-
公开(公告)号:US20240046916A1
公开(公告)日:2024-02-08
申请号:US18491890
申请日:2023-10-23
发明人: Manda MILLER , Kirk GOLDMAN , Jon A. HOFFMAN , John PISTONE , Dimple NANWANI , Theodore CLARK
IPC分类号: G10L13/027
CPC分类号: G10L13/027 , G06V10/10
摘要: The present disclosure provides techniques for graphics translation. A subset of a plurality of natural language image descriptions for an image of a product is received. A set of shared natural language descriptors is identified in the subset of the plurality of natural language image descriptions. The set of shared natural language descriptors is aggregated, and a description for the first image is generated based on the aggregated set of shared natural language image descriptions.
-
公开(公告)号:US11895409B2
公开(公告)日:2024-02-06
申请号:US17158917
申请日:2021-01-26
发明人: Eran Pinhasov , Scott Cheng , Eran Scharam , Anatoly Gurevich
IPC分类号: H04N23/61 , H04N23/80 , G06V20/10 , G06V20/00 , H04N1/60 , G06V10/10 , H04N23/66 , H04N23/70 , H04N101/00 , H04N23/88
CPC分类号: H04N23/80 , G06V10/10 , G06V20/10 , G06V20/35 , H04N1/6072 , H04N1/6083 , H04N23/61 , H04N23/66 , H04N23/70 , H04N23/88 , H04N2101/00
摘要: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.
-
公开(公告)号:US11832365B2
公开(公告)日:2023-11-28
申请号:US17738245
申请日:2022-05-06
发明人: Rhodes B. Baker , Craig Alan Casey , Galen Edgar Knode , Brent Protzman , Thomas M. Shearer , James P. Steiner
IPC分类号: G06T5/20 , G06T5/50 , G06T7/11 , G06T7/246 , G06V10/10 , G06V10/141 , G06V10/22 , G06V20/52 , H05B47/105 , H05B47/19 , H05B45/20 , H05B47/11 , H05B47/115 , H05B47/125 , H05B47/13 , H05B45/12 , H05B45/10 , H04N23/62 , H04N23/661 , H04N23/667 , G01V8/20 , H04N1/40 , G05B15/02 , H04N7/18 , F24F120/10 , F24F130/30 , F24F11/88 , F24F11/56 , F24F110/10
CPC分类号: H05B47/105 , G01V8/20 , G05B15/02 , G06T5/20 , G06T5/50 , G06T7/11 , G06T7/246 , G06V10/10 , G06V10/141 , G06V10/235 , G06V20/52 , H04N1/40012 , H04N23/62 , H04N23/661 , H04N23/667 , H05B45/10 , H05B45/12 , H05B45/20 , H05B47/11 , H05B47/115 , H05B47/125 , H05B47/13 , H05B47/19 , F24F11/56 , F24F11/88 , F24F2110/10 , F24F2120/10 , F24F2130/30 , G06T2207/10004 , G06T2207/10016 , G06T2207/10024 , G06T2207/10048 , G06T2207/20224 , G06T2207/30196 , G06T2207/30232 , H04N7/185 , H04N2201/0084
摘要: A visible light sensor (VLS) may be configured to sense environmental characteristics using images of a space. The VLS may be controlled in one or more modes, including a daylight glare sensor mode, a daylighting sensor mode, a color sensor mode, and/or an occupancy/vacancy sensor mode. In the daylight glare sensor mode, the VLS may be configured to decrease or eliminate glares. In the daylighting sensor mode and/or color sensor mode, the VLS may be configured to provide a preferred amount of light and color temperature, respectively, within the space. In the occupancy/vacancy sensor mode, the VLS may be configured to detect an occupancy/vacancy condition within the space and adjust one or more control devices according to the occupation or vacancy of the space. The visible light sensor may be configured to protect the privacy of users within the space via software, a removable module, and/or a special sensor.
-
公开(公告)号:US11816520B2
公开(公告)日:2023-11-14
申请号:US17625536
申请日:2020-07-09
发明人: Jung Ji Kwon , Young Ho Kim , Jung Nyun Kim , Seok Hyun Nam , Won Young Kim , Seon U. Bang
CPC分类号: G06K19/06046 , G06V10/10 , H01B7/36 , G06K2019/06253
摘要: A cable comprises: a cable core; and a cable sheath layer formed on the outside of the cable core, wherein the cable sheath layer has, on the outer surface thereof, a pattern corresponding to a binary code. A recognition rate is improved, and a problem of the productivity of the cable being reduced may be prevented by adjusting the widths of the pattern, corresponding to the binary code printed on the cable, in the vertical direction and the horizontal direction, and a plurality of patterns corresponding to the binary code printed on the cable are provided to prevent, even when the cable is buried in the ground or contacts a facility and a pattern corresponding to some binary patterns is not exposed, a pattern corresponding to the other binary patterns from being exposed and unrecognizable.
-
公开(公告)号:US11763113B2
公开(公告)日:2023-09-19
申请号:US17692492
申请日:2022-03-11
申请人: Digimarc Corporation
IPC分类号: G06K7/10 , G06Q10/087 , G06Q20/20 , G06Q30/00 , G06V10/10 , G06V10/147 , G06V20/20 , G06V30/224 , G07G1/00 , G06K7/14 , G06V10/40 , G06F3/147 , G06Q10/08 , G06Q30/0601
CPC分类号: G06K7/10861 , G06K7/1456 , G06Q10/087 , G06Q20/201 , G06Q20/208 , G06Q30/00 , G06V10/10 , G06V10/147 , G06V20/20 , G06V30/224 , G07G1/0045 , G06F3/147 , G06Q10/08 , G06Q30/0601 , G06T2201/0065 , G06V10/40
摘要: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.
