194 , G06T3/40 , G06T7/60 , H04N23/11 , H04N23/51 , H04N23/56 , H04N23/71 , H04N23/74 , H04N23/957 , H04N25/75 , H04N25/767 , H04N25/772
摘要： A stereo imaging system includes an optical assembly and a computational pixel imager (CPI) having a plurality of pixels. Each pixel includes a light sensor and counters that convert a photocurrent from the light sensor to a digital signal. The optical assembly, which directs light from a light field to the CPI, includes an optical field combiner and first and second primary lens assemblies, which are configured to receive first and second portions of the light from the light field, respectively, and to direct the first and second portions of the light to the optical field combiner. The optical field combiner includes a modulator configured to modulate the first and second portions of the light and to direct modulated first and second portions of the light onto the CPI. The counters are configured to perform digital signal processing on the digital signal.

19. 发明授权

US11631275B2 Image processing method and apparatus, terminal, and computer-readable storage medium 有权
公开(公告)号：US11631275B2
公开(公告)日：2023-04-18
申请号：US17006071
申请日：2020-08-28
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： Wei Xiong , Fei Huang
IPC分类号： G06V40/16 , G06K9/62 , G06T3/40
摘要： Embodiments of the present disclosure disclose an image processing method and apparatus, a terminal, and a computer-readable storage medium, that are generally related to the field of computer technologies. The method can include obtaining a trained pixel classification model. The pixel classification model can be used for determining a classification identifier of each pixel in any image with the classification identifier including a head classification identifier. The head classification identifier can be used for indicating that a corresponding pixel is located in a head region. The method can further include classifying each pixel in the target image based on the pixel classification model to obtain a classification identifier of the pixel in the target image, and determining a head region in the target image according to pixels whose classification identifiers are a head classification identifier and editing the head region.

20. 发明授权

US11631163B2 Mobile data augmentation engine for personalized on-device deep learning system 有权
公开(公告)号：US11631163B2
公开(公告)日：2023-04-18
申请号：US16946989
申请日：2020-07-14
申请人： Samsung Electronics Co., Ltd.
发明人： Chenchi Luo , Yingmao Li , Youngjun Yoo
IPC分类号： G06N3/04 , G06T5/50 , G06T5/00 , G06T3/40
摘要： A method includes processing, using at least one processor of an electronic device, each of multiple images using a photometric augmentation engine, where the photometric augmentation engine performs one or more photometric augmentation operations. The method also includes applying, using the at least one processor, multiple layers of a convolutional neural network to each of the images, where each layer generates a corresponding feature map. The method further includes processing, using the at least one processor, at least one of the feature maps using at least one feature augmentation engine between consecutive layers of the multiple layers, where the at least one feature augmentation engine performs one or more feature augmentation operations.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式