公开(公告)号：WO2022250783A2

公开(公告)日：2022-12-01

申请号：PCT/US2022/022851

申请日：2022-03-31

申请人： MASSACHUSETTS INSTITUTE OF TECHNOLOGY

发明人： DEANGELUS, Marianne, A. ,  GOODWIN, Justin ,  KAUSHIK, Neela ,  OPIPARI, Anthony ,  KILLIAN, Taylor

IPC分类号： G06V10/00 ,  G01S13/865 ,  G01S13/867 ,  G01S13/887 ,  G01S13/89 ,  G01S17/894 ,  G06V10/454 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/82 ,  G06V20/52 ,  G06V2201/05

摘要： Described herein are systems for detecting a representation of an object in a radio frequency (RF) image. The system transmits one or more first RF signals toward an object, and receives one or more second RF signals, associated with the one or more transmitted RF signals, that have been reflected from the object. The system determines a plurality of first feature maps corresponding to a RF image associated with the one or more second RF signals. The system combines the plurality of first feature maps. The system further detects a representation of the object in the RF image based at least in part on the combined plurality of first feature maps.

公开(公告)号：WO2021144505A1

公开(公告)日：2021-07-22

申请号：PCT/FI2021/050021

申请日：2021-01-14

申请人： TEKNOLOGIAN TUTKIMUSKESKUS VTT OY

发明人： KORKALO, Otto ,  KEMPPI, Paul ,  HONKAMAA, Petri ,  KIURU, Tero ,  HIRVONEN, Mervi

IPC分类号： G01S7/40 ,  G01S7/41 ,  G01S13/86 ,  G01S13/89 ,  G01S13/42 ,  G01S13/931 ,  G01S13/865 ,  G01S13/933 ,  G01S7/4052 ,  G01S7/406 ,  G01S7/4082 ,  G01S7/417

摘要： According to an example aspect of the present invention, there is provided a method comprising, receiving, from a radar, a first reflected signal and a second reflected signal, determining a reference signal of the first reflected signal and training an artificial neural network using the first reflected signal and the reference signal of the first reflected signal, upon training, determining an output of the artificial neural network associated with the first reflected signal and providing a magnitude and angle image of the radar associated with the second reflected signal based on the output of the artificial neural network associated with the first reflected signal.

公开(公告)号：WO2021122337A1

公开(公告)日：2021-06-24

申请号：PCT/EP2020/085649

申请日：2020-12-10

申请人： VOLKSWAGEN AKTIENGESELLSCHAFT

发明人： SCHLICHT, Peter ,  HÜGER, Fabian

IPC分类号： G01S17/86 ,  G01S17/931 ,  G01S17/89 ,  G06T5/00 ,  G01S13/86 ,  G01S15/931 ,  G01S13/931 ,  G01S7/02 ,  G01S7/36 ,  G01S7/495 ,  G01S7/537 ,  G01S13/89 ,  G01S13/862 ,  G01S13/865 ,  G01S13/867 ,  G01S15/86 ,  G01S2013/9323 ,  G01S2013/9324 ,  G01S7/023 ,  G06K9/00805 ,  G06K9/036 ,  G06K9/6255 ,  G06K9/6273 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30168 ,  G06T2207/30252 ,  G06T7/001

摘要： Die Erfindung betrifft ein Verfahren zum Erkennen einer Entfremdung einer Sensordatendomäne von einer Referenzdatendomäne, wobei erfasste Sensordaten (10) mindestens eines Sensors (51) empfangen werden, wobei mittels eines Distanzmaßes jeweils Distanzen (11) zwischen Teilausschnitten (23) der empfangenen Sensordaten (10) und zum stückweisen Ersetzen mittels Quilting der Sensordaten (10) verwendeten und der Referenzdatendomäne angehörenden Sensordatenpatches (60) bestimmt werden oder solche Distanzen (11) erhalten werden, und wobei ein Entfremdungssignal (21) in Abhängigkeit der bestimmten Distanzen (11) erzeugt und bereitgestellt wird. Ferner betrifft die Erfindung eine Vorrichtung (1) zum Erkennen einer Entfremdung einer Sensordatendomäne von einer Referenzdatendomäne, ein Kraftfahrzeug (50) mit mindestens einer solchen Vorrichtung (1) sowie ein Computerprogramm und ein Datenträgersignal.

