公开(公告)号：WO00028725A2

公开(公告)日：2000-05-18

申请号：PCT/US1999/026126

申请日：1999-11-05

IPC: G06T1/00 ,  G06F17/30 ,  G06T7/00 ,  G11B27/00 ,  H04N5/76 ,  H04N5/91 ,  H04N5/92 ,  H04N7/08 ,  H04N7/081 ,  H04N7/26 ,  H04N

CPC classification number: G06F17/30011 ,  G06F17/3028 ,  G06F17/3079 ,  G06F17/30796 ,  G06F17/30858 ,  G06K9/00677 ,  G06K9/46

Abstract: Systems and methods for describing video content establish video description records which include an object set, an object hierarchy and entity relation graphs. Video objects can include global ojects, segment objects and local objects. The video objects are further defined by a number of features organized in classes, which in turn are further defined by a number of feature descriptors. The relationships between and among the objects in the object set are defined by the object hierarchy and entity relation graphs. The video description records provide a standard vehicle for describing the content and context of video information for subsequent access and processing by computer applications such as search engines, filters, and archive systems.

Abstract translation: 用于描述视频内容的系统和方法建立包括对象集，对象层次和实体关系图的视频描述记录。 视频对象可以包括全局对象，段对象和本地对象。 视频对象进一步由分类组织的特征进一步定义，而这些特征进一步由多个特征描述符定义。 对象集合中的对象之间的关系由对象层次结构和实体关系图定义。 视频描述记录提供用于描述视频信息的内容和上下文的标准车辆，用于随后由诸如搜索引擎，过滤器和归档系统的计算机应用程序访问和处理。

公开(公告)号：WO00028467A1

公开(公告)日：2000-05-18

申请号：PCT/US1999/026127

申请日：1999-11-05

IPC: G06T1/00 ,  G06F17/30 ,  G06T7/00 ,  G11B27/00 ,  H04N5/76 ,  H04N5/91 ,  H04N5/92 ,  H04N7/08 ,  H04N7/081 ,  H04N7/26 ,  G06K9/00 ,  G06F3/00 ,  G06F7/00 ,  G06F15/00 ,  G06K9/34 ,  G06K9/36 ,  G06K9/46 ,  G06K9/56 ,  G06K9/60 ,  G09C5/00 ,  H04N7/12

CPC classification number: G06F17/30011 ,  G06F17/3028 ,  G06F17/3079 ,  G06F17/30796 ,  G06F17/30858 ,  G06K9/00677 ,  G06K9/46

Abstract: Systems and methods for describing image content establish image description records which include an object set (24), an object hierarchy (26) and entity relation graphs (28). For image content, image objects can include global objects (O0 8) and local objects (O1 2 and O2 6). The image objects are further defined by a number of features of different classes (36, 38 and 40), which in turn are further defined by a number of feature descriptors. The relationships between and among the objects in the object set are defined by the object hierarchy (26) and entity relation graphs (28). The image description records provide a standard vehicle for describing the content and context of image information for subsequent access and processing by computer applications such as search engines, filters, and archive systems.

Abstract translation: 用于描述图像内容的系统和方法建立包括对象集（24），对象层次（26）和实体关系图（28）的图像描述记录。 对于图像内容，图像对象可以包括全局对象（O0 8）和本地对象（O1 2和O2 6）。 图像对象由不同类别（36,38和40）的多个特征进一步限定，而又由许多特征描述符进一步限定。 对象集合中的对象之间和之间的关系由对象层次结构（26）和实体关系图（28）定义。 图像描述记录提供用于描述图像信息的内容和上下文的标准车辆，用于随后由计算机应用（例如搜索引擎，过滤器和归档系统）的访问和处理。

公开(公告)号：WO2019079517A1

公开(公告)日：2019-04-25

申请号：PCT/US2018/056377

申请日：2018-10-17

Applicant: PLOTA, Troy ,  CONNELLY, Sascha

Inventor： PLOTA, Troy ,  CONNELLY, Sascha

IPC: G06K9/00 ,  G06K9/40 ,  H03L7/00 ,  H03M1/12 ,  H04N7/01 ,  H04N9/64

CPC classification number: G06K9/40 ,  G06K9/00677 ,  G06K9/4609 ,  H03L7/00 ,  H04N1/32219

Abstract: A computer system for automating the shifting of pixels within a digital video receives a first starting point through a user interface. The first starting point is received through a user selection of a first beginning portion of a video frame. The system then receives a first ending point through the user interface. The first ending point is received through a user selection of a first ending portion of the user interface. The system selects a first set of pixels that lie between the first starting point and the first ending point. The system then shifts the first set of pixels in the first direction, wherein shifting the first set of pixels comprises rendering and re-rendering in a loop the first set of pixels being shifted.

