公开(公告)号：US11756306B2

公开(公告)日：2023-09-12

申请号：US18094388

申请日：2023-01-08

Applicant: Hangzhou Juyan Xincheng Technology Co. Ltd.

Inventor： Xiao Feng Ren ,  Xin Xie ,  Yu Guo ,  Dong Yan Guo ,  Zhen Hua Wang ,  Jian Hua Zhang ,  Du Si Zhang

IPC: G06V20/52 ,  G06T7/292 ,  G06T7/246 ,  G06V10/82 ,  G06V10/774 ,  G06T7/73 ,  H04N7/18 ,  G08B21/02 ,  G06V40/10 ,  H04N23/90

CPC classification number: G06V20/52 ,  G06T7/248 ,  G06T7/292 ,  G06T7/74 ,  G06V10/774 ,  G06V10/82 ,  G06V40/10 ,  G08B21/02 ,  H04N7/181 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30196 ,  G06T2207/30241 ,  G06T2207/30244 ,  G06V2201/07 ,  H04N23/90

Abstract: The embodiment of the present invention discloses an anti-drowning safety alarm method and device for swimming pools. Acquiring images taken by multiple cameras; inputting the images into a target detection model to detect human bodies and heads, so as to obtain human body target detection boxes and human head target detection boxes; calculating the relationship between the human heads and the human bodies according to these boxes; performing multi-camera fusion on the human body target detection boxes and the human head target detection boxes to obtain the human body boxes and head boxes; determining the relative position relationship between the human bodies or the human heads and the water surface; calculating the correlation between the bounding box sequence at the current moment and that at the previous moment to obtain the human tracking trajectory; updating the state database; generating alarm information according to the state database.

公开(公告)号：US20230281961A1

公开(公告)日：2023-09-07

申请号：US17871877

申请日：2022-07-22

Applicant: Hamidreza FAZLALI ,  Richard XU ,  Bingbing LIU

Inventor： Hamidreza FAZLALI ,  Richard XU ,  Bingbing LIU

IPC: G06V10/77 ,  G06V10/771 ,  G06V10/82

CPC classification number: G06V10/7715 ,  G06V10/771 ,  G06V10/82 ,  G06V2201/07

Abstract: A system and method for 3D object detection using multi-resolution features recovery using panoptic segmentation information. Panoptic segmentation predictions from a panoptic segmentation network and intermediate feature maps from one or more early layers of an object detection network are received. Feature vectors are retrieved from the intermediate feature maps using the panoptic segmentation predictions. The retrieved feature vectors are combined with feature maps from one or more late layers of the object detection network for generating object detection predictions.

公开(公告)号：US20230281859A1

公开(公告)日：2023-09-07

申请号：US18176305

申请日：2023-02-28

Applicant: CANON KABUSHIKI KAISHA

Inventor： KENTARO WATANABE

IPC: G06T7/70 ,  G06V10/25 ,  G06F3/14

CPC classification number: G06T7/70 ,  G06V10/25 ,  G06F3/14 ,  G06V2201/07

Abstract: An image processing apparatus configured to process a captured image includes a detection unit configured to detect an object from the image and to acquire first and second detection areas, a relevant area setting unit configured to set the first detection area as a relevant area relevant to the second detection area, a search area setting unit configured to set a search area related to the object in the image, and a target setting unit configured to set an arbitrary area in the image as a target area for processing, wherein, in a case where the search area and the second detection area or the relevant area overlap, the target setting unit sets the second detection area as the target area, and wherein the detection unit detects a train as the object and acquires the first and second detection areas.

公开(公告)号：US20230281826A1

公开(公告)日：2023-09-07

申请号：US18178821

申请日：2023-03-06

Applicant: NEC Laboratories America, Inc.

Inventor： Samuel Schulter

IPC: G06T7/12 ,  G06T1/00 ,  G06V10/25 ,  G06V10/74

CPC classification number: G06T7/12 ,  G06T1/0021 ,  G06V10/25 ,  G06V10/761 ,  G06V2201/07 ,  G06T2207/20081

Abstract: Methods and systems for training an image segmentation model include embedding training images, from multiple training datasets having differing label spaces, in a joint latent space to generate first features. Textual labels of the training images are embedded in the joint latent space to generate second features. A segmentation model is trained using the first features and the second features.

公开(公告)号：US11741705B1

公开(公告)日：2023-08-29

申请号：US17813347

申请日：2022-07-19

Applicant: TP Lab, Inc.

Inventor： Chi Fai Ho ,  Benson Junwun Ho

IPC: G06V20/20 ,  H04W4/029 ,  G06F16/787

CPC classification number: G06V20/20 ,  G06F16/787 ,  H04W4/029 ,  G06V2201/07

Abstract: A tracking system obtains first recognized object and its first information, detected in image(s) captured by camera(s). The first information includes the first recognized object's first features, first feature locations, first real-world dimensions, and a first time. A list of tracking objects is obtained, each including a second recognized object and its second information. The second information includes the second recognized object's second features, second feature locations, and second real-world dimensions. The system compares the first features with the second features stored in a given tracking object, the first feature locations with the second feature locations, and the first real-world dimensions with the second real-world dimensions. When they match, the first information comprising the first time is stored in the given tracking object.

公开(公告)号：US20230267745A1

公开(公告)日：2023-08-24

申请号：US18111743

申请日：2023-02-20

Applicant: RF Code, Inc.

