公开(公告)号：WO2005086078A1

公开(公告)日：2005-09-15

申请号：PCT/US2005/006758

申请日：2005-03-02

Applicant: SARNOFF CORPORATION ,  HIRVONEN, David ,  CAMUS, Theodore, Armand

Inventor： HIRVONEN, David ,  CAMUS, Theodore, Armand

IPC: G06K9/00

CPC classification number: G06K9/00214 ,  G06K9/3241

Abstract: A method and apparatus for classifying an object in an image is disclosed. A depth image is provided. Areas of the depth image unsatisfactory for object identification are eliminated from consideration. A plurality of two-dimensional projections of surface normals in the depth image is determined. One or more objects are classified based on the plurality of surface normals.

Abstract translation: 公开了一种用于对图像中的对象进行分类的方法和装置。 提供深度图像。 考虑到物体识别的深度图像不能令人满意的区域。 确定深度图像中的表面法线的多个二维投影。 基于多个表面法线分类一个或多个对象。

公开(公告)号：WO2009158662A3

公开(公告)日：2009-12-30

申请号：PCT/US2009/048935

申请日：2009-06-26

Applicant: GLOBAL RAINMAKERS, INC. ,  HANNA, Keith, J. ,  RIDDLE, George, H. ,  HIRVONEN, David ,  SLINEY, David

Inventor： HANNA, Keith, J. ,  RIDDLE, George, H. ,  HIRVONEN, David ,  SLINEY, David

IPC: H05B37/02 ,  G06K9/00

Abstract: A method of providing active illumination during biometry that utilizes pulsed lighting synchronized to frame acquisition. Two distinct illumination modalities are provided: the first maximizes the quality of images captured by the imaging system, and the second minimizes the overall illumination perceived by the user in combination with the first. The two modalities are provided substantially simultaneously. The first modality always includes a set of pulses synchronized with frame acquisition. The second modality may be either a second set of pulses not synchronized with frame acquisition or constant background illumination. The two modalities may be generated by two separate sources of illumination or by the same single illumination source. Adding the second modality to the first reduces user discomfort and the chances of an epileptic response as compared to using the first modality alone. The two modalities may have different wavelengths, pulse durations, or intensities.

公开(公告)号：WO2009158662A2

公开(公告)日：2009-12-30

申请号：PCT/US2009048935

申请日：2009-06-26

Applicant: GLOBAL RAINMAKERS INC ,  HANNA KEITH J ,  RIDDLE GEORGE H ,  HIRVONEN DAVID ,  SLINEY DAVID

Inventor： HANNA KEITH J ,  RIDDLE GEORGE H ,  HIRVONEN DAVID ,  SLINEY DAVID

IPC: H05B37/02 ,  G06K9/00

CPC classification number: G06K9/2027

Abstract: A method of providing active illumination during biometry that utilizes pulsed lighting synchronized to frame acquisition. Two distinct illumination modalities are provided: the first maximizes the quality of images captured by the imaging system, and the second minimizes the overall illumination perceived by the user in combination with the first. The two modalities are provided substantially simultaneously. The first modality always includes a set of pulses synchronized with frame acquisition. The second modality may be either a second set of pulses not synchronized with frame acquisition or constant background illumination. The two modalities may be generated by two separate sources of illumination or by the same single illumination source. Adding the second modality to the first reduces user discomfort and the chances of an epileptic response as compared to using the first modality alone. The two modalities may have different wavelengths, pulse durations, or intensities.