公开(公告)号：WO2018187451A1

公开(公告)日：2018-10-11

申请号：PCT/US2018/026054

申请日：2018-04-04

Applicant: RING INC.

Inventor： SIMINOFF, James ,  TROUGHTON, Mark ,  GILBOA, Aviv ,  LEMBERGER, Elliot ,  SOMMERLATT, Darrell ,  JACOBSON, Alex

IPC: H04N7/18 ,  H04N5/91 ,  G06K9/00 ,  G08B13/196 ,  G10L25/57 ,  G06F17/28 ,  H04N5/77

CPC classification number: H04N7/186 ,  G06K9/00268 ,  G06K9/00288 ,  G06K9/00677 ,  G06K9/00771 ,  G06K9/00979 ,  G06K9/2018 ,  G06K2009/00738 ,  G06K2209/01 ,  G08B3/10 ,  G08B13/19669 ,  G08B13/19671 ,  G08B27/003 ,  G10L25/51 ,  H04N5/77 ,  H04N5/91 ,  H04N7/18

Abstract: Systems and methods for augmenting and sharing data from audio/video (A/V) recording and communication devices are provided. In one embodiment, a method may include receiving, from an A/V recording and communication device, image data representing an image, analyzing the image data to determine one or more objects depicted by the image data, based on the analyzing the image data, determining at least one comment associated with the one or more objects; transmitting, to a first client device associated with the A/V recording and communication device, the image data representing the image and the at least one comment, receiving, from the first client device, consent for sharing the image data with a geographic area network, the consent indicating a selection of a comment from the at least one comment, and transmitting, to a second client device, the image data representing the image and the comment.

公开(公告)号：WO2018125932A1

公开(公告)日：2018-07-05

申请号：PCT/US2017/068573

申请日：2017-12-27

Applicant: SHUTTERSTOCK, INC.

Inventor： HOHWALD, Heath ,  LAZARE, Lawrence

IPC: G06F17/30 ,  G06N3/08

CPC classification number: G06F16/5838 ,  G06F3/04817 ,  G06F3/04842 ,  G06F16/51 ,  G06F16/9038 ,  G06F16/9535 ,  G06K9/00677 ,  G06K9/4628 ,  G06K9/4671 ,  G06K9/6218 ,  G06K9/6269 ,  G06K9/6274 ,  G06N3/0454 ,  G06N3/08

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for clustering search results based on image composition. A system may, for each image in a set of images, determine a compositional vector representing one or more objects and corresponding locations within the image using a trained computer-operated convolutional neural network. The system may provide each image through a clustering algorithm to produce one or more clusters based on compositional similarity. The system may provide images from the set of images clustered by composition, in which the images include a different listing of images for each of the one or more clusters. The system may provide a prioritized listing of images responsive to a user search query, in which the prioritized listing of images includes a different listing of images for each cluster of compositional similarity based on the metadata of each image associated with the cluster.

公开(公告)号：WO2018021723A1

公开(公告)日：2018-02-01

申请号：PCT/KR2017/007333

申请日：2017-07-07

Applicant: 삼성전자 주식회사

Inventor： 산드한투샤르 바라사에브 ,  신대규 ,  이희국 ,  유주완 ,  이서영 ,  정유민 ,  박지윤 ,  이정은

IPC: G06T7/33 ,  G06T7/269 ,  G06T7/32

CPC classification number: G06K9/6255 ,  G06K9/00677 ,  G06K9/6807 ,  G06T7/269 ,  G06T7/32 ,  G06T7/33

Abstract: 본 발명의 다양한 실시 예들은 복수의 이미지들에 대한 영상 인식을 수행하고, 상기 영상 인식의 결과에 적어도 일부 기초하여, 상기 복수의 이미지들 간의 유사도(similarity)를 계산하고, 상기 계산된 유사도에 적어도 일부 기초하여, 상기 복수의 이미지들 중 둘 이상의 이미지를 포함하는 그룹을 생성하고, 상기 그룹 내에 포함된 둘 이상의 이미지들 간의 유사도에 적어도 일부 기초하여, 디스플레이될 시퀀스를 결정하고, 상기 디스플레이 상에, 상기 시퀀스에 따라, 상기 둘 이상의 이미지들을 표시하도록 하는 인스트럭션들을 저장할 수 있다. 이외에도 다양한 다른 실시예들이 가능하다.

