公开(公告)号：WO2008151818A2

公开(公告)日：2008-12-18

申请号：PCT/EP2008/004772

申请日：2008-06-13

Applicant: STICHTING IMEC NEDERLAND ,  I.KNOW NV ,  PENDERS, Julien, Frederic, Emmanuel, Pierre ,  BRANDS, Michael, Rik, Frans

Inventor： PENDERS, Julien, Frederic, Emmanuel, Pierre ,  BRANDS, Michael, Rik, Frans

IPC: G06K9/00

CPC classification number: G06K9/00979 ,  A63F2300/10 ,  G06F19/00 ,  G06F19/3418 ,  G16H50/20 ,  H04L67/12

Abstract: A method of and a system (1) for sensor signal data analysis, wherein sensor signal data (12) from a plurality of sensors are acquired (2). Signal processing (3; 4) is performed on the sensor signal data (12) to extract (4) one or more features of the sensor signal data (12). The features are signal extracts that are distinguishable among and reproducible along the sensor signal data (12). With at least one of the features a plurality of information attributes is associated (10), and information evaluation (11) is performed on the plurality of information attributes.

Abstract translation: 一种用于传感器信号数据分析的方法和系统（1），其中获取来自多个传感器的传感器信号数据（12）（2）。 对传感器信号数据（12）执行信号处理（3; 4），以提取（4）传感器信号数据（12）的一个或多个特征。 这些特征是沿着传感器信号数据（12）可区分并且可再现的信号提取。 利用与多个信息属性相关联的特征中的至少一个（10），并且对多个信息属性执行信息评估（11）。

公开(公告)号：WO2008104537A1

公开(公告)日：2008-09-04

申请号：PCT/EP2008/052306

申请日：2008-02-26

Applicant: ACCENTURE Global Services GmbH ,  LINAKER, Fredrik

Inventor： LINAKER, Fredrik

IPC: G06Q30/00 ,  G06K9/00

CPC classification number: H04W24/00 ,  G06K9/00979 ,  G06Q30/06

Abstract: The invention concerns a method of accessing information using a wireless mobile device (1) having a display (3), and video capturing unit, the method comprising: establishing a video call with a remote server (6) such that said remote server receives video images captured by said mobile device during the video call; performing image recognition to identify at least one first object (4) in said captured video; and generating a signal for transmission to said mobile device, said signal comprising information relating to said first object.

Abstract translation: 本发明涉及使用具有显示器（3）的无线移动设备（1）和视频捕获单元访问信息的方法，所述方法包括：与远程服务器（6）建立视频通话，使得所述远程服务器接收视频 在视频呼叫期间由所述移动设备捕获的图像; 执行图像识别以识别所述捕获的视频中的至少一个第一对象（4）; 以及产生用于传输到所述移动设备的信号，所述信号包括与所述第一对象有关的信息。

公开(公告)号：WO2006054169A1

公开(公告)日：2006-05-26

申请号：PCT/IB2005/003488

申请日：2005-11-16

Applicant: ACTIVCARD INC. ,  LE SAINT, Eric F. ,  WEN, Wu ,  HAMID, Laurence

Inventor： LE SAINT, Eric F. ,  WEN, Wu ,  HAMID, Laurence

IPC: G06K9/68 ,  G07C9/00

CPC classification number: G06K9/6293 ,  G06K9/00013 ,  G06K9/00885 ,  G06K9/00979

Abstract: A method, system and computer program product for improving error discrimination in biometric authentication systems. The error discrimination is set to a predetermined security policy. A plurality of biometric samples are provided and authenticated by a computer system in conjunction with a security token. An alternate embodiment allows inputting of the plurality of biometric samples in a predetermined sequence. The predetermined input sequence is maintained as an authentication secret which may be used to further reduce the authentication transaction error rate. A user may input one or more biometric samples, where a portion of the biometric samples are inputted in a predetermined sequence, selecting from among a plurality of available processing units, a set of processing units which will generate intermediate results from the processing of the biometric samples, processing at least a portion of the biometric samples by the selected set of processing units to provide intermediate results, verifying the predetermined sequence, and arbitrating the intermediate results to generate a final result which at least meets a predetermined security policy. Various embodiments provide for a security token to perform at least a portion of the processing or the arbitration function.

