-
公开(公告)号：US20190236394A1
公开(公告)日：2019-08-01
申请号：US16376704
申请日：2019-04-05
Applicant: Adobe Inc.
Inventor： Brian Price , Scott Cohen , Mai Long , Jun Hao Liew
CPC classification number: G06K9/3241 , G06K9/4628 , G06K2009/366
Abstract: Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.
-
公开(公告)号：US20180260972A1
公开(公告)日：2018-09-13
申请号：US15979214
申请日：2018-05-14
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Alexander Jay Bruen Trevor , Michelle Jung-Ah Ho , David Klein , Stephen David Miller , Shuichi Tsutsumi , Radu Bogdan Rusu
CPC classification number: G06T19/006 , G06K9/00228 , G06K9/00671 , G06K9/22 , G06K9/3233 , G06K2009/366 , G06T7/33 , G06T2200/32 , G06T2207/10016 , G06T2207/10024 , G06T2207/30241 , G06T2207/30244
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. According to particular embodiments, the spatial relationship between multiple images and video is analyzed together with location information data, for purposes of creating a representation referred to herein as a surround view for presentation on a device. A visual guide can provided for capturing the multiple images used in the surround view. The visual guide can be a synthetic object that is rendered in real-time into the images output to a display of an image capture device. The visual guide can help user keep the image capture device moving along a desired trajectory.
-
公开(公告)号：US20180253865A1
公开(公告)日：2018-09-06
申请号：US15448541
申请日：2017-03-02
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Brian Lynn Price , Stephen Schiller , Scott Cohen , Ning Xu
CPC classification number: G06T7/194 , G06K9/4604 , G06K9/4652 , G06K2009/366 , G06K2009/4666 , G06N3/088 , G06T7/11 , G06T7/90 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084
Abstract: Methods and systems are provided for generating mattes for input images. A neural network system can be trained where the training includes training a first neural network that generates mattes for input images where the input images are synthetic composite images. Such a neural network system can further be trained where the training includes training a second neural network that generates refined mattes from the mattes produced by the first neural network. Such a trained neural network system can be used to input an image and trimap pair for which the trained system will output a matte. Such a matte can be used to extract an object from the input image. Upon extracting the object, a user can manipulate the object, for example, to composite the object onto a new background.
-
公开(公告)号：US20180165827A1
公开(公告)日：2018-06-14
申请号：US15376537
申请日：2016-12-12
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef HOLZER , Alexander Jay Bruen Trevor , Michelle Jung-Ah Ho , David Klein , Stephen David Miller , Shuichi Tsutsumi , Radu Bogdan Rusu
CPC classification number: G06T7/70 , G06K9/00228 , G06K9/00671 , G06K9/22 , G06K9/3233 , G06K2009/366 , G06T7/97 , G06T19/006 , G06T2207/10004 , G06T2207/10028
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. According to particular embodiments, the spatial relationship between multiple images and video is analyzed together with location information data, for purposes of creating a representation referred to herein as a surround view for presentation on a device. A visual guide can provided for capturing the multiple images used in the surround view. The visual guide can be a synthetic object that is rendered in real-time into the images output to a display of an image capture device. The visual guide can help user keep the image capture device moving along a desired trajectory.
-
公开(公告)号：US09778661B2
公开(公告)日：2017-10-03
申请号：US15167154
申请日：2016-05-27
Applicant: SZ DJI TECHNOLOGY CO., LTD.
IPC: G05D1/08 , G05D3/00 , G06F7/00 , G06F17/00 , G05D1/10 , B64C39/02 , B64D47/08 , G01C21/20 , G06T7/73 , G06T7/246 , H04N7/18 , G06K9/00 , H04N5/232 , H04N5/243
CPC classification number: G05D1/101 , B64C39/024 , B64C2201/108 , B64C2201/126 , B64C2201/141 , B64C2201/146 , B64D47/08 , G01C11/34 , G01C21/20 , G06K9/0063 , G06K2009/366 , G06T7/246 , G06T7/73 , G06T2207/10032 , G06T2207/30252 , H04N5/23238 , H04N5/243 , H04N7/181 , H04N7/185
Abstract: Systems and methods for navigating a vehicle within an environment are provided. In one aspect, a method comprises: (a) selecting, with aid of a processor, a subset of a plurality of sensors to be used for navigating the vehicle within the environment based on one or more predetermined criteria, wherein the plurality of sensors are arranged on the vehicle such that each sensor of the plurality of sensors is configured to obtain sensor data from a different field of view; (b) processing, with aid of the processor, the sensor data from the selected sensor(s) so as to generate navigation information for navigating the vehicle within the environment; and (c) outputting, with aid of the processor, signals for controlling the vehicle based on the navigation information.
-
Patent Agency Ranking
公开(公告)号：US20170230518A1
公开(公告)日：2017-08-10
申请号：US15217065
申请日：2016-07-22
Applicant: FUJI XEROX CO., LTD.
