-
公开(公告)号:US20180369872A1
公开(公告)日:2018-12-27
申请号:US15634694
申请日:2017-06-27
Applicant: KENNETH J. McGARVEY , GERALD R. RICHERT , ELLIOT T. BURCH , BRET J. LARREAU
Inventor: KENNETH J. McGARVEY , GERALD R. RICHERT , ELLIOT T. BURCH , BRET J. LARREAU
CPC classification number: B07C5/3422 , B07C5/366 , B07C2501/0018 , B07C2501/0081 , G06K9/00771 , G06K9/3216 , G06K9/3233 , G06K9/3241 , G06K9/6289 , G06K2209/17
Abstract: A method of sorting is described and which includes a step of acquiring a multiplicity of synchronized image signals of a product stream which is to be sorted; generating a multiplicity of fused sensor signals; forming an image model previously acquired from the objects to be sorted; identifying objects in the product stream, and generating object presence and defect signals; determining a spatial orientation of the objects in the product stream; detecting the defects and removing the defects from the product stream.
-
公开(公告)号:US20180357509A1
公开(公告)日:2018-12-13
申请号:US15779904
申请日:2016-11-17
Applicant: Delphi Technologies, LLC
Inventor: Rafal Dlugosz , Waldemar Dworakowski , Zofia Dlugosz , Krzysztof Gongolewski
CPC classification number: G06K9/6211 , G06K9/3233 , G06T7/80 , G06T2207/30208 , G06T2207/30244
Abstract: A method for identification of characteristic points of a calibration pattern within an image includes: (i) overlaying a template arrangement of template points over the candidate point such that a principal point of the template points coincides with the candidate point, wherein the template arrangement corresponds to the calibration pattern or to a sub-pattern of the calibration pattern, (ii) for each template point of the template arrangement, except the principal point, identifying from the set of candidate points the candidate point closest to the template point, and (iii) determining a degree of deviation by summing the distances between each template point of the template arrangement, except the principal point, and the candidate point closest to this template point; and identifying as characteristic points of the calibration pattern all those candidate points of the set of candidate points with a degree of deviation below a deviation threshold.
-
公开(公告)号:US20180315180A1
公开(公告)日:2018-11-01
申请号:US15901551
申请日:2018-02-21
Applicant: FUJITSU LIMITED
Inventor: Joseph TOWNSEND
CPC classification number: G06T7/0008 , G01N29/06 , G06K9/3233 , G06K9/6218 , G06T2207/10024 , G06T2207/10132
Abstract: A computer-implemented method of automatically locating a portion of interest in image or matrix data derived from an item under consideration includes: identifying parts of the image or matrix data that satisfy a preset threshold as objects which are possibly parts of the portion of the interest; applying at least one preselected filter to the data corresponding to the objects to find a set of objects consisting of the objects most likely to be part of the portion of interest; sorting the objects of the set into clusters according to a predefined criterion; and using a known characteristic of the portion of interest to identify which one of the clusters corresponds to the portion of interest.
-
公开(公告)号:US20180285692A1
公开(公告)日:2018-10-04
申请号:US15486392
申请日:2017-04-13
Applicant: ULSee Inc.
Inventor: Jingjing Xiao
CPC classification number: G06K9/6269 , G06K9/00664 , G06K9/3233 , G06K9/4604 , G06K9/4628 , G06K9/6256 , G06K9/627 , G06K2009/3291 , G06T7/70 , G06T2210/12
Abstract: We propose a tracking framework that explicitly encodes both generic features and category-based features. The tracker consists of a shared convolutional network (NetS), which feeds into two parallel networks, NetC for classification and NetT for tracking. NetS is pre-trained on ImageNet to serve as a generic feature extractor across the different object categories for NetC and NetT.NetC utilizes those features within fully connected layers to classify the object category. NetT has multiple branches, corresponding to multiple categories, to distinguish the tracked object from the background. Since each branch in NetT is trained by the videos of a specific category or groups of similar categories, NetT encodes category-based features for tracking. During online tracking, NetC and NetT jointly determine the target regions with the right category and foreground labels for target estimation.
-
公开(公告)号:US20180285611A1
公开(公告)日:2018-10-04
申请号:US15764985
申请日:2016-09-29
Applicant: Datalogic IP Tech S.r.l.
Inventor: Francesco D'ERCOLI , Marco BASSANI , Claudio SAPORETTI , Marco CUMOLI
CPC classification number: G06K7/10722 , G06K7/10861 , G06K7/1413 , G06K7/1417 , G06K9/00201 , G06K9/3233 , G06K9/6289 , G06K2209/40 , H04N5/247 , H04N13/204
Abstract: The invention relates to a method and a system for reading coded information from an object. The system comprises one or more three-dimensional cameras configured such as to capture three-dimensional images of the object and a processor configured such as to process the captured three-dimensional images. The processor is designed to: identify planes upon which faces of the object lie; extract two-dimensional images that lie on the identified planes; and apply coded information recognition algorithms to at least part of the extracted two-dimensional images.
