公开(公告)号：US20230401738A1

公开(公告)日：2023-12-14

申请号：US18237937

申请日：2023-08-25

Applicant: Mitsubishi Electric Corporation

Inventor： Shingo MINE

IPC: G06T7/70 ,  G06T15/00 ,  G06T7/50 ,  G06V10/28 ,  G06V10/74

CPC classification number: G06T7/70 ,  G06T15/00 ,  G06T7/50 ,  G06V10/28 ,  G06V10/761 ,  G06V2201/07 ,  G06T2207/10024 ,  G06T2207/20101

Abstract: An image processing device includes an object detecting unit that processes captured image data representing a captured image, which is an image including an object or detection target and a background of the object, to generate processed image data representing a processed image, which is an image in which the object is detected; an expected-data generating unit that generates expected data representing an expected image, which a virtual image in which the object represented by an attribute is placed at a position on the background on the basis of object data representing the position of the object and background data representing the background; and a detection-result determining unit that compares the processed image data and the expected data to determine whether or not the object is detected correctly in the processed image data.

公开(公告)号：US20230401264A1

公开(公告)日：2023-12-14

申请号：US17854383

申请日：2022-06-30

Applicant: Dell Products L.P.

Inventor： Si Chen ,  Zhenzhen Lin ,  Qiang Chen

IPC: G06F16/907 ,  G06V20/40 ,  G06V10/77 ,  H04W4/44

CPC classification number: G06F16/907 ,  G06V20/46 ,  G06V10/7715 ,  H04W4/44 ,  G06V2201/07

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for data processing. The method may include receiving a data conversion strategy from a server. The method may further include determining, in response to receiving unstructured data from a field device, metadata of the unstructured data based on the received data conversion strategy to form a set of metadata. In addition, the method may include transmitting at least a part of the set of metadata to the server. According to embodiments of the present disclosure, edge computing can be performed on unstructured data, which not only enables timely processing of monitoring data, but also reduces computing load on the side of the server, thereby improving the user experience.

公开(公告)号：US11842545B2

公开(公告)日：2023-12-12

申请号：US17319171

申请日：2021-05-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Longzhen Lai

IPC: G06T7/55 ,  G06V20/58 ,  G06T7/246 ,  G06T7/70 ,  B60W30/095 ,  G08G1/16 ,  G06V20/56

CPC classification number: G06V20/58 ,  B60W30/0956 ,  G06T7/248 ,  G06T7/55 ,  G06T7/70 ,  G06V20/588 ,  G08G1/166 ,  G08G1/167 ,  B60W2420/42 ,  B60W2552/53 ,  B60W2554/4029 ,  G06T2207/30256 ,  G06T2207/30261 ,  G06V2201/07

Abstract: This application provides a collision detection method and related apparatus. An image taken by a photographing unit may be used to predict whether a collision with a to-be-detected target will occur. In a current collision prediction method, a type of the to-be-detected target needs to be determined first based on the image taken by the photographing unit, which requires consuming of a large amount of computing power. In the collision prediction method provided in this application, a change trend of a distance between the to-be-detected target and a vehicle in which the apparatus is located may be determined based on the distances between the to-be-detected target and the vehicle at different moments, to predict a collision between the to-be-detected target and the vehicle. This method can improve efficiency in collision prediction and reduce energy consumption in predicting collision.

公开(公告)号：US20230396733A1

公开(公告)日：2023-12-07

申请号：US18250020

申请日：2020-10-22

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Isaac Lagnado ,  Christopher Steven ,  Robert Campbell

IPC: H04N7/14 ,  G06T7/20 ,  G06T11/60 ,  G06V10/141 ,  G06V10/74 ,  G06V40/16

CPC classification number: H04N7/147 ,  G06T7/20 ,  G06T11/60 ,  G06V10/141 ,  G06V10/761 ,  G06V40/172 ,  G06V2201/07

Abstract: In example implementations, an apparatus is provided. The apparatus includes a video camera to capture images, a proximity sensor to measure a distance of a moving object from the video camera, and a processor communicatively coupled to the video camera and the proximity sensor. The processor is to execute a video call application, detect the moving object within the video images transmitted by the video call application, determine that the moving object is located at a distance greater than a distance threshold, and remove the moving object from the video images transmitted by the video call application in response to the distance of the moving object being located being greater than the distance threshold.

公开(公告)号：US20230394944A1

公开(公告)日：2023-12-07

申请号：US18328706

申请日：2023-06-02

Applicant: SkyBell Technologies IP, LLC

Inventor： Joseph Frank Scalisi ,  Desiree Mejia ,  Gregory Saul Harrison

IPC: G08B13/196 ,  G08B13/14 ,  H04N7/18 ,  G08B3/10 ,  G06Q10/0833 ,  G08B15/00 ,  G06V20/52

CPC classification number: G08B13/19695 ,  G08B13/1472 ,  H04N7/188 ,  G08B13/19658 ,  G08B13/19684 ,  G08B3/10 ,  G06Q10/0833 ,  G08B15/00 ,  H04N7/186 ,  G06V20/52 ,  G08B13/19619 ,  G08B13/19656 ,  G06V2201/07

Abstract: Delivery parcel detection systems can include a doorbell having a first wireless communication system and a parcel holding system configured for placement in an entryway. The doorbell can be communicatively coupled to the parcel holding system. The parcel holding system can comprise a sensor configured to detect a delivery parcel located on the parcel holding system. Systems can include a first communication sent from the parcel holding system to the doorbell in response to the parcel holding system detecting an arrival, a movement, or a removal of the delivery parcel. Systems can also include a second communication sent from the doorbell to a remote computing device in response to the doorbell receiving the first communication.