Abstract translation: 一种在生物测量期间提供有源照明的方法，其利用与帧采集同步的脉冲照明。 提供了两种不同的照明模式：第一最大化由成像系统拍摄的图像的质量，第二最小化由用户结合第一视觉感知的整体照明。 这两种方式基本同时提供。 第一种模式总是包含与帧采集同步的一组脉冲。 第二模式可以是与帧获取或恒定背景照明不同步的第二组脉冲。 两种模式可以由两个独立的照明源或相同的单一照明源产生。 与第一种模式相比，将第二种模式添加到第一种模式可减少用户不适和癫痫反应的可能性。 这两种方式可能具有不同的波长，脉冲持续时间或强度。

公开(公告)号：WO2009029757A1

公开(公告)日：2009-03-05

申请号：PCT/US2008/074737

申请日：2008-08-29

Applicant: GLOBAL RAINMAKERS, INC. ,  HANNA, Keith, J. ,  HIRVONEN, David, James ,  NEEDHAM RIDDLE, George, Herbert

Inventor： HANNA, Keith, J. ,  HIRVONEN, David, James ,  NEEDHAM RIDDLE, George, Herbert

IPC: G06K9/00

CPC classification number: G06K9/00604 ,  A61B3/14 ,  G06K9/0061 ,  G06K9/2054 ,  G06K9/209 ,  G06K9/60

Abstract: A system and related method for acquiring high quality images of the iris of an unconstrained subject comprising a camera; a controllable focusing component; a focus controller component that controls the lens to focus at successively different points within a focus range, such focus control performed without any input from measurement of whether the image is in focus or out of focus, be it based from measurements of the image or other distance metrics to the subject; and a sharpness detection component that rejects the most out-of-focus images based on measurement of focus on the image is disclosed.

Abstract translation: 一种用于获取包含相机的无约束对象的虹膜的高质量图像的系统和相关方法; 可控聚焦组件; 焦点控制器组件，其控制透镜在聚焦范围内的连续不同点聚焦，这样的聚焦控制执行而没有测量图像是聚焦还是不在焦点的任何输入，是基于图像或其他 距离指标到主题; 并且公开了基于对图像上的焦点的测量来拒绝最多的失焦图像的锐度检测部件。

公开(公告)号：WO2006028434A3

公开(公告)日：2006-03-16

申请号：PCT/US2004/021554

申请日：2004-07-06

Applicant: SARNOFF CORPORATION ,  Ford Motor Company ,  SOUTHALL, John ,  CAMUS, Theodore ,  HIRVONEN, David

Inventor： SOUTHALL, John ,  CAMUS, Theodore ,  HIRVONEN, David

IPC: G06K7/14

Abstract: A vehicle vision system that uses a depth map, image intensity data, and system calibration parameter to determine a target's dimensions and relative position. Initial target boundary information is projected onto the depth map and onto the image intensity. A visibility analysis determines whether the rear of a target is within the system's field of view. If so, the mapped image boundary is analyzed to determine an upper boundary of the target. Then, vertical image edges of the mapped image boundary are found by searching for a strongest pair of vertical image edges that are located at about the same depth. Then, the bottom of the mapped image boundary is found (or assumed from calibration parameters). Then, the target's position is found by an averaging technique. The height and width of the target are then computed.

公开(公告)号：WO2004114202A1

公开(公告)日：2004-12-29

申请号：PCT/US2004/018963

申请日：2004-06-14

Applicant: SARNOFF CORPORATION ,  FORD MOTOR COMPANY ,  MANDELBAUM, Robert ,  CAMUS, Theodore ,  HIRVONEN, David ,  CALL, Billie Joe ,  HILL, Ian, Gregory ,  RIEDER, Andre ,  SOUTHALL, John

Inventor： MANDELBAUM, Robert ,  CAMUS, Theodore ,  HIRVONEN, David ,  CALL, Billie Joe ,  HILL, Ian, Gregory ,  RIEDER, Andre ,  SOUTHALL, John

IPC: G06K9/00

CPC classification number: G06K9/00805 ,  G06K9/00201 ,  G06K9/3241 ,  G06T7/593 ,  G06T2207/20064 ,  G06T2207/30252