Inventor： Shinya MIYAMORI
CPC classification number: H04N1/00029 , G06K9/36 , G06K9/522 , G06K2009/366 , H04N1/00005 , H04N1/00015 , H04N1/00039 , H04N1/00058 , H04N1/00344 , H04N1/393 , H04N1/4078 , H04N1/6008 , H04N1/6047
Abstract: A terminal device includes an acquisition unit that acquires image information of a read-out original, a display unit that displays the image information acquired by the acquisition unit, a detection unit that detects pitch information by performing frequency analysis of the image information displayed by the display unit, and a control unit that controls the image information so as to be enlarged or reduced in accordance with a size of the original and controls to display the pitch information so as to be superimposed on the image information which is enlarged or reduced.
-
公开(公告)号：US20170132469A1
公开(公告)日：2017-05-11
申请号：US15346620
申请日：2016-11-08
Applicant: Shoou Jiah Yiu
Inventor： Shoou Jiah Yiu , Gerald Friedland
CPC classification number: G06K9/3241 , G06K9/00711 , G06K2009/3291 , G06K2009/366
Abstract: Disclosed is a computer implemented method for identifying an object in a plurality of images. The method may include a step of receiving, through an input device, a delineation of the object in at least one image of the plurality of images. Further, the method may include a step of identifying, using the processor, an image region corresponding to the object in the at least one image based on the delineation. Furthermore, the method may include a step of tracking, using the processor, the image region across the plurality of images.
-
公开(公告)号：US20170045895A1
公开(公告)日：2017-02-16
申请号：US15167154
申请日：2016-05-27
Applicant: SZ DJI TECHNOLOGY CO., LTD.
CPC classification number: G05D1/101 , B64C39/024 , B64C2201/108 , B64C2201/126 , B64C2201/141 , B64C2201/146 , B64D47/08 , G01C11/34 , G01C21/20 , G06K9/0063 , G06K2009/366 , G06T7/246 , G06T7/73 , G06T2207/10032 , G06T2207/30252 , H04N5/23238 , H04N5/243 , H04N7/181 , H04N7/185
Abstract: Systems and methods for navigating a vehicle within an environment are provided. In one aspect, a method comprises: (a) selecting, with aid of a processor, a subset of a plurality of sensors to be used for navigating the vehicle within the environment based on one or more predetermined criteria, wherein the plurality of sensors are arranged on the vehicle such that each sensor of the plurality of sensors is configured to obtain sensor data from a different field of view; (b) processing, with aid of the processor, the sensor data from the selected sensor(s) so as to generate navigation information for navigating the vehicle within the environment; and (c) outputting, with aid of the processor, signals for controlling the vehicle based on the navigation information.
Abstract translation: 提供了用于在环境中导航车辆的系统和方法。 一方面，一种方法包括：（a）借助于处理器，根据一个或多个预定准则，选择要用于在环境内导航车辆的多个传感器的子集，其中所述多个传感器是 布置在车辆上，使得多个传感器中的每个传感器被配置成从不同的视野获得传感器数据; （b）借助于处理器处理来自所选择的传感器的传感器数据，以便产生用于在环境内导航车辆的导航信息; 以及（c）借助于处理器，根据导航信息输出用于控制车辆的信号。
-
9.发明授权Method and apparatus for identifying a desired object of an image using a suggestive marking 有权使用提示标记识别图像的期望对象的方法和装置公开(公告)号：US09460362B2
公开(公告)日：2016-10-04
申请号：US14298006
申请日：2014-06-06
Applicant: Adobe Systems Incorporated
Inventor： Anand Samuel Edwin , Charan Raj
CPC classification number: G06K9/4604 , G06K2009/366 , G06T7/12 , G06T11/60 , G06T2207/20021 , G06T2207/20096
Abstract: A computer implemented method and apparatus for identifying a desired object of an image by using a suggestive marking. The method comprises receiving a first marking to an image, the first marking suggesting a desired object of the image and the desired object being defined by a boundary; generating, based on the first marking, a plurality of output images, wherein each image of the plurality of output images indicates a computer-identified object; and displaying the plurality of output images.
Abstract translation: 一种用于通过使用提示标记来识别图像的期望对象的计算机实现的方法和装置。 所述方法包括：向图像接收第一标记，所述第一标记表示所述图像的期望对象，所述期望对象由边界定义; 基于所述第一标记生成多个输出图像，其中所述多个输出图像中的每个图像指示计算机识别的对象; 并显示多个输出图像。
-
公开(公告)号：US09202138B2
公开(公告)日：2015-12-01
申请号：US13645463
申请日：2012-10-04
Applicant: Adobe Systems Incorporated
Inventor： Jonathan W. Brandt , Zhe Lin , Vuong Le , Lubomir D. Bourdev
CPC classification number: G06K9/6209 , G06K9/00228 , G06K9/2081 , G06K2009/366
Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. A profile model and a shape model may be applied to an object in an image to determine locations of feature points for each object component. Input may be received to move one of the feature points to a fixed location. Other ones of the feature points may be automatically adjusted to different locations based on the moved feature point.
Abstract translation: 公开了用于特征点定位的方法和装置的各种实施例。 轮廓模型和形状模型可以应用于图像中的对象，以确定每个对象分量的特征点的位置。 可以接收输入以将特征点中的一个移动到固定位置。 其他特征点可以根据所移动的特征点自动调整到不同的位置。
-
-
-
-
-
-
-
-
-
Search Results
153
records
(took 0.031 seconds)
