-
公开(公告)号：WO2023078254A1
公开(公告)日：2023-05-11
申请号：PCT/CN2022/129042
申请日：2022-11-01
Applicant: 珠海优特电力科技股份有限公司
Abstract: 本公开提供了一种刀闸分合状态确定方法、装置、设备、介质及产品，该方法包括：获取刀闸监控图像；提取所述刀闸监控图像中多个预设区域的图像特征；所述多个预设区域至少包括刀闸处于合位状态时刀闸所处的合位位置区域和刀闸处于分位状态时刀闸所处的分位位置区域；将所述刀闸监控图像中各所述预设区域的图像特征与预设刀闸模板图像对应预设区域的图像特征进行结构相似性比较；根据结构相似性比较的结果确定刀闸分合状态。
-
公开(公告)号：WO2023074229A1
公开(公告)日：2023-05-04
申请号：PCT/JP2022/035967
申请日：2022-09-27
Applicant: パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ
Abstract: 情報処理装置は、第１人物の顔と第２人物の顔との類似度を示す顔類似度を取得し、第１人物の音声と第２人物の音声との類似度を示す音声類似度を取得し、第１人物が第２人物と同一人物であるかを判定する際に用いられる閾値を含む統合範囲内に顔類似度がある場合、前記顔類似度及び前記音声類似度を統合することによって統合類似度を算出し、統合類似度を最終類似度として決定し、顔類似度が統合範囲内にない場合、顔類似度を最終類似度として算出し、最終類似度を出力する。
-
公开(公告)号：WO2023060575A1
公开(公告)日：2023-04-20
申请号：PCT/CN2021/124169
申请日：2021-10-15
Applicant: 中国科学院深圳先进技术研究院
IPC: G06V10/74
Abstract: 一种图像识别方法，适用于图像处理技术领域，包括：将待处理图像分割为预设数目个分块图像；其中，所述待处理图像包括待识别图像和参考图像；分别对每个所述分块图像进行特征提取处理，得到每个所述分块图像分别对应的分块特征信息（S102）；根据各个所述分块图像的位置信息和对应的所述分块特征信息，确定所述待识别图像和所述参考图像之间的相似度权重（S103）；根据各个所述分块特征信息以及所述相似度权重，确定所述待识别图像和所述参考图像之间的目标相似度（S103）；根据所述目标相似度，确定所述待识别图像的识别结果（S104）。能够提高图像识别的鲁棒性和准确率。
-
公开(公告)号：WO2023040506A1
公开(公告)日：2023-03-23
申请号：PCT/CN2022/110247
申请日：2022-08-04
Applicant: 腾讯科技（深圳）有限公司
Abstract: 一种基于模型的数据处理方法、装置、电子设备、计算机可读存储介质及计算机程序产品，方法包括：对第一训练样本集合进行抽取，得到第二训练样本集合和查询视频，第一训练样本集合包括不同类型的视频样本；通过动作识别模型中的嵌入层网络，对第二训练样本集合进行处理，得到第一帧特征序列；通过嵌入层网络，对查询视频进行处理，得到第二帧特征序列；通过动作识别模型中的时序关系网络，对第一帧特征序列进行处理，得到第一时序关系描述子；通过时序关系网络，对第二帧特征序列进行处理，得到第二时序关系描述子；根据第一时序关系描述子和第二时序关系描述子，对动作识别模型的模型参数进行调整。
-
5.发明申请
公开(公告)号：WO2023039075A1
公开(公告)日：2023-03-16
申请号：PCT/US2022/042920
申请日：2022-09-08
Applicant: SELEX ES INC.
Inventor： CHILD, Todd
Abstract: Embodiments of a system and method for data and security management are disclosed. An embodiment of the method may include capturing data relating to a plurality of targets from a plurality of sensors. The method may include correlating one or more targets to the data and classifying at least a portion of the data based on one or more correlations of the one or more targets. The method may include storing in a database the capture data according to one or more of partitioning, complex indexing, or pre-search statistical processing, with one or more of time, date, and location data with each associated data, wherein the data comprises high volumes of data received substantially continuous. The method may include retrieving a subset of the based on a user request. The method may include generating one or more graphical representations based on retrieved subsets of data to thereby enable targeted tracking.
-
Patent Agency Ranking
公开(公告)号：WO2022178505A1
公开(公告)日：2022-08-25
申请号：PCT/US2022/070667
申请日：2022-02-15
Applicant: SCHLUMBERGER TECHNOLOGY CORPORATION , SCHLUMBERGER CANADA LIMITED , SERVICES PETROLIERS SCHLUMBERGER , GEOQUEST SYSTEMS B.V.
