公开(公告)号：US08600227B2

公开(公告)日：2013-12-03

申请号：US13239642

申请日：2011-09-22

申请人： Beilei Xu ,  Lalit Keshav Mestha ,  Yao Rong Wang ,  Peter Paul

发明人： Beilei Xu ,  Lalit Keshav Mestha ,  Yao Rong Wang ,  Peter Paul

IPC分类号： G03B11/00

CPC分类号： G06K9/209 ,  G01J3/2823 ,  G01J3/36 ,  G02B5/201 ,  G02B5/208 ,  G03B11/00 ,  G06K9/00255 ,  G06K2009/00932

摘要： A filter array for a multi-resolution multi-spectral camera system is described which not only captures 2D images at multiple wavelength bands simultaneously but also at a spatial resolution that meets the demand for spatial feature extraction. The present system optimizes filter bands that provide high image contrast at the highest possible resolution to enable spatial feature extraction and other wavelength bands at lower resolution to achieve maximum number of wavelength bands (e.g. spectral resolution) for multi-spectral analysis. After determining the required spatial resolution and number of wavelength bands for spectral analysis, multiple filters are arranged in a geometric pattern with each filter being designed to have specified wavelength and spatial resolution. Physical sizes of filters differ within each filter group. This maximizes the detector usage while optimizing the trade-off between spatial resolution and spectral resolution. Filter gaps are fixed or tuned to wavelengths of interest.

摘要翻译： 描述了用于多分辨率多光谱照相机系统的滤光器阵列，其不仅在多个波长带同时捕获2D图像，而且以满足空间特征提取需求的空间分辨率捕获。 本系统优化以最高可能分辨率提供高图像对比度的滤波器频带，以便能够以较低分辨率进行空间特征提取和其他波长带，以实现用于多光谱分析的最大数量的波段（例如光谱分辨率）。 在确定所需的空间分辨率和用于频谱分析的波长带数之后，多个滤波器以几何图形排列，每个滤波器被设计为具有指定的波长和空间分辨率。 每个过滤器组中过滤器的物理尺寸不同。 这最大限度地提高了检测器的使用率，同时优化了空间分辨率和光谱分辨率之间的折衷。 滤波器间隙固定或调谐到感兴趣的波长。

公开(公告)号：US09202118B2

公开(公告)日：2015-12-01

申请号：US13324308

申请日：2011-12-13

申请人： Yao Rong Wang ,  Beilei Xu ,  Peter Paul

发明人： Yao Rong Wang ,  Beilei Xu ,  Peter Paul

IPC分类号： G06K9/00

CPC分类号： G06K9/00838 ,  G06K9/00221 ,  G06K9/00362

摘要： What is disclosed is a system and method for determining a pixel classification threshold for vehicle occupancy determination. An IR image of a moving vehicle is captured using a multi-band IR imaging system. A driver's face is detected using a face recognition algorithm. Multi-spectral information extracted from pixels identified as human tissue of the driver's face is used to determine a pixel classification threshold. This threshold is then used to facilitate a classification of pixels of a remainder of the IR image. Once pixels in the remainder of the image have been classified, a determination can be made whether the vehicle contains additional human occupants other than the driver. An authority is alerted in the instance where the vehicle is found to be traveling in a HOV/HOT lane requiring two or more human occupants and a determination has been made that the vehicle contains an insufficient number of human occupants.

摘要翻译： 公开的是用于确定车辆占用确定的像素分类阈值的系统和方法。 使用多频带IR成像系统捕获移动车辆的IR图像。 使用人脸识别算法检测驾驶员的脸部。 使用从识别为驾驶员脸部的人体组织的像素提取的多光谱信息来确定像素分类阈值。 然后使用该阈值来促进红外图像的其余部分的像素的分类。 一旦图像的其余部分中的像素被分类，则可以确定车辆是否包含驾驶员以外的其他人员。 在发现车辆在需要两个或更多人的乘客的HOV / HOT车道中行驶的情况下，警告当局，并且已经确定车辆包含的人数不足。

