公开(公告)号：US06557752B1

公开(公告)日：2003-05-06

申请号：US08661899

申请日：1996-06-12

申请人： Yaser Yacoob

发明人： Yaser Yacoob

IPC分类号： G06F1700

CPC分类号： G07F7/1008 ,  G06Q20/341 ,  G06Q20/346 ,  G06Q20/3576 ,  G07C3/00 ,  G07C5/0858 ,  G07F9/02

摘要： A computerized “smart card” which has a read/write memory and formatted data storage blocks is used to track the life history of one or more associated machine(s) (e.g., vehicles, medical instrumentation and apparatus, business and copying machines, etc.). The smart card can store a variety of information including machine identification, hardware/software specifications, debit/credit, regulated performance, warranty/insurance, maintenance/service and operational transactions that might impact the hardware, software or the intended operation or performance of the machine. The smart card will be equipped to interact with any of a plurality of autonomous reader/writer smart card units and computer-based reader/writer smart card units that may be equipped to interact with any of the plurality of computer databases through the utilization of land or wireless communications links. Preferably, each smart card will be associated with one or more specific machines at the time of sale of the machines, and will be periodically updated at each transaction (e.g., repair, scheduled maintenance, transfer of title, etc.) using reader/writer units operated by service technicians, repair shops, insurance agents, or the like. Thus, upon transfer of title of the machine, the smart card will also be transferred to provide the new owner with a complete life history for the machine. The stored life history can be used for valuation, maintenance scheduling, problem trouble shooting, and other applications. In the case of a single card being associated with a group of machines (e.g., a company with a fleet of cars, trucks or buses, or a company with several photocopiers, etc.), the card can also be used to track the scheduled replacement of individual machines within the group. Provisions are also made to associate new cards with existing machines to track the future life history of a particular machine.

公开(公告)号：US06170742B2

公开(公告)日：2001-01-09

申请号：US09428914

申请日：1999-10-28

申请人： Yaser Yacoob

发明人： Yaser Yacoob

IPC分类号： G06F1700

CPC分类号： G07F7/1008 ,  G06Q20/341 ,  G06Q20/346 ,  G06Q20/3576 ,  G07C3/00 ,  G07C5/0858 ,  G07F9/02

摘要： A computerized “smart card” which has a read/write memory and formatted data storage blocks is used to track the life history of one or more associated machine(s) (e.g., vehicles, medical instrumentation and apparatus, business and copying machines, etc.). The smart card can store a variety of information including machine identification, hardware/software specifications, debit/credit, regulated performance, warranty/insurance, maintenance/service and operational transactions that might impact the hardware, software or the intended operation or performance of the machine. The smart card will be equipped to interact with any of a plurality of autonomous reader/writer smart card units and computer-based reader/writer smart card units that may be equipped to interact with any of the plurality of computer databases through the utilization of land or wireless communications links. Preferably, each smart card will be associated with one or more specific machines at the time of sale of the machines, and will be periodically updated at each transaction (e.g., repair, scheduled maintenance, transfer of title, etc.) using reader/writer units operated by service technicians, repair shops, insurance agents, or the like. The stored life history can be used for valuation, maintenance scheduling, problem trouble shooting, and other applications.

摘要翻译： 具有读/写存储器和格式化数据存储块的计算机化的“智能卡”用于跟踪一个或多个相关机器（例如，车辆，医疗仪器和设备，商业和复印机等）的寿命 。）。 智能卡可以存储可能影响硬件，软件或预期操作或性能的各种信息，包括机器识别，硬件/软件规格，借记/信用，规范性能，保修/保险，维护/服务和操作交易 机。 该智能卡将被配备成与多个自主的读/写器智能卡单元和基于计算机的读/写智能卡单元中的任何一个进行交互，这些单元可以被配备为通过利用土地与多个计算机数据库中的任何一个进行交互 或无线通信链路。 优选地，每个智能卡将在销售机器时与一个或多个特定机器相关联，并且将使用读/写器在每次交易（例如，维修，定期维护，标题转移等）周期性地更新 由维修技术人员，维修店，保险代理等操作的单元。 存储的生命历史可用于估价，维护计划，故障排除和其他应用。

