-
公开(公告)号：US20150092978A1
公开(公告)日：2015-04-02
申请号：US14039437
申请日：2013-09-27
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Dongdong WU , Yongmian Zhang , Haisong Gu
CPC classification number: G06K9/00342 , G06K2009/00738
Abstract: A method for recognizing abnormal behavior is disclosed, the method includes: capturing at least one video stream of data on one or more subjects; extracting body skeleton data from the at least one video stream of data; classifying the extracted body skeleton data as normal behavior or abnormal behavior; and generating an alert, if the extracted skeleton data is classified as abnormal behavior.
Abstract translation: 公开了一种用于识别异常行为的方法，所述方法包括：在一个或多个主体上捕获至少一个视频数据流; 从所述至少一个视频数据流中提取身体骨骼数据; 将提取的身体骨骼数据分类为正常行为或异常行为; 并且如果所提取的骨架数据被分类为异常行为，则生成警报。
-
公开(公告)号：US10853698B2
公开(公告)日：2020-12-01
申请号：US16347237
申请日：2017-10-27
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Logan Courtney , Haisong Gu
Abstract: A method, a system, and a computer readable recording medium are disclosed for performing object recognition. The method includes receiving image data from an image; performing a multilayer feature extraction on the image data; generating current feature maps from the multilayer feature extraction; generating a region of proposal network map from at least the current feature maps, the region of proposal network map having one or more regions of interest; inputting previously generated feature maps and the current feature maps into a classifier with the region of proposed network map; and classifying the one or more regions of interest in the region of proposal network map.
-
Patent Agency Ranking
公开(公告)号：US09703387B2
公开(公告)日：2017-07-11
申请号：US14840596
申请日：2015-08-31
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Nandita M. Nayak , Ghassem Tofighi , Haisong Gu
CPC classification number: G06F3/017 , G06F3/0304 , G06F3/0425 , G06F3/04842 , G06F3/04845 , G06K9/00342 , G06K9/00355
Abstract: A method, a system, and a non-transitory computer readable medium are disclosed for real-time interaction with a user interface recognizing a gesture. The method including capturing three-dimensional (3D) data on a subject; detecting a pointing action by the subject from the 3D data; computing an initial estimate of a target region from the pointing action, the initial estimate of the target region having a defined radius around a center point; and tracking the pointing action of the subject and performing a series of iterations wherein the defined radius of the target region changes based on the detected pointing action.
-
公开(公告)号：US20190295260A1
公开(公告)日：2019-09-26
申请号：US16345894
申请日：2017-10-27
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Sachin Mehta , Haisong Gu
Abstract: A method, a computer readable recording medium, and a system are disclosed for image segmentation using controlled feedback in a neural network. The method includes extracting image data from an image; performing one or more semantic segmentations on the extracted image data; introducing one or more classifiers to each of the one or more semantic segmentations, each of the one or more classifiers assigning a probability to one or more classes of objects within the image; and generating a segmentation mask from the one or more semantic segmentations.
-
公开(公告)号：US09953215B2
公开(公告)日：2018-04-24
申请号：US15507735
申请日：2015-08-27
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Quentin Auge , Yongmian Zhang , Haisong Gu
IPC: G06K9/00
CPC classification number: G06K9/00342 , G06K9/00201 , G06K9/00765
Abstract: A method, system and non-transitory computer readable medium are disclosed for recognizing gestures, the method includes capturing at least one three-dimensional (3D) video stream of data on a subject; extracting a time-series of skeletal data from the at least one 3D video stream of data; isolating a plurality of points of abrupt content change called temporal cuts, the plurality of temporal cuts defining a set of non-overlapping adjacent segments partitioning the time-series of skeletal data; identifying among the plurality of temporal cuts, temporal cuts of the time-series of skeletal data having a positive acceleration; and classifying each of the one or more pair of consecutive cuts with the positive acceleration as a gesture boundary.
-
公开(公告)号：US09922245B2
公开(公告)日：2018-03-20
申请号：US14461057
申请日：2014-08-15
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Yongmian Zhang , Hung-Shou Tai , Haisong Gu
CPC classification number: G06K9/00389 , G06K9/6212 , H04N5/332
Abstract: A method, a system, and a non-transitory computer readable medium for recognizing an object. The method includes emitting an array of infrared rays from an infrared emitter towards a projection region, the projection region including a first object; generating a reference infrared image by recording an intensity of ray reflection from the projection region without the first object; generating a target infrared image by recording the intensity of ray reflection from the projection region with the first object; comparing the target infrared image to the reference infrared image to generate a predetermined intensity threshold; and extracting the first object from the target infrared image, if the intensity of ray reflection of the target infrared image of the first object exceeds the predetermined intensity threshold.
-
公开(公告)号：US09823755B2
公开(公告)日：2017-11-21
申请号：US14632661
申请日：2015-02-26
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Yongmian Zhang , Jingwen Zhu , Toshiki Ohinata , Haisong Gu
CPC classification number: G06F3/0317 , G06F3/011 , G06F3/038 , G06K9/00375
Abstract: A method and system are disclosed for recognizing an object, the method including emitting one or more arranged patterns of infrared rays (IR) from an infrared emitter towards a projection region, the one or more arranged patterns of infrared rays forming unique dot patterns; mapping the one or more arranged patterns of infrared rays on the operation region to generate a reference image; capturing an IR image and a RGB image of an object with a wearable device, the wearable device including an infrared (IR) camera and a RGB camera; extracting IR dots from the IR image and determining a match between the extracted IR dots and the reference image; determining a position of the RGB image on the reference image; and mapping the position of the RGB image to a coordinate on the projection region.
-
-
-
-
-
-
Search Results
17
records
(took 0.018 seconds)