公开(公告)号：US08611608B2

公开(公告)日：2013-12-17

申请号：US13215401

申请日：2011-08-23

申请人： Zhigang Fan ,  Abu Saeed Islam ,  Peter Paul ,  Beilei Xu ,  Lalit Keshav Mestha

发明人： Zhigang Fan ,  Abu Saeed Islam ,  Peter Paul ,  Beilei Xu ,  Lalit Keshav Mestha

IPC分类号： G06K9/00

CPC分类号： G06K9/00234 ,  G06K9/00838 ,  G06K9/2018

摘要： What is disclosed is a system and method for determining whether a front seat in a motor vehicle is occupied based on seat pattern recognition. The present invention takes advantage of the observation that an unoccupied seat of a motor vehicle exhibits features which are distinguishable from an occupied seat. An unoccupied motor vehicle seat typically features long contiguous horizontal line segments and curve segments, and substantially uniform areas encompassed by these segments which are not present in an occupied seat. The present method provides a long horizontal edge test which uses location information within a defined window of the image, edge linking, softness of the edge, number of lines, line/curve fitting, and other techniques to locate horizontal edges in the image which define a seat, and a uniformity step which determines whether the area bounded by the horizontal edges is relatively uniform indicating an unoccupied seat.

摘要翻译： 公开的是基于座椅图案识别来确定机动车辆中的前排座椅是否被占用的系统和方法。 本发明利用了这样的观察结果：机动车辆的空闲座椅表现出与被占用座椅不同的特征。 未占用的机动车辆座椅通常具有长的连续水平线段和曲线段，以及由这些段所包围的基本均匀的区域，其不存在于被占用的座椅中。 本方法提供了一种长的水平边缘测试，它使用图像的定义窗口内的位置信息，边缘链接，边缘柔软度，线数，线/曲线拟合以及其他技术来定位图像中的水平边缘 一个座位和一个均匀性步骤，确定由水平边缘限定的区域是否相对均匀，表示空闲的座位。

公开(公告)号：US20120200682A1

公开(公告)日：2012-08-09

申请号：US13023310

申请日：2011-02-08

申请人： Lalit Keshav Mestha ,  Beilei Xu ,  Peter Paul

发明人： Lalit Keshav Mestha ,  Beilei Xu ,  Peter Paul

IPC分类号： H04N7/18 ,  G06K9/62

CPC分类号： G06K9/0063 ,  G06K2009/00644

摘要： What is disclosed is a novel system and method for simultaneous spectral decomposition suitable for image object identification and categorization for scenes and objects under analysis. The present system captures different spectral planes simultaneously using a Fabry-Perot multi-filter grid each tuned to a specific wavelength. A method for classifying pixels in the captured image is provided. The present system and method finds its uses in a wide array of applications such as, for example, occupancy detection in a transportation management system and in medical imaging and diagnosis for healthcare management. The teachings hereof further find their uses in other applications where there is a need to capture a two dimensional view of a scene and decompose the scene into its spectral bands such that objects in the image can be appropriately identified.

摘要翻译： 所公开的是一种用于同时频谱分解的新型系统和方法，适用于分析场景和物体的图像对象识别和分类。 本系统使用每个调谐到特定波长的法布里 - 珀罗多滤波器网格同时捕获不同的频谱平面。 提供了一种用于对拍摄图像中的像素进行分类的方法。 本系统和方法在广泛的应用中发现其用途，例如在运输管理系统中的占用检测以及用于医疗管理的医学成像和诊​​断。 其中的教导进一步发现它们在其他应用中的用途，其中需要捕获场景的二维视图并将场景分解为其光谱带，使得可以适当地识别图像中的对象。

公开(公告)号：US20130106622A1

公开(公告)日：2013-05-02

申请号：US13284286

申请日：2011-10-28

申请人： Peter Paul ,  Mark Cantelli ,  Beilei Xu ,  Abu Islam

发明人： Peter Paul ,  Mark Cantelli ,  Beilei Xu ,  Abu Islam

IPC分类号： G08G1/01

CPC分类号： G08G1/0175 ,  G08G1/0116

摘要： An upstream vehicle detection system captures images of a vehicle as it travels through a high occupancy vehicle (HOV) lane or high occupancy vehicle tolling (HOT) station and generates an hypothesis as to whether the vehicle is complying with HOV or HOT rules based on image analysis. A database of historical information about various vehicles' compliance with HOV or HOT rules is consulted to determine whether the vehicle has previously been identified as a potential violator and pulled over by law enforcement as a result. If the vehicle was previously pulled over by law enforcement and determined to be complying with HOV or HOT rules (a false positive), then the violation hypothesis may be weighted in favor of not pulling the vehicle over.