Abstract translation: 一种用于改善生物识别系统中的误差识别的方法，系统和计算机程序产品。 误差判别被设定为预定的安全策略。 多个生物特征样本由计算机系统与安全令牌一起提供和认证。 替代实施例允许以预定顺序输入多个生物特征样本。 预定输入序列被保持为可用于进一步降低认证交易错误率的认证秘密。 用户可以输入一个或多个生物特征样本，其中以预定顺序输入生物特征样本的一部分，从多个可用处理单元中选择一组处理单元，其将从生物测定的处理中产生中间结果 采样，通过所选择的一组处理单元处理至少一部分生物特征样本，以提供中间结果，验证预定序列，以及仲裁中间结果以产生至少满足预定安全策略的最终结果。 各种实施例提供安全令牌以执行处理或仲裁功能的至少一部分。

公开(公告)号：WO2004006184A3

公开(公告)日：2004-03-18

申请号：PCT/IL0300555

申请日：2003-07-03

Applicant: TALMON GAD ,  ASHANI ZVI

Inventor： TALMON GAD ,  ASHANI ZVI

IPC: G06T7/00 ,  G06K9/00 ,  G06K9/36 ,  G06T7/20 ,  G08B13/196 ,  H04N7/18

CPC classification number: G06K9/00979 ,  G06K9/00 ,  G06K2009/3291 ,  G06T7/20 ,  G06T7/246 ,  G08B13/19608 ,  G08B13/19652 ,  G08B13/19656 ,  G08B13/19667 ,  G08B13/1968 ,  H04N7/181

Abstract: Method and system for performing event detection and object tracking in image streams by installing in field, a set of image acquisition devices, where each device includes a local programmable processor for converting the acquired image stream that consist of one or more images, to a digital format, and a local encoder for generating features from the image stream. These features are parameters that are related to attributes of objects in the image stream. The encoder also transmits a feature stream, whenever the motion features exceed a corresponding threshold. Each image acquisition device is connected to a data network through a corresponding data communication channel. An image processing server that determines the threshold and processes the feature stream is also connected to the data network. Whenever the server receives features from a local encoder through its corresponding data communication channel and the data network, the server provides indications regarding events in the image streams by processing the feature stream and transmitting these indications to an operator.

Abstract translation: 通过在现场安装一组图像采集设备来执行图像流中的事件检测和对象跟踪的方法和系统，其中每个设备包括本地可编程处理器，用于将所获取的由一个或多个图像组成的图像流转换为数字 格式以及用于从图像流中生成特征的本地编码器。 这些功能是与图像流中的对象属性相关的参数。 只要运动特征超过相应的阈值，编码器也会发送特征流。 每个图像采集设备通过相应的数据通信通道连接到数据网络。 确定阈值并处理特征流的图像处理服务器也连接到数据网络。 只要服务器通过其相应的数据通信信道和数据网络从本地编码器接收特征，服务器就通过处理特征流并将这些指示发送给操作者来提供关于图像流中的事件的指示。

公开(公告)号：WO2019040659A1

公开(公告)日：2019-02-28

申请号：PCT/US2018/047591

申请日：2018-08-22

Applicant: BOSSA NOVA ROBOTICS IP, INC.

Inventor： SAVVIDES, Marios ,  LIN, An, Pang ,  VENUGOPALAN, Shreyas ,  THANIKKAL, Ajmal ,  SINGH, Karanhaar ,  ADLER, Gavriel ,  NEBLETT, Kyle ,  PALMER, Christopher

IPC: G06T7/00 ,  G07G3/00 ,  G08B13/00 ,  G08B13/18

CPC classification number: G06K9/00771 ,  G06F16/784 ,  G06K9/00362 ,  G06K9/00369 ,  G06K9/00979

Abstract: A method for processing arrival or removal of packages within the field of view of a video camera includes providing a database for recording packages placed in the field of view. Based on real-time analysis of successive image frames in the camera, a human person's entry and exit from the field of view of the camera is also detected. Delivery or removal of objects is recorded in the database. In one embodiment, the method also determines whether or not a newly arrived package is placed alongside or on top of an existing package.

