公开(公告)号：US09679191B1

公开(公告)日：2017-06-13

申请号：US14792995

申请日：2015-07-07

Applicant: Waymo LLC

Inventor： Jiajun Zhu ,  Christopher Paul Urmson ,  Dirk Haehnel ,  Nathaniel Fairfield ,  Russell Leigh Smith

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  B60R1/00

CPC classification number: G06K9/00201 ,  B60R1/00 ,  B60R2300/30 ,  B60W30/08 ,  B60W30/186 ,  B60W2050/0292 ,  B60W2530/14 ,  B60W2550/22 ,  B62D6/00 ,  G01C21/3617 ,  G05D1/0055 ,  G05D1/0088 ,  G05D1/021 ,  G05D1/0214 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0257 ,  G05D1/0274 ,  G05D1/0276 ,  G05D1/0278 ,  G05D2201/0213 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/3241 ,  G06T7/0044 ,  G06T7/0057 ,  G06T7/20 ,  G06T7/223 ,  G06T7/231 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/30236 ,  G06T2207/30252 ,  G06T2207/30261

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

公开(公告)号：US20170161546A1

公开(公告)日：2017-06-08

申请号：US14962239

申请日：2015-12-08

Applicant: Mitsubishi Electric Research Laboratories, Inc.

Inventor： Esra Cansizoglu ,  Yuichi Taguchi

IPC: G06K9/00 ,  G06K9/32 ,  G06T7/00 ,  H04N13/02

CPC classification number: G06K9/00201 ,  G06K9/00214 ,  G06K9/3233 ,  G06K9/6211 ,  G06K9/6261 ,  G06T7/73 ,  G06T2200/04 ,  G06T2207/10004 ,  H04N13/204 ,  H04N2013/0074 ,  H04N2013/0092

Abstract: A method and system detects and localizes an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The frame are segmented into segments, wherein each segment includes one or more features, and for each segment, searching an object map for a similar segment, and only if there is a similar segment in the object map, registering the segment in the frame with the similar segment to obtain a predicted pose of the object. The predicted poses are combined to obtain the pose of the object, which can be outputted.

公开(公告)号：US20170155887A1

公开(公告)日：2017-06-01

申请号：US15396790

申请日：2017-01-02

Applicant: Amazon Technologies, Inc.

Inventor： Dong Zhou

IPC: H04N13/02 ,  H04N13/00 ,  H04N5/232 ,  H04N5/265 ,  H04N13/04 ,  G06K9/00

CPC classification number: H04N13/239 ,  G06K9/00 ,  G06K9/00201 ,  G06K9/00744 ,  G06K9/228 ,  G06T5/002 ,  G06T5/50 ,  G06T2207/10021 ,  G06T2207/30201 ,  H04N5/23248 ,  H04N5/23258 ,  H04N5/23264 ,  H04N5/23267 ,  H04N5/265 ,  H04N13/128 ,  H04N13/25 ,  H04N2013/0081

Abstract: Depth information can be used to assist with image processing functionality, such as image stabilization and blur reduction. In at least some embodiments, depth information obtained from stereo imaging or distance sensing, for example, can be used to determine a foreground object and background object(s) for an image or frame of video. The foreground object then can be located in later frames of video or subsequent images. Small offsets of the foreground object can be determined, and the offset accounted for by adjusting the subsequent frames or images. Such an approach provides image stabilization for at least a foreground object, while providing simplified processing and reduce power consumption. Similarly processes can be used to reduce blur for an identified foreground object in a series of images, where the blur of the identified object is analyzed.

公开(公告)号：US20170154211A1

公开(公告)日：2017-06-01

申请号：US15430133

申请日：2017-02-10

Applicant: Victor Shaburov ,  Yurii Monastyrshyn

Inventor： Victor Shaburov ,  Yurii Monastyrshyn

IPC: G06K9/00 ,  G06Q30/02 ,  G06T7/33 ,  G10L25/63 ,  H04N7/15 ,  H04N7/14

CPC classification number: G06K9/00315 ,  G06K9/00201 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/6209 ,  G06Q30/0281 ,  G06T7/337 ,  G06T7/344 ,  G06T2207/10016 ,  G06T2207/30201 ,  G10L25/57 ,  G10L25/63 ,  H04N7/147 ,  H04N7/15

Abstract: Methods and systems for videoconferencing include recognition of emotions related to one videoconference participant such as a customer. This ultimately enables another videoconference participant, such as a service provider or supervisor, to handle angry, annoyed, or distressed customers. One example method includes the steps of receiving a video that includes a sequence of images, detecting at least one object of interest (e.g., a face), locating feature reference points of the at least one object of interest, aligning a virtual face mesh to the at least one object of interest based on the feature reference points, finding over the sequence of images at least one deformation of the virtual face mesh that reflect face mimics, determining that the at least one deformation refers to a facial emotion selected from a plurality of reference facial emotions, and generating a communication bearing data associated with the facial emotion.