-
公开(公告)号:US11749028B2
公开(公告)日:2023-09-05
申请号:US17175443
申请日:2021-02-12
发明人: Yuki Totori , Tomohiro Taguchi , Hideta Nishizawa , Shinya Nakano , Shogo Fujiwara , Hiroaki Kubo
摘要: An electronic device includes an acquiring unit configured to acquire a positional relationship between a subject and the electronic device, a normalization unit configured to normalize posture information of the subject based on a positional relationship acquired by the acquiring unit and a controlling unit configured to perform control to perform predetermined notification in a case where posture information of the subject that is normalized satisfies a predetermined condition, and control not to perform the predetermined notification in a case where posture information of the subject that is normalized is not the predetermined posture.
-
公开(公告)号:US11743418B2
公开(公告)日:2023-08-29
申请号:US17178164
申请日:2021-02-17
发明人: Marius Buibas , John Quinn
IPC分类号: G06T7/50 , G06T7/62 , G06T17/00 , G06F18/22 , G06F18/24 , H04N23/56 , H04N23/90 , G06V10/82 , H04N5/272 , G06N5/04 , G06F18/214 , H04N23/74 , G06V10/56 , G06V10/10 , G06V10/764 , G06V10/774 , G06V20/64 , G06T7/70
CPC分类号: H04N5/272 , G06F18/214 , G06F18/22 , G06F18/24 , G06N5/04 , G06T7/50 , G06T7/62 , G06T7/70 , G06T17/00 , G06V10/10 , G06V10/56 , G06V10/764 , G06V10/774 , G06V10/82 , G06V20/64 , H04N23/56 , H04N23/74 , H04N23/90 , G06T2207/20081
摘要: System that facilitates rapid onboarding of an autonomous (cashier-less) store by capturing images of the store's items from multiple angles, with varying background colors, and that builds a classifier training dataset from these images. Background surfaces may for example be coated with retroreflective tape or film, and variable-color incident light sources may generate the desired background colors. Embodiments may automatically rotate or otherwise reorient the item placed in the onboarding system, so that a relatively small number of cameras can capture views from multiple angles. When an item is placed in the system, a fully automated process may generate a sequence of item orientations and background colors, and may capture and process images from the cameras to create training images. Images of the item from multiple angles, under varying lighting conditions, may be captured without requiring an operator to move or reorient the item.
-
公开(公告)号:US11729488B2
公开(公告)日:2023-08-15
申请号:US17876988
申请日:2022-07-29
发明人: Kenji Ouchi
CPC分类号: H04N23/61 , G06N3/08 , G06V10/10 , H04N23/64 , H04N23/651 , H04N23/695
摘要: The present invention eliminates meaningless searching for an object, and increases the probability that an image the user likes can be obtained. An image capturing apparatus comprises an image capturing device configured to capture an object image, an object detection unit configured to detect an object from image data captured by the image capturing device, a state detection unit configured to detect information pertaining to a state in which the image capturing apparatus is being held, and a control unit configured to control a range in which the object detection unit searches for an object, on the basis of state information of the image capturing apparatus detected by the state detection unit.
-
公开(公告)号:US11704904B2
公开(公告)日:2023-07-18
申请号:US17269544
申请日:2019-09-02
申请人: Sony Corporation
发明人: Keitaro Yamamoto , Suguru Aoki , Ryuta Satoh , Ryoji Eki
IPC分类号: G06V20/10 , G06V10/10 , G06V20/56 , G06F18/214 , G06F18/21 , H04N25/75 , H04N23/61 , H04N25/50 , H04N25/58 , H04N25/79 , H04N25/441 , H04N25/445 , G06V10/25
CPC分类号: G06V20/10 , G06F18/214 , G06F18/217 , G06V10/10 , G06V10/25 , G06V20/56 , H04N23/61 , H04N25/441 , H04N25/445 , H04N25/50 , H04N25/58 , H04N25/75 , H04N25/79
摘要: An imaging apparatus according to an embodiment includes: an imaging unit having a pixel region in which a plurality of pixels is arranged; a readout controller that controls readout of pixel signals from pixels included in the pixel region; a first unit-of-readout setting unit that sets a unit of readout as a part of the pixel region, for which the readout controller performs readout of the pixel signal; an image output unit that outputs a first image based on the pixel signal read out from the unit of readout to a subsequent stage; a second unit-of-readout controller that controls the unit of readout in which the readout controller performs readout of the pixel signal; and a recognition unit that learns training data for each of the units of readout, performs a recognition process on the pixel signal for each of the units of readout, and outputs a recognition result.
-
20.
公开(公告)号:US20230194426A1
公开(公告)日:2023-06-22
申请号:US18154405
申请日:2023-01-13
发明人: Gary Skinner , Geraint Evans , Stanley Hong
IPC分类号: G01N21/64 , B01L3/00 , G01N21/05 , G02B21/06 , G02B21/16 , G02B21/36 , G02B27/42 , G06V10/10
CPC分类号: G01N21/6452 , B01L3/5085 , G01N21/05 , G02B21/06 , G02B21/16 , G02B21/365 , G02B27/425 , G06V10/10 , B01L2300/0654 , B01L2300/0663 , B01L2300/0893 , B01L2300/0896
摘要: Techniques are described for reducing the number of angles needed in structured illumination imaging of biological samples through the use of patterned flowcells, where nanowells of the patterned flowcells are arranged in, e.g., a square array, or an asymmetrical array. Accordingly, the number of images needed to resolve details of the biological samples is reduced. Techniques are also described for combining structured illumination imaging with line scanning using the patterned flowcells.
-
-
-
-
-
-
-
-
-