-
公开(公告)号：US11841920B1
公开(公告)日：2023-12-12
申请号：US15432869
申请日：2017-02-14
IPC分类号： G06K9/62 , G06K9/00 , G06T7/73 , G06K9/78 , G06T7/285 , G06T7/246 , G06N3/04 , G06N3/08 , G06F3/01 , G06V10/10 , G06V20/64 , G06V40/20 , G06F18/214 , G06F18/24 , G06V10/70
CPC分类号： G06F18/214 , G06F18/24 , G06N3/04 , G06N3/08 , G06T7/248 , G06T7/285 , G06T7/74 , G06V10/70 , G06V20/64 , G06V40/28 , G06F3/011 , G06F3/017 , G06T2207/10021 , G06T2207/10028 , G06T2207/20081 , G06T2207/30196
摘要： The technology disclosed introduces two types of neural networks: “master” or “generalists” networks and “expert” or “specialists” networks. Both, master networks and expert networks, are fully connected neural networks that take a feature vector of an input hand image and produce a prediction of the hand pose. Master networks and expert networks differ from each other based on the data on which they are trained. In particular, master networks are trained on the entire data set. In contrast, expert networks are trained only on a subset of the entire dataset. In regards to the hand poses, master networks are trained on the input image data representing all available hand poses comprising the training data (including both real and simulated hand images).
-
公开(公告)号：US20220394172A1
公开(公告)日：2022-12-08
申请号：US17339040
申请日：2021-06-04
摘要： Methods and devices related to determining image sensor settings using LiDAR are described. In an example, a method can include receiving, at a processing resource via a LiDAR sensor, first signaling indicative of location data, elevation data, and/or light energy intensity data associated with an object, receiving, at the processing resource via an image sensor, second signaling indicative of data representing an image of the object, generating, based at least in part on the first signaling, additional data representing a frame of reference for the object, transmitting to a user interface third signaling indicative of the data representing the frame of reference for the object and the data representing the image of the object, and displaying, at the user interface and based at least in part on the third signaling, another image that comprises a combination of the frame of reference and the data representing the image.
-
公开(公告)号：US20220192752A1
公开(公告)日：2022-06-23
申请号：US17128230
申请日：2020-12-21
摘要： A system for registering operating images includes an X-ray imaging machine, a visible-light camera, a rectifier and a computer system. The X-ray imaging machine captures a first X-ray image of the rectifier, and the visible-light camera captures a first visible-light image of the rectifier at the same time. The computer system recognizes the rectifier in the first X-ray image and in the first visible-light image to compute a conversion model between a coordinate system of the X-ray imager and a coordinate system of the visible-light camera. The X-ray imaging machine also captures a second X-ray image of a patient on which a positioning marker is set, and the visible-light camera captures a second visible-light image of the positioning marker. The computer system provides a navigation interface by combining the second X-ray image and the second visible-light image based on the conversion model.
-
公开(公告)号：US11356643B2
公开(公告)日：2022-06-07
申请号：US17400887
申请日：2021-08-12
申请人： Google LLC
发明人： Jason Evans Goulden , Rengarajan Aravamudhan , Hae Rim Jeong , Michael Dixon , James Edward Stewart , Sayed Yusef Shafi , Sahana Mysore , Seungho Yang , Yu-An Lien , Christopher Charles Burns , Rajeev Conrad Nongpiur , Jeffrey Boyd
IPC分类号： H04N7/18 , G05B15/02 , G06K9/00 , G08B7/06 , G06K9/78 , H04M11/02 , G08B13/196 , G08B3/10 , H04N7/14 , G06F3/0482
摘要： A method of presenting appropriate actions for responding to a visitor to a smart home environment via an electronic greeting system of the smart home environment, including detecting a visitor of the smart home environment; obtaining context information from the smart home environment regarding the visitor; based on the context information, identifying a plurality of appropriate actions available to a user of a client device for interacting with the visitor via the electronic greeting system; and causing the identified actions to be presented to the user of the client device.
