公开(公告)号：US08363956B1

公开(公告)日：2013-01-29

申请号：US11028008

申请日：2004-12-30

申请人： William M. Silver ,  E. John McGarry ,  Matthew L. Hill ,  Nigel J. Foster ,  Sanjay Nichani ,  Willard P. Foster ,  Adam Wagman

发明人： William M. Silver ,  E. John McGarry ,  Matthew L. Hill ,  Nigel J. Foster ,  Sanjay Nichani ,  Willard P. Foster ,  Adam Wagman

IPC分类号： G06K9/62

CPC分类号： G06K9/6201 ,  G06K9/481 ,  G06K9/6204

摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.

公开(公告)号：US08244041B1

公开(公告)日：2012-08-14

申请号：US11029104

申请日：2004-12-31

申请人： William M. Silver ,  E. John McGarry ,  Nigel J. Foster ,  Sanjay Nichani

发明人： William M. Silver ,  E. John McGarry ,  Nigel J. Foster ,  Sanjay Nichani

IPC分类号： G06K9/62

CPC分类号： G06K9/6201 ,  G06K9/481 ,  G06K9/6204

摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.

摘要翻译： 公开了一种用于确定图像中的预定图案的一个或多个实例的不存在或不存在以及用于在多维空间内确定每个找到的实例的位置的方法。 模型代表要发现的模式，该模型包括多个探针。 每个探针表示在给定姿势下在图像中进行测试的相对位置，每个这样的测试提供了该模式存在于姿势的证据。 该方法还包括在多个姿势中的每个姿势下的模型与运行时图像的比较。 在每个姿态计算匹配得分以提供匹配得分表面。 然后，匹配得分与接受阈值进行比较，并用于提供图像中图案的任何实例的位置。

公开(公告)号：US08199975B2

公开(公告)日：2012-06-12

申请号：US11954513

申请日：2007-12-12

申请人： Dean Arthur Pomerleau ,  Jay W. Gowdy ,  Matthew Troup ,  Sanjay Nichani

发明人： Dean Arthur Pomerleau ,  Jay W. Gowdy ,  Matthew Troup ,  Sanjay Nichani

IPC分类号： G06K9/00

CPC分类号： H04N5/247 ,  B60R1/00 ,  B60R1/12 ,  B60R11/04 ,  B60R2001/1253 ,  B60R2011/004 ,  B60R2300/107 ,  B60R2300/30 ,  B60R2300/804 ,  B60R2300/8066 ,  G06T7/593 ,  G06T2207/10012 ,  G06T2207/30261 ,  G08G1/166 ,  G08G1/167 ,  H04N7/18 ,  H04N13/239 ,  H04N2013/0074

摘要： This invention provides a system and method for object detection and collision avoidance for objects and vehicles located behind the cab or front section of an elongated, and possibly tandem, vehicle. Through the use of narrow-baseline stereo vision that can be vertically oriented relative to the ground/road surface, the system and method can employ relatively inexpensive cameras, in a stereo relationship, on a low-profile mounting, to perform reliable detection with good range discrimination. The field of detection is sufficiently behind and aside the rear area to assure an adequate safety zone in most instances. Moreover, this system and method allows all equipment to be maintained on the cab of a tandem vehicle, rather than the interchangeable, and more-prone-to-damage cargo section and/or trailer. One or more cameras can be mounted on, or within, the mirror on each side, on aerodynamic fairings or other exposed locations of the vehicle. Image signals received from each camera can be conditioned before they are matched and compared for disparities viewed above the ground surface, and according to predetermined disparity criteria.

摘要翻译： 本发明提供了一种用于物体检测和碰撞避免的系统和方法，所述系统和方法位于延伸且可能串联的车辆的驾驶室或前部后面的物体和车辆。 通过使用可以相对于地面/路面垂直取向的窄基线立体视觉，该系统和方法可以采用相对便宜的立体声关系，在低调安装上，以便良好地执行可靠的检测 范围歧视。 在大多数情况下，检测领域足够落后于后部区域，以确保足够的安全区域。 此外，该系统和方法允许所有设备都保持在串联车辆的驾驶室上，而不是可互换的和更容易受损的货物部分和/或拖车。 一个或多个摄像机可以安装在每侧的反射镜上或内部，在空气动力学整流罩或车辆的其他暴露位置上。 在匹配之前，可以调整从每个摄像机接收到的图像信号，并且根据预定的视差标准对在地面以上观察到的差异进行比较。

公开(公告)号：US20070047837A1

公开(公告)日：2007-03-01

申请号：US11215307

申请日：2005-08-29

申请人： John Schwab ,  Sanjay Nichani

发明人： John Schwab ,  Sanjay Nichani

IPC分类号： G06K9/36

CPC分类号： G06K9/00771 ,  G06T7/0008 ,  G06T7/593 ,  G07C9/025

摘要： A stereo imaging based vision system and method provides enhanced portal security through stereoscopy. In particular, a system detects non-people objects within the chamber of a revolving door by acquiring two-dimensional (2D) images from different vantage points, and computing a filtered set of three-dimensional (3D) features of the door compartment by using both the acquired 2D images and model 2D images. Applying image processing techniques to the filtered 3D feature set, non-people objects can be detected.