摘要翻译： 上游车辆检测系统在行驶通过高占用车辆（HOV）车道或高占用车辆收费站（HOT）站时捕获车辆的图像，并产生关于车辆是否符合基于图像的HOV或HOT规则的假设 分析。 咨询有关各种车辆符合HOV或HOT规则的历史信息数据库，以确定车辆以前是否被确定为潜在的违规者，并因此被执法人员拖欠。 如果车辆以前被执法人员拉扯，并决定遵守HOV或HOT规则（假阳性），则违反假设可能被加权，有利于不拉车。

公开(公告)号：US07911652B2

公开(公告)日：2011-03-22

申请号：US11222260

申请日：2005-09-08

申请人： Nancy B. Goodman ,  Robert P. Loce ,  William J. Nowak ,  Howard A. Mizes ,  Peter Paul ,  Beilei Xu ,  Wencheng Wu ,  Jack Lestrange

发明人： Nancy B. Goodman ,  Robert P. Loce ,  William J. Nowak ,  Howard A. Mizes ,  Peter Paul ,  Beilei Xu ,  Wencheng Wu ,  Jack Lestrange

IPC分类号： G06T5/00

CPC分类号： B41J29/393 ,  G03G15/5062 ,  G03G2215/00067

摘要： A test target is written in a non image zone at set time intervals. The test target is sensed. At least one of frequency, amplitude and phase of banding, which is inherent in a printing device, is determined based on the sensed test target. At least one banding compensation parameter based at least on one of the determined frequency, amplitude and phase of banding is determined. Characteristics of producing an image based on the determined banding compensation parameter are adjusted to compensate the banding inherent in the printing device.

摘要翻译： 测试目标以设定的时间间隔写入非图像区域。 感测测试目标。 基于感测的测试目标来确定打印设备中固有的条带的频率，幅度和相位中的至少一个。 确定至少一个带状补偿参数，至少基于所确定的条带的频率，振幅和相位之一。 调整基于确定的条带补偿参数产生图像的特性，以补偿打印装置固有的条带。

公开(公告)号：US09019358B2

公开(公告)日：2015-04-28

申请号：US13023310

申请日：2011-02-08

申请人： Lalit Keshav Mestha ,  Beilei Xu ,  Peter Paul

发明人： Lalit Keshav Mestha ,  Beilei Xu ,  Peter Paul

IPC分类号： H04N7/18 ,  G06K9/00

CPC分类号： G06K9/0063 ,  G06K2009/00644

摘要： What is disclosed is a novel system and method for simultaneous spectral decomposition suitable for image object identification and categorization for scenes and objects under analysis. The present system captures different spectral planes simultaneously using a Fabry-Perot multi-filter grid each tuned to a specific wavelength. A method for classifying pixels in the captured image is provided. The present system and method finds its uses in a wide array of applications such as, for example, occupancy detection in a transportation management system and in medical imaging and diagnosis for healthcare management. The teachings hereof further find their uses in other applications where there is a need to capture a two dimensional view of a scene and decompose the scene into its spectral bands such that objects in the image can be appropriately identified.

摘要翻译： 所公开的是一种用于同时频谱分解的新型系统和方法，适用于分析场景和物体的图像对象识别和分类。 本系统使用每个调谐到特定波长的法布里 - 珀罗多滤波器网格同时捕获不同的频谱平面。 提供了一种用于对拍摄图像中的像素进行分类的方法。 本系统和方法在广泛的应用中发现其用途，例如在运输管理系统中的占用检测以及用于医疗管理的医学成像和诊​​断。 其中的教导进一步发现它们在其他应用中的用途，其中需要捕获场景的二维视图并将场景分解为其光谱带，使得可以适当地识别图像中的对象。

公开(公告)号：US08824742B2

公开(公告)日：2014-09-02

申请号：US13527228

申请日：2012-06-19

申请人： Sandra Skaff ,  Beilei Xu ,  Peter Paul ,  Craig Saunders ,  Florent Perronnin

发明人： Sandra Skaff ,  Beilei Xu ,  Peter Paul ,  Craig Saunders ,  Florent Perronnin

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC分类号： G06K9/00785 ,  G06K9/00832 ,  G06N99/005

摘要： A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor/representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.