-
公开(公告)号:US20180270445A1
公开(公告)日:2018-09-20
申请号:US15926545
申请日:2018-03-20
Applicant: Samsung Electronics Co., Ltd.
Inventor: Gaurav KHANDELWAL , Madhupa CHOWDHURY , Ajay VIJAYVARGIYA , Alok Shankarlal SHUKLA
CPC classification number: H04N5/783 , G06K9/00758 , G06K9/00765 , G06K9/3233 , G06T2207/10016 , G11B27/005 , H04N5/23232 , H04N5/232945 , H04N5/247 , H04N5/772 , H04N21/4728
Abstract: A method and an electronic device for capturing and generating a video content from an initial video is provided. The method includes displaying a selected region of interest (ROI) in the video at a high frame rate and high-resolution. The generated video content includes a first region and a second region. The first region is obtained by capturing frames in the ROI of the initial video at a first frame rate. The second region is obtained by capturing full video frames at a second frame rate. The first region and the second region are then combined thereby generating a slow motion video.
-
公开(公告)号:US20180270436A1
公开(公告)日:2018-09-20
申请号:US15976640
申请日:2018-05-10
Applicant: Tobii AB
Inventor: Magnus Ivarsson , Per-Edvin Stoltz , David Masko , Niklas Ollesson , Mårten Skogö , Peter Blixt , Henrik Jönsson
CPC classification number: H04N5/378 , G06F3/012 , G06F3/013 , G06K9/00604 , G06K9/3208 , G06K9/3233 , G06T7/70 , G06T2207/10152 , H04N5/2256 , H04N5/332 , H04N5/345 , H04N9/04553
Abstract: Techniques for reducing a read out time and power consumption of an image sensor used for eye tracking are described. In an example, a position of an eye element in an active area of a sensor is determined. The eye element can be any of an eye, a pupil of the eye, an iris of the eye, or a glint at the eye. A region of interest (ROI) around the position of the eye is defined. The image sensor reads out pixels confined to the ROI, thereby generating an ROI image that shows the eye element.
-
18.
公开(公告)号:US20180260961A1
公开(公告)日:2018-09-13
申请号:US15909708
申请日:2018-03-01
Applicant: CANON KABUSHIKI KAISHA
Inventor: Yu Narita
CPC classification number: G06T7/20 , G06K9/3233 , G06K9/4609 , G06K9/4671 , G06K9/481 , G06K2009/3291 , G06K2009/6213 , G06T7/246 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021 , G06T2207/30241 , H04N5/232
Abstract: A circuitry of an image processing device divides a first image into a plurality of regions, extracts a feature point from each of the regions, tracks the feature point among a plurality of images to detect a motion vector, estimates a notable target of the first image, calculates the priority level of setting of a tracking feature point for each of the regions for tracking motion of the notable target, and sets the tracking feature point to any of the regions based on the priority level.
-
公开(公告)号:US20180260653A1
公开(公告)日:2018-09-13
申请号:US15979316
申请日:2018-05-14
Applicant: Oath Inc.
Inventor: Daozheng Chen , Mihyoung Sally Lee , Brian Webb , Ralph Rabbat , Ali Khodaei , Paul Krakow , Dave Todd , Samantha Giordano , Max Chern
CPC classification number: G06K9/46 , G06K9/3233 , G06K9/6289 , G06T3/0012
Abstract: Briefly, embodiments disclosed herein relate to image cropping, such as for digital images, for example.
-
公开(公告)号:US20180249095A1
公开(公告)日:2018-08-30
申请号:US15443751
申请日:2017-02-27
Applicant: Intel Corporation
Inventor: Chia-Hsun Lee , Haowei Liu , Amit Shahar
CPC classification number: G06T7/11 , G01N21/3563 , G01S7/4802 , G01S17/46 , G01S17/89 , G06K9/2018 , G06K9/209 , G06K9/3233 , G06K9/6267 , H04N13/254 , H04N13/271
Abstract: Systems, apparatuses, and/or methods to characterize a material. For example, and apparatus may include a pattern receiver to receive an IR pattern corresponding to non-uniform IR radiation that is to result from an interaction with a material, such as a translucent material. The apparatus may further include a characterizer to make a characterization of the material, such as a translucent material, based on the IR pattern. The characterization may differentiate the material, such as a translucent material, from one or more other materials, such as one or more other translucent materials.
-
-
-
-
-
-
-
-
-