-
公开(公告)号：US11727052B2
公开(公告)日：2023-08-15
申请号：US17011909
申请日：2020-09-03
发明人： Xiao Bian , Bernard Patrick Bewlay , Colin James Parris , Feng Xue , Shaopeng Liu , Arpit Jain , Shourya Sarcar
IPC分类号： G06V10/25 , G06F16/583 , G06F16/51 , G06F16/901 , G06N3/045
CPC分类号： G06F16/583 , G06F16/51 , G06F16/9014 , G06N3/045 , G06V10/25
摘要： A method of inspecting a component using an image retrieval module includes storing an inspection image file in a memory and identifying a region of interest in the inspection image file. The method further includes accessing a database storing image files and determining feature vectors associated with the image files. The method also includes determining a hash code for each image file based on the feature vectors and classifying a subset of image files as relevant based on the hash codes. The method further includes sorting the subset of image files based on the feature vectors and generating search results based on the sorted subset of image files. The image retrieval module includes a convolutional neural network configured to learn from the determination of the feature vectors and increase the accuracy of the image retrieval module in classifying the image files.
-
公开(公告)号：US11145051B2
公开(公告)日：2021-10-12
申请号：US16862107
申请日：2020-04-29
发明人： Eric Michael Gros , Junli Ping , Arpit Jain , Ming-Ching Chang , Peter Henry Tu
摘要： The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.
-
公开(公告)号：US20200258207A1
公开(公告)日：2020-08-13
申请号：US16862107
申请日：2020-04-29
发明人： Eric Michael Gros , Junli Ping , Arpit Jain , Ming-Ching Chang , Peter Henry Tu
摘要： The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.
-
公开(公告)号：US20200175669A1
公开(公告)日：2020-06-04
申请号：US16208668
申请日：2018-12-04
发明人： Xiao Bian , Arpit Jain , David Scott Diwinsky , Bernard Patrick Bewlay , Steeves Bouchard , Jean-Philippe Choiniere , Marc-Andre Marois , Stephane Harel , John Karigiannis
IPC分类号： G06T7/00
摘要： An inspection system includes one or more imaging devices and one or more processors. The imaging devices generate a first set of images of a work piece at a first position relative to the work piece and a second set of images of the work piece at a second position relative to the work piece. At least some of the images in the first and second sets are acquired using different light settings. The processors analyze the first set of images to generate a first prediction image associated with the first position, and analyze the second set of images to generate a second prediction image associated with the second position. The first and second prediction images include respective candidate regions. The processors merge the first and second prediction images to detect at least one predicted defect in the work piece depicted in at least one of the candidate regions.
-
公开(公告)号：US10607406B2
公开(公告)日：2020-03-31
申请号：US15879743
申请日：2018-01-25
发明人： Shiraj Sen , Steven Robert Gray , Arpit Jain , Huan Tan , Douglas Forman , Judith Ann Guzzo
IPC分类号： G06T17/10 , G01B11/24 , G05D1/10 , G06T7/70 , G06T17/05 , G01B21/20 , G01B17/06 , G01S17/89 , G01B15/04 , B64C39/02 , B63G8/00 , G06T19/00
摘要： A method for generating a three-dimensional model of an asset includes receiving input parameters corresponding to constraints of a mission plan for operating an unmanned vehicle around an asset, generating the mission plan based on the input parameters including information of a representative asset type, wherein the mission plan includes waypoints identifying locations and orientations of one or more image sensors of the unmanned vehicle, generating a flight path for the unmanned vehicle connecting the waypoints that satisfy one or more predefined criteria, monitoring a vehicle state of the unmanned vehicle during execution of the flight path from one waypoint to the next waypoint, determining, at each waypoint, a local geometry of the asset sensed by the one or more image sensors, changing the mission plan on-the-fly based on the local geometry, and capturing images of the asset along waypoints of the changed mission plan.
-
公开(公告)号：US10262236B2
公开(公告)日：2019-04-16
申请号：US15584129
申请日：2017-05-02
摘要： A system that generates training images for neural networks includes one or more processors configured to receive input representing one or more selected areas in an image mask. The one or more processors are configured to form a labeled masked image by combining the image mask with an unlabeled image of equipment. The one or more processors also are configured to train an artificial neural network using the labeled masked image to one or more of automatically identify equipment damage appearing in one or more actual images of equipment and/or generate one or more training images for training another artificial neural network to automatically identify the equipment damage appearing in the one or more actual images of equipment.
