-
公开(公告)号：WO2022251758A1
公开(公告)日：2022-12-01
申请号：PCT/US2022/071442
申请日：2022-03-30
Applicant: QUALCOMM INCORPORATED
Inventor： GRUHLKE, Russell , SIVALINGAM, Ravishankar , KIDWELL, JR., Donald William , PARK, Edwin Chongwoo
IPC: G06V10/147 , G06V40/00 , G06V40/12
Abstract: In some aspects, a device may detect that an object is contacting a display of the device. The device may illuminate, based at least in part on detecting that the object is contacting the display, a plurality of pixel regions of the display. The plurality of pixel regions may be illuminated sequentially. The device may obtain, using one or more photosensors, a set of data relating to light that is reflected from at least a portion of the object based at least in part on illuminating the plurality of pixel regions. The set of data may include respective data for each sequential illumination of the plurality of pixel regions. The device may generate an image of at least the portion of the object based at least in part on the set of data. Numerous other aspects are described.
-
公开(公告)号：WO2021252343A1
公开(公告)日：2021-12-16
申请号：PCT/US2021/036146
申请日：2021-06-07
Applicant: POSOKHOW, Bruno André
Inventor： POSOKHOW, Bruno André
Abstract: Puppeting a representation of a host user as an avatar in a virtual or augmented reality environment includes continually tracking only the user's head and wrist positions and orientations in a 3D space; converting the tracked head and wrist positions and orientations into corresponding head and wrist positions and orientations of the avatar; and transmitting only the avatar head and wrist positions and orientations to a client. The method further includes using an inverse kinematics algorithm to determine a kinematic chain from at least one wrist to the head of the avatar, with the head and wrist positions and orientations as constraints to the inverse kinematics algorithm. Changes in the head and wrist positions and orientations of the user cause corresponding changes in head and wrist positions and orientations of the avatar.
-
13.发明申请
公开(公告)号：WO2021245439A2
公开(公告)日：2021-12-09
申请号：PCT/IB2020/055195
申请日：2020-06-02
Applicant: SARABI, Soroush , TORKCHERIK, Afshin , NAJJARI, Hassan , RASHIDIAN, Amir hossein
Inventor： SHADLO, Ameneh , SOLTANMORADI, Ali , KHOUNJAM AGHBELAGH, Nasim , SARABI, Ali
Abstract: A method for preparing data to identify different species of animals and identify their behavioral characteristics through machine learning, machine vision, and deep learning approaches (all deep learning algorithms) to Preventing the dangers and injuries of the presence of animals near the refinery facilities and also preparing technical data and measuring the amount of pollutants leaving the refinery and permanent inspection of facilities. in this method pixels matrix in the image is defined by deep learning techniques to pre-learned models of pixel values and create image library comprises images of different species of animals and different part of refinery and this about extracting relevant images is performed by deep learning and machine vision methods to Preventing the dangers and injuries of the presence of animals near the refinery facilities and at least the animal species is conditioned, animal will learn during the time to not fall within the danger range.
-
公开(公告)号：WO2023089347A1
公开(公告)日：2023-05-25
申请号：PCT/HU2022/050082
申请日：2022-11-14
Applicant: SEMMELWEIS EGYETEM
Inventor： VÁG, János , SIMON, Botond Barna
IPC: G06V40/00 , G06V10/75 , A61B5/1171 , G06T7/00 , A61C9/00
Abstract: The method for biometric identification includes a data acquisition process and an identification process carried out at a later time after the data acquisition process. During the data acquisition process (a) recording (100), by an imaging device, 3D digital image of the palate of a plurality of people, (b) based on the 3D image, generating (110), by a computer, a 3D surface model of the palate, (c) identifying (120) at least three predefined reference points in the 3D surface model, (d) in the 3D surface model, determining (130), by the computer, the distances between said reference points, and a data set is formed of the distances, (e) associating (140) the data set with unique personal identification data of the respective person, and (f) storing (150) the data set and the associated personal identification data in a database. In the identification process (g) recording (160), by imaging device, a further 3D digital image of a person's palate, (h) using said further 3D digital image, performing (170) the above steps (b) to (d), by a computer, to produce a further data set, (i) comparing (180) the further data set, by the computer, with the data sets stored in the database, and selecting the best matching one or more data sets, and (j) outputting (190), by the computer, the personal identification data belonging to the best matching one or more data sets.
-
15.发明申请
公开(公告)号：WO2023075628A1
公开(公告)日：2023-05-04
申请号：PCT/RU2021/000464
申请日：2021-10-27
Inventor： БАБИН, Александр Павлович
Abstract: Изобретение относится к средствам определения порога идентификации для биометрических образцов в системе контроля доступа. Способ определения порога идентификации для биометрических образцов в системе контроля доступа содержит этапы, на которых: получают ретроспективные данные о результатах сравнения биометрических образцов, проходящих идентификацию, с зарегистрированными биометрическими шаблонами, при которых результат имеет наивысший скоринговый балл; отбирают данные идентификации образцов за выбранный период времени; определяют информацию о поменьше мере двух максимальных скоринговых баллов, значения которых выше порога аутентификации; формируют гистограммы распределения скоринговых баллов; рассчитывают значение вероятности ложноположительной идентификации; определяют порог идентификации для биометрических образцов и назначают полученный порог идентификации для по меньшей мере одного биометрического сенсора. Изобретение позволяет повысить точность определения порога идентификации для биометрических образцов в системе контроля доступа.