摘要翻译： 基于立体成像的视觉系统和方法通过立体镜提供增强的门禁安全性。 特别地，系统通过从不同的有利位置获取二维（2D）图像并通过使用以下方式计算门室的三维（3D）特征的滤波集合来检测旋转门室内的非人物体： 所获得的2D图像和2D图像。 将图像处理技术应用于过滤的3D特征集，可以检测非人物对象。

公开(公告)号：US07167575B1

公开(公告)日：2007-01-23

申请号：US09563011

申请日：2000-04-29

申请人： Sanjay Nichani ,  Robert Wolff ,  William Silver ,  David A. Schatz

发明人： Sanjay Nichani ,  Robert Wolff ,  William Silver ,  David A. Schatz

IPC分类号： G06K9/00

CPC分类号： G08B13/19604 ,  G08B13/1961

摘要： A two-dimensional (2-D) machine-vision safety-solution involving a method and apparatus for performing high-integrity, high efficiency machine vision. A known structured lighting texture pattern is projected upon a target area. A model image of the pattern on an empty target field is stored during an initial training step. The machine vision safety solution digitally interprets a camera image of the light reflected by the objects in the target area to detect and characterize a pattern in the image. The pattern characterization is then processed to determine if a distortion of the characterization factors is larger than a predetermined threshold, and results in an alarm condition.

摘要翻译： 二维（2-D）机器视觉安全解决方案涉及一种执行高完整性，高效率机器视觉的方法和装置。 将已知的结构化照明纹理图案投影到目标区域上。 在初始训练步骤中存储空目标区域上的模式的模型图像。 机器视觉安全解决方案数字地解释由目标区域中的物体反射的光的照相机图像，以检测和表征图像中的图案。 然后处理图案表征以确定特征因子的失真是否大于预定阈值，并且导致报警状况。

公开(公告)号：US06829371B1

公开(公告)日：2004-12-07

申请号：US09728503

申请日：2000-11-30

申请人： Sanjay Nichani ,  William Silver ,  David A. Schatz

发明人： Sanjay Nichani ,  William Silver ,  David A. Schatz

IPC分类号： G06K900

CPC分类号： F16P3/142

摘要： A two-dimensional (2-D) machine-vision safety method and apparatus performs high-integrity, high efficiency machine vision. The system digitally filters a configurable number of time-sequenced camera images of a viewed area to create a filtered image. Objects within view in a training phase are detected and compared to objects detected in a runtime phase. Each new image is then compared to the previously created model and a pixel-oriented difference image is calculated. The difference image is then processed for segmentation features attributable to an intruder object. Alarm conditions are determined from threshold parameters related to location of the intruder objects. For segmentation results that exceed a predetermined threshold, an alarm condition is set. Setup parameters are automatically generated by analysis of distinctively marked physical boundaries in an image. Automatic tools assist in optimization of setup configurations, based on size and speed of intruding objects, system response time, and camera geometry.

摘要翻译： 二维（2-D）机器视觉安全方法和装置执行高完整性，高效率的机器视觉。 该系统数字地过滤可观看区域的可配置数量的时间序列相机图像，以创建过滤图像。 在训练阶段的视图内的对象被检测并与运行时阶段中检测到的对象进行比较。 然后将每个新图像与先前创建的模型进行比较，并计算像素取向的差分图像。 然后对可归因于入侵者对象的分段特征处理差异图像。 报警条件由与入侵者对象位置相关的阈值参数确定。 对于超过预定阈值的分割结果，设置报警条件。 通过分析图像中明显标记的物理边界来自动生成设置参数。 自动工具有助于根据入侵物体的大小和速度，系统响应时间和摄像机几何优化设置配置。

公开(公告)号：US06469734B1

公开(公告)日：2002-10-22

申请号：US09563010

申请日：2000-04-29

申请人： Sanjay Nichani ,  Robert Wolff ,  William Silver ,  David A. Schatz

发明人： Sanjay Nichani ,  Robert Wolff ,  William Silver ,  David A. Schatz

IPC分类号： H04N718

CPC分类号： H04N7/188

摘要： A two-dimensional (2-D) machine-vision safety-solution involving a method and apparatus for performing high-integrity, high efficiency machine vision. The machine vision safety solution digitally filters a configurable number of time-sequenced images of a viewed area to create a filtered image. A textured background is used as a static target and viewed under ambient light, or alternatively a texture is observed under IR light. An artificial texture can be created with a particularized pattern. Each new image is then compared to the previously created model and a pixel-oriented difference image is calculated. The difference image is then processed for segmentation features attributable to an intruder object. For segmentation results that exceed a predetermined threshold, an alarm condition is set.

