公开(公告)号：US11734783B2

公开(公告)日：2023-08-22

申请号：US16713743

申请日：2019-12-13

Applicant: Tata Consultancy Services Limited

Inventor： Prasant Kumar Misra ,  Arunchandar Vasan ,  Krishna Kumar Sunil Komdam ,  Anand Sivasubramaniam ,  Alok Ranjan

IPC: G06K9/00 ,  G06K9/62 ,  G06Q50/30 ,  G06V20/58 ,  G06V20/10 ,  G06F18/23 ,  G06F18/214

CPC classification number: G06Q50/30 ,  G06F18/214 ,  G06F18/23 ,  G06V20/10 ,  G06V20/582 ,  G06V20/584 ,  G06V2201/07 ,  G06V2201/08 ,  G06V2201/10

Abstract: This disclosure relates generally to method and system for detecting on-street parking violations. The method include capturing, by using an media capturing device embodied in an electronic device mounted in a vehicle, a video stream of a scene during a trip of the vehicle. The video stream is processed at the electronic device to identify target objects such as no-parking signage and vehicles parked in the vicinity thereof. A meta-information associated with the target objects is stored in form of a short-term historian in a repository associated with the electronic device. The absolute locations of the target objects are determined and the historian is updated with the values of the absolute locations. A set of unique target objects is determined from amongst the target objects and a meta-information associated with the unique objects is sent to a cloud server for determining parking violations.

公开(公告)号：US20230252183A1

公开(公告)日：2023-08-10

申请号：US17922725

申请日：2021-03-25

Applicant: SONY GROUP CORPORATION

Inventor： CHIE YAMADA ,  NORIKO TOTSUKA ,  HIROAKI OGAWA ,  YASUHARU ASANO ,  AKIRA TAKAHASHI ,  CHIKA MYOGA ,  MASANOBU NAKAMURA ,  KANA NISHIKAWA ,  MASAHIRO YAMAMOTO ,  MICHAEL HENTSCHEL

IPC: G06F21/62 ,  G06V10/25 ,  G06V10/74 ,  G06V10/75 ,  G06V40/16 ,  G06V10/774 ,  G06T11/00 ,  G06F40/20

CPC classification number: G06F21/6245 ,  G06F40/20 ,  G06T11/00 ,  G06V10/25 ,  G06V10/759 ,  G06V10/761 ,  G06V10/774 ,  G06V40/172 ,  G06V2201/10

Abstract: An information processing apparatus performing processing for protecting privacy and security on an image uploaded to an SNS site is provided. The information processing apparatus includes: a region estimating unit configured to estimate candidate regions of object detection from an image; a topic estimating unit configured to estimate a topic of the image on the basis of text information accompanying the image; a region evaluating unit configured to evaluate the candidate regions estimated by the region estimating unit on the basis of relationships with the topic estimated by the topic estimating unit; and an image generating unit configured to generate an image on the basis of evaluation results acquired by the region evaluating unit. The topic estimating unit described above estimates the topic on the basis of words to which tags are added.

公开(公告)号：US11710075B2

公开(公告)日：2023-07-25

申请号：US17396499

申请日：2021-08-06

Applicant: BARDAVON HEALTH DIGITAL, INC.

Inventor： Manish Shah ,  Jeffrey Greenberg ,  Evan Minamoto ,  Navin Gupta ,  Paolo Tagliani ,  Francisco Jose Montiel Navarro

IPC: G06K9/00 ,  G06N20/00 ,  G06F3/0482 ,  G06T7/70 ,  G06T7/00 ,  G06V20/20 ,  G06V20/40 ,  G06F18/24 ,  G06F18/40 ,  G06F18/214 ,  G06V20/52

CPC classification number: G06N20/00 ,  G06F3/0482 ,  G06F18/214 ,  G06F18/24 ,  G06F18/40 ,  G06T7/0002 ,  G06T7/70 ,  G06V20/20 ,  G06V20/41 ,  G06V20/52 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06V2201/10

Abstract: Methods, systems, and devices are provided for identifying hazards. According to one aspect, a computer-implemented method can include receiving a plurality of sensor data including one or more image files from a mobile device. The method can include generating one or more position and label pairs based on the plurality of sensor data. The method can include assigning a hazard recognition to each of the position and label pairs. The method can include assigning a score associated to each of the hazard recognitions. The method can include displaying a result including one or more image results based on the one or more image files, one or more hazard recognitions, the one or more hazard recognitions associated with at least one of the one or more image results, and one or more scores associated to each of the hazard recognitions.