公开(公告)号：WO2019013918A1

公开(公告)日：2019-01-17

申请号：PCT/US2018/037318

申请日：2018-06-13

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： LIM, Chew How ,  LIM, Bing Qin ,  ABDULLAH, Mohd Faisal ,  GAN, Guo Dong ,  RAMANATHAN, Rm Muthaiah

IPC: G06K9/00

CPC classification number: G06T7/246 ,  G06K9/00248 ,  G06K9/00255 ,  G06K9/00765 ,  G06K9/00912 ,  G06K9/00979 ,  G06K2209/21 ,  G06T7/73 ,  G06T2207/30196 ,  G10L15/20

Abstract: A recognition device (100) and method (200) for recognizing a target (302). The recognition device (100) includes a sensor (112) and an electronic processor (102). The electronic processor (102) configured to receive the characteristic from the sensor (112). The electronic processor (102) identifies a profile based on the characteristic and compares the profile to a plurality of predetermined profiles (103) to determine an identity profile. The electronic processor (102) identifies the target (302) based on the identity profile and determines, based on at least one selected from the group consisting of a location of the target (302), speed of the target (302), and a direction of movement of the target (302), a virtual geographic boundary (300). The electronic processor (102) causes a transmission of the at least one selected from the group consisting of the identity profile and the characteristic to at least one associated device located in the virtual geographic boundary (300).

公开(公告)号：WO2018231480A1

公开(公告)日：2018-12-20

申请号：PCT/US2018/034259

申请日：2018-05-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： SCHLESINGER, Benny ,  WEINBERG, Shira

IPC: G01S17/93 ,  G01S13/93 ,  G06K9/00 ,  G08G1/16 ,  G01S15/93 ,  G07C5/08 ,  G01C21/28

CPC classification number: G05D1/0214 ,  G01C21/28 ,  G06K9/00805 ,  G06K9/00979 ,  G06K9/22 ,  G06K9/6289 ,  G07C5/008 ,  G07C5/08 ,  G07C5/0841 ,  G08G1/0112 ,  G08G1/0133 ,  G08G1/0141 ,  G08G1/0967 ,  G08G1/096716 ,  G08G1/096758 ,  G08G1/096775 ,  G08G1/096791 ,  G08G1/164 ,  G08G1/165 ,  G08G1/166

Abstract: Implementations described herein disclose a road hazard detection method including receiving a plurality of mobile device sensor signals from one or more sensors located on a mobile device within a vehicle, determining the road hazard encountered by the vehicle by analyzing the plurality of mobile device sensor signals, and reporting the existence of the road hazard to other users. In one implementation, the road hazard detection method also uses sensor signals from various sensors located on the vehicle and/or sensor signals from mobile devices of users on other vehicles to determine the road hazard.

公开(公告)号：WO2017209978A1

公开(公告)日：2017-12-07

申请号：PCT/US2017/033438

申请日：2017-05-19

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： BAUMERT, David ,  APACIBLE, Johnson T. ,  BADER, Stephen David ,  BEHRINGER, Adam Edwin ,  LAURINO, Joseph ,  LI, Michelle ,  WANG, Hsiao-Lan

IPC: G06T7/73 ,  G10L15/26 ,  H04N21/61 ,  G06K9/00 ,  G06T19/00 ,  H04N21/81 ,  H04N21/8405 ,  H04N7/14 ,  H04N21/4728

CPC classification number: G06T19/006 ,  G06F3/013 ,  G06F3/167 ,  G06K9/00671 ,  G06K9/00979 ,  G06K9/3233 ,  G10L15/22 ,  H04N7/147 ,  H04N21/4728 ,  H04N21/61 ,  H04N21/8133 ,  H04N21/8405 ,  H04N2007/145

Abstract: Techniques for augmenting video content to enhance context of the video content are described herein. In some instances, a video may be captured at a first location and transmitted to a second location, where the video is output in real-time. A context surrounding a user that is capturing the video and/or a user that is viewing the video may be used to augment the video with additional content. For example, the techniques may process speech or other input associated with either user, a gaze associated with either user, a previous conversation for either user, an area of interest identified by either user, a level of understanding of either user, an environmental condition, and so on. Based on the processing, the techniques may determine augmentation content. The augmentation content may be displayed with the video in an overlaid manner to enhance the experience of the user viewing the video.

