-
公开(公告)号：US20100014780A1
公开(公告)日：2010-01-21
申请号：US12174106
申请日：2008-07-16
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
IPC分类号： G06K9/36
CPC分类号： G06T5/20 , G06T1/00 , G06T5/002 , G06T7/33 , G06T2207/10116 , G06T2207/30008
摘要： A method to stitch images includes the steps of: determining a template window in the first digital image and a target window in the second digital image and extracting selected features from the selected windows and a template in the template window; extracting selected features from within the template at a first resolution; matching the selected features in the target window; extracting selected features from within the template and target window at a second resolution higher than the first resolution; matching the selected features in the target window; performing a first evaluation of the second estimate of the stitching location; blending the second estimate of the stitching location; performing an evaluation of the stitching location; stitching the first digital image and a second digital image using the stitching location to create a stitched image; and saving the stitched image to memory. A system to perform the method is also described.
摘要翻译： 缝合图像的方法包括以下步骤：确定第一数字图像中的模板窗口和第二数字图像中的目标窗口，并从所选择的窗口中提取所选特征以及模板窗口中的模板; 以第一分辨率从模板内提取所选特征; 匹配目标窗口中选定的要素; 以高于第一分辨率的第二分辨率从模板和目标窗口内提取所选特征; 匹配目标窗口中选定的要素; 执行缝合位置的第二估计的第一评估; 混合拼接位置的第二估计; 对缝合位置进行评估; 使用缝合位置缝合第一数字图像和第二数字图像以创建缝合图像; 并将缝合的图像保存到存储器。 还描述了执行该方法的系统。
-
公开(公告)号：US08600193B2
公开(公告)日：2013-12-03
申请号：US12174106
申请日：2008-07-16
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
CPC分类号： G06T5/20 , G06T1/00 , G06T5/002 , G06T7/33 , G06T2207/10116 , G06T2207/30008
摘要： A method to stitch images includes the steps of: determining a template window in the first digital image and a target window in the second digital image and extracting selected features from the selected windows and a template in the template window; extracting selected features from within the template at a first resolution; matching the selected features in the target window; extracting selected features from within the template and target window at a second resolution higher than the first resolution; matching the selected features in the target window; performing a first evaluation of the second estimate of the stitching location; blending the second estimate of the stitching location; performing an evaluation of the stitching location; stitching the first digital image and a second digital image using the stitching location to create a stitched image; and saving the stitched image to memory. A system to perform the method is also described.
摘要翻译： 缝合图像的方法包括以下步骤：确定第一数字图像中的模板窗口和第二数字图像中的目标窗口，并从所选择的窗口中提取所选特征以及模板窗口中的模板; 以第一分辨率从模板内提取所选特征; 匹配目标窗口中选定的要素; 以高于第一分辨率的第二分辨率从模板和目标窗口内提取所选特征; 匹配目标窗口中选定的要素; 执行缝合位置的第二估计的第一评估; 混合拼接位置的第二估计; 对缝合位置进行评估; 使用缝合位置缝合第一数字图像和第二数字图像以创建缝合图像; 并将缝合的图像保存到存储器。 还描述了执行该方法的系统。
-
公开(公告)号：US08135200B2
公开(公告)日：2012-03-13
申请号：US12167373
申请日：2008-07-03
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
IPC分类号： G06K9/00
CPC分类号： G06K9/3233 , G06K2209/05
摘要： A method to identify a Region Of Interest (ROI) within an image includes the steps of: reading a digital image; finding predetermined brightness values; analyzing lines near a plurality of outer edges of the digital image; identifying an entire area of the digital image as the ROI if the found brightness values are also found in lines near the plurality of outer edges of the digital image; computing Radon transforms to generate one dimensional (1D) projections of the digital image if the found brightness values are not found in the lines; detecting a set of edges within the 1D projections; selecting edges from the set of edges; validating the selected edges to identify a set of validated edges; computing the ROI from the set of validated edges of the 1D projections; and saving the computed ROI to memory. A system to perform the method is also described.
摘要翻译： 识别图像内的感兴趣区域（ROI）的方法包括以下步骤：读取数字图像; 找到预定的亮度值; 分析数字图像的多个外边缘附近的线; 如果在数字图像的多个外边缘附近的线中也发现所发现的亮度值，则将数字图像的整个区域识别为ROI; 如果在行中没有找到发现的亮度值，则计算Radon变换以产生数字图像的一维（1D）投影; 检测一维投影内的一组边缘; 从该组边缘中选择边缘; 验证所选择的边缘以识别一组经验证的边缘; 从1D投影的验证边缘的集合计算ROI; 并将计算出的ROI保存到存储器中。 还描述了执行该方法的系统。
-
公开(公告)号：US07245250B1
公开(公告)日：2007-07-17
申请号：US11204892
申请日：2005-08-16
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
IPC分类号： G01S13/90
CPC分类号： G01S13/9011 , G01S7/003
摘要： A method is disclosed of generating multi-resolution images using synthetic aperture radar (SAR) phase history data. A high resolution SAR image may be formed from the phase history data, or a lower resolution SAR image may be formed from a sub-aperture of the phase history data. The multi-resolution images may also be compressed. Compressed multi-resolution images are progressively transmitted to a client until the client receives an image with adequate image quality and/or resolution. Compressed multi-resolution images may also be used for iterative target detection, where images are analyzed by a target detection processor, starting with a lowest resolution image, going to a highest resolution image, until an adequate image of the target or scene is obtained. If a target is not found in the multi-resolution images, a new sub-aperture is chosen on the phase history data, and the target detection process repeats for the new sub-aperture.