公开(公告)号：US11704888B2

公开(公告)日：2023-07-18

申请号：US17376088

申请日：2021-07-14

Applicant: Focal Systems, Inc.

Inventor： Francois Chaubard

IPC: G06V10/25 ,  G06V10/34 ,  G06V20/64 ,  G06F18/214 ,  G06F18/21 ,  G06V10/774

CPC classification number: G06V10/25 ,  G06F18/214 ,  G06F18/217 ,  G06V10/34 ,  G06V10/774 ,  G06V20/653 ,  G06V2201/10

Abstract: A method for generating training examples for a product recognition model is disclosed. The method includes capturing images of a product using an array of cameras. A product identifier for the product is associated with each of the images. A bounding box for the product is identified in each of the images. The bounding boxes are smoothed temporally. A segmentation mask for the product is identified in each bounding box. The segmentation masks are optimized to generate an optimized set of segmentation masks. A machine learning model is trained using the optimized set of segmentation masks to recognize an outline of the product. The machine learning model is run to generate a set of further-optimized segmentation masks. The bounding box and further-optimized segmentation masks from each image are stored in a master training set with its product identifier as a training example to be used to train a product recognition model.

公开(公告)号：US11688169B1

公开(公告)日：2023-06-27

申请号：US17822999

申请日：2022-08-29

Applicant: BNSF Railway Company

Inventor： Nicholas Dryer ,  Zachery Bettis ,  Bryan Gabric ,  Michael Ibanez ,  Yasha Hajizeinalibiouki

IPC: G06V20/50 ,  G06V10/70 ,  G06T7/70 ,  G06V20/40 ,  H04N5/77 ,  G06V20/17 ,  G06Q10/087 ,  G01S19/45 ,  H04N7/18

CPC classification number: G06V20/50 ,  G01S19/45 ,  G06Q10/087 ,  G06T7/70 ,  G06V10/70 ,  G06V20/17 ,  G06V20/41 ,  H04N5/77 ,  H04N7/183 ,  G06T2207/10016 ,  G06T2207/10032 ,  G06T2207/30244 ,  G06V2201/10

Abstract: Methods and systems for providing mechanisms for automated inventory control are provided. In embodiments, an operational workflow for providing automated inventory control includes automated data collection and automated image data analysis. The automated data collection includes capturing image data for a storage facility by a capturing device (e.g., an unmanned aerial system (UAS)). The automated image data analysis includes functionality to detect objects (e.g., containers, trailers, empty slots, and/or other objects) appearing in the image data (e.g., using a machine learning (ML) model), to identify the objects in the image data (e.g., using the ML model), to inspect the objects (e.g., including determining a condition and/or location of the objects) based on the collected image data and metadata associated with the image capturing device and correlated to the image data (e.g., using an advance mathematical rule-based analysis), and/or to generate results that may be used by an inventory management system.

公开(公告)号：US11687584B2

公开(公告)日：2023-06-27

申请号：US17192168

申请日：2021-03-04

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Yoshihiro Oe ,  Kazuya Nishimura

IPC: G06F16/58 ,  G06V20/56 ,  G06V20/58 ,  G06F16/53 ,  G06F16/51 ,  G06F18/28 ,  G06F18/2431 ,  G06V20/70

CPC classification number: G06F16/5866 ,  G06F16/51 ,  G06F16/53 ,  G06F18/2431 ,  G06F18/28 ,  G06V20/56 ,  G06V20/58 ,  G06V20/70 ,  G06V20/582 ,  G06V2201/10

Abstract: A method of generating log data that includes a plurality of records, in which information detected through image recognition processing on a plurality of image frames is recorded. The method includes, detecting objects in each image frame through the image recognition processing, generating a record including identification information of each image frame and the aggregated number of objects detected in the image frame for each image frame, and adding metadata relating to the detected objects to the corresponding record when the aggregated number of objects is equal to or greater than one. When the aggregated number of objects is zero, the metadata related to the detected objects is not added to the record.

