-
公开(公告)号:US20190244026A1
公开(公告)日:2019-08-08
申请号:US16267455
申请日:2019-02-05
申请人: Robert Bosch GmbH
CPC分类号: G06K9/00677 , G06K9/00523 , G06K9/00536 , G06N3/08 , G06N20/00 , G06T7/20 , G06T2207/30241 , H04N5/23206 , H04N5/247
摘要: A method for training a person recognition model using images from a camera 100, wherein the method has at least a reading-in step in which a detection signal 135 representing a detected person within a monitoring area of at least the camera 100 in a camera network is read in. The method also has at least a collecting step in which a plurality of image signals 140 from the camera 100 are collected using the detection signal 135 which has been read in, wherein the collected image signals 140 represent a recorded image section from each image from the camera 100. Finally, the method has at least an adapting step in which the person recognition model is adapted using the collected image signals 140 in order to recognize the detected person in an image from the camera 100 or from an at least second camera in the camera network.
-
公开(公告)号:US20190236407A1
公开(公告)日:2019-08-01
申请号:US16262974
申请日:2019-01-31
申请人: FUJITSU LIMITED
发明人: Masaru TODORIKI , Yuhei UMEDA , Ken KOBAYASHI
CPC分类号: G06K9/6232 , G06K9/00523 , G06K9/00536
摘要: A detection device adds, with regard to each of a plurality of sets of time-series data including a plurality of items, a time-shift term to at least any of the plurality of items included in each of the plurality of sets of time-series data. The detection device generates a plurality of attractors from the plurality of sets of time-series data to which the time-shift term has been added. The detection device generates a plurality of Betti sequences from each of the plurality of attractors by executing a persistent homology transformation on each of the plurality of attractors, each of the plurality of Betti sequences indicating a correspondence relationship between a Betti number and a scale value has been used for the persistent homology transformation. The detection device detects a state change in the plurality of sets of time-series data based on a time change in the plurality of Betti sequences.
-
公开(公告)号:US20180348278A1
公开(公告)日:2018-12-06
申请号:US16057997
申请日:2018-08-08
发明人: Larry J. House , Dale C. Engelhart
CPC分类号: G01R29/26 , G06F21/44 , G06K9/00536 , G06K9/00577 , G06K9/6276
摘要: A system and method of electronic component authentication or component classification can reduce the vulnerability of systems (e.g., satellites, weapons, critical infrastructure, aerospace, automotive, medical systems) to counterfeits. Intrinsic deterministically random property data can be obtained from a set of authentic electronic components, processed, and clustered to create a classifier that can distinguish whether an unknown electronic component is authentic or counterfeit.
-
公开(公告)号:US20180322342A1
公开(公告)日:2018-11-08
申请号:US15585764
申请日:2017-05-03
发明人: David Clifford , Orhan Demirovic , Orhan Bulan , Eric Hatfield , David Hiemenga , Mohannad Murad
CPC分类号: G06K9/00536 , B60R1/00 , B60R2300/30 , B60R2300/8006 , G06K9/00832 , G06K9/6202 , G06K9/6215 , G06T7/11 , G06T7/70 , G06T2207/10016 , G06T2207/30268 , H04N7/183
摘要: A method and apparatus for detecting and classifying objects associated with a vehicle are provided. The method includes capturing a first image and a second image of a cabin of a vehicle, dividing the first image and the second image into a plurality of regions, comparing a first region of the first image to a second region of the second image, in response to detecting a difference between the second region and the first region, classifying an object present in the difference between the second region and the first region and labeling the classified object, and providing a notification of the classified object to at least one from among an occupant of the vehicle and an operator of the vehicle.
-
公开(公告)号:US20180307654A1
公开(公告)日:2018-10-25
申请号:US15952626
申请日:2018-04-13
CPC分类号: G06N20/00 , G01R31/26 , G01R31/2894 , G06F15/76 , G06F21/44 , G06K9/00536 , G06K9/00577 , G06K9/6269 , G06N7/005 , G06N20/10
摘要: A system and method for selecting a test vector for use in classification of electronic components. The system and method can quickly and automatically select a test vector that, when applied to a set of training electronic components, causes the electronic components to produce side channel information that can be used to build a classifier that accurately classifies a set of test electronic components.
