公开(公告)号：US20190251331A1

公开(公告)日：2019-08-15

申请号：US16277469

申请日：2019-02-15

申请人： DMAI, Inc.

发明人： Nishant Shukla

IPC分类号： G06K9/00 ,  G06T7/73 ,  G06T7/80 ,  G10L15/22

CPC分类号： G06K9/00201 ,  G06K9/00248 ,  G06T7/73 ,  G06T7/80 ,  G06T2207/30201 ,  G06T2207/30241 ,  G06T2207/30242 ,  G10L15/22

摘要： The present teaching relates to method, system, medium, and implementations for understanding a three dimensional (3D) scene. Image data acquired by a camera at different time instances with respect to the 3D scene are received wherein the 3D scene includes a user or one or more objects. The face of the user is detected and tracked at different time instances. With respect to some of the time instances, a 2D user profile representing a region in the image data occupied by the user is generated based on a corresponding face detected and a corresponding 3D space in the 3D scene is estimated based on calibration parameters associated with the camera. Such estimated 3D space occupied by the user in the 3D scene is used to dynamically update a 3D space occupancy record of the 3D scene.

公开(公告)号：US20190247848A1

公开(公告)日：2019-08-15

申请号：US16309832

申请日：2017-06-14

申请人： CELLPLY S.R.L.

发明人： Massimo BOCCHI ,  Andrea FAENZA ,  Laura ROCCHI ,  Dario BISCARINI ,  Nicola PECORARI

IPC分类号： B01L3/00 ,  B01L3/02 ,  G01N1/30 ,  G01N33/50 ,  G01N35/10 ,  G01N1/31 ,  G01N15/14 ,  G06T7/00 ,  G06K9/00

CPC分类号： B01L3/50273 ,  B01L3/0275 ,  B01L3/502715 ,  B01L2200/027 ,  B01L2200/0689 ,  B01L2300/06 ,  B01L2300/0609 ,  B01L2300/0816 ,  B01L2300/0832 ,  B01L2300/0861 ,  B01L2400/04 ,  B01L2400/0406 ,  B01L2400/0487 ,  G01N1/30 ,  G01N1/31 ,  G01N15/1463 ,  G01N15/1484 ,  G01N33/5011 ,  G01N35/10 ,  G01N35/1011 ,  G01N2015/1006 ,  G01N2015/1493 ,  G01N2015/1497 ,  G01N2500/10 ,  G06K9/00147 ,  G06T7/0012 ,  G06T7/0014 ,  G06T2207/10056 ,  G06T2207/30024 ,  G06T2207/30072 ,  G06T2207/30242

摘要： A method for analysis of biological samples, implemented in a reversed open microwell system which includes an array of open microwells, a microchannel, an input port for reagents and/or biological samples and an output port. The ports are in microfluidic communication with the microchannel. The microchannel has a cross-section area of micrometric dimensions and provides fluid to the microwells. The microwell system is inserted in an automated management system that includes: an incubator at controlled temperature, humidity and CO2, fluid dispensing system, phase-contrast and fluorescence image acquisition. A kit introduces fluids in a microfluidic device that includes a tip. A microfluidic device and system include a microchannel and an input region having a vertical channel. The tip and the vertical channel are dimensioned to produce an interference coupling. A discharge region includes: a discharge container connected with the microfluidic device through a discharge channel and an output port.

公开(公告)号：US20190244340A1

公开(公告)日：2019-08-08

申请号：US16270397

申请日：2019-02-07

申请人： FLASCHEBOTTLE TECHNOLOGIES INC.

发明人： Philippe Perron ,  Yilong Zhang ,  Douglas Long

IPC分类号： G06T7/00 ,  G06T7/62 ,  G06K9/00

CPC分类号： G06T7/0002 ,  G06K9/00536 ,  G06T7/62 ,  G06T2207/30242

摘要： A computer-implemented method, a computer system, and a computer program product are provided for estimating output data that includes or is based on a number of containers, which may or may not be in receptacles. The method involves using an object detection algorithm operating on an input digital image to detect container images and receptacle images (if any), and using an estimation algorithm operating on the detected images to estimate the number of containers. Estimating the number of containers may involve counting the number of containers within different container classes, as determined by the object detection algorithm. Estimating the number of containers may involve estimating a size of a receptacle in a detected receptacle image based on analysis of a detected reference container image. A detected reference object image may be used to assist with classifying detected container images in different container classes.