摘要翻译： 二维（2-D）机器视觉安全解决方案涉及一种执行高完整性，高效率机器视觉的方法和装置。 机器视觉安全解决方案数字地过滤可视化区域的可配置数量的时间序列图像以创建过滤图像。 纹理背景用作静态目标并在环境光下观察，或者在红外光下观察纹理。 可以使用特定图案创建人造纹理。 然后将每个新图像与先前创建的模型进行比较，并计算像素取向的差分图像。 然后对可归因于入侵者对象的分段特征处理差异图像。 对于超过预定阈值的分割结果，设置报警条件。

公开(公告)号：US20130028400A1

公开(公告)日：2013-01-31

申请号：US13556813

申请日：2012-07-24

申请人： Raymond Fix ,  Sanjay Nichani ,  Chethan Reddy

发明人： Raymond Fix ,  Sanjay Nichani ,  Chethan Reddy

IPC分类号： H04M11/00

CPC分类号： G09B5/12 ,  H04L51/36

摘要： A Skqueak™ is an interactively created electronic memo/message that combines a voiceover with user-interaction elements on a selected background. The background could be images, sequence of images from a video, entire video, files such as documents or pre-canned templates. The user inter-action elements are sketch animations, text animations, symbols, shapes, emoticons, image transformation events (pan, zoom, rotation etc.). Skqueak™ also denotes the application that allows the creation of a Skqueak™. Skqueak™ also represents a web service available at www.skqueak.com that allows the creation, viewing, storing, sharing, searching, annotating, and manipulation of Skqueaks.

摘要翻译： Skqueak™是一种交互式创建的电子备忘录/消息，将选择的背景与用户交互元素相结合。 背景可以是图像，来自视频的图像序列，整个视频，诸如文档或预先装模板的文件。 用户互动元素是草图动画，文本动画，符号，形状，表情符号，图像变换事件（平移，缩放，旋转等）。 Skqueak™还表示允许创建Skqueak™的应用程序。 Skqueak™还可以在www.skqueak.com上提供Web服务，允许创建，查看，存储，共享，搜索，注释和操纵Skqueaks。

公开(公告)号：US08326084B1

公开(公告)日：2012-12-04

申请号：US11019931

申请日：2004-12-21

申请人： Cyril C. Marrion, Jr. ,  Sanjay Nichani

发明人： Cyril C. Marrion, Jr. ,  Sanjay Nichani

IPC分类号： G06K9/00

CPC分类号： G06K9/00778 ,  G06T7/248 ,  G06T7/285 ,  G06T7/593 ,  G06T2207/30201 ,  G07C9/00 ,  G07C9/025 ,  H04N5/2351 ,  H04N13/296

摘要： A system and method of auto-exposure control is provided for image acquisition hardware using three dimensional information to identify a region(s) of interest within an acquired 2D image or images upon which to apply traditional auto-exposure techniques. By performing auto-exposure analysis over the region of interest, the acquisition property settings can be assigned such that the light levels within the region of interest fall within the linear range, producing sufficient grayscale information for identifying particular objects and profiles in subsequently acquired images. For example, in a machine vision application that detects people passing through a doorway, the region of interest can be the portion of the 2D image that generated 3D features of a head and shoulders profile within a 3D model of the doorway scene. With higher quality images, more accurate detection of people candidates within the monitored scene results.

摘要翻译： 为使用三维信息的图像采集硬件提供自动曝光控制的系统和方法，以识别所采集的2D图像内的感兴趣区域或应用传统自动曝光技术的图像。 通过在感兴趣的区域上执行自动曝光分析，可以分配采集属性设置，使得感兴趣区域内的光级落在线性范围内，产生用于识别随后获取的图像中的特定对象和轮廓的足够的灰度信息。 例如，在检测通过门口的人的机器视觉应用中，感兴趣的区域可以是在门口场景的3D模型内产生头部和肩部轮廓的3D特征的2D图像的部分。 以更高质量的图像，更准确地检测监视场景内的人员候选人的结果。

公开(公告)号：US08320675B1

公开(公告)日：2012-11-27

申请号：US11026004

申请日：2004-12-31

申请人： William M. Silver ,  E. John McGarry ,  Sanjay Nichani ,  Adam Wagman

发明人： William M. Silver ,  E. John McGarry ,  Sanjay Nichani ,  Adam Wagman

IPC分类号： G06K9/00

CPC分类号： G06K9/6201 ,  G06K9/481 ,  G06K9/6204

摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.