Inventor： Jonathan Andrew Guy

IPC: G06V20/52 ,  G06T7/70 ,  G06T7/194 ,  G06V10/60 ,  G06T7/90

CPC classification number: G06V20/52 ,  G06T7/70 ,  G06T7/194 ,  G06V10/60 ,  G06T7/90 ,  G06T2207/10048 ,  G06V2201/07

Abstract: Systems, methods, and devices are described for monitoring and protecting electronic hardware, data assets, and the facility itself, particularly well-suited to monitoring remote facilities and resources in edge locations, including for determining door state for both equipment and personnel doors, and for determining values of one or more environmental parameters, using optical image analytics. An example system includes one or more edge-located hardware monitoring devices having one or more physical sensors, and custom software distributed across edge, cloud, mobile, and enterprise platforms. An example monitoring device can include an embedded computer, various sensors of different types, one or more cameras, a power supply, and several communication interfaces. All or virtually all sensing and processing capabilities can be integrated into the edge device, which utilizes low-cost sensors and video analytics to monitor the environment.

公开(公告)号：US20230267694A1

公开(公告)日：2023-08-24

申请号：US18111208

申请日：2023-02-17

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： Edward W. Breitweiser ,  Ryan Gross ,  Jeffrey W. Stoiber ,  Craig Cope ,  Christopher N. Kawakita ,  Matthew L. Floyd

IPC: G06T19/00 ,  G06V10/44 ,  G06V10/70 ,  G06Q40/08

CPC classification number: G06T19/006 ,  G06V10/44 ,  G06V10/70 ,  G06Q40/08 ,  G06V2201/07

Abstract: Embodiments of extended reality (XR) methods and systems for handling home-related information are disclosed. In one embodiment, a computer-implemented method may include (1) obtaining one or more XR preferences for a party; (2) presenting, using one or more devices associated with the party instructions constructed to guide the party to move throughout or around a real property, and prompts constructed to direct the party to capture data representing one or more of the real property or belongings; (3) determining, by one or more processors processing the captured data, asset data representing one or more of the real property or the belongings; and/or (4) presenting, in a virtualized environment in accordance with the party's XR preferences via an XR device, one or more visual depictions of the determined asset data such that the party or an insurance representative can at least one of view, modify, or approve the asset data.

公开(公告)号：US20230267671A1

公开(公告)日：2023-08-24

申请号：US18102160

申请日：2023-01-27

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Dae-Hwan KIM ,  Ki-Hong KIM ,  Yong-Wan KIM ,  Jin-Sung CHOI

IPC: G06T13/40 ,  G06T7/11 ,  G06T7/50 ,  G06T7/70 ,  G06V10/25 ,  G06V10/764

CPC classification number: G06T13/40 ,  G06T7/11 ,  G06T7/50 ,  G06T7/70 ,  G06V10/25 ,  G06V10/764 ,  G06V2201/07 ,  G06T2207/20044 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: Disclosed herein is an apparatus for synchronization with a virtual avatar. The apparatus may include a body part detection unit for detecting a human body part in an input 2D image, a visible body part estimation unit for estimating the shape and pose of a visible body part based on the detected body part, an invisible body part generation unit for generating a shape and pose of an invisible body part based on the body part and the shape and pose thereof, a body estimation unit for estimating a full-body shape and pose based on the shape and pose of the visible body part and the shape and pose of the invisible body part, and a virtual avatar synchronization unit for encoding and transmitting the estimated full-body shape and pose information for synchronization with a virtual avatar modeled in advance in a server.

公开(公告)号：US20230267584A1

公开(公告)日：2023-08-24

申请号：US18012128

申请日：2021-05-26

Applicant: Beijing Bytedance Network Technology Co., Ltd.

Inventor： Yifan LU

IPC: G06T5/50 ,  G06T17/00 ,  G06T7/70 ,  G06V10/25

CPC classification number: G06T5/50 ,  G06T7/70 ,  G06T17/00 ,  G06V10/25 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06T2207/20221 ,  G06V2201/07

Abstract: Disclosed are a virtual clothing changing method and apparatus. One specific embodiment of the method comprises: extracting foot images from a target image in which the feet are displayed; generating foot posture information on the basis of the foot images; and on the basis of the foot posture information, superimposing a clothing pattern onto the feet displayed in the target image. The embodiment not only makes it convenient for a customer to buy suitable clothing, but also ensures the accuracy of virtual clothing changing, thereby facilitating an improvement in the experience of the customer buying the clothing.

公开(公告)号：US20230267292A1

公开(公告)日：2023-08-24

申请号：US18169010

申请日：2023-02-14

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Ganglu Wu ,  Shiyuan Yang ,  Xiao Zhou ,  Qi Wang ,  Qunwei Liu ,  Youming Luo

IPC: G06K7/14 ,  G06T9/00 ,  G06V10/25 ,  G06Q30/0601

CPC classification number: G06K7/1413 ,  G06T9/00 ,  G06V10/25 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06V2201/07

Abstract: An automated checkout system modifies received images of machine-readable labels to improve the performance of a label detection model that the system uses to decode item identifiers encoded in the machine-readable labels. For example, the automated checkout system may transform subregions of an image of a machine-readable label to adjust for distortions in the image's depiction of the machine-readable label. Similarly, the automated checkout system may identify readable regions within received images of machine-readable labels and apply a label detection model to those readable regions. By modifying received images of machine-readable labels, these techniques improve on existing computer-vision technologies by allowing for the effective decoding of machine-readable labels based on real-world images using relatively clean training data.