-
Patent Agency Ranking
公开(公告)号：WO2023040578A1
公开(公告)日：2023-03-23
申请号：PCT/CN2022/113474
申请日：2022-08-19
Applicant: 浙江灵创网络科技有限公司 , 东胜神州旅游管理有限公司
Inventor： 黄水财
Abstract: 本发明提供了一种基于童脸识别的儿童坐姿检测方法及系统，涉及儿童坐姿矫正的技术领域，通过自动识别儿童的年龄，并根据儿童年龄的不同，对儿童坐姿进行实时检测与智能监督。本发明仅需对眼、肩、鼻、腿、膝、脚等几处人体关键部位的骨骼位置信息进行简单的综合数学运算既可得到人体骨骼关系信息，再将人体骨骼关系信息与相应的设定阈值进行比较，即可判断人体坐姿状态。相比现有需要使用高位特征向量、积分计算等方法，不需要对坐姿进行单独的模型训练，只需对关键数据进行测算，大大降级了坐姿检测时间与精确度。
-
公开(公告)号：WO2023012546A1
公开(公告)日：2023-02-09
申请号：PCT/IB2022/056418
申请日：2022-07-12
Applicant: Q (CUE) LTD.
Inventor： MAIZELS, Aviad , BARLIYA, Avi , KORNBLAU, Giora , WEXLER, Yonatan
Abstract: A method for generating speech includes uploading a reference set of features that were extracted from sensed movements of one or more target regions of skin on faces of one or more reference human subjects in response to words articulated by the subjects and without contacting the one or more target regions. A test set of features is extracted a from the sensed movements of at least one of the target regions of skin on a face of a test subject in response to words articulated silently by the test subject and without contacting the one or more target regions. The extracted test set of features is compared to the reference set of features, and, based on the comparison, a speech output is generated, that includes the articulated words of the test subject.
-
公开(公告)号：WO2023012527A1
公开(公告)日：2023-02-09
申请号：PCT/IB2022/054527
申请日：2022-05-16
Applicant: Q (CUE) LTD.
Inventor： MAIZELS, Aviad , BARLIYA, Avi , KORNBLAU, Giora , WEXLER, Yonatan
Abstract: A sensing device (20, 60) includes a bracket (22) configured to fit an ear of a user (24) of the device. An optical sensing head (28) is held by the bracket in a location in proximity to a face of the user and senses light reflected from the face and to output a signal in response to the detected light. Processing circuitry (70, 75) processes the signal to generate a speech output.
-
公开(公告)号：WO2022245747A1
公开(公告)日：2022-11-24
申请号：PCT/US2022/029479
申请日：2022-05-16
Applicant: SNAP INC.
Inventor： ANVARIPOUR, Kaveh , DESSERREY, Laurent
IPC: G06F9/451 , G06F1/16 , G06F3/00 , G06F3/01 , G06F3/03 , G06F3/0482 , G06V20/00 , G06V40/00 , H04N5/232 , H04N21/00 , G06F3/04812 , G06F3/04817 , G06Q50/00 , H04L51/00 , H04N21/2743
Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting shortcuts based on a scan operation. The program and method provide for receiving a user request to identify at least one object depicted in an image captured by a device camera; determining, in response to receiving the user request, an attribute of an object depicted in the image; selecting, from a plurality of shortcuts for performing with respect to the image, a shortcut that is associated with the attribute of the object, each shortcut of the plurality of shortcuts corresponding to a combination of individual functions to apply to the image; and causing display of an interface with a user-selectable element for performing the selected shortcut with respect to the image.
-
20.发明申请
公开(公告)号：WO2021257546A1
公开(公告)日：2021-12-23
申请号：PCT/US2021/037409
申请日：2021-06-15
Applicant: STRONGARM TECHNOLOGIES, INC.
Inventor： SPINELLI, Michael, Patrick , BOMMIREDDY, Sivasankara, Reddy , KIM, Michael, Dohyun , PETTERSON, Sean, Michael
Abstract: Systems and methods of the present disclosure enable automated recognition of user performed activities and tasks using sensor data by receiving raw sensor data while a user performs a series of activities wearing at least one sensor for a predetermined interval of time. The raw sensor data is converted into a set of feature values. An action recognition machine learning model is used to generate action labels indicative of actions performed by the user during the predetermined interval of time based on trained action model parameters and the set of feature values. A task recognition machine learning model is used to generate task labels indicative of tasks performed by the user during the predetermined interval of time based on trained task model parameters, the set of action labels and the set of feature values, and a message is displayed with an indication of the task labels to a user.
-
-
-
-
-
-
-
-
-
Search Results
21
records
(took 0.013 seconds)