公开(公告)号：US09658620B1

公开(公告)日：2017-05-23

申请号：US14727273

申请日：2015-06-01

Applicant: Waymo LLC

Inventor： Christopher Paul Urmson ,  Dmitri A. Dolgov ,  Andrew Hughes Chatham ,  Philip Nemec

IPC: B62D6/00 ,  G05D1/02 ,  G05D1/00 ,  G01C21/36

CPC classification number: G06K9/00201 ,  B60R1/00 ,  B60R2300/30 ,  B60W30/08 ,  B60W30/186 ,  B60W2050/0292 ,  B60W2530/14 ,  B60W2550/22 ,  B62D6/00 ,  G01C21/3617 ,  G05D1/0055 ,  G05D1/0088 ,  G05D1/021 ,  G05D1/0214 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0257 ,  G05D1/0274 ,  G05D1/0276 ,  G05D1/0278 ,  G05D2201/0213 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/3241 ,  G06T7/0044 ,  G06T7/0057 ,  G06T7/20 ,  G06T7/223 ,  G06T7/231 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/30236 ,  G06T2207/30252 ,  G06T2207/30261

Abstract: A system and method is provided of providing recommendations to a user of a vehicle. In one aspect, the vehicle navigates autonomously and the sensors provide information that is based on the location of the vehicle and output from sensors directed to the environment surrounding the vehicle. In further aspects, both current and previous sensor data is used to make the recommendation, as well as data based on the sensors of other vehicles.

公开(公告)号：US09646335B2

公开(公告)日：2017-05-09

申请号：US14863325

申请日：2015-09-23

Applicant: A9.com, Inc.

Inventor： Xiaofan Lin ,  Arnab Sanat Kumar Dhua ,  Douglas Ryan Gray ,  Atul Kumar ,  Yu Lou

IPC: G06K9/00 ,  G06Q30/06 ,  G06F3/00

CPC classification number: H04N5/23293 ,  G06F3/005 ,  G06K9/00201 ,  G06K9/00456 ,  G06K9/00671 ,  G06K9/344 ,  G06Q30/0269 ,  G06Q30/0623 ,  G06Q30/0641 ,  G06T11/60

Abstract: Various embodiments enable a computing device to perform tasks such as processing an image to recognize text or an object in an image to identify a particular product or related products associated with the text or object. In response to recognizing the text or the object as being associated with a product available for purchase from an electronic marketplace, one or more advertisements or product listings associated with the product can be displayed to the user. Accordingly, additional information for the associated product can be displayed, enabling the user to learn more about and purchase the product from the electronic marketplace through the portable computing device.

公开(公告)号：US20170121113A1

公开(公告)日：2017-05-04

申请号：US15260837

申请日：2016-09-09

Applicant: Berkshire Grey Inc.

Inventor： Thomas WAGNER ,  Kevin AHEARN ,  Benjamin COHEN ,  Michael DAWSON-HAGGERTY ,  Christopher GEYER ,  Thomas KOLETSCHKA ,  Kyle MARONEY ,  Matthew T. MASON ,  Gene Temple PRICE ,  Joseph ROMANO ,  Daniel SMITH ,  Siddhartha SRINIVASA ,  Prasanna VELAGAPUDI ,  Thomas ALLEN

IPC: B65G1/137 ,  G05B19/12 ,  B25J19/02

CPC classification number: G06K7/1443 ,  B25J9/1694 ,  B25J9/1697 ,  B25J19/022 ,  B25J19/023 ,  B65G1/1373 ,  G05B19/124 ,  G05B19/4183 ,  G05B2219/14005 ,  G05B2219/36371 ,  G05B2219/45045 ,  G05B2219/45047 ,  G05B2219/45063 ,  G06K7/10693 ,  G06K7/1404 ,  G06K7/1447 ,  G06K9/00033 ,  G06K9/00201 ,  G06K19/06028 ,  G06K2209/19 ,  G06Q10/087 ,  Y02P90/10

Abstract: A robotic system is disclosed that include an articulated arm and a first perception system for inspecting an object, as well as a plurality of additional perception systems, each of which is arranged to be directed toward a common area in which an object may be positioned by the robotic arm such that a plurality of views within the common area may be obtained by the plurality of additional perception systems.

公开(公告)号：US09630320B1

公开(公告)日：2017-04-25

申请号：US14793246

申请日：2015-07-07

Applicant: Industrial Perception, Inc.

