专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

FR3122798A1 SYSTEMES ET PROCEDES IMPLIQUANT INTELLIGENCE ARTIFICIELLE ET LA TECHNOLOGIE EN NUAGE POUR SYSTEME DE PERIPHERIQUE ET DE SERVEUR SUR PUCE 未知
公开(公告)号：FR3122798A1
公开(公告)日：2022-11-11
申请号：FR2204225
申请日：2022-05-04
申请人： UNIQUIFY INC
发明人： LEE JOSHUA
IPC分类号： G06N3/02 , H04N21/23 , G06V20/40 , H04N21/80
摘要： Des aspects de la présente invention impliquent des systèmes, procédés, instructions informatiques, et un système périphérique impliquant une mémoire configurée pour stocker un modèle de détection/classement d'objet sous une forme de réseau neuronal entraîné représenté par une ou plus valeur(s) de paramètre(s) quantifiées logarithmiquement, le modèle de détection/classement d'objet étant configuré pour classer un ou plus objet(s) sur des données d'image via une ou plus opération(s) de réseau neuronal selon les valeurs de paramètres quantifiées logarithmiquement du réseau neuronal entraîné ; et un système sur puce (SoC) ou une circuiterie/un matériel/des instructions informatiques équivalent(e)s de celui-ci configuré(e/es) pour recevoir les données d'image ; exécuter un ou plus modèle(s) de réseau(x) neuronal(-aux) entraîné(s) via l'une ou plus opération(s) de réseau neuronal en lien avec les données d’image ;ajouter une ou plus superposition(s) aux données d'image sur la base d’un ou plus objet(s) classé(s) à partir des données d'image ; et fournir les données image, avec les superpositions ajoutées, en tant que sortie.

2. 发明专利

GB2604851A A system for accessing a web page 未知
公开(公告)号：GB2604851A
公开(公告)日：2022-09-21
申请号：GB202101968
申请日：2021-02-12
申请人： TEKKPRO LTD
发明人： DANIEL ROBERT COX , COLIN KEITH TUNNICLIFFE
IPC分类号： G06F16/43 , G06F16/953 , G06F16/955 , G06Q30/06 , G06V10/70 , G06V20/40
摘要： System comprising a screen (5) for viewing content (6) comprising a plurality of scenes, items (30,31,32) shown in each scene, a mobile camera device (1) having a camera (7), processor, connection to internet (2) and access to computing devices (56,57,100) in the internet comprising a machine learning cloud (100) and a database (107) comprising scene identifiers (75), each scene identifier (106) associated with item data (85) describing the items shown in that scene. The system comprises the steps of a user (15) capturing an image (49) of the screen displaying the content with the mobile camera device, processing the image to obtain a prepared image (58), sending the prepared image (60) to the machine learning cloud, executing a comparison algorithm (104) to compare the prepared image with stock images (101) obtained from stock scenes of pre-recorded stock content, each stock scene assigned a scene identifier (106), the machine learning cloud identifying the scene with a degree of certainty, inserting the respective scene identifier in the database to obtain the item data appearing in the scene, sending at least a portion of the item data or related data to the user, with a link to the web page for each item.

3. 发明专利

DE112021000259T5 Anweisungsgenerierung mit einem oder mehreren neuronalen Netzwerken 未知
公开(公告)号：DE112021000259T5
公开(公告)日：2022-09-08
申请号：DE112021000259
申请日：2021-01-21
申请人： NVIDIA CORP
发明人： KOTHARI PRANIT P , PARDESHI SIDDHANT , GAIKWAD VINAYAK VILAS
IPC分类号： G06V20/40 , G06V10/82
摘要： Es werden Vorrichtungen, Systeme und Techniken zur Erstellung von Anleitungstext vorgestellt. In mindestens einer Ausführungsform wird ein Anleitungsvideo analysiert, um logische Schritte eines in diesem Video gezeigten Prozesses oder einer in diesem Video gezeigten Aufgabe zu bestimmen, und für diese logischen Schritte wird ein instruktiver Text erzeugt.

4. 发明专利

CA3148663A1 METHODS, SYSTEMS, AND APPARATUSES FOR IMPROVED VIDEO FRAME ANALYSIS AND CLASSIFICATION 未知
公开(公告)号：CA3148663A1
公开(公告)日：2022-08-12
申请号：CA3148663
申请日：2022-02-14
申请人： COMCAST CABLE COMM LLC
发明人： HOSSEINI MOHAMMAD , HASAN MD MAHMUDUL
IPC分类号： G06V20/40 , G06V10/56 , G06V10/764
摘要： Described herein are methods, systems, and apparatuses for improved video frame analysis and classification. A computer vision model may be trained to predict whether a video frame(s) depicts a particular object(s), event(s), or imagery using color features of the video frame(s). Another computer vision model may focus on grayscale features of the video frame(s) (e.g., black and white features) to verify the prediction when the grayscale features of the video frame(s) indicate the particular object(s), event(s), or imagery is depicted in the video frame(s).

