-
公开(公告)号：US10147021B2
公开(公告)日：2018-12-04
申请号：US15056669
申请日：2016-02-29
Applicant: General Electric Company
Inventor： Ting Yu , Peter Henry Tu , Xiaoming Liu , Ser Nam Lim
Abstract: A novel technique for performing video matting, which is built upon a proposed image matting algorithm that is fully automatic is disclosed. The disclosed methods utilize a PCA-based shape model as a prior for guiding the matting process, so that manual interactions required by most existing image matting methods are unnecessary. By applying the image matting algorithm to these foreground windows, on a per frame basis, a fully automated video matting process is attainable. The process of aligning the shape model with the object is simultaneously optimized based on a quadratic cost function.
-
公开(公告)号：US20180336454A1
公开(公告)日：2018-11-22
申请号：US15600294
申请日：2017-05-19
Applicant: General Electric Company
Inventor： Ser Nam Lim , Xiao Bian , Wei-Chih Hung , David Scott Diwinsky
Abstract: The systems and methods herein relate to artificial neural networks. The systems and methods examine an input image having a plurality of instances using an artificial neural network, and generate an affinity graph based on the input image. The affinity graph is configured to indicate positions of the instances within the input image. The systems and methods further identify a number of instances of the input image by clustering the instances based on the affinity graph.
-
公开(公告)号：US20170167289A1
公开(公告)日：2017-06-15
申请号：US15041160
申请日：2016-02-11
Applicant: General Electric Company
Inventor： David Scott Diwinsky , Ser Nam Lim
CPC classification number: F01D21/003 , F01D5/005 , F01D17/02 , F05D2270/80 , F05D2270/804 , G01N21/9515 , G01N21/954 , G02B23/2461 , G02B23/2476 , G02B23/2484
Abstract: A method for locating probes within a gas turbine engine may generally include positioning a plurality of location transmitters relative to the engine and inserting a probe through an access port of the engine, wherein the probe includes a probe tip and a location signal receiver configured to receive location-related signals transmitted from the location transmitters. The method may also include determining a current location of the probe tip within the engine based at least in part on the location-related signals and identifying a virtual location of the probe tip within a three-dimensional model of the engine corresponding to the current location of the probe tip within the engine. Moreover, the method may include providing for display the three-dimensional model of the engine, wherein the virtual location of the probe tip is displayed as a visual indicator within the three-dimensional model.
-
公开(公告)号：US20170167285A1
公开(公告)日：2017-06-15
申请号：US14963695
申请日：2015-12-09
Applicant: General Electric Company
Inventor： David Scott Diwinsky , Ser Nam Lim
CPC classification number: F01D17/02 , F05D2220/32 , F05D2260/81 , F05D2270/80 , F05D2270/804 , F05D2270/8041 , G01M15/14
Abstract: A method for locating probes within a gas turbine engine may generally include positioning a plurality of location transmitters relative to the engine and inserting a probe through an access port of the engine, wherein the probe includes a probe tip and a location signal receiver configured to receive location-related signals transmitted from the location transmitters. The method may also include determining a current location of the probe tip within the engine based at least in part on the location-related signals and identifying a virtual location of the probe tip within a three-dimensional model of the engine corresponding to the current location of the probe tip within the engine. Moreover, the method may include providing for display the three-dimensional model of the engine, wherein the virtual location of the probe tip is displayed as a visual indicator within the three-dimensional model.
-
公开(公告)号：US09483820B2
公开(公告)日：2016-11-01
申请号：US14282296
申请日：2014-05-20
Applicant: General Electric Company
Inventor： Ser Nam Lim , Jilin Tu , Li Guan , Craig Ronald Hoffmann
CPC classification number: G06T7/001 , G06K9/46 , G06K9/4642 , G06K9/4671 , G06K9/52 , G06K9/62 , G06K9/6215 , G06K9/6218 , G06K9/6267 , G06K2209/19 , G06T2207/10016 , G06T2207/30164
Abstract: A method and system for detecting a damaged machine component during operation of the machine are provided. The damaged machine component detection system includes one or more processors, one or more memory devices communicatively coupled to the one or more processors, an image capture device configured to generate a stream of temporally-spaced images of a scene including a machine component of interest, the images generated in real-time, and a grouping model configured to compare features of a current image of the stream of images to features of previously captured images sorted into a plurality of groups of images having similar features, generate an alert if predetermined features of the current image deviate from corresponding features of the grouped images by a predetermined amount, and update the groups with the current image if the predetermined features of the current image are similar to corresponding features of the grouped images by a predetermined amount. The system also includes an output device configured to output at least one of the alert and the current image.
Abstract translation: 提供了一种用于在机器运行期间检测损坏的机器部件的方法和系统。 损坏的机器部件检测系统包括一个或多个处理器，通信地耦合到一个或多个处理器的一个或多个存储器设备，被配置为生成包括感兴趣的机器部件的场景的时间间隔图像的图像捕获设备， 实时生成的图像，以及分组模型，其被配置为将图像流的当前图像的特征与排列成具有相似特征的多组图像的先前拍摄图像的特征进行比较，如果预定特征 如果当前图像的预定特征与分组图像的对应特征类似于预定量，则当前图像与分组图像的相应特征偏离预定量，并且更新具有当前图像的组。 该系统还包括被配置为输出警报和当前图像中的至少一个的输出设备。
-
Patent Agency Ranking
公开(公告)号：US11060979B2
公开(公告)日：2021-07-13
申请号：US14577255
申请日：2014-12-19
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Ser Nam Lim , Joseph Vincent Pawlowski , Li Guan , Yogesh Agarwal , Binod Pandey , Srivatsa Dhanvantri
Abstract: An optical imaging and processing system includes an optical connection and an optical element disposed at a first end of the optical connection. The first end of the optical connection is configured to extend into a turbine component interior such that the optical element is disposed within the turbine component interior. The system also includes a photodiode array disposed at a second end of the optical connection, where the optical element is configured to transmit a video stream of the turbine component interior to the photodiode array as the optical element is moved within the turbine component interior between multiple vantage points. The system also includes a processor coupled to the photodiode array, wherein the processor is configured to process the video stream to generate a three-dimensional model of at least a portion of the turbine component interior without utilizing a previously defined three-dimensional model input of the turbine component interior.