公开(公告)号：US5802220A

公开(公告)日：1998-09-01

申请号：US574176

申请日：1995-12-15

申请人： Michael J. Black ,  Yaser Yacoob

发明人： Michael J. Black ,  Yaser Yacoob

IPC分类号： G06K9/00 ,  G06T7/20 ,  G06F9/36

CPC分类号： G06K9/00248 ,  G06K9/00315 ,  G06T7/2006 ,  G06T7/2046 ,  G06T2207/10016 ,  G06T2207/30201

摘要： A system tracks human head and facial features over time by analyzing a sequence of images. The system provides descriptions of motion of both head and facial features between two image frames. These descriptions of motion are further analyzed by the system to recognize facial movement and expression. The system analyzes motion between two images using parameterized models of image motion. Initially, a first image in a sequence of images is segmented into a face region and a plurality of facial feature regions. A planar model is used to recover motion parameters that estimate motion between the segmented face region in the first image and a second image in the sequence of images. The second image is warped or shifted back towards the first image using the estimated motion parameters of the planar model, in order to model the facial features relative to the first image. An affine model and an affine model with curvature are used to recover motion parameters that estimate the image motion between the segmented facial feature regions and the warped second image. The recovered motion parameters of the facial feature regions represent the relative motions of the facial features between the first image and the warped image. The face region in the second image is tracked using the recovered motion parameters of the face region. The facial feature regions in the second image are tracked using both the recovered motion parameters for the face region and the motion parameters for the facial feature regions. The parameters describing the motion of the face and facial features are filtered to derive mid-level predicates that define facial gestures occurring between the two images. These mid-level predicates are evaluated over time to determine facial expression and gestures occurring in the image sequence.

摘要翻译： 系统通过分析图像序列来跟踪人的头部和脸部特征。 该系统提供两个图像帧之间的头部和面部特征的运动的描述。 运动的这些描述进一步被系统分析以识别面部运动和表达。 该系统使用图像运动的参数化模型分析两幅图像之间的运动。 首先，图像序列中的第一图像被分割成面部区域和多个面部特征区域。 平面模型用于恢复估计第一图像中的分割面部区域与图像序列中的第二图像之间的运动的运动参数。 使用平面模型的估计运动参数将第二图像扭曲或向后移回第一图像，以便相对于第一图像对面部特征进行建模。 使用仿射模型和具有曲率的仿射模型来恢复估计分割的面部特征区域和翘曲的第二图像之间的图像运动的运动参数。 面部特征区域的恢复的运动参数表示第一图像和翘曲图像之间的面部特征的相对运动。 使用面部区域的恢复的运动参数来跟踪第二图像中的面部区域。 使用恢复的面部区域的运动参数和面部特征区域的运动参数来跟踪第二图像中的面部特征区域。 描述描述脸部和面部特征的运动的参数被过滤以得出定义在两个图像之间出现的面部手势的中间谓词。 随着时间的推移评估这些中级谓词以确定图像序列中出现的面部表情和手势。

公开(公告)号：US5774591A

公开(公告)日：1998-06-30

申请号：US572776

申请日：1995-12-15

申请人： Michael J. Black ,  Yaser Yacoob

发明人： Michael J. Black ,  Yaser Yacoob

IPC分类号： G06K9/00

CPC分类号： G06K9/00315 ,  G06K9/00248

摘要： A system tracks human head and facial features over time by analyzing a sequence of images. The system provides descriptions of motion of both head and facial features between two image frames. These descriptions of motion are further analyzed by the system to recognize facial movement and expression. The system analyzes motion between two images using parameterized models of image motion. Initially, a first image in a sequence of images is segmented into a face region and a plurality of facial feature regions. A planar model is used to recover motion parameters that estimate motion between the segmented face region in the first image and a second image in the sequence of images. The second image is warped or shifted back towards the first image using the estimated motion parameters of the planar model, in order to model the facial features relative to the first image. An affine model and an affine model with curvature are used to recover motion parameters that estimate the image motion between the segmented facial feature regions and the warped second image. The recovered motion parameters of the facial feature regions represent the relative motions of the facial features between the first image and the warped image. The face region in the second image is tracked using the recovered motion parameters of the face region. The facial feature regions in the second image are tracked using both the recovered motion parameters for the face region and the motion parameters for the facial feature regions. The parameters describing the motion of the face and facial features are filtered to derive mid-level predicates that define facial gestures occurring between the two images. These mid-level predicates are evaluated over time to determine facial expression and gestures occurring in the image sequence.

摘要翻译： 系统通过分析图像序列来跟踪人的头部和脸部特征。 该系统提供两个图像帧之间的头部和面部特征的运动的描述。 运动的这些描述进一步被系统分析以识别面部运动和表达。 该系统使用图像运动的参数化模型分析两幅图像之间的运动。 首先，图像序列中的第一图像被分割成面部区域和多个面部特征区域。 平面模型用于恢复估计第一图像中的分割面部区域与图像序列中的第二图像之间的运动的运动参数。 使用平面模型的估计运动参数将第二图像扭曲或向后移回第一图像，以便相对于第一图像对面部特征进行建模。 使用仿射模型和具有曲率的仿射模型来恢复估计分割的面部特征区域和翘曲的第二图像之间的图像运动的运动参数。 面部特征区域的恢复的运动参数表示第一图像和翘曲图像之间的面部特征的相对运动。 使用面部区域的恢复的运动参数来跟踪第二图像中的面部区域。 使用恢复的面部区域的运动参数和面部特征区域的运动参数来跟踪第二图像中的面部特征区域。 描述描述脸部和面部特征的运动的参数被过滤以得出定义在两个图像之间出现的面部手势的中间谓词。 随着时间的推移评估这些中级谓词以确定图像序列中出现的面部表情和手势。