-
公开(公告)号:US20180288119A1
公开(公告)日:2018-10-04
申请号:US15524434
申请日:2015-10-28
发明人: Kuo-Chu Lee , Shoshana Loeb
CPC分类号: H04L65/4084 , G06K9/00536 , H04L67/125 , H04L67/22 , H04L67/38
摘要: A method and system for event pattern (EP) guided content services are disclosed. A service entity may receive sensor events from a plurality of users, the sensor events corresponding to behavior data detected from the plurality of users, identify content creator candidates from among the plurality of users based on a pattern of events which correspond to sensor events received from an active user, select a content creator from among the content creator candidates based on a best match to the pattern of events, transmit a request for content of the selected content creator, deliver content created by the content creator to the active user, and monitor progress of the active user based on a playback of the content by the active user.
-
公开(公告)号:US20180272210A1
公开(公告)日:2018-09-27
申请号:US15916915
申请日:2018-03-09
发明人: Kazuhiro SHIBUYA , Takuya HIRAIDE , Masaki UKAWA
CPC分类号: A63B60/46 , A63B69/3632 , G06K9/00342 , G06K9/00523 , G06K9/00536
摘要: A swing analyzing device (a sensor unit) includes an exercise-information acquiring section configured to acquire an output of an inertial sensor (an acceleration sensor and an angular velocity sensor), an information acquiring section (a movement-information acquiring section) configured to acquire at least either one of position information and movement information, and a control section (a sampling-rate control section) configured to control a storage sampling rate of the storage of the output of the inertial sensor. The control section changes the storage sampling rate according to at least either one of the position information and the movement information.
-
公开(公告)号:US10080686B2
公开(公告)日:2018-09-25
申请号:US15711118
申请日:2017-09-21
发明人: Wayne C. Boncyk , Ronald H. Cohen
IPC分类号: G06K9/00 , A61F9/08 , G06Q20/24 , G06Q20/40 , G06F17/30 , A63F13/00 , H04N5/91 , G06F3/0482 , H04N21/81 , H04N21/254 , G06Q20/32 , H04N21/442 , G06Q20/20 , G06Q30/02 , A63F13/92 , A63F13/335 , G07F17/32 , G06Q20/34 , G06K9/18 , A63F13/213 , G06Q20/10 , H04N21/4722 , G06Q40/00 , G06K9/32 , G06Q30/06 , G06K9/62 , G06Q20/14 , G06K9/46 , H04N21/234 , H04N21/414 , H04N5/232 , A63F13/45 , H04N21/658 , H04N21/231 , H04N21/478 , G06K9/64 , H04L29/08 , G06F17/22 , H04N5/225 , A63F13/792 , G06Q30/04 , G06K9/78 , H04N1/00 , G06K9/34 , H04N7/18 , A63F13/35 , G06K9/22 , G06Q10/02 , H04N21/4782 , A63F13/65 , G06Q90/00 , H04N21/4223 , G06T7/136 , G06T7/246
CPC分类号: A61F9/08 , A63F13/00 , A63F13/12 , A63F13/20 , A63F13/213 , A63F13/335 , A63F13/35 , A63F13/45 , A63F13/65 , A63F13/70 , A63F13/792 , A63F13/92 , G06F3/0482 , G06F16/24 , G06F16/29 , G06F16/50 , G06F16/51 , G06F16/583 , G06F16/5838 , G06F16/5846 , G06F16/5854 , G06F16/5866 , G06F16/94 , G06F16/9554 , G06F16/9558 , G06F17/2235 , G06K9/00536 , G06K9/0063 , G06K9/00664 , G06K9/00671 , G06K9/18 , G06K9/228 , G06K9/3241 , G06K9/34 , G06K9/46 , G06K9/4652 , G06K9/4671 , G06K9/6201 , G06K9/6202 , G06K9/6203 , G06K9/6212 , G06K9/6215 , G06K9/6218 , G06K9/6262 , G06K9/64 , G06K9/78 , G06Q10/02 , G06Q20/102 , G06Q20/14 , G06Q20/202 , G06Q20/208 , G06Q20/24 , G06Q20/327 , G06Q20/3567 , G06Q20/40145 , G06Q30/0217 , G06Q30/0241 , G06Q30/0253 , G06Q30/0257 , G06Q30/0267 , G06Q30/0268 , G06Q30/0269 , G06Q30/0277 , G06Q30/04 , G06Q30/0601 , G06Q30/0623 , G06Q30/0635 , G06Q30/0643 , G06Q40/00 , G06Q90/00 , G06T7/10 , G06T7/11 , G06T7/13 , G06T7/136 , G06T7/194 , G06T7/246 , G06T7/33 , G06T7/337 , G06T7/73 , G07F17/3206 , G07F17/3241 , G07F17/3244 , G09B21/006 , H04L67/02 , H04L67/10 , H04N1/00244 , H04N5/225 , H04N5/23206 , H04N5/23222 , H04N5/23229 , H04N5/91 , H04N7/183 , H04N7/185 , H04N21/23109 , H04N21/23418 , H04N21/254 , H04N21/41407 , H04N21/4223 , H04N21/44222 , H04N21/4722 , H04N21/4781 , H04N21/47815 , H04N21/4782 , H04N21/6582 , H04N21/812 , H04N21/8126 , H04N21/8173 , H04N2201/3253 , H04N2201/3254 , H04N2201/3274
摘要: A digital image segment of a human body part is captured and matched against a reference image segment. If the match score meets a threshold, the digital image segment is stored and the human body part is recognized as a target object. An information address corresponding to the object is then used to access information and initiate communication pertinent to the object. If the match score does not meet a threshold, a second image containing a representation of the human body part is obtained.