-
公开(公告)号：US20180342069A1
公开(公告)日：2018-11-29
申请号：US15605243
申请日：2017-05-25
Applicant: General Electric Company
Inventor： Ser Nam Lim , David Scott Diwinsky , Wei Wang , Swaminathan Sankaranarayanan , Xiao Bian , Arpit Jain
Abstract: A system includes one or more processors configured to analyze obtained image data representing a rotor blade to detect a candidate feature on the rotor blade and determine changes in the size or position of the candidate feature over time. The one or more processors are configured to identify the candidate feature on the rotor blade as a defect feature responsive to the changes in the candidate feature being the same or similar to a predicted progression of the defect feature over time. The predicted progression of the defect feature is determined according to an action-guidance function generated by an artificial neural network via a machine learning algorithm. Responsive to identifying the candidate feature on the rotor blade as the defect feature, the one or more processors are configured to automatically schedule maintenance for the rotor blade, alert an operator, or stop movement of the rotor blade.
-
公开(公告)号：US20180253866A1
公开(公告)日：2018-09-06
申请号：US15495313
申请日：2017-04-24
Applicant: General Electric Company
Inventor： Arpit Jain , Swaminathan Sankaranarayanan , David Scott Diwinsky , Ser Nam Lim , Kari Thompson
CPC classification number: G06N7/005 , G06K9/6267 , G06K9/628 , G06N3/0454 , G06N3/0472 , G06N3/0481 , G06N3/084 , G06N3/088
Abstract: A method includes determining object class probabilities of pixels in a first input image by examining the first input image in a forward propagation direction through layers of artificial neurons of an artificial neural network. The object class probabilities indicate likelihoods that the pixels represent different types of objects in the first input image. The method also includes selecting, for each of two or more of the pixels, an object class represented by the pixel by comparing the object class probabilities of the pixels with each other, determining an error associated with the object class that is selected for each pixel of the two or more pixels, determining one or more image perturbations by back-propagating the errors associated with the object classes selected for the pixels of the first input image through the layers of the neural network without modifying the neural network, and modifying a second input image by applying the one or more image perturbations to one or more of the first input image or the second input image prior to providing the second input image to the neural network for examination by the neurons in the neural network for automated object recognition in the second input image.
-
公开(公告)号：US10060857B1
公开(公告)日：2018-08-28
申请号：US15814880
申请日：2017-11-16
Applicant: General Electric Company
Inventor： Steeves Bouchard , Stephane Harel , John Karigiannis , Nicolas Saudrais , David Cantin , Ser Nam Lim , Maxime Beaudoin Pouliot , Jean-Philippe Choiniere
IPC: B25J9/18 , G01N21/88 , G01N21/954 , G01S17/89 , G01S7/481
CPC classification number: G01N21/8851 , B25J9/1697 , B25J11/00 , G01N21/88 , G01N21/91 , G01N21/9515 , G01N21/954 , G01N2021/9544 , G01N2021/9548 , G01S7/4815 , G01S7/4817 , G01S17/89
Abstract: A system includes one or more processors configured to create a projection matrix based on a three-dimensional (3D) model of a part and sensor data associated with a workpiece in a workspace of a robotic manipulator. The projection matrix provides a mapping between sensor coordinates associated with the sensor data and 3D coordinates associated with the 3D model. The one or more processors are configured to identify a set of sensor coordinates from the sensor data corresponding to a feature indication associated with the workpiece, and to determine from the set of sensor coordinates a set of 3D coordinates using the projection matrix.
-
公开(公告)号：US09886754B2
公开(公告)日：2018-02-06
申请号：US15090646
申请日：2016-04-05
Applicant: General Electric Company
Inventor： Ser Nam Lim , Ning Zhou , Joao Vitor Baldini Soares
CPC classification number: G06T7/001 , E02F9/267 , E02F9/2808 , G06T7/248 , G06T7/254 , G06T7/269 , G06T7/74 , G06T7/90 , G06T2207/10016 , G06T2207/30164
Abstract: A method for detecting missing tooth in mining shovel, implemented using a processing device, includes receiving a pair of image frames from a camera disposed on a rope mine shovel configured to carry a mining load. A tooth line region corresponding to the pair of image frames is detected to generate a pair of tooth line regions based on a shovel template set. A difference image is determined based on the pair of image frames and the pair of tooth line regions. Further, a response map representative of possible tooth positions is determined based on the difference image using a tooth template matching technique. A tooth line is selected among a plurality of candidate tooth lines based on the response map. Further, a tooth condition is determined based on the tooth line and the difference image. The tooth condition is notified to an operator of the rope mine shovel.
-
-
-
-
-
-
-
-
-
Search Results
53
records
(took 0.021 seconds)