Inventor： MAKHIJANI, Hemantkumar Prakashbhai
IPC: G06F16/54 , G06F16/538 , G06F16/532 , G06F3/0481 , G06V10/74 , G06V10/774
Abstract: A method may include displaying, in a graphical user interface (GUI) of a display device, an image generated from a well log, receiving, via the GUI, a selection of a portion of the image, obtaining, for the portion of the image, search metadata, and deriving, from the portion of the image, a search pattern including a constraint on a value of a search parameter. The method may further include performing, using the search pattern, a search within the image to obtain search results including matching portions of the image, marking, in the GUI, locations of the search results within the image, receiving, via the GUI, a selection of a search result, and presenting, in the GUI, the search result.
-
公开(公告)号：WO2022139480A1
公开(公告)日：2022-06-30
申请号：PCT/KR2021/019647
申请日：2021-12-22
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： CHANCHLANI, Pankaj , SHRIVATSAVA, Saurabh Kumar , KULSHRESTHA, Ashwini Kumar , GUPTA, Tarun , GUPTA, Prabhat Kumar
Abstract: Embodiments herein disclose a method and electronic device (100) for identifying user. The method includes capturing multiple image frames of a portion of face of the user and extracting facial descriptors from the multiple image frames. Further, the method includes generating first facial descriptor coordinates using the facial descriptors and determining a first distance between the first facial descriptor coordinates and second facial descriptor coordinates. The method also includes resizing the first facial descriptor coordinates radially and angularly based on the first distance and a weight associated with the facial descriptors and determining a second distance between the resized first facial descriptor coordinates and the second facial descriptor coordinates. Further, the method includes identifying whether the second distance between the resized first facial descriptor coordinates and the facial descriptor coordinates is less than a second distance threshold and identifying the user of the electronic device (100).
-
公开(公告)号：WO2022130364A1
公开(公告)日：2022-06-23
申请号：PCT/IB2021/062051
申请日：2021-12-20
Applicant: TILITER PTY LTD.
Inventor： SAMPSON, Christopher Bradley Rodney , ASGHAR, Sufyan , DO, Khai Van , DONG, Rui
Abstract: In some embodiments, a method can include capturing images of produce. The method can further include generating simulated images of produce based on the images of produce. The method can further include associating each image of produce from the images of produce and each simulated image of produce from the simulated images of produce with a category indicator, an organic type indicator, and a bag type indicator, to generate a training set. The method can further include training a machine leaning model using the training set such that when the machine learning model is executed, the machine learning model receives an image and generates a predicted category indicator of the image, a predicted organic type indicator of the image, and a predicted bag type indicator of the image.
-
9.发明申请
公开(公告)号：WO2022130363A1
公开(公告)日：2022-06-23
申请号：PCT/IB2021/062050
申请日：2021-12-20
Applicant: TILITER PTY LTD.
Inventor： SAMPSON, Christopher Bradley Rodney , DO, Khai Van
IPC: G06K9/62 , G06V10/82 , G06T11/60 , G06T11/00 , G06T7/73 , G06T7/00 , G06V10/74 , G06V20/68 , G06Q30/00
Abstract: In some embodiments, a method includes receiving an image of produce and an image of marking. The image of produce has a set of pixels, each associated with a position and a color value. The method further includes generating a grayscale image from the image of produce. The method further includes cropping out a portion from the grayscale image. The method further includes locating a marking position pixel on the image of produce by: (a) producing a list of pixels that are part of the cropped portion, (b) selecting, from the list of pixels, a subset of pixels having grayscale pixel values above a threshold, and (c) randomly selecting the marking position pixel from the subset of pixels. The method further includes overlaying the image of marking on the image of produce by coinciding a pixel of the image of marking with the marker position pixel.
-
公开(公告)号：WO2023085862A1
公开(公告)日：2023-05-19
申请号：PCT/KR2022/017785
申请日：2022-11-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： BAI, Mengmeng , ZUO, Li , WEN, Wei , CAO, Lei , SONG, Xiansong , NA, Jaekeun , WANG, Changwei
Abstract: Methods and apparatuses for performing image processing using artificial intelligence are provided. In an embodiment, an image processing method includes acquiring a target image based on an editing operation on an original image, performing a filling processing operation on the target image to obtain a first filled image including a first target region, identifying a target patch based on the first filled image, calculating a similarity value between the target patch and at least one patch related to the first filled image using a first artificial intelligence(AI) model, determining a target residual patch corresponding to the target patch based on the similarity value and generating a processing result image based on the target residual patch.
-
-
-
-
-
-
-
-
-
Search Results
57
records
(took 0.019 seconds)
