-
1.
公开(公告)号:US20230129263A1
公开(公告)日:2023-04-27
申请号:US17540757
申请日:2021-12-02
发明人: Hye Ran BYUN , Mi Rae Do , Seog Kyu JEON , Ki Beom HONG
摘要: A multi-level transferable region-based domain adaptive object detection apparatus includes: an image-level feature part that extracts an image-level feature by providing unlabeled target data to a plurality of convolutional layers; an RPN-level feature part that determines region candidates by providing the image-level feature to a region proposal network (RPN) and performing RPN-level domain adaptation and transferable region filtering; and an instance-level feature part that extracts a region of interest (RoI) pooling feature by conducting dynamic instance sampling on the region candidates.
-
公开(公告)号:US20230127199A1
公开(公告)日:2023-04-27
申请号:US17904856
申请日:2021-05-12
发明人: Thanh Quoc Tran , Hugh Watson , Jitesh Joshi , Abhilash K , Rohit Tiwari
IPC分类号: G06V20/69 , G06V10/22 , G06V10/774 , G06V10/82
摘要: Aspects of the present disclosure relate to a method of processing an input image of a culture device for a condition. The method can include receiving the input image and classifying the input image with a trained machine learning model that is configured to be trained on a training set of images having the condition. The method can include determining that the condition exists in the input image based on the classification and performing at least one action in response to the determination that the condition exists.
-
公开(公告)号:US20230125696A1
公开(公告)日:2023-04-27
申请号:US17972499
申请日:2022-10-24
申请人: Zaru, Inc.
发明人: Susheel Khamkar , Lino Fabiani , Edwin Villanueva
IPC分类号: G06Q30/04 , G06Q10/06 , G06F16/93 , G06F30/27 , G06F40/117 , G06F40/186 , G06V10/22 , G06V30/413
摘要: Described are approaches for assigning tasks between machine resources (e.g., AI task performers, AI task validators), human resources (e.g., task performers, task validators), and/or other smart systems to facilitate collaborative text detection, text recognition, and text retrieval in order to optimize system performance along a variety of different selection criteria specifying various performant dimensions, including, but not limited to improving system efficiency, reducing task performer and/or task validator idle time, improving triage outcomes, reducing data processing loads, maintaining client confidentiality, etc., that may be associated with one or more customers.
-
公开(公告)号:US20230124561A1
公开(公告)日:2023-04-20
申请号:US17968677
申请日:2022-10-18
申请人: Apprentice FS, Inc.
发明人: Frank Maggiore
摘要: One variation of the method for distributing censored videos of manufacturing procedures performed within a facility includes: accessing a video feed captured by a local device interfacing with a local operator during performance of a procedure within the facility; interpreting a set of objects depicted in the video feed based on features extracted from the video feed; accessing a minimum censorship specification for the procedure, the minimum censorship specification defining a set of object types corresponding to a first degree of censorship; identifying a subset of objects, in the set of objects, depicted in the video feed related to the procedure based on the set of object types defined in the minimum censorship specification; fogging the subset of objects in the video feed to generate a censored video feed; and serving the censored video feed to a remote viewer portal accessed by a remote viewer.
-
公开(公告)号:US11631258B2
公开(公告)日:2023-04-18
申请号:US17837966
申请日:2022-06-10
发明人: Youngwan Seo
摘要: A processing device includes a first processor configured to detect a bounding box of a distant vehicle, in an input image generated by imaging the distant vehicle, and extract at least one feature of the distant vehicle. A second processor is configured to estimate a geometry of a road on which the distant vehicle is located, based on a position of at least one feature relative to at least a portion of the bounding box.
-
公开(公告)号:US11626994B2
公开(公告)日:2023-04-11
申请号:US17227116
申请日:2021-04-09
摘要: A system and method for identifying whether an article is properly presented and duly owned by or licensed to a user and releasing assigned content to the user upon confirmation of such verifiably owned or licensed article. A manipulated user device equipped with at least one camera is deployed to determine if the article is properly presented. The device captures images and the system has the ability to determine from the images and any additional spatial information the orientation and/or position parameters of the article to confirm whether a valid spatial relationship exists between the article and the user device. Due ownership or license is verified by relying on tokens (e.g., Non-Fungible Tokens) and blockchain transaction records. The assigned content released to the user can be contextual and can range from items such as images, music, videos, games, virtual content, augmented content, coupons (virtual or physical), promotions, special offers and the like.