Abstract: A vision system for a vehicle that identifies and classifies objects (targets) located proximate a vehicle. The system comprises a sensor array that produces imagery that is processed to generate depth maps of the scene proximate a vehicle. The depth maps are processed and compared to pre-rendered templates of target objects that could appear proximate the vehicle. A target list is produced by matching the pre-rendered templates to the depth map imagery. The system processes the target list to produce target size and classification estimates. The target is then tracked as it moves near a vehicle and the target position, classification and velocity are determined. This information can be used in a number of ways. For example, the target information may be displayed to the driver, the information may be used for an obstacle avoidance system that adjusts the trajectory or other parameters of the vehicle to safely avoid the obstacle. The orientation and/or configuration of the vehicle may be adapted to mitigate damage resulting from an imminent collision, or the driver may be warned of an impending collision.

Abstract translation: 用于识别和分类位于车辆附近的物体（目标）的车辆的视觉系统。 该系统包括产生图像的传感器阵列，其被处理以生成紧邻车辆的场景的深度图。 处理深度图并将其与可能出现在车辆附近的目标对象的预渲染模板进行比较。 通过将预渲染的模板匹配到深度图图像来生成目标列表。 系统处理目标列表以产生目标大小和分类估计。 然后在车辆附近移动时跟踪目标，并确定目标位置，分类和速度。 该信息可以以多种方式使用。 例如，可以向驾驶员显示目标信息，该信息可以用于调整车辆的轨迹或其他参数以避免障碍物的障碍物回避系统。 车辆的方向和/或构造可以适于减轻由于即将发生的碰撞造成的损坏，或者可能警告驾驶员即将发生的碰撞。

公开(公告)号：WO2013109295A3

公开(公告)日：2013-10-10

申请号：PCT/US2012032391

申请日：2012-04-05

Applicant: EYELOCK INC ,  HANNA KEITH J ,  GREENE GARY ALAN ,  HIRVONEN DAVID JAMES ,  HOYOS HECTOR T ,  RIDDLE GEORGE HERBERT NEEDHAM

Inventor： HANNA KEITH J ,  GREENE GARY ALAN ,  HIRVONEN DAVID JAMES ,  HOYOS HECTOR T ,  RIDDLE GEORGE HERBERT NEEDHAM

IPC: G06K9/46 ,  G06K9/00 ,  G06K9/36

CPC classification number: G06K9/00604 ,  G06K9/00912

Abstract: The present disclosure is directed towards a compact, mobile apparatus for iris image acquisition, adapted to address effects of ocular dominance in the subject and to guide positioning of the subject's iris for the image acquisition. The apparatus may include a sensor for acquiring an iris image from a subject. A compact mirror may be oriented relative to a dominant eye of the subject, and sized to present an image of a single iris to the subject when the apparatus is positioned at a suitable distance for image acquisition. The mirror may assist the subject in positioning the iris for iris image acquisition. The mirror may be positioned between the sensor and the iris during iris image acquisition, and transmit a portion of light reflected off the iris to the sensor.

Abstract translation: 本公开涉及用于虹膜图像采集的紧凑型移动装置，其适于解决对象中眼睛优势的影响并且引导用于图像采集的被摄体虹膜的定位。 该装置可以包括用于从受试者获取虹膜图像的传感器。 紧凑的反射镜可以相对于被摄体的主要眼睛定向，并且其尺寸设计成当设备定位在适当的距离处以用于图像采集时，将单个虹膜的图像呈现给被摄体。 镜子可以帮助被摄体定位虹膜以进行虹膜图像采集。 在光圈图像采集期间，镜可以定位在传感器和光圈之间，并将从光圈反射的一部分光传输到传感器。

公开(公告)号：WO2009029765A1

公开(公告)日：2009-03-05

申请号：PCT/US2008/074751

申请日：2008-08-29

Applicant: GLOBAL RAINMAKERS, INC. ,  HANNA, Keith, J. ,  HIRVONEN, David James ,  SLINEY, David Hammond ,  RIDDLE, George Herbert Needham

Inventor： HANNA, Keith, J. ,  HIRVONEN, David James ,  SLINEY, David Hammond ,  RIDDLE, George Herbert Needham

IPC: G06K9/00

CPC classification number: G06K9/00604 ,  A61B3/14 ,  G06K9/0061 ,  G06K9/2054 ,  G06K9/209 ,  G06K9/60

Abstract: A system and method for obtaining biometric imagery such as iris imagery from large capture volumes is disclosed wherein a substantially rotationally symmetric mirror such as a cone or sphere is rotated at a constant velocity about a central axis.