公开(公告)号：US20190205679A1

公开(公告)日：2019-07-04

申请号：US16296774

申请日：2019-03-08

申请人： NEC CORPORATION

发明人： Shinichi MIYAMOTO

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/20 ,  G06T7/60 ,  G06T1/00

CPC分类号： G06K9/00838 ,  G06K9/00255 ,  G06K9/00261 ,  G06K9/00832 ,  G06K9/2018 ,  G06K9/209 ,  G06K9/624 ,  G06T1/00 ,  G06T7/60 ,  G06T2207/30242

摘要： The image processing system generates a plurality of separated images based on a first image acquired by photographing an object and a second image acquired by photographing the object in a state of receiving light of a first specific wavelength band. The image processing system specifies, from among the plurality of separated images, a separated image in which reflection on the object is reduced as compared to the first image. The image processing system outputs the separated image.

公开(公告)号：US20190188811A1

公开(公告)日：2019-06-20

申请号：US16276964

申请日：2019-02-15

申请人： Michael Sasson ,  Ron Zass ,  Shalom Bellaish ,  Moshe Nachman

发明人： Michael Sasson ,  Ron Zass ,  Shalom Bellaish ,  Moshe Nachman

IPC分类号： G06Q50/08 ,  G06Q40/02 ,  G06Q40/08 ,  G06T7/00 ,  G06K9/00

CPC分类号： G06T7/001 ,  G06K9/00624 ,  G06K9/00637 ,  G06K9/00671 ,  G06K9/6215 ,  G06K9/623 ,  G06K9/6256 ,  G06K9/78 ,  G06N20/00 ,  G06Q10/06311 ,  G06Q40/025 ,  G06Q40/08 ,  G06Q40/12 ,  G06Q50/08 ,  G06T7/0004 ,  G06T2207/20092 ,  G06T2207/30132 ,  G06T2207/30242

摘要： Systems and methods for generating financial assessments based on construction site images are provided. For example, image data captured from a construction site using at least one image sensor may be obtained. Further, at least one electronic record associated with the construction site may be obtained. The image data and the at least one electronic record may be analyzed to generate at least one financial assessment related to the construction site. For example, the image data may be analyzed to identify at least one discrepancy between the at least one electronic record and the construction site, and the identified at least one discrepancy may be used in the generation of the at least one financial assessment.

公开(公告)号：US20190130214A1

公开(公告)日：2019-05-02

申请号：US15797117

申请日：2017-10-30

申请人： SAP SE

发明人： Sivakumar N ,  Praveenkumar A K ,  Raghavendra D ,  Vijay G ,  Pratik Shenoy ,  Kishan Kumar Kedia

IPC分类号： G06K9/62 ,  G06N99/00 ,  G06N3/04 ,  G06T7/73 ,  G06T7/60 ,  G06K9/00

CPC分类号： G06K9/6256 ,  G06K9/00208 ,  G06K9/00771 ,  G06K9/00973 ,  G06K9/3241 ,  G06K9/34 ,  G06K9/4628 ,  G06K9/6204 ,  G06K9/6218 ,  G06K9/6268 ,  G06K9/6273 ,  G06K9/6284 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/084 ,  G06N5/047 ,  G06N20/00 ,  G06Q10/087 ,  G06T7/60 ,  G06T7/75 ,  G06T2200/28 ,  G06T2207/30242

摘要： In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.

公开(公告)号：US20190122381A1

公开(公告)日：2019-04-25

申请号：US15901397

申请日：2018-02-21

申请人： Microsoft Technology Licensing, LLC

发明人： Donna Katherine LONG ,  Arthur Charles TOMLIN ,  Kenneth Liam KIEMELE ,  John Benjamin HESKETH

IPC分类号： G06T7/70

CPC分类号： G06T7/70 ,  G06K9/00771 ,  G06K9/00993 ,  G06T2207/20081 ,  G06T2207/30242

摘要： The present disclosure provides apparatus and methods for automated tracking and counting of objects in a set of image frames using a resource-constrained device based on analysis of a selected subset of image frames, and based on selectively timing when resource-intensive operations are performed.