公开(公告)号：US20230199192A1

公开(公告)日：2023-06-22

申请号：US17963924

申请日：2022-10-11

Applicant: Alibaba Group Holding Limited

Inventor： Tae Meon BAE ,  Minghai QIN ,  Guanlin WU ,  Yen-kuang CHEN ,  Qinggang ZHOU ,  Shaolin XIE

IPC: H04N19/136 ,  H04N19/103 ,  G06V20/40 ,  A63F13/355 ,  H04N19/179

CPC classification number: H04N19/136 ,  A63F13/355 ,  G06V20/41 ,  G06V20/46 ,  H04N19/103 ,  H04N19/179 ,  A63F2300/534 ,  A63F2300/538 ,  G06V2201/10

Abstract: Scene aware video content encoding techniques can determine if video content is a given content type and is one of one or more given titles that include one or more given scenes. The one or more given scenes of the video content of the given type and given one of the titles can be encoded using corresponding scenes specific encoding parameter values, and the non-given scenes can be encoded using one or more general encoding parameter values. The one or more given titles can be selected based on a rate of streaming of various video content titles of the given type.

公开(公告)号：US20230188679A1

公开(公告)日：2023-06-15

申请号：US18080426

申请日：2022-12-13

Applicant: HANWHAT TECHWIN CO., LTD.

Inventor： Jeong Eun LIM ,  Jin Ook Hur ,  Seung In Noh

IPC: H04N7/18 ,  G06V20/40 ,  G06V20/52

CPC classification number: H04N7/181 ,  G06V20/41 ,  G06V20/49 ,  G06V20/52 ,  G06V2201/10

Abstract: An image transmission method performed by instructions in an image transmission device including a processor and a memory storing the instructions executable by the processor includes, receiving a video, recognizing an object from the received video, generating metadata of the recognized object, calculating a score of the recognized object using the generated metadata; selecting the recognized object as a main object when the score exceeds a reference value, transmitting the metadata on the selected main object, and transmitting one of an image frame including the main object in the video and a best shot cropped from the image frame.

公开(公告)号：US20230186610A1

公开(公告)日：2023-06-15

申请号：US18065364

申请日：2022-12-13

Applicant: Regeneron Pharmaceuticals, Inc.

Inventor： Aslam Nagarkatti ,  Shiva Naveen Ravi ,  Kaushik Krishna Pradeep ,  Qingyan Hu ,  Marco Hernandez

IPC: G06V10/774 ,  G06V20/69 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V10/774 ,  G06V10/82 ,  G06V10/764 ,  G06V20/698 ,  G06V2201/10

Abstract: Methods and systems for particle classification are provided herein. A plurality of images of fluids/samples of pharmaceutical products, drugs, medicines, etc., may be analyzed using one or more machine learning models. The one or more machine learning models may comprise, for example, a convolution neural network. The one or more machine learning models may identify and classify one or more sub-visible particles in each image. The one or more one or more sub-visible particles may comprise, for example, cells, pathogens, protein aggregates, silicon oil droplets, fibers, air bubbles, glass particles, a combination thereof, and/or the like.

公开(公告)号：US20230177814A1

公开(公告)日：2023-06-08

申请号：US17457319

申请日：2021-12-02

Applicant: Comcast Cable Communications, LLC

Inventor： Ehsan Younessian

IPC: G06V10/776 ,  G06V20/40 ,  G06V20/70 ,  G06N20/00

CPC classification number: G06V10/776 ,  G06V20/41 ,  G06V20/70 ,  G06N20/00 ,  G06V2201/10

Abstract: Training data associated with detection of objects within a content asset may be generated in an automated manner. A content asset, such as video content, may be associated with metadata. A relevance score indicating a likelihood of the content asset comprising at least one object may be determined based on the metadata. A portion of the content asset may be identified as containing an instance of the object. The identified portion of the content asset may be a false identification if the relevance score for the content asset fails to satisfy a threshold value, or a positive identification if it satisfies the threshold value. The results, e.g., negative training data if the identified portion of the content asset is a false identification, may be used as negative training data for a multimedia detector that is based on a machine learning model.