Abstract translation: 本发明的各种实施例至少部分地基于图像识别的结果对多个图像执行图像识别并且计算多个图像之间的相似度 并且至少部分基于所计算的相似度来生成包括所述多个图像中的至少两个的组，并且基于包括在所述组中的两个或更多个图像之间的相似度的至少一部分来生成要显示的序列 并在显示屏上存储指令，以按照顺序显示两幅或多幅图像。 各种其他的实施例是可能的。

公开(公告)号：WO2017155641A2

公开(公告)日：2017-09-14

申请号：PCT/US2017/016273

申请日：2017-02-02

Applicant: PROXY TECHNOLOGIES, INC.

Inventor： CESARANO, Patrick, C. ,  KLINGER, John

CPC classification number: G05D1/0214 ,  B64C39/024 ,  B64C2201/021 ,  B64C2201/024 ,  B64C2201/141 ,  B64C2201/143 ,  B64C2201/146 ,  G01B9/021 ,  G01B11/00 ,  G01C21/165 ,  G01N21/8851 ,  G01N27/20 ,  G01N2201/12 ,  G01S7/006 ,  G01S13/02 ,  G01S13/06 ,  G01S13/42 ,  G01S15/02 ,  G01S19/13 ,  G01S2013/0254 ,  G05B11/42 ,  G05B13/024 ,  G05B13/042 ,  G05D1/0022 ,  G05D1/0027 ,  G05D1/0088 ,  G05D1/0094 ,  G05D1/02 ,  G05D1/0202 ,  G05D1/0204 ,  G05D1/0206 ,  G05D1/021 ,  G05D1/0246 ,  G05D1/0278 ,  G05D1/104 ,  G05D2201/0207 ,  G06K9/00637 ,  G06K9/00677 ,  G08G5/0039 ,  G08G5/045 ,  G08G9/02 ,  H01Q3/26 ,  H01Q3/2617 ,  H01Q3/28 ,  H01Q3/36 ,  H04B7/0617 ,  H04B7/18506 ,  H04N5/225 ,  H04N7/183 ,  H04N2005/2255

Abstract: Some embodiments are directed to an unmanned vehicle for use with a companion unmanned vehicle. The unmanned vehicle can include a satellite navigation unit that is configured to receive a satellite signal indicative of a current position of the unmanned vehicle. The unmanned vehicle can also include an inertial navigation unit that is configured to determine the current position of the unmanned vehicle. The unmanned vehicle can also include a control unit disposed in communication with the satellite navigation unit and the inertial navigation unit. The control unit is configured to determine a planned position of the unmanned vehicle based on the planned path, compare the current position determined by the inertial navigation unit with the planned position based on the planned path, and control the movement of the unmanned vehicle based on at least the comparison between the current position and the planned position.

Abstract translation: 一些实施例针对用于伴随无人驾驶车辆的无人驾驶车辆。 无人驾驶车辆可以包括卫星导航单元，其被配置为接收指示无人驾驶车辆的当前位置的卫星信号。 无人驾驶车辆还可以包括被配置成确定无人驾驶车辆的当前位置的惯性导航单元。 无人驾驶车辆还可以包括设置成与卫星导航单元和惯性导航单元通信的控制单元。 控制单元被配置为基于计划路径确定无人驾驶车辆的计划位置，将由惯性导航单元确定的当前位置与基于计划路径的计划位置进行比较，并且基于规则路径控制无人驾驶车辆的移动 至少比较当前位置和计划位置。

公开(公告)号：WO2017136602A1

公开(公告)日：2017-08-10

申请号：PCT/US2017/016294

申请日：2017-02-02

Applicant: PROXY TECHNOLOGIES, INC.

Inventor： CESARANO, Patrick, C.

IPC: G01V3/00 ,  G01S3/16 ,  G08C25/02 ,  G01P15/00

CPC classification number: G05D1/0214 ,  B64C39/024 ,  B64C2201/021 ,  B64C2201/024 ,  B64C2201/141 ,  B64C2201/143 ,  B64C2201/146 ,  G01B9/021 ,  G01B11/00 ,  G01C21/165 ,  G01N21/8851 ,  G01N27/20 ,  G01N2201/12 ,  G01S7/006 ,  G01S13/02 ,  G01S13/06 ,  G01S13/42 ,  G01S15/02 ,  G01S19/13 ,  G01S2013/0254 ,  G05B11/42 ,  G05B13/024 ,  G05B13/042 ,  G05D1/0022 ,  G05D1/0027 ,  G05D1/0088 ,  G05D1/0094 ,  G05D1/02 ,  G05D1/0202 ,  G05D1/0204 ,  G05D1/0206 ,  G05D1/021 ,  G05D1/0246 ,  G05D1/0278 ,  G05D1/104 ,  G05D2201/0207 ,  G06K9/00637 ,  G06K9/00677 ,  G08G5/0039 ,  G08G5/045 ,  G08G9/02 ,  H01Q3/26 ,  H01Q3/2617 ,  H01Q3/28 ,  H01Q3/36 ,  H04B7/0617 ,  H04B7/18506 ,  H04N5/225 ,  H04N7/183 ,  H04N2005/2255