-
公开(公告)号：US11337432B1
公开(公告)日：2022-05-24
申请号：US16373979
申请日：2019-04-03
发明人： Yang Tao , Robert Vinson , Dongyi Wang , Maxwell Holmes , Gary E. Seibel
摘要： A vision guided intelligent system for automated crab meat picking operates in a fully automated or semi-automatic modes of operation using a crab meat picking routine based on (a) the CNN model localization of back-fin knuckles algorithm, and/or (b) the Deep Learning model which accurately locates not only knuckle positions, but also crab legs and crab cores, with a high pixel accuracy (up to 0.9843), and low computation time. The subject system uses a concept of analyzing crab morphologies obtained from digital crab images, and, using a Deep Learning architecture integrated in the system, segments crab images into five regions of interest in a single step with high accuracy and efficiency. The image segmentation results are used for generating crab cut lines in XYZ and angular directions, determining starting cutting points in Z plane, and guiding cutting tools and end effectors to automatically cut crabs and harvest crab meat.
-
公开(公告)号：US11295377B1
公开(公告)日：2022-04-05
申请号：US16706319
申请日：2019-12-06
摘要： The AUTOMATIC REMOTE DEPOSIT IMAGE PREPARATION APPARATUSES, METHODS AND SYSTEMS (hereinafter “MultiCrop”) transforms uploaded check images and check deposit information inputs via MultiCrop components image into deposit confirmation outputs. For example, in one embodiment, a user may employ a personal computer connected to a web camera, and/or a smartphone with a built-in camera to initiate the remote deposit by holding a check in front of the camera, and the MultiCrop may capture images of the check and send them to a financial institution for deposit processing.
-
公开(公告)号：US11295182B2
公开(公告)日：2022-04-05
申请号：US16557373
申请日：2019-08-30
发明人： Edward Hatton , H. Sprague Ackley
摘要： A method for template matching can include iteratively selecting a template set of points to project over a centerline of a candidate symbol; conducting a template matching analysis; assigning a score to each template set; and selecting a template set with a highest assigned score. For example, the score can depend on proximity of the template points to a center and/or boundaries of a principal tracing path of the symbol. Additionally, one or more template sets having a top rank can be selected for a secondary analysis of proximity of the template points to a boundary of a printing of the symbol. The method can further include using the template with the highest score to interpret the candidate symbol.
-
公开(公告)号：US11217052B2
公开(公告)日：2022-01-04
申请号：US17225346
申请日：2021-04-08
发明人： Kunihiro Murakami , Katsuhiko Sakakibara , Makoto Matsushita , Junya Sato , Kiyonori Yoshida , Tae Sugimura , Takashi Hayashi , Jun Endo
摘要： A processing device includes a control unit configured to perform: identifying a user when the user enters a vehicle and performing a process of guaranteeing a boarded state of the user while the user is in the vehicle; receiving information on a predetermined procedure for performing an authentication process from the user; and transmitting user information which is required for performing the predetermined procedure as information on the user of whom the boarded state in the vehicle is guaranteed to an external device that is installed at a first place for the predetermined procedure in a state in which the boarded state of the user is guaranteed.
-
公开(公告)号：US20210392319A1
公开(公告)日：2021-12-16
申请号：US17446317
申请日：2021-08-30
发明人： Galina Okouneva
IPC分类号： H04N17/00 , B60R1/00 , G06T7/80 , G06T7/579 , G06T7/73 , G06T7/246 , G06T7/33 , G06T7/70 , G06K9/00 , G06K9/62 , G06K9/78 , G06T7/00 , H04N5/232 , H04N5/247
摘要： A vehicular camera calibration system includes a camera disposed at a vehicle, and an electronic control unit (ECU). The camera calibration system utilizes an intrinsic parameter of the camera and uses a kinematic model of motion of the vehicle that is determined at least in part via processing of multiple frames of captured image data. The camera calibration system, responsive to processing of multiple frames of image data captured by the camera as the vehicle moves along a path of travel, and based at least in part on (i) an intrinsic parameter of the camera and (ii) the kinematic model of motion of the vehicle, determines misalignment of the camera. The camera calibration system determines camera misalignment without use of a fiducial marker in the field of view of the camera as the vehicle moves along the path of travel and without use of reference points on the vehicle.
-
公开(公告)号：US20210365755A1
公开(公告)日：2021-11-25
申请号：US17058347
申请日：2018-11-12
摘要： A multiple-pattern fiducial for a heterogeneous imaging sensor system. The multiple-pattern fiducial includes a first pattern detectable by a first wavelength of electromagnetic energy, and a second pattern detectable by a second wavelength of electromagnetic energy.
-
-
-
-
-
-
-
-
-
搜索结果
1688 条记录 (耗时 0.029 秒)
