公开(公告)号：US20170365084A1

公开(公告)日：2017-12-21

申请号：US15620043

申请日：2017-06-12

Applicant: FUJITSU LIMITED

Inventor： Naoko Hayashida

IPC: G06T13/40 ,  G02B27/01 ,  G06K9/00 ,  G06F3/01

CPC classification number: G06T13/40 ,  G02B27/017 ,  G02B27/0172 ,  G02B27/0179 ,  G02B2027/014 ,  G02B2027/0178 ,  G02B2027/0187 ,  G06F3/011 ,  G06F3/017 ,  G06K9/00201 ,  G06T2200/04 ,  G06T2219/024

Abstract: An image generating apparatus includes memory and processors programed to execute a process including acquiring first data indicating a position of a body portion of a predetermined person being sensed at first timing, generating a first image having the position of the body portion indicated by the first data reflected in an avatar representing the predetermined person, acquiring second data indicating a position of the body portion of the predetermined person being sensed at second timing, determining whether to reflect the position of the body portion of the body indicated by the second data in the avatar according to change in movement of the predetermined person from the first to the second data, and outputting a second image having the position of the body portion indicated by the second data reflected in the avatar when determined to reflect the position of the body portion indicated by the second data.

公开(公告)号：US20170364771A1

公开(公告)日：2017-12-21

申请号：US15624643

申请日：2017-06-15

Applicant: Pedro Henrique Oliveira Pinheiro ,  Ronan Stéfan Collobert ,  Piotr Dollar

Inventor： Pedro Henrique Oliveira Pinheiro ,  Ronan Stéfan Collobert ,  Piotr Dollar

IPC: G06K9/62 ,  G06N3/04 ,  G06N5/04 ,  G06N99/00

CPC classification number: G06K9/6212 ,  G06K9/00201 ,  G06K9/4628 ,  G06K9/6271 ,  G06N3/04 ,  G06N5/04 ,  G06N99/005

Abstract: In one embodiment, a plurality of patches of an image are processed using a first deep-learning model to detect a plurality of features associated with the first patch of the image. Each patch includes one or more pixels of the image. Using a second deep-learning model, a respective object proposal is generated for each of the plurality of patches of the image. The second deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and each object proposal includes a prediction as to a location of an object in the patch. Using a third deep-learning model, a respective score is computed for each object proposal generated using the second deep-learning model. The third deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and the object score may include a likelihood that the patch contains an entire object.

公开(公告)号：US20170345172A1

公开(公告)日：2017-11-30

申请号：US15601005

申请日：2017-05-22

Applicant: The Procter & Gamble Company

Inventor： Jennifer Joan Gustin ,  David John Maltbie

IPC: G06T7/521 ,  G06T7/174 ,  G06T7/00 ,  G06K9/00 ,  A61F13/15

CPC classification number: G06K9/00201 ,  A61F13/15203 ,  A61F13/84 ,  G06T7/001 ,  G06T2200/04 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10048 ,  G06T2207/30108 ,  G06T2207/30196

Abstract: A method of analyzing fit and appearance of absorbent articles. The method may include marking a panelist with markers and positioning the panelist in an orientation. The panelist may then be imaged with an image capture device. From the data gathered by the image capture device a first three dimensional surface representation may be generated. The panelist may also be imaged with an absorbent article. The panelist wearing the absorbent article may be placed in the orientation and imaged with the image capture device. The data gathered during the second imaging session may be used to generate a second three dimensional surface representation. Each of the first and second three dimensional surface representations may be aligned to the global coordinate system using the markers. The first and second three dimensional surface representations may be compared to one another to obtain information on volume, surface area, length, perimeter, and other characteristics.

公开(公告)号：US20170345165A1

公开(公告)日：2017-11-30

申请号：US15166595

申请日：2016-05-27

Applicant: Intel Corporation

Inventor： David Stanhill ,  Ziv Aviv

IPC: G06T7/269 ,  G06T7/50 ,  G06T7/55

CPC classification number: G06T7/269 ,  G06K9/00201 ,  G06K9/03 ,  G06K9/3233 ,  G06T7/11 ,  G06T7/50 ,  G06T7/55 ,  G06T2207/10028

Abstract: A three-dimensional depiction of an object to be tracked may be tracked using a depth sensing camera. An indication of the object's movement is developed. Also, an amount of pixels in the depiction that are not part of the object is estimated. Then the indication is corrected based on said amount of pixels that are not part of the object.

