-
71.发明公开
公开(公告)号：EP4000040A1
公开(公告)日：2022-05-25
申请号：EP19842609.0
申请日：2019-12-03
申请人： AImotive Kft.
发明人： LÉRANT, Mátyás
-
-
公开(公告)号：EP3627445B1
公开(公告)日：2022-03-30
申请号：EP19209823.4
申请日：2012-05-03
发明人： SHARMA, Piyush , SWAMINATHAN, Ashwin , REZAIIFAR, Ramin , XUE, Qi
-
公开(公告)号：EP3968627A1
公开(公告)日：2022-03-16
申请号：EP20802358.0
申请日：2020-04-21
发明人： GAO, Chenqiong , YIN, Zelong , XIE, Nianhua
摘要： The present application provides a method for implanting information into a video, a computer device and a storage medium. The method comprises: constructing a model conforming to pixel distribution characteristics of an implantation region in a reference frame, and controlling the update of the model on the basis of a frame to be detected subsequent to the reference frame; recognizing, on the basis of the model, the background and the foreground of an implantation region in the frame to be detected, and generating a template for blocking the background and exposing the foreground; applying the template to information to be implanted, to block content of said information which may block the foreground; using said information, to which the template has been applied, to overlay the implantation region in the frame to be detected, so that the foreground is highlighted relative to said information. The present application efficiently integrates information into background content of a video.
-
公开(公告)号：EP3964562A1
公开(公告)日：2022-03-09
申请号：EP20796277.0
申请日：2020-04-23
申请人： NIKON CORPORATION
发明人： ICHIHASHI Toru , KII Hiroaki , TAKASAKI Tetsuomi , UOZUMI Takayuki , YAMAZAKI Yoichi , KINEHARA Masaki
IPC分类号： C12M1/34 , G06T7/00 , G06T7/246 , C12Q1/02 , G01N33/483
摘要： A cell tracking method is a cell tracking method for performing cell tracking on the basis of a plurality of cell images captured in time series, and includes an extraction process of extracting a tracking region corresponding to the cell for each of the plurality of cell images, a position calculation process of calculating a change in a position of the tracking region extracted in the extraction process on the basis of the plurality of cell images and tracking the cell on the basis of the calculated change in the position of the tracking region, a determination process of determining whether or not the cell as a tracking target is in a cell division state on the basis of the cell image, and a stop process of stopping the tracking of the cell when the cell is determined to be in the cell division state in the determination process.
-
公开(公告)号：EP3909504A3
公开(公告)日：2022-03-09
申请号：EP21175982.4
申请日：2018-05-28
摘要： A method for monitoring a person performing a physical exercise based on a sequence of image frames showing the person's exercise activity is described. The method comprises the steps of extracting, based on the sequence of image frames, for each image frame a set of body key points using a neural network, the set of body key points being indicative of the person's posture in the image frame, and deriving, based on a subset of the body key points in each image frame, at least one characteristic parameter indicating the progression of the person's movement. The method further comprises detecting a start loop condition by evaluating the time progression of at least one of the characteristic parameters, said start loop condition indicating a transition from a start posture of the person to the person's movement when performing the physical exercise.
-
公开(公告)号：EP3948800A1
公开(公告)日：2022-02-09
申请号：EP20783241.1
申请日：2020-04-06
发明人： HOLLADAY, Matthew , GOEL, Vikash
-
公开(公告)号：EP3340173B1
公开(公告)日：2022-02-02
申请号：EP16206316.8
申请日：2016-12-22
发明人： Lorentzon, Mattis , Medley, Fredrik
-
79.发明公开
公开(公告)号：EP3933756A1
公开(公告)日：2022-01-05
申请号：EP20183009.8
申请日：2020-06-30
摘要： The invention concerns a method (100) of monitoring a building element (16). Using an image capturing device (12) and a computing device (14), the method (100) comprises the steps (100.a, 100.b, 100.d, 100.c, 100.d, 100.e) of attributing a visual feature (28, 30, 44, 46) to each one of a first and a second region (24, 26, 40, 42) of the building element (16); taking a first plurality of images of the visual features (28, 30, 44, 46) by the image capturing device (12) at a first point of time; taking a second plurality of images of the visual features (28, 30, 44, 46) by the image capturing device (12) at a second point of time; causing the computing device (14) to process the images of the first and the second plurality of images in order to derive at least one of the distances between the two visual features (28, 30, 44, 46) and the relative orientations of the two visual features (28, 30, 44, 46) within the first plurality of images and within the second plurality of images; and causing the computing device (14) to deduce a state of the building element (16) from at least one of the difference between the distances and the difference between the relative orientations. Furthermore, the invention concerns several devices. The method enables a robust and cost-efficient monitoring of building elements (16).
-
公开(公告)号：EP3933674A1
公开(公告)日：2022-01-05
申请号：EP21161716.2
申请日：2021-03-10
发明人： ZHANG, Chengquan , HE, Bin
摘要： The present disclosure provides a method, apparatus, device and storage medium for processing an image, and relates to the fields of artificial intelligence, deep learning, computer vision and large data. A specific implementation solution is: acquiring a target video including a target image frame and at least one image frame of a labeled target object; based on the labeled target object in the at least one image frame, determining a search area for the target object in the target image frame; based on the search area, determining center position information of the target object; based on a labeled area in which the target object is located and the center position information, determining a target object area; and based on the target object area, segmenting the target image frame. This implementation method can robustly locate the target object and provide a fine target segmentation result.
-
-
-
-
-
-
-
-
-
搜索结果
880 条记录 (耗时 0.019 秒)