5. 发明专利

CA2951852C DETECTION OF DEMARCATING SEGMENTS IN VIDEO 未知
公开(公告)号：CA2951852C
公开(公告)日：2022-05-24
申请号：CA2951852
申请日：2015-06-02
申请人： ARRIS ENTPR LLC
发明人： LI RENXIANG , ISHTIAQ FAISAL , EMEOTT STEPHEN P , BRASKICH ANTHONY J
IPC分类号： G06V20/40 , G11B27/10 , H04N21/43 , H04N21/80
摘要： A method of detecting frames in a video that demarcate a pre-determined type of video segment within the video is provided. The method includes identifying visually distinctive candidate marker frames within the video, grouping the candidate marker frames into a plurality of groups based on visual similarity, computing a collective score for each of the groups based on temporal proximity of each of the candidate marker frames within the group to related events occurring within the video, and selecting at least one of the groups based on the collective proximity scores as marker frames that demarcate the pre-determined type of video segment. A video processing electronic device and at least one non-transitory computer readable storage medium having computer program instructions stored thereon for performing the method are also provided.

6. 发明专利

IL291276D0 Sports timing based on a camera system 未知
公开(公告)号：IL291276D0
公开(公告)日：2022-05-01
申请号：IL29127622
申请日：2022-03-10
申请人： MYLAPS B V
IPC分类号： G06V20/40
摘要： Methods and systems for determining a passing time of an object passing a timing line across a sports track are described, wherein a method may comprise receiving a sequence of video frames captured by at least one camera system, each video frame representing a picture of scene of one or more objects, for example a person, an animal or a vehicle, moving along a track and each video frame being time-stamped; determining depth maps for the sequence of video frames, a depth map comprising information regarding the distance between the one or more objects in the picture of a video frame and the camera system; detecting one or more objects in the video frames using an object detection algorithm, the one or more objects detected by the detection algorithm defined one or more detected objects; determining a detected object in the video frames passing a timing line across a sports track, the timing line being defined by a virtual plane located across the track at a predetermined distance from the camera system, the determination of the passing being based on the coordinates of the virtual plane and the depth maps; determining a passing time based on a time stamp of a video frame comprising a detected object passing the timing line.

7. 发明专利

IL290002D0 Automatic control of wearable display device based on external conditions 未知
公开(公告)号：IL290002D0
公开(公告)日：2022-03-01
申请号：IL29000222
申请日：2022-01-20
申请人： MAGIC LEAP INC
IPC分类号： G02B27/00 , G02B27/01 , G06T19/00 , G06V20/20 , G06V20/40 , G06V30/194 , G06V40/19 , G06V40/20
摘要： Embodiments of a wearable device can include a head-mounted display (HMD) which can be configured to display virtual content. While the user is interacting with visual or audible virtual content, the user of the wearable may encounter a triggering event such as, for example, an emergency condition or an unsafe condition, detecting one or more triggering objects in an environment, or determining characteristics of the user's environment (e.g., home or office). Embodiments of the wearable device can automatically detect the triggering event and automatically control the HMD to deemphasize, block, or stop displaying the virtual content. The HMD may include a button that can be actuated by the user to manually deemphasize, block, or stop displaying the virtual content.

8. 发明专利

NL2029338B1 KEY PERSON RECOGNITION IN IMMERSIVE VIDEO 未知
公开(公告)号：NL2029338B1
公开(公告)日：2022-12-06
申请号：NL2029338
申请日：2021-10-07
申请人： INTEL CORP
发明人： XIAOFENG TONG , WENLONG LI , HAIHUA LIN , MING LU , LIWEI LIAO
IPC分类号： G06V10/44 , G06V10/762 , G06V20/40
摘要： Techniques related to key person recognition in multi-camera immersive video attained for a scene are discussed. Such techniques include detecting predefined person formations in the scene based on an arrangement of the persons in the scene, generating a feature vector for each person in the detected formation, and applying a classifier to the feature vectors to indicate one or more key persons in the scene.

9. 发明专利

FR3122797A1 SYSTEMES ET PROCEDES IMPLIQUANT INTELLIGENCE ARTIFICIELLE ET LA TECHNOLOGIE EN NUAGE POUR SYSTEME DE SERVEUR SUR PUCE 未知
公开(公告)号：FR3122797A1
公开(公告)日：2022-11-11
申请号：FR2204216
申请日：2022-05-04
申请人： UNIQUIFY INC
发明人： LEE JOSHUA , KIM SAMJUNG
IPC分类号： H04N21/23 , G06N3/02 , G06V20/40 , H04N21/80
摘要： Des exemples d'implémentations décrits ici ont trait à des systèmes et procédés pour un dispositif concentrateur serveur qui est configuré pour exécuter des modèles d'intelligence artificielle/de réseau neuronal via traitement de données d'entrée et génération de métadonnées ou d'instructions vers des dispositifs périphériques. Dans des exemples d'implémentations, les opérations d’IA/de RN sont menées en exécutant des décalages logiques (par ex. par des circuits décaleurs) sur des paramètres quantifiés logarithmiquement correspondant à de telles opérations.

10. 发明专利

GB2599877B Comparing video sequences using fingerprints 未知
公开(公告)号：GB2599877B
公开(公告)日：2022-10-12
申请号：GB202200457
申请日：2016-08-24
申请人： GRASS VALLEY LTD
发明人： JONATHAN DIGGINS
IPC分类号： G06V20/40 , G06F16/732 , H04N21/234
摘要： A first sequence of video fingerprints at a first image repetition rate is compared with a second sequence of video fingerprints at a second, different image repetition rate. A converted sequence of fingerprints is generated from the first or second sequence of fingerprints by forming a combination of the values of a number of neighbouring fingerprints. The combination is a weighted average based on the temporal location of the respective neighbouring fingerprints in the first sequence of fingerprints with respect to the fingerprint in the converted sequence. A correlation is then performed between the converted sequence of fingerprints and the other sequence of fingerprints.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式