公开(公告)号：US09830704B1

公开(公告)日：2017-11-28

申请号：US15284420

申请日：2016-10-03

Applicant: Amazon Technologies, Inc.

Inventor： Pragyana K. Mishra

IPC: G06T7/00 ,  G06K9/00 ,  G06K9/46 ,  H04N5/77 ,  H04N7/18 ,  G06T7/40

CPC classification number: H04N7/181 ,  G06K9/00201 ,  G06K9/00221 ,  G06K9/00771 ,  G06K9/00791 ,  G06K9/00993 ,  G06K9/4661 ,  G06K9/6227 ,  G06K2009/00738 ,  G06K2209/01 ,  G06T7/004 ,  G06T7/0081 ,  G06T7/0085 ,  G06T7/408 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20056 ,  G06T2207/20081 ,  G06T2207/20144 ,  G06T2207/30232 ,  G06T2207/30244 ,  G06T2207/30252 ,  H04N1/00204 ,  H04N5/77 ,  H04N5/91 ,  H04N2101/00

Abstract: Where a plurality of machine learning algorithms is available to process information or data in the furtherance of a task, one of the algorithms may be identified as particularly well-suited or appropriate based on attributes of the information or data. Such attributes of the imaging data may be determined by any means, and a prediction as to the performance (e.g., one or more metrics) or success of each of the algorithms may be made. One of the algorithms may ultimately be selected based on such predictions, as well as the computing resources that are available for executing the algorithms, and any other relevant constraints.

公开(公告)号：US09826133B2

公开(公告)日：2017-11-21

申请号：US14807440

申请日：2015-07-23

Applicant: ORCAM TECHNOLOGIES LTD.

Inventor： Yonatan Wexler ,  Amnon Shashua

IPC: G06F1/18 ,  G06F1/16 ,  G06F3/01 ,  G02B27/00 ,  G02B27/01 ,  G06K9/00 ,  H04N5/232 ,  H04N7/18 ,  H04N1/21 ,  G06Q30/02 ,  G01S3/786 ,  H04N5/225 ,  G06F3/00 ,  G06F3/038 ,  H04N5/235 ,  G06F17/30 ,  G06T7/20 ,  H04N5/44 ,  G06K9/62 ,  G06F3/03 ,  G06T7/00 ,  G06T7/73

CPC classification number: H04N5/2259 ,  G01S3/7864 ,  G02B27/0093 ,  G02B27/017 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0178 ,  G02B2027/0187 ,  G06F1/163 ,  G06F1/1686 ,  G06F1/18 ,  G06F1/188 ,  G06F3/005 ,  G06F3/011 ,  G06F3/012 ,  G06F3/017 ,  G06F3/0304 ,  G06F3/038 ,  G06F17/30277 ,  G06F2203/011 ,  G06K9/00201 ,  G06K9/00208 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00335 ,  G06K9/00624 ,  G06K9/00671 ,  G06K9/00677 ,  G06K9/00718 ,  G06K9/6262 ,  G06K2209/21 ,  G06K2209/25 ,  G06Q30/0246 ,  G06Q30/0257 ,  G06Q30/0267 ,  G06Q30/0269 ,  G06T7/20 ,  G06T7/74 ,  G06T7/97 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/30232 ,  H04N1/2112 ,  H04N5/2251 ,  H04N5/2252 ,  H04N5/2254 ,  H04N5/2257 ,  H04N5/2258 ,  H04N5/23206 ,  H04N5/23216 ,  H04N5/23219 ,  H04N5/23229 ,  H04N5/23245 ,  H04N5/23258 ,  H04N5/2353 ,  H04N5/44 ,  H04N7/183 ,  H04N7/185

Abstract: A wearable apparatus and method are provided for capturing image data. In one implementation, a wearable apparatus for capturing image data is provided. The wearable apparatus includes at least one image sensor for capturing image data of an environment of a user, wherein a field of view of the image sensor includes a chin of the user. The wearable apparatus includes two or more microphones, and an attachment mechanism configured to enable the image sensor and microphones to be worn by the user. The wearable apparatus includes a processing device programmed to capture at least one image, identify the chin of the user to obtain a location of the chin, select a microphone from the two or more microphones based on the location, process input from the selected microphone using a first processing scheme, and process input from a microphone that is not selected using a second processing scheme.