-
公开(公告)号:US11626194B2
公开(公告)日:2023-04-11
申请号:US17100059
申请日:2020-11-20
申请人: Enlitic, Inc.
发明人: Jordan Prosky , Li Yao , Eric C. Poblenz , Kevin Lyman , Ben Covington , Anthony Upton
IPC分类号: G06F40/295 , G06V30/194 , G16H10/60 , G16H30/40 , G16H15/00 , G06K9/62 , G06T5/00 , G06T5/50 , G06T7/00 , G06T11/00 , G06N5/04 , G16H30/20 , G06N20/00 , G06F9/54 , G06T7/187 , G06T7/11 , G06F3/0482 , G06T3/40 , A61B5/00 , G16H50/20 , G06F21/62 , G06Q20/14 , G16H40/20 , G06F3/0484 , G06Q10/0631 , G16H10/20 , G06N5/045 , G06T7/10 , G06T11/20 , G06F16/245 , G06T7/44 , G06N20/20 , H04L67/12 , G06V10/22 , H04L67/01 , G06V10/82 , G16H50/70 , G06T7/70 , G16H50/30 , A61B5/055 , A61B6/03 , A61B8/00 , A61B6/00 , G06Q50/22
摘要: An intensity transform augmentation system is operable to receive a training set of medical scans. Random intensity transformation function parameters are generated for each medical scan of the training set of medical scans. A plurality of augmented images are generated, where each of the plurality of augmented images is generated by performing a intensity transformation function on one of the training set of medical scans by utilizing the random intensity transform parameters generated for the one of the training set of medical scan. A computer vision model is generated by performing a training step on the plurality of augmented images. A new medical scan is received via the receiver. Inference data is generated by performing an inference function that utilizes the computer vision model on the new medical scan. The inference data is transmitted to a client device for display via a display device.
-
公开(公告)号:US11625854B2
公开(公告)日:2023-04-11
申请号:US17508784
申请日:2021-10-22
发明人: Xiaoli Guo , Ningning Yang
摘要: An intelligent forklift and a method for detecting a pose deviation of a container are provided. The intelligent forklift includes a working state monitor, an image sensor, and a processor. The working state monitor is configured to monitor a working state of the intelligent forklift while the intelligent forklift is carrying and moving a stock container and send a trigger to the image sensor based on the working state. The image sensor is configured to capture an RGBD image frame containing the stock container in response to the trigger and to transmit the RGBD image frame to the processor. The processor is configured to receive the RGBD image frame, detect a pose deviation degree of the stock container and provide an alarm and/or a prompt based on a detection result of the pose deviation degree for adjusting the pose of the stock container.
-
9.
公开(公告)号:US20230098284A1
公开(公告)日:2023-03-30
申请号:US17935496
申请日:2022-09-26
申请人: Robert Bosch GmbH
发明人: Andras Gabor Kupcsik , Philipp Christian Schillinger , Alexander Kuss , Anh Vien Ngo , Miroslav Gabriel , Zohar Feldman
IPC分类号: G06V10/774 , G06V10/82 , G06V10/22
摘要: A method for generating training data for supervised learning for training a neural network to identify, from digital images of objects, locations of the objects for interacting with the objects. The method includes: acquiring, for each training object, at least one digital reference image and a plurality of further images of the training object; for each training object, specifying a location of the training object, mapping the at least one reference image onto a descriptor image, identifying descriptors of the specified location, mapping the further images of the training object onto further descriptor images, and determining locations in the further images by locating points in the further images, the descriptors of which in the further descriptor images correspond to the specified descriptors of the at least one specified location; and generating the training data for supervised learning by marking the determined locations for the further images of the training objects.
-
公开(公告)号:US20230098133A1
公开(公告)日:2023-03-30
申请号:US17487337
申请日:2021-09-28
发明人: Kun Yan Yin , Xue Ping Liu , Yun Jing Zhao , Fei Wang , Yu Tao Wu , Guan Chao Li
IPC分类号: G06T7/90 , G06V10/774 , G06V10/22 , G06V10/762 , G06V10/50 , G06V10/56
摘要: A system and method for adaptive color assignments to image labels during annotation of datasets includes preparing a dataset for image labeling by an annotator by: leveraging a global color analyzer to perform a global color distribution of a plurality of images to identify one or more overall colors present in the plurality of images, and a local color analyzer to perform a local color distribution for each image to identify one or more colors present in an area of interest of the image, and selecting a plurality of candidate colors to be used as image labels by the annotator, based on an output of the global color analyzer and an output of the local color analyzer.
-
-
-
-
-
-
-
-
-