公开(公告)号：WO2022241345A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/071238

申请日：2022-03-21

申请人： QUALCOMM INCORPORATED

发明人： ANSARI, Amin ,  SUBRAMANIAN, Sundar ,  GOWAIKAR, Radhika Dilip ,  SADEK, Ahmed Kamel ,  JOHN WILSON, Makesh Pravin ,  SLOBODYANYUK, Volodimir ,  SANYAL, Shantanu Chaisson ,  HAMILTON, Michael John

IPC分类号： G01S13/86 ,  G01S7/41 ,  G01S13/42 ,  G01S13/931 ,  G06T7/50 ,  G01S13/865 ,  G01S13/867 ,  G01S13/89 ,  G01S2013/93273 ,  G01S7/417 ,  G06N20/00 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30252 ,  G06T7/11 ,  G06T7/521 ,  G06T7/579

摘要： A device for processing image data is disclosed. The device can obtain a radar point cloud and one or more frames of camera data. The device can determine depth estimates of one or more pixels of the one or more frames of camera data. The device can generate a pseudo lidar point cloud using the depth estimates of the one or more pixels of the one or more frames of camera data, wherein the pseudo lidar point cloud comprises a three-dimensional representation of at least one frame of the one or more frames of camera data. The device can determine one or more object bounding boxes based on the radar point cloud and the pseudo lidar point cloud.

公开(公告)号：WO2021262603A1

公开(公告)日：2021-12-30

申请号：PCT/US2021/038262

申请日：2021-06-21

申请人： NVIDIA CORPORATION

发明人： PARK, Minwoo ,  KWON, Junghyun ,  KOCAMAZ, Mehmet K. ,  SEO, Hae-Jong ,  RODRIGUEZ HERVAS, Berta ,  CHOE, Tae Eun

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06K9/68 ,  G06K9/20 ,  B60W2554/4029 ,  B60W2554/4044 ,  B60W2556/35 ,  B60W60/00272 ,  G01S13/862 ,  G01S13/865 ,  G01S13/867 ,  G01S13/931 ,  G01S17/931 ,  G01S2013/93271 ,  G01S2015/938 ,  G06K9/6288 ,  G06K9/6293 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/0481 ,  G06N3/084 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T7/292 ,  G06V10/16 ,  G06V10/454 ,  G06V20/56 ,  G06V20/58 ,  G06V20/588 ,  G06V30/2552

摘要： In various examples, a multi-sensor fusion machine learning model – such as a deep neural network (DNN) – may be deployed to fuse data from a plurality of individual machine learning models. As such, the multi-sensor fusion network may use outputs from a plurality of machine learning models as input to generate a fused output that represents data from fields of view or sensory fields of each of the sensors supplying the machine learning models, while accounting for learned associations between boundary or overlap regions of the various fields of view of the source sensors. In this way, the fused output may be less likely to include duplicate, inaccurate, or noisy data with respect to objects or features in the environment, as the fusion network may be trained to account for multiple instances of a same object appearing in different input representations.

公开(公告)号：WO2021229523A2

公开(公告)日：2021-11-18

申请号：PCT/IB2021/054147

申请日：2021-05-14

申请人： MARTELLA S.R.L. ,  FAITA, Marco Mario

发明人： MARTELLA, Simona

IPC分类号： G01S11/12 ,  G01S5/16 ,  G01S13/76 ,  G01S13/86 ,  G01S13/88 ,  G08B21/02 ,  G08B21/22 ,  G16H40/63 ,  G16H50/80 ,  H04W74/08 ,  G01S13/765 ,  G01S13/865 ,  G01S17/74 ,  G08B21/0266

摘要： The present invention describes an electronic personal protective device (2) comprising a rechargeable battery (3), a transceiver (4) configured to send and receive wireless signals (FR1, FR2) with predetermined power and sensitivity as a function of the action radius (r) which is to be monitored, a memory unit (5) containing a unique recognition code (ID1, ID2), an actuator (6) configured to warn the person wearing said electronic device (2), a processing unit (20) configured to: generate and send to said transceiver (4) a frame (FR1, FR2) at programmable time intervals (Tadv), receive and process frames (FR1, FR2) sent from other electronic personal protective devices (2) placed within said action radius (r), generate an alarm signal (S_AL), if a second electronic device (2) is located within said action radius (r), send said alarm signal (S_AL) to said actuator (6). The invention further describes a corresponding method and computer program.

公开(公告)号：WO2020180503A1

公开(公告)日：2020-09-10

申请号：PCT/US2020/019283

申请日：2020-02-21

申请人： WAYMO LLC

发明人： WACHTER, Luke ,  DROZ, Pierre-Yyves

IPC分类号： G01S7/497 ,  G01S7/4861 ,  G01S7/481 ,  G01S7/4865 ,  G01S17/931 ,  G01S13/865 ,  G01S13/867 ,  G01S13/931 ,  G01S15/86 ,  G01S17/86 ,  G01S2013/93273 ,  G01S7/4815 ,  G01S7/4817 ,  G01S7/4863 ,  G06K9/0063

摘要： Example embodiments relate to range calibration of light detectors. An example method includes emitting a first light signal toward a first region of a calibration target having a first reflectivity and detecting a reflection of the first light signal. The detected reflection of the first light signal has a first intensity. The example method further includes emitting a second light signal toward a second region of the calibration target having a second reflectivity and detecting a reflection of the second light signal from the second region of the calibration target. The detected reflection of the second light signal has a second intensity. Still further, the example method includes determining a first apparent range based on the detected reflection of the first light signal, determining a second apparent range based on the detected reflection of the second light signal, and generating walk-error calibration data for the detector.