Abstract: An unmanned vehicle for use with an entity physically spaced from the unmanned vehicle, the unmanned vehicle having objective parameters corresponding to controlled parameters of the entity. The unmanned vehicle comprises a transceiver that is configured to wirelessly receive an input signal from the entity, wherein the input signal is indicative of the controlled parameters of the entity. The unmanned vehicle further comprises a Phase-Locked Loop (PLL) circuit that is configured to generate a command signal based on a phase of the input signal and a phase of a reference signal, wherein the reference signal is indicative of the objective parameters of the unmanned vehicle. The transceiver is further configured to wirelessly transmit the command signal to the entity such that the entity controls the controlled parameters of the entity based on the command signal.

Abstract translation: 用于与无人驾驶交通工具实体间隔的实体一起使用的无人驾驶交通工具，无人驾驶交通工具具有与实体的受控参数相对应的客观参数。 无人驾驶交通工具包括收发器，其被配置为无线地接收来自实体的输入信号，其中输入信号指示实体的受控参数。 无人驾驶交通工具还包括锁相环（PLL）电路，其被配置为基于输入信号的相位和参考信号的相位来生成命令信号，其中参考信号表示参考信号的目标参数 无人驾驶车辆。 该收发器进一步被配置为将该命令信号无线传输到该实体，使得该实体基于该命令信号来控制该实体的受控参数。

公开(公告)号：WO2017088257A1

公开(公告)日：2017-06-01

申请号：PCT/CN2015/099608

申请日：2015-12-29

Applicant: 小米科技有限责任公司

Inventor： 陈志军 ,  侯文迪 ,  龙飞

IPC: G06F17/30

CPC classification number: G06K9/00677 ,  G06F3/0484 ,  G06F3/16 ,  G06F17/30259 ,  G06F17/30274 ,  G06F17/30752 ,  G06F17/30769 ,  G06K9/00087 ,  G06K9/00221 ,  G06K9/00288

Abstract: 本公开是关于一种基于面孔相册的音乐播放方法、装置和终端设备，该方法包括：获取用户触发的观看目标面孔相册中图片的观看指令；获取用户的特征信息；根据用户的特征信息确定用户与目标面孔相册中图片对应的被观看者的人物关系；根据预先设定的各人物关系与各音乐类型的对应关系，确定与确定出的人物关系对应的目标音乐类型；播放目标面孔相册中的图片以及与目标音乐类型对应的音乐。在观看某面孔相册时能够基于观看者与被观看者的人物关系而自动选择并播放对应的音乐，降低了用户的操作复杂度，提高了用户体验。

公开(公告)号：WO2017062357A1

公开(公告)日：2017-04-13

申请号：PCT/US2016/055323

申请日：2016-10-04

Applicant: GOOGLE INC.

Inventor： KONTKANEN, Janne, Matias

IPC: G06T15/04 ,  G06T15/20 ,  G06T15/50 ,  G06T17/00 ,  G06T15/00

CPC classification number: G06F17/30256 ,  G06K9/00677 ,  G06T15/00 ,  G06T15/04 ,  G06T15/20 ,  G06T15/205 ,  G06T15/503 ,  G06T17/00

Abstract: A system and method is provided for displaying surfaces of an object (240) from a vantage point (230) different from the vantage point from which imagery of the object was captured (210, 220). In some aspects, imagery (710) may be generated for display by combining visual characteristics from multiple source images (215, 225) and applying greater weight to the visual characteristics of some of the source images relative to the other source images. The weight may be based on the orientation of the surface (310) relative to the location from which the image was captured (320) and the location from which the object will be displayed (430).

Abstract translation: 提供了一种系统和方法，用于从与捕获对象的图像的有利位置不同的有利位置（210,220）显示对象（240）的表面。 在一些方面，可以通过组合来自多个源图像（215,225）的视觉特征并且相对于其它源图像对一些源图像的视觉特征应用更大的权重来生成图像（710）用于显示。 重量可以基于表面（310）相对于从其捕获图像的位置（320）的方向和将要显示对象的位置（430）。