-
公开(公告)号:US20180268293A1
公开(公告)日:2018-09-20
申请号:US15921107
申请日:2018-03-14
申请人: SHIMADZU CORPORATION
发明人: Akira NODA
CPC分类号: G06N3/08 , G01N30/86 , G06F17/18 , G06K9/00536 , G06N3/0436 , G06N3/084 , G06N5/048 , G06N7/005 , G06N7/08 , G06N20/10
摘要: Using training data, machine learning is performed to construct a learning model which is a non-linear function for discrimination or regression analysis (S2). A degree of contribution of each input dimension is calculated from a partial differential value of that function. Input dimensions to be invalidated are determined using a threshold defined by a Gaussian distribution function based on the degrees of contribution (S3-S5). Machine learning is once more performed using the training data with the partially-invalidated input dimensions (S6). A new value of the degree of contribution of each input dimension is determined from the obtained learning model, and the degree of contribution is updated using the old and new values (S7-S8). After the processes of Steps S5-S8 are iterated a specified number of times (S9), useful dimensions are determined based on the finally obtained degrees of contribution, and the machine-learning model is constructed (S10).
-
公开(公告)号:US10064559B2
公开(公告)日:2018-09-04
申请号:US15832879
申请日:2017-12-06
申请人: Facense Ltd.
发明人: Arie Tzvieli , Gil Thieberger , Ari M Frank
IPC分类号: A61B7/04 , A61B5/01 , A61B5/08 , A61B5/093 , A61B7/00 , A61B5/16 , G09B19/00 , G06N99/00 , G06T7/00 , G06K9/00 , G06K9/62 , G06T7/60 , G01J5/10 , A61B5/00 , H04N5/232 , H04N5/33 , G01J5/00
CPC分类号: A61B5/015 , A61B5/0075 , A61B5/0077 , A61B5/0816 , A61B5/0935 , A61B5/165 , A61B5/168 , A61B5/6803 , A61B5/6814 , A61B5/7267 , A61B7/00 , A61B7/003 , A61B7/04 , A61B2562/0271 , G01J5/0014 , G01J5/0025 , G01J5/10 , G01J2005/0077 , G02B27/017 , G02B2027/0181 , G06F3/012 , G06F3/0304 , G06F2203/011 , G06K9/00255 , G06K9/00281 , G06K9/00536 , G06K9/00885 , G06K9/6202 , G06K9/6256 , G06K9/6267 , G06N20/00 , G06T7/0014 , G06T7/60 , G06T2207/30201 , G09B19/00 , G09B23/28 , H04N5/23219 , H04N5/33
摘要: Brain activity, and in particular which hemisphere is relatively more effective, is correlated with the dominant nostril (i.e., the nostril through which most of the air is exhaled when breathing through the nose). Thus, identifying which of the nostrils is dominant may have various applications. Described herein are systems and methods for identifying the dominant nostril. In one embodiment, a system includes at least one inward-facing head-mounted thermal camera (CAM) and a computer. The at least one CAM does not occlude any of the user's mouth and nostrils and is used to take thermal measurements of first and second regions below the right and left nostrils (THROI1 and THROI2, respectively). The computer identifies the dominant nostril based on THROI1 and THROI2. Optionally, the computer detects, utilizing THROI1 and THROI2, the three-dimensional (3D) shape of the exhale stream from at least one of the nostrils.
-
-
-
-
-
-
-
-
-