公开(公告)号：WO2022150070A2

公开(公告)日：2022-07-14

申请号：PCT/US2021/051391

申请日：2021-09-22

申请人： COAST AUTONOMOUS, INC.

发明人： LEFEVRE, Pierre ,  ROYERE, Cyril

IPC分类号： B60W60/00 ,  B60W40/02 ,  B60W40/105 ,  B60W10/20 ,  B60W30/08 ,  B60W30/18 ,  B60W50/00 ,  B60W2050/0091 ,  B60W2050/0292 ,  B60W2420/42 ,  B60W2420/52 ,  B60W2556/10 ,  B60W2556/35 ,  B60W2710/20 ,  B60W2720/10 ,  B60W2720/12 ,  B60W30/09 ,  B60W50/029 ,  B60W60/0015 ,  G01S13/865 ,  G01S13/867 ,  G01S13/931 ,  G01S17/86 ,  G01S17/931 ,  G01S2013/9318 ,  G01S2013/93185 ,  G01S2013/9319 ,  G01S2013/9321 ,  G01S2013/9323 ,  G01S2013/9324

摘要： A system for controlling autonomous vehicles includes a first sensor system having a first sensor and a first data box. The first sensor system may be configured to determine a first vehicle control decision. The system may further include a second sensor system including a second sensor and a second data box. The second sensor system may be configured to determine a second vehicle control decision. The system further includes a controller configured to receive the first vehicle control decision and the second vehicle control decision from the first sensor system and the second sensor system; determine a priority ranking for the first vehicle control decision and the second vehicle control decision; select, based on the priority ranking, a vehicle control decision from the first vehicle control decision and the second vehicle control decision; and implement, responsive to the determining, the selected vehicle control decision.

公开(公告)号：WO2022029685A1

公开(公告)日：2022-02-10

申请号：PCT/IB2021/057213

申请日：2021-08-05

申请人： SPECTROMA LIMITED

发明人： EDWARDS, David John ,  EDWARDS, Charlotte Elizabeth

IPC分类号： A61B5/0507 ,  G03H1/00 ,  G01S13/89 ,  G01N22/00 ,  A61B5/0536 ,  G01N29/00 ,  G01S13/42 ,  G01S13/865 ,  G01S13/867 ,  G01S15/89 ,  G01S17/89 ,  G01S7/024 ,  G01S7/03 ,  G03H1/0443 ,  G03H1/0866 ,  G03H2001/266 ,  G03H2001/267 ,  G03H2210/33 ,  G03H2222/14 ,  G03H2226/13 ,  G03H5/00

摘要： A microwave imaging system and method are disclosed for generating a 3-D map of a body. The system comprises a source of coherent microwave radiation for irradiating the body, at least one microwave detector for detecting at a plurality of locations around the body the amplitude and phase of radiation that has passed through, or has been reflected by, the body, an analyser connected to receive signals from the or each detector and from the source and operative to produce a holographic image indicative at each detection location the phase of the received radiation relative to the phase of radiation received directly from the source at the same location, and a processor for processing the holographic image to calculate in three dimensions the positions of localized physical parameters within the body.

公开(公告)号：WO2021242392A2

公开(公告)日：2021-12-02

申请号：PCT/US2021/024689

申请日：2021-03-29

申请人： BATTELLE MEMORIAL INSTITUTE

发明人： GEORGE, Anthony ,  KENT, Thomas ,  MILLER, Blaine ,  LISZEWSKI, Katie ,  GILABERT, Russell ,  MCDONLEY, Timothy

IPC分类号： G01N21/88 ,  G01N21/956 ,  G01N2021/8845 ,  G01N2021/8867 ,  G01N2021/95638 ,  G01N21/8806 ,  G01N21/8851 ,  G01N21/95684 ,  G01S13/865 ,  G01S13/89 ,  G01S17/86 ,  G01S17/89 ,  G06T3/0068 ,  G06T3/4038

摘要： A multimodal inspection system (MIS) is disclosed herein. The MIS may use one or more modalities to inspect a sample. Some of the modalities include, but are not limited to, Raman, visible (VIS), terahertz (THz) spectroscopy, longwave infrared (LWIR), shortwave infrared (SWIR), laser profilometry (LP), electromagnetic interference (EMI) near field probing, and/or, Millimeter Wave (MMW) radar.