公开(公告)号：US20230394789A1

公开(公告)日：2023-12-07

申请号：US18327145

申请日：2023-06-01

Applicant: SEIKO EPSON CORPORATION

Inventor： Kota TAKEUCHI ,  Ippei KUROTA

IPC: G06V10/75 ,  H04N5/74

CPC classification number: G06V10/758 ,  H04N5/74 ,  G06V2201/07

Abstract: An image processing method includes acquiring a first captured image that is produced by capturing an image of an object with an imaging device at first time and that contains a first point, acquiring a second captured image that is produced by capturing an image of the object with the imaging device at second time different from the first time and that contains a second point corresponding to the first point, and outputting first output information that is information for image processing based on at least one of the first and second captured images when a first indicator value generated based on the coordinates of the first point in the first captured image and the coordinates of the second point in the second captured image is smaller than or equal to a threshold.

公开(公告)号：US20230394724A1

公开(公告)日：2023-12-07

申请号：US18169286

申请日：2023-02-15

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Quoc Viet PHAM

IPC: G06T11/20 ,  G06V10/25 ,  G06F16/903

CPC classification number: G06T11/206 ,  G06V10/25 ,  G06F16/90335 ,  G06V2201/07

Abstract: An image processing apparatus according to an embodiment includes a hardware processor. The processor receives input of an image and receives input of a query including one or more words. The processor calculates a word heat map for each of the words. The word heat map indicates a degree of relation between the word and each of subregions included in the image. The processor calculates weight of each of the words. The processor calculates, on the basis of the word heat maps and the weights, a query heat map indicating a degree of relation between the query and each of the subregions included in the image. The processor detects an image region from the image on the basis of the query heat map and outputs the image region. The image region corresponds to an object related to the query.

公开(公告)号：US11836957B2

公开(公告)日：2023-12-05

申请号：US17847880

申请日：2022-06-23

Applicant: 7-Eleven, Inc.

Inventor： Sumedh Vilas Datar ,  Sailesh Bharathwaaj Krishnamurthy ,  Shahmeer Ali Mirza

IPC: G06K9/00 ,  G06V10/147 ,  G06T7/292 ,  G06V20/52 ,  G06V20/40 ,  G06V10/764 ,  G06V10/82 ,  G06V10/24 ,  G06V40/10 ,  G06V40/20 ,  G06V10/62

CPC classification number: G06V10/147 ,  G06T7/292 ,  G06V10/245 ,  G06V10/764 ,  G06V10/82 ,  G06V20/41 ,  G06V20/52 ,  G06V40/10 ,  G06V40/20 ,  G06V40/28 ,  G06T2207/30208 ,  G06V10/62 ,  G06V20/44 ,  G06V2201/07

Abstract: An image sensor is positioned such that a field-of-view of the image sensor encompasses at least a portion of a rack storing items. The image sensor generates angled-view images of the items stored on the rack. A tracking subsystem determines that a person is within a threshold distance of the rack and receives image frames of the angled-view images. A pixel position of a wrist of the person is determined in at least a subset of the received image frames, thereby determining a set of pixel positions of the wrist. An aggregated wrist position is determined based on the set of pixel positions. If the aggregated wrist position is determined to correspond to a position on a shelf of the rack, a trigger signal is provided indicating a shelf-interaction event has occurred.

公开(公告)号：US11836903B2

公开(公告)日：2023-12-05

申请号：US16989405

申请日：2020-08-10

Applicant: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.

Inventor： Yuhu Jia

IPC: G06T5/50 ,  G06T7/194 ,  G06T7/215 ,  G06T7/11 ,  G06T7/246 ,  G06T7/269 ,  G06T7/73 ,  G06V20/40 ,  G06V10/20 ,  G06V10/10 ,  G06V10/147 ,  G06V10/22 ,  G06V10/62

CPC classification number: G06T5/50 ,  G06T7/11 ,  G06T7/194 ,  G06T7/215 ,  G06T7/246 ,  G06T7/269 ,  G06T7/73 ,  G06V10/255 ,  G06V20/46 ,  G06V20/48 ,  G06V20/49 ,  G06T2207/10016 ,  G06V10/10 ,  G06V10/147 ,  G06V10/22 ,  G06V10/62 ,  G06V2201/07

Abstract: This present disclosure relates to a subject recognition method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a current image frame and detecting whether there is a moving subject in the current image frame; when there is no moving subject in the current image frame, obtaining a motion state transition condition; when the current image frame satisfies the motion state transition condition, obtaining a target subject in a previous image frame; and determining a target subject in the current image frame based on the target subject in the previous image frame.

公开(公告)号：US20230386212A1

公开(公告)日：2023-11-30

申请号：US18202384

申请日：2023-05-26

Applicant: SKYLARK LABS INC.

Inventor： AMARJOT SINGH

IPC: G06V20/52 ,  G06V10/25 ,  G06V40/16 ,  G06V20/40

CPC classification number: G06V20/52 ,  G06V10/25 ,  G06V40/174 ,  G06V20/44 ,  G06V2201/07

Abstract: This disclosure relates to method and system for monitoring activities and events in real-time. The method includes receiving video data of an area from each of one or more cameras. The video data includes a plurality of frames. For each frame of the plurality of frames, the method further includes generating in real-time, a space-time-behaviour dataset corresponding to the frame; identifying in real-time, at least one of an event from a plurality of predefined events, or an associated cause of an event from a plurality of predefined causes, based on the space-time-behaviour dataset; determining in real-time, a set of cause parameters or a set of event parameters, based on the space-time-behaviour dataset; and determining in real-time, whether at least one of the cause or the event corresponds to suspicious activity based on the comparison with parameters of the plurality of predefined causes and the plurality of predefined events.