Abstract translation: 公开了一种用于从大的捕获体积获得诸如虹膜图像之类的生物特征图像的系统和方法，其中基本上旋转对称的反射镜例如锥体或球体围绕中心轴线以恒定的速度旋转。

公开(公告)号：WO2005004035A2

公开(公告)日：2005-01-13

申请号：PCT/US2004021550

申请日：2004-07-02

Applicant: SARNOFF CORP ,  FORD MOTOR CO ,  CHANG PENG ,  HIRVONEN DAVID ,  CAMUS THEODORE

Inventor： CHANG PENG ,  HIRVONEN DAVID ,  CAMUS THEODORE

IPC: B60Q1/00 ,  G01C5/00 ,  G01C21/30 ,  G01S1/00 ,  G01V3/00 ,  G06F15/00 ,  G06F19/00 ,  G06K20060101 ,  G06K9/00 ,  G06K9/36 ,  G08B21/00 ,  G06K

CPC classification number: G06K9/00624 ,  G06K9/00805 ,  G06K9/3241

Abstract: A vision system that forms a map of a scene proximate a platform, e.g., a vehicle, that determines the actual ground plane form the map, and that corrects the map for differences between the actual ground plane and an assumed ground plane. The vision system may remove the actual ground plane from the map to prevent false positives. The vision system can further identify and classify objects and, if appropriate, take evasive action.

Abstract translation: 形成靠近平台（例如，车辆）的场景的地图的视觉系统，其确定实际地平面形成地图，并且校正地图以获得实际接地平面与假定地平面之间的差异。 视觉系统可以从地图中去除实际的地平面，以防止误报。 视觉系统可以进一步识别和分类对象，如果适当，采取回避行动。

公开(公告)号：WO2006028434A2

公开(公告)日：2006-03-16

申请号：PCT/US2004021554

申请日：2004-07-06

Applicant: SARNOFF CORP ,  FORD MOTOR CO ,  SOUTHALL JOHN ,  CAMUS THEODORE ,  HIRVONEN DAVID

Inventor： SOUTHALL JOHN ,  CAMUS THEODORE ,  HIRVONEN DAVID

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06K9/00624 ,  G06T7/55

Abstract: A vehicle vision system that uses a depth map, image intensity data, and system calibration parameter to determine a target's dimensions and relative position. Initial target boundary information is projected onto the depth map and onto the image intensity. A visibility analysis determines whether the rear of a target is within the system's field of view. If so, the mapped image boundary is analyzed to determine an upper boundary of the target. Then, vertical image edges of the mapped image boundary are found by searching for a strongest pair of vertical image edges that are located at about the same depth. Then, the bottom of the mapped image boundary is found (or assumed from calibration parameters). Then, the target's position is found by an averaging technique. The height and width of the target are then computed.

Abstract translation: 一种车辆视觉系统，其使用深度图，图像强度数据和系统校准参数来确定目标的尺寸和相对位置。 初始目标边界信息被投影到深度图和图像强度上。 可视性分析确定目标的后部是否在系统的视野内。 如果是，则分析映射的图像边界以确定目标的上边界。 然后，通过搜索位于大约相同深度的最强的一对垂直图像边缘来找到映射图像边界的垂直图像边缘。 然后，找到映射图像边界的底部（或从校准参数假设）。 然后，通过平均技术找到目标的位置。 然后计算目标的高度和宽度。