公开(公告)号：US09672427B2

公开(公告)日：2017-06-06

申请号：US15334172

申请日：2016-10-25

Applicant: Google Inc.

Inventor： Jason N. Laska ,  Wei Hua ,  Prateek Reddy ,  Akshay R. Bapat ,  Lawrence W. Neal

IPC: G06K9/00 ,  G06K9/62 ,  H04N5/14 ,  H04N7/18 ,  G08B13/196 ,  G06T7/20 ,  G06K9/32

CPC classification number: G06K9/00771 ,  G06F3/0481 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/04855 ,  G06F3/0488 ,  G06F3/04883 ,  G06K9/00288 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00765 ,  G06K9/3241 ,  G06K9/6226 ,  G06K9/6227 ,  G06K9/6267 ,  G06K2009/00738 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/30232 ,  G08B13/196 ,  G08B13/19608 ,  G08B13/19613 ,  G08B13/19615 ,  G08B13/19682 ,  G08B13/19691 ,  G11B27/005 ,  G11B27/028 ,  G11B27/031 ,  G11B27/105 ,  G11B27/30 ,  G11B27/34 ,  H04L12/2803 ,  H04N5/144 ,  H04N5/145 ,  H04N5/93 ,  H04N7/18 ,  H04N7/181 ,  H04N7/183 ,  H04N21/23418 ,  H04N21/42204 ,  H04N21/4314 ,  H04N21/6581 ,  H04N21/8456 ,  H04W4/80

Abstract: The various embodiments described herein include methods, devices, and systems for categorizing motion events. In one aspect, a method includes: (1) obtaining a plurality of video frames, the plurality of video frames corresponding to a scene and a motion event candidate; (2) identifying one or more visual characteristics of the scene; (3) obtaining one or more background factors for the scene; (4) utilizing the obtained background factors to identify one or more motion entities; (5) for each identified motion entity: (a) classifying the motion entity by performing object recognition; and (b) obtaining one or more representative motion vectors based on a motion track of the motion entity; and (6) assigning a motion event category to the motion event candidate based on the identified visual characteristics, the obtained background factors, the classified motion entities, and the obtained representative motion vectors.

公开(公告)号：US09501915B1

公开(公告)日：2016-11-22

申请号：US14737963

申请日：2015-06-12

Applicant: GOOGLE INC.

Inventor： Jason N. Laska ,  Wei Hua ,  Prateek Reddy ,  Akshay R. Bapat ,  Lawrence W. Neal

IPC: G08B13/196 ,  H04N5/14 ,  G06K9/00 ,  H04N7/18 ,  G06T7/20

CPC classification number: G06K9/00771 ,  G06F3/0481 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/04855 ,  G06F3/0488 ,  G06F3/04883 ,  G06K9/00288 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00765 ,  G06K9/3241 ,  G06K9/6226 ,  G06K9/6227 ,  G06K9/6267 ,  G06K2009/00738 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/30232 ,  G08B13/196 ,  G08B13/19608 ,  G08B13/19613 ,  G08B13/19615 ,  G08B13/19682 ,  G08B13/19691 ,  G11B27/005 ,  G11B27/028 ,  G11B27/031 ,  G11B27/105 ,  G11B27/30 ,  G11B27/34 ,  H04L12/2803 ,  H04N5/144 ,  H04N5/145 ,  H04N5/93 ,  H04N7/18 ,  H04N7/181 ,  H04N7/183 ,  H04N21/23418 ,  H04N21/42204 ,  H04N21/4314 ,  H04N21/6581 ,  H04N21/8456 ,  H04W4/80

Abstract: The various embodiments described herein include methods, devices, and systems for analyzing video streams. In one aspect, a method includes, while receiving a video stream: obtaining motion start information indicating that a portion of the video stream includes a motion event candidate; and segmenting the portion of the video stream into a plurality of segments including an initial segment. The method also includes obtaining a first categorization for the motion event candidate based on the initial segment; and, in accordance with the obtained first categorization, generating a log entry for the motion event candidate including the first categorization. The method further includes: in response to obtaining motion end information, obtaining a second categorization for the motion event based on the plurality of segments; and updating the log entry for the motion event candidate based on the obtained second categorization.

Abstract translation: 本文描述的各种实施例包括用于分析视频流的方法，设备和系统。 一方面，一种方法包括：在接收视频流的同时，获取指示视频流的一部分包括运动事件候选的运动开始信息; 以及将所述视频流的所述部分分割成包括初始段的多个段。 该方法还包括基于初始段获得运动事件候选的第一分类; 并且根据获得的第一分类，生成包括第一分类的运动事件候选的日志条目。 该方法还包括：响应于获得运动结束信息，基于多个段获得运动事件的第二分类; 以及基于获得的第二分类来更新运动事件候选的日志条目。

公开(公告)号：US20170270365A1

公开(公告)日：2017-09-21

申请号：US15613013

申请日：2017-06-02

Applicant: GOOGLE INC.