-
公开(公告)号：US20190066317A1
公开(公告)日：2019-02-28
申请号：US15685867
申请日：2017-08-24
发明人： Ming-Ching Chang , Junli Ping , Eric Michael Gros , Arpit Jain , Peter Henry Tu
摘要： The present approach relates to an automatic and efficient motion plan for a drone to collect and save a qualified dataset that may be used to improve reconstruction of 3D models using the acquired data. The present architecture provides an automatic image processing context, eliminating low quality images and providing improved image data for point cloud generation and texture mapping.
-
公开(公告)号：US20170329307A1
公开(公告)日：2017-11-16
申请号：US15584995
申请日：2017-05-02
发明人： Mauricio Castillo-Effen , Victor Robert Abate , John Michael Lizzi, JR. , Huan Tan , Charles Burton Theurer , Charles Robert Gilman , Shiraj Sen , Peter Henry Tu , Arpit Jain
IPC分类号： G05B19/4065 , B25J9/16
CPC分类号： B25J9/1661 , B25J9/1602 , B25J9/163 , B25J9/1664 , B25J9/1671 , B25J9/1697 , F01D5/005 , F22B37/00 , G05B19/042 , G05B19/048 , G05B19/4065 , G05B19/4097 , G05B2219/35134 , G05B2219/40323 , G05B2219/42329 , G05B2219/49007 , G05D1/0094 , G05D1/101 , G06Q10/08 , Y02P90/083 , Y10S901/01 , Y10S901/44
摘要： A processing system having at least one processor operatively coupled to at least one memory. The processor receives sensor data from the at least one sensor indicating one or more characteristics of the asset. The processor generates, updates, or maintains a digital representation that models the one or more characteristics of the asset. The processor detects a defect of the asset based at least in part on the one or more characteristics. The processor generate an output signal encoding or conveying instructions to provide a recommendation to an operator, to control the at least one robot to address the defect on the asset, or both, based on the defect and the digital representation of the asset.
-
公开(公告)号：US11869192B2
公开(公告)日：2024-01-09
申请号：US17091725
申请日：2020-11-06
发明人： Mohammed Yousefhussien , Arpit Jain , James Vradenburg Miller , Achalesh Kumar , Walter V Dixon, III
IPC分类号： G06T7/11 , G06T17/05 , G06Q10/06 , G06Q10/0631 , G06Q10/0639 , G06V20/10 , G06V10/764 , G06V10/82 , G06N3/04 , G06N3/08
CPC分类号： G06T7/11 , G06Q10/06312 , G06Q10/06315 , G06Q10/06393 , G06T17/05 , G06V10/764 , G06V10/82 , G06V20/188 , G06N3/04 , G06N3/08 , G06T2207/10032 , G06T2207/30188
摘要： According to some embodiments, a system and method are provided comprising a vegetation module to receive image data from an image source; a memory for storing program instructions; a vegetation processor, coupled to the memory, and in communication with the vegetation module, and operative to execute program instructions to: receive image data; estimate a vegetation segmentation mask; generate at least one of a 3D point cloud and a 2.5D Digital Surface Model based on the received image data; estimate a relief surface using a digital terrain model; generate a vegetation masked digital surface model based on the digital terrain model, the vegetation segmentation mask and at least one of the 3D point cloud and the 2.5D DSM; generate a canopy height model based on the generated vegetation masked digital surface model; and generate at least one analysis with an analysis module, wherein the analysis module receives the generated canopy height model prior to execution of the analysis module, and wherein the analysis module uses the generated canopy height model in the generation of the at least one analysis. Numerous other aspects are provided.
-
公开(公告)号：US20220067082A1
公开(公告)日：2022-03-03
申请号：US17011909
申请日：2020-09-03
发明人： Xiao Bian , Bernard Patrick Bewlay , Colin James Parris , Feng Xue , Shaopeng Liu , Arpit Jain , Shourya Sarcar
IPC分类号： G06F16/583 , G06F16/901 , G06F16/51 , G06N3/04
摘要： A method of inspecting a component using an image retrieval module includes storing an inspection image file in a memory and identifying a region of interest in the inspection image file. The method further includes accessing a database storing image files and determining feature vectors associated with the image files. The method also includes determining a hash code for each image file based on the feature vectors and classifying a subset of image files as relevant based on the hash codes. The method further includes sorting the subset of image files based on the feature vectors and generating search results based on the sorted subset of image files. The image retrieval module includes a convolutional neural network configured to learn from the determination of the feature vectors and increase the accuracy of the image retrieval module in classifying the image files.
-
-
-
-
-
-
-
-
-
搜索结果
41 条记录 (耗时 0.02 秒)