公开(公告)号：US09824260B2

公开(公告)日：2017-11-21

申请号：US14793337

申请日：2015-07-07

Applicant: Microsoft Technology Licensing, LLC

Inventor： Anis Ahmad ,  Jonathan Hoof ,  Daniel Kennett

IPC: G06K9/00 ,  G06T5/00 ,  G06T19/00

CPC classification number: G06K9/00201 ,  G06T5/005 ,  G06T19/00 ,  G06T2207/10028

Abstract: Embodiments described herein can be used to detect holes in a subset of pixels of a depth image that has been specified as corresponding to a user, and to fill such detected holes. Additionally, embodiments described herein can be used to produce a low resolution version of a subset of pixels that has been specified as corresponding to a user, so that when an image including a representation of the user is displayed, the image respects the shape of the user, yet is not a mirror image of the user. Further, embodiments described herein can be used to identify pixels, of a subset of pixels specified as corresponding to the user, that likely correspond to a floor supporting the user. This enables the removal of the pixels, identified as likely corresponding to the floor, from the subset of pixels specified as corresponding to the user.

公开(公告)号：US20170323159A1

公开(公告)日：2017-11-09

申请号：US15220418

申请日：2016-07-27

Applicant: SMART THIRD-I LTD.

Inventor： Amos Cohen

IPC: G06K9/00 ,  H04M1/02

CPC classification number: G06K9/00671 ,  G06K9/00201 ,  G06K9/46 ,  H04M1/0264 ,  H04M1/0266 ,  H04M1/72522 ,  H04M2250/52

Abstract: Disclosed are methods, circuits, devices, systems and functionally associated machine executable code for obstacle avoidance and/or providing location related indicators/information. According to embodiments, there may be provided a mobile communication device comprising a digital display assembly with a digital display panel and display driving circuits to selectively drive current to display elements of the display panel in accordance with instructions provided by a processing unit. The processing unit is configured to instruct said display circuits to cause said display panel to display a screen including both user selected information and a video feed from a walking camera functionally associated with the mobile communication device.

公开(公告)号：US20170322633A1

公开(公告)日：2017-11-09

申请号：US15657465

申请日：2017-07-24

Applicant: EMPIRE TECHNOLOGY DEVELOPMENT LLC

Inventor： Zhen Shen ,  Qi Li ,  Xuefeng Song

IPC: G06F3/01 ,  G06K9/00 ,  G06F3/00 ,  G06F3/042

CPC classification number: G06F3/017 ,  G06F3/005 ,  G06F3/0416 ,  G06F3/0425 ,  G06F2203/04101 ,  G06F2203/04804 ,  G06K9/00201 ,  G06K9/00335

Abstract: In one example, a system may include a display including a display screen; a display controller configured to display visual information on the display screen of the display screen, control at least portions of one or more pixels corresponding to the display screen to render the display screen transparent; and a depth camera, positioned behind the display screen, that is configured to obtain depth image information of one or more objects in front of the display screen when at least portions of the one or more pixels are rendered transparent.

公开(公告)号：US09811752B2

公开(公告)日：2017-11-07

申请号：US14644086

申请日：2015-03-10

Applicant: Toyota Motor Engineering & Manufacturing North America, Inc.

Inventor： Kenichi Yamamoto

IPC: G06F1/16 ,  G06K9/00 ,  G06K9/32

CPC classification number: G06K9/3241 ,  G06F1/163 ,  G06K9/00201 ,  G06K9/00228 ,  G06K2209/21

Abstract: A wearable smart device includes a sensor configured to detect data corresponding to a detected object, a memory configured to store a contact list including contact information for a plurality of contact devices and to store stored data corresponding to a plurality of stored objects, an antenna and a processor. The processor is programmed to determine whether the detected object can be identified by comparing the detected data to the stored data, to transmit the detected data to at least one of the plurality of contact devices via the antenna in response to not being able to identify the detected object by comparing the detected data to the stored data and to receive an identification of the detected object from the at least one of the plurality of contact devices. The wearable smart device also includes an output unit to output the identification of the detected object.