公开(公告)号：US20190120946A1

公开(公告)日：2019-04-25

申请号：US16161035

申请日：2018-10-15

申请人： DeepMap Inc.

发明人： Mark Damon Wheeler ,  Lin Yang

IPC分类号： G01S7/497 ,  G01S17/89 ,  G05D1/02

CPC分类号： H04N5/2329 ,  B60R1/00 ,  G01C21/3602 ,  G01S7/4817 ,  G01S7/497 ,  G01S7/4972 ,  G01S17/023 ,  G01S17/42 ,  G01S17/87 ,  G01S17/89 ,  G01S17/936 ,  G05D1/0088 ,  G05D1/0231 ,  G05D1/0248 ,  G05D1/0287 ,  G05D2201/0213 ,  G06K9/00791 ,  G06K9/6202 ,  G06T7/13 ,  G06T7/33 ,  G06T7/55 ,  G06T7/80 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20092 ,  G06T2207/20221 ,  G06T2207/30241 ,  G06T2207/30242 ,  G06T2207/30252 ,  H04N5/04 ,  H04N5/2253 ,  H04N5/232 ,  H04N5/247 ,  H04N13/106

摘要： A system calibrates one or more sensors mounted to an autonomous vehicle. From the one or more sensors, the system identifies a primary sensor and a secondary sensor. The system determines a reference angle for the primary sensor, and based on that reference angle for the primary sensor, a scan-start time representing a start of a scan and a scan-end time representing an end of a scan. The system receives, from the primary sensor, a primary set of scan data recorded from the scan-start time to the scan-end time. The system receives, from the secondary sensor, a secondary set of sensor data recorded from the scan-start time to the scan-end time. The system calibrates the primary and secondary sensors by determining a relative transform for transforming points between the first set of scan data and the second set of scan data.

公开(公告)号：US20190096056A1

公开(公告)日：2019-03-28

申请号：US15714339

申请日：2017-09-25

申请人： United Technologies Corporation

发明人： Michael J. Giering ,  Ryan B. Noraas ,  Kishore K. Reddy ,  Edgar A. Bernal

IPC分类号： G06T7/00 ,  G06T7/13 ,  G06T7/12 ,  G06K9/62

CPC分类号： G06T7/0006 ,  G06K9/6202 ,  G06K9/6289 ,  G06T7/0004 ,  G06T7/001 ,  G06T7/12 ,  G06T7/13 ,  G06T7/174 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20152 ,  G06T2207/20221 ,  G06T2207/30136 ,  G06T2207/30164 ,  G06T2207/30242

摘要： A material characterization system includes an imaging unit, a material characterization controller, and an imaging unit controller. The electronic imaging unit generates a test image of a specimen composed of a material. The electronic material characterization controller determines values of a plurality of parameters and maps the parameters to corresponding ground truth labeled outputs. The mapped parameters are applied to at least one test image to predict a presence of at least one target attribute of the specimen in response to applying the learned parameters. The test image is convert to a selected output image format so as to generate a synthetic image including the predicted at least one attribute. The electronic imaging unit controller performs a material characterization analysis that characterizes the material of the specimen based on the predicted at least one attribute included in the synthetic image.

公开(公告)号：US20180359411A1

公开(公告)日：2018-12-13

申请号：US15399531

申请日：2017-01-05

申请人： Nixie Labs, Inc.

发明人： Christoph Benedikt Kohstall ,  Jelena Jovanovic

IPC分类号： H04N5/232

CPC分类号： H04N5/23222 ,  G06T7/70 ,  G06T2207/20081 ,  G06T2207/30242 ,  H04N5/23212 ,  H04N5/23296 ,  H04N5/23299

摘要： Cameras with autonomous adjustment and learning functions and associated systems and methods are disclosed. A camera in accordance with a particular embodiment includes a system that determines a parameter of each of a plurality of existing photographs, the parameter being representative of a characteristic of each existing photograph, determines a figure of merit associated with each existing photograph, the figure of merit being representative of a price, popularity, and/or reputation of each existing photograph, and correlates the figures of merit with the parameters to determine a target parameter. A camera in accordance with another embodiment can include a system that analyzes a preview image from the camera, classifies the preview image, determines a parameter of the preview image associated with the classification, compares the parameter to the target parameter, and adjusts the camera to cause the preview image to have the target parameter.