Inventor： Jason N. Laska ,  Wei Hua ,  Prateek Reddy ,  Akshay R. Bapat ,  Lawrence W. Neal

IPC: G06K9/00 ,  H04N7/18 ,  H04N5/14 ,  G06F3/0488 ,  G06F3/0481 ,  G06F3/0482 ,  G06F3/0484 ,  G06F3/0485 ,  G06K9/32 ,  G11B27/00 ,  G11B27/028 ,  G11B27/031 ,  G11B27/10 ,  G11B27/30 ,  G11B27/34 ,  H04N5/93 ,  G08B13/196 ,  G06K9/62

CPC classification number: G06K9/00771 ,  G06F3/0481 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/04855 ,  G06F3/0488 ,  G06F3/04883 ,  G06K9/00288 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00765 ,  G06K9/3241 ,  G06K9/6226 ,  G06K9/6227 ,  G06K9/6267 ,  G06K2009/00738 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/30232 ,  G08B13/196 ,  G08B13/19608 ,  G08B13/19613 ,  G08B13/19615 ,  G08B13/19682 ,  G08B13/19691 ,  G11B27/005 ,  G11B27/028 ,  G11B27/031 ,  G11B27/105 ,  G11B27/28 ,  G11B27/30 ,  G11B27/34 ,  H04L12/2803 ,  H04N5/144 ,  H04N5/145 ,  H04N5/93 ,  H04N7/18 ,  H04N7/181 ,  H04N7/183 ,  H04N21/23418 ,  H04N21/42204 ,  H04N21/4314 ,  H04N21/6581 ,  H04N21/8456 ,  H04W4/80

Abstract: The various embodiments described herein include methods, devices, and systems for categorizing motion events. In one aspect, a method is performed at a camera device. The method includes: (1) capturing a plurality of video frames via the image sensor, the plurality of video frames corresponding to a scene in a field of view of the camera; (2) sending the video frames to the remote server system in real-time; (3) while sending the video frames to the remote server system in real-time: (a) determining that motion has occurred within the scene; (b) in response to determining that motion has occurred within the scene, characterizing the motion as a motion event; and (c) generating motion event metadata for the motion event; and (4) sending the generated motion event metadata to the remote server system concurrently with the video frames.

公开(公告)号：US20170046574A1

公开(公告)日：2017-02-16

申请号：US15334172

申请日：2016-10-25

Applicant: Google Inc.

Inventor： Jason N. Laska ,  Wei Hua ,  Prateek Reddy ,  Akshay R. Bapat ,  Lawrence W. Neal

IPC: G06K9/00 ,  G06K9/32 ,  H04N7/18 ,  G08B13/196 ,  G06T7/20

CPC classification number: G06K9/00771 ,  G06F3/0481 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/04855 ,  G06F3/0488 ,  G06F3/04883 ,  G06K9/00288 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00765 ,  G06K9/3241 ,  G06K9/6226 ,  G06K9/6227 ,  G06K9/6267 ,  G06K2009/00738 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/30232 ,  G08B13/196 ,  G08B13/19608 ,  G08B13/19613 ,  G08B13/19615 ,  G08B13/19682 ,  G08B13/19691 ,  G11B27/005 ,  G11B27/028 ,  G11B27/031 ,  G11B27/105 ,  G11B27/30 ,  G11B27/34 ,  H04L12/2803 ,  H04N5/144 ,  H04N5/145 ,  H04N5/93 ,  H04N7/18 ,  H04N7/181 ,  H04N7/183 ,  H04N21/23418 ,  H04N21/42204 ,  H04N21/4314 ,  H04N21/6581 ,  H04N21/8456 ,  H04W4/80

Abstract: The various embodiments described herein include methods, devices, and systems for categorizing motion events. In one aspect, a method includes: (1) obtaining a plurality of video frames, the plurality of video frames corresponding to a scene and a motion event candidate; (2) identifying one or more visual characteristics of the scene; (3) obtaining one or more background factors for the scene; (4) utilizing the obtained background factors to identify one or more motion entities; (5) for each identified motion entity: (a) classifying the motion entity by performing object recognition; and (b) obtaining one or more representative motion vectors based on a motion track of the motion entity; and (6) assigning a motion event category to the motion event candidate based on the identified visual characteristics, the obtained background factors, the classified motion entities, and the obtained representative motion vectors.

Abstract translation: 本文描述的各种实施例包括用于对运动事件进行分类的方法，装置和系统。 一方面，一种方法包括：（1）获得多个视频帧，对应于场景的多个视频帧和运动事件候选; （2）识别场景的一个或多个视觉特征; （3）获取场景的一个或多个背景因子; （4）利用获得的背景因子来识别一个或多个运动实体; （5）对于每个识别的运动实体：（a）通过执行对象识别对运动实体进行分类; 和（b）基于运动实体的运动轨迹获得一个或多个代表运动矢量; 以及（6）基于所识别的视觉特征，所获得的背景因子，分类的运动实体和所获得的代表性运动矢量，将运动事件类别分配给运动事件候选。