摘要翻译： 用于检测车辆占用违规的系统包括图像捕获模块，其从定位成查看迎面而来的交通的相机获取包括车厢的图像。 该系统包括违规判定装置，其包括处理用于确定图像描述符的图像像素的特征提取模块。 该过程选自连续平均量化变换; 尺度不变特征变换; 梯度直方图; 一个视觉词汇表示; Fisher矢量表示法 以及上述的组合。 该系统还包括分类器，其确定车辆图像描述符/表示相对于超平面位于投影特征空间中的距离。 分类器确定距离是否满足阈值，并在满足阈值时对图像进行分类。 处理器实现模块。 图形用户界面输出分类。

公开(公告)号：US08649566B2

公开(公告)日：2014-02-11

申请号：US12838942

申请日：2010-07-19

申请人： Beilei Xu ,  Wencheng Wu ,  Peter Paul ,  Palghat Ramesh

发明人： Beilei Xu ,  Wencheng Wu ,  Peter Paul ,  Palghat Ramesh

IPC分类号： G06K9/00 ,  G06K9/03 ,  G06K9/20

CPC分类号： H04N1/00002 ,  G06K9/036 ,  H04N1/00018 ,  H04N1/00047 ,  H04N1/00084

摘要： A method for detecting motion quality error of printed documents having text in a printing system includes: printing a document having text lines, each text line comprising a plurality of characters; scanning the printed document to generate a scanned image; detecting positions in a process direction of the printing system of one of text lines and characters in the scanned image; determining position errors in the process direction in the printed document based on the detected positions in the scanned image; determining at least one motion quality defect of the printing system in the process direction based on the determined position errors; and initiating an activity associated with said printing system in response to a motion quality error having been determined. A system for detecting motion quality error of printed documents is also disclosed.

摘要翻译： 一种用于检测在打印系统中具有文本的打印文档的运动质量错误的方法，包括：打印具有文本行的文档，每个文本行包括多个字符; 扫描打印文档以生成扫描图像; 检测所述扫描图像中的文本行和文字之一的所述打印系统的处理方向的位置; 基于扫描图像中检测到的位置确定打印文档中的处理方向上的位置误差; 基于所确定的位置误差，确定所述打印系统在所述处理方向上的至少一个运动质量缺陷; 以及响应于已经确定的运动质量错误，发起与所述打印系统相关联的活动。 还公开了一种用于检测打印文件的运动质量误差的系统。

公开(公告)号：US20130336538A1

公开(公告)日：2013-12-19

申请号：US13527228

申请日：2012-06-19

申请人： Sandra Skaff ,  Beilei Xu ,  Peter Paul ,  Craig Saunders ,  Florent Perronnin

发明人： Sandra Skaff ,  Beilei Xu ,  Peter Paul ,  Craig Saunders ,  Florent Perronnin

IPC分类号： G06K9/62

CPC分类号： G06K9/00785 ,  G06K9/00832 ,  G06N99/005

摘要： A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor/representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.

摘要翻译： 用于检测车辆占用违规的系统包括图像捕获模块，其从定位成查看迎面而来的交通的相机获取包括车厢的图像。 该系统包括违规判定装置，其包括处理用于确定图像描述符的图像像素的特征提取模块。 该过程选自连续平均量化变换; 尺度不变特征变换; 梯度直方图; 一个视觉词汇表示; Fisher矢量表示法 以及上述的组合。 该系统还包括分类器，其确定车辆图像描述符/表示相对于超平面位于投影特征空间中的距离。 分类器确定距离是否满足阈值，并在满足阈值时对图像进行分类。 处理器实现模块。 图形用户界面输出分类。