Inventor： Kurt Konolige ,  Ethan Rublee ,  Stefan Hinterstoisser ,  Troy Straszheim ,  Gary Bradski ,  Hauke Malte Strasdat

IPC: G05B19/04 ,  G05B19/18 ,  B25J9/16 ,  G06T19/00 ,  G06T7/00

CPC classification number: B25J9/163 ,  B25J5/00 ,  B25J9/0093 ,  B25J9/1612 ,  B25J9/162 ,  B25J9/1664 ,  B25J9/1671 ,  B25J9/1687 ,  B25J9/1694 ,  B25J9/1697 ,  B25J19/00 ,  B25J19/021 ,  B65G41/008 ,  B65G47/46 ,  B65G47/50 ,  B65G61/00 ,  B65H67/065 ,  G01B11/254 ,  G05B2219/31312 ,  G05B2219/39391 ,  G05B2219/40053 ,  G05B2219/40298 ,  G05B2219/40442 ,  G05B2219/40543 ,  G06K9/00201 ,  G06K9/00664 ,  G06K9/3208 ,  G06K9/4604 ,  G06K9/4661 ,  G06K9/52 ,  G06K9/6202 ,  G06T7/0065 ,  G06T7/13 ,  G06T7/529 ,  G06T7/55 ,  G06T7/593 ,  G06T7/60 ,  G06T17/00 ,  G06T19/003 ,  G06T2200/04 ,  H04N5/33 ,  H04N13/239 ,  H04N2013/0081 ,  Y10S901/01 ,  Y10S901/02 ,  Y10S901/06 ,  Y10S901/09 ,  Y10S901/47

Abstract: Methods and systems for detecting and reconstructing environments to facilitate robotic interaction with such environments are described. An example method may involve determining a three-dimensional (3D) virtual environment representative of a physical environment of the robotic manipulator including a plurality of 3D virtual objects corresponding to respective physical objects in the physical environment. The method may then involve determining two-dimensional (2D) images of the virtual environment including 2D depth maps. The method may then involve determining portions of the 2D images that correspond to a given one or more physical objects. The method may then involve determining, based on the portions and the 2D depth maps, 3D models corresponding to the portions. The method may then involve, based on the 3D models, selecting a physical object from the given one or more physical objects. The method may then involve providing an instruction to the robotic manipulator to move that object.

公开(公告)号：US09628755B2

公开(公告)日：2017-04-18

申请号：US12904980

申请日：2010-10-14

Applicant: Brian McDowell ,  Darren Apfel

Inventor： Brian McDowell ,  Darren Apfel

IPC: H04N7/01 ,  G06K9/00 ,  G06K9/20 ,  G06T7/20 ,  H04N13/02 ,  H04N7/14 ,  G06T7/246

CPC classification number: H04N7/147 ,  A63F2300/572 ,  G06K9/00201 ,  G06K9/00261 ,  G06K9/2036 ,  G06T7/248 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/30196 ,  H04N13/204

Abstract: A system for automatically tracking movement of a user participating in a video chat application executing in a computing device is disclosed. A capture device connected to the computing device captures a user in a field of view of the capture device and identifies a sub-frame of pixels identifying a position of the head, neck and shoulders of the user in a capture frame of a capture area. The sub-frame of pixels is displayed to a remote user at a remote computing system who is participating in the video chat application with the user. The capture device automatically tracks the position of the head, neck and shoulders of the user as the user moves to a next location within the capture area. A next sub-frame of pixels identifying a position of the head, neck and shoulders of the user in the next location is identified and displayed to the remote user at the remote computing device.

公开(公告)号：US20170097413A1

公开(公告)日：2017-04-06

申请号：US15286512

申请日：2016-10-05

Applicant: Google Inc.

Inventor： Nicholas Edward Gillian ,  Carsten C. Schwesig ,  Jaime Lien ,  Patrick M. Amihood ,  Ivan Poupyrev

IPC: G01S13/86 ,  G01S7/41

CPC classification number: G06F3/017 ,  A63F13/21 ,  A63F13/24 ,  A63F2300/8082 ,  G01S7/41 ,  G01S7/415 ,  G01S13/56 ,  G01S13/66 ,  G01S13/86 ,  G01S13/865 ,  G01S13/867 ,  G01S13/90 ,  G01S13/931 ,  G01S19/42 ,  G06F1/163 ,  G06F3/011 ,  G06F3/0346 ,  G06F3/0484 ,  G06F3/165 ,  G06F16/245 ,  G06F21/6245 ,  G06F2203/0384 ,  G06K9/00201 ,  G06K9/6288 ,  G06K9/629 ,  G06T7/75 ,  G08C17/02 ,  G08C2201/93 ,  H04Q9/00 ,  H04Q2209/883

Abstract: This document describes apparatuses and techniques for radar-enabled sensor fusion. In some aspects, a radar field is provided and reflection signals that correspond to a target in the radar field are received. The reflection signals are transformed to provide radar data, from which a radar feature indicating a physical characteristic of the target is extracted. Based on the radar features, a sensor is activated to provide supplemental sensor data associated with the physical characteristic. The radar feature is then augmented with the supplemental sensor data to enhance the radar feature, such as by increasing an accuracy or resolution of the radar feature. By so doing, performance of sensor-based applications, which rely on the enhanced radar features, can be improved.