Abstract translation: 这里描述了用于增强视频内容以增强视频内容的上下文的技术。 在一些情况下，可以在第一位置处捕捉视频并将其传输至第二位置，其中实时输出视频。 围绕正在捕捉视频的用户和/或正在观看视频的用户的上下文可以用于用附加内容来扩充视频。 例如，这些技术可以处理与用户相关的语音或其他输入，与用户相关的注视，用户的先前对话，用户识别的感兴趣的区域，对任一用户的理解水平，环境条件 ， 等等。 基于处理，这些技术可以确定增强内容。 增强内容可以以覆盖的方式与视频一起显示，以增强用户观看视频的体验。

公开(公告)号：WO2017170384A1

公开(公告)日：2017-10-05

申请号：PCT/JP2017/012364

申请日：2017-03-27

Applicant: 日本電気株式会社

Inventor： 岩田　太地 ,  延藤　圭史

IPC: G06T7/00 ,  G06F21/32

CPC classification number: G06F21/32 ,  G06K9/00006 ,  G06K9/00221 ,  G06K9/00892 ,  G06K9/00906 ,  G06K9/00912 ,  G06K9/00979 ,  G06K9/00993 ,  G06K9/036

Abstract: 生体データ処理装置（５００）は、ユーザに所定の動作を要求するメッセージを表示部に表示させる制御部（５０）と、認証部（５２）と、を有し、認証部（５２）は、ユーザの生体データと予め登録された生体データとの照合により算出された第１のスコアが所定の閾値以上である場合、かつ、メッセージが表示された後に検出部が所定の動作を最初に検出してから生体データ処理装置での認証処理が終了するまでの間、検出部が所定の動作を継続して検出した場合、ユーザの認証を成功と判定する。

Abstract translation:

生物测定数据处理装置（500）包括控制单元，用于显示一个消息请求的预定操作来在显示单元（50）上的用户，认证单元（52），一个 规定的认证单元（52），当通过与先前登记的生物统计数据和所述生物测定数据的核对中计算出的第一得分低于预定的阈值以上的情况下，并且检测单元显示消息后 从一开始就确定操作来检测直到在所述生物测定数据处理装置中的认证处理完成时，当所述检测单元连续地检测预定的操作，用户的成功认证。

公开(公告)号：WO2017125915A1

公开(公告)日：2017-07-27

申请号：PCT/IL2017/050055

申请日：2017-01-17

Applicant: AGT INTERNATIONAL GMBH ,  REINHOLD COHN AND PARTNERS

Inventor： RAMBACH, Jason ,  HUBER, Marco ,  BALTHASAR, Mark Ryan

IPC: G06K9/00

CPC classification number: G06K9/00288 ,  G06K9/00268 ,  G06K9/00979 ,  G06K9/52 ,  G06K9/6215

Abstract: A method and system of recognizing a face image comprising a plurality of processing nodes. Nodes obtain parts of the face image and extract features of the obtained part thereby generating a feature template. Nodes compare the feature template with stored subject templates and calculate an initial similarity score in respect of each comparison, thereby generating an initial score vector associated with a plurality of subjects. Nodes average the initial similarity score vectors generated by it and by at least two predefined nodes, giving rise to an intermediate score vector. The intermediate score vector is repeatedly averaged until a convergence condition is met, thereby generating a final score vector. A node associates the face image to the subject corresponding to the highest score in the final score vector thereby recognizing the face image.

Abstract translation: 识别包括多个处理节点的面部图像的方法和系统。 节点获取人脸图像的一部分并提取获得的部分的特征，从而生成特征模板。 节点将特征模板与存储的主题模板进行比较，并计算关于每个比较的初始相似度分数，由此生成与多个主体相关联的初始分数向量。 节点平均由它和由至少两个预定义节点产生的初始相似度得分向量，产生中间得分向量。 中间分数向量被重复平均，直到满足收敛条件，从而生成最终分数向量。 节点将脸部图像与对应于最终得分向量中的最高分的对象相关联，从而识别脸部图像。