摘要翻译： 公开了一种使用合成孔径雷达（SAR）相位历史数据生成多分辨率图像的方法。 可以从相位历史数据形成高分辨率SAR图像，或者可以从相位历史数据的子孔径形成较低分辨率的SAR图像。 多分辨率图像也可以被压缩。 压缩的多分辨率图像逐渐传输到客户端，直到客户端接收到具有足够图像质量和/或分辨率的图像。 压缩的多分辨率图像也可以用于迭代目标检测，其中图像由目标检测处理器分析，以最低分辨率图像开始，进入最高分辨率图像，直到获得目标或场景的足够图像。 如果在多分辨率图像中没有找到目标，则在相位历史数据上选择新的子孔径，并且针对新的子孔径重复目标检测过程。
-
公开(公告)号：US06410872B1
公开(公告)日：2002-06-25
申请号：US09461079
申请日：1999-12-14
IPC分类号： B07C5342
摘要： A sorting system (110) conveys articles, such as peaches (114) on a conveyor belt (112) past an inspection zone (126) that is lighted by an illumination source (90) radiating a number of emission peaks over visible and infrared portions of the spectrum. The illumination source generates the radiation from an Indium Iodide lamp (92) that is reflected off a parabolic reflector (94) and through a “soda straw” collimator (100) to illuminated the peaches. A detector system (118) employs line scanning visible and infrared cameras (142, 140) to sense visible and IR wavelength reflectance values for the peach meat (124) and peach pit or pit fragments (126). Various image processing and analysis methologies, such as subtraction, ratio, logarithmic, regression, combination, angle, distance, and shape may be employed to enhance the image contrast and classify the resulting data for sorting the peaches. Employing subtraction also cancels “glint” caused by specular reflections of the illumination source off the peaches and into the cameras.
-
6.发明授权公开(公告)号：US07508520B1
公开(公告)日：2009-03-24
申请号：US11521265
申请日：2006-09-14
申请人： Raymond Todd Lines , Norman A. Lopez , Joseph L. Lippert , Darryl Guy Murdock , Dawn Lenz , Michael Stoogenke , Matthew C. Severski , Hooshmand M. Kalayeh
发明人： Raymond Todd Lines , Norman A. Lopez , Joseph L. Lippert , Darryl Guy Murdock , Dawn Lenz , Michael Stoogenke , Matthew C. Severski , Hooshmand M. Kalayeh
IPC分类号： G01N21/00
CPC分类号： G01N21/3504 , G01N21/39 , G01N2021/1797 , G01N2021/3513 , G01N2021/393 , G01N2021/394 , G01N2021/395
摘要： Methods and systems for obtaining a target fluid map of a survey area using a differential absorption LIDAR (DIAL) system are provided. Pulse bursts are transmitted toward the survey area, where each pulse burst includes an off-line pulse and at least one on-line pulse. Pulse bursts, each being associated with a measurement point, are received from the survey area. A concentration path length (CPL) corresponding to a respective on-line pulse, a spatial location associated with the CPL, and an error associated with the CPL are determined for each measurement point. The CPL for each measurement point is arranged within the survey area to form the target fluid map.
摘要翻译： 提供了使用差分吸收LIDAR（DIAL）系统获得测量区域的目标流体图的方法和系统。 脉冲脉冲串被发送到测量区域，其中每个脉冲脉冲串包括离线脉冲和至少一个在线脉冲。 从测量区域接收到与测量点相关联的脉冲串。 对于每个测量点确定对应于相应在线脉冲的浓度路径长度（CPL），与CPL相关联的空间位置以及与CPL相关联的错误。 每个测量点的CPL被安排在测量区域内以形成目标流体图。
-
公开(公告)号：US07474685B2
公开(公告)日：2009-01-06
申请号：US11135768
申请日：2005-05-24
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
CPC分类号： G01N21/3504 , G01N21/39 , G01N2021/394
摘要： A multi-line tunable laser system, which uses lasers as light sources to illuminate, identify and or quantify one or more targets based on multi-dimensional spectral characteristics of each target. The system includes a plurality of laser sources, each tunable to emit an electromagnetic wave, and at least one tuning controller for tuning and locking each beam of light to a wavelength of required spectral line-width. The system also includes a transmitter for transmitting each beam of light to illuminate one or more targets, and a receiver for receiving light returning from the targets and converting the returned light to electrical signals for identifying and or quantifying the targets. The system further includes N tunable lasers where, M of the N lasers are each tuned to a wavelength that is partially absorbed by the targets, and L of the N (one or more) of the lasers are each tuned to a wavelength that is absorption-free of the targets.
摘要翻译： 一种多线可调谐激光系统，其基于每个目标的多维光谱特征，其使用激光器作为光源来照亮，识别和/或定量一个或多个目标。 该系统包括多个可调谐以发射电磁波的激光源，以及至少一个调谐控制器，用于将每个光束调谐并锁定到所需光谱线宽的波长。 该系统还包括用于发射每个光束以照亮一个或多个目标的发射器，以及用于接收从目标物返回的光并将返回的光转换成用于识别和/或定量目标的电信号的接收器。 该系统还包括N个可调谐激光器，其中N个激光器的M均被调谐到由靶标部分吸收的波长，并且N（一个或多个）激光器中的L每个被调谐到被吸收的波长 - 免费的目标。
-
8.发明授权System and method for remote quantitative detection of fluid leaks from a natural gas or oil pipeline 有权用于从天然气或石油管道远程定量检测流体泄漏的系统和方法公开(公告)号：US06995846B2
公开(公告)日：2006-02-07
申请号：US10959363
申请日：2004-10-06
IPC分类号： G01N21/00
CPC分类号： G01N21/3504 , G01N21/31 , G01N21/39 , G01N33/0047 , G01N2021/1793 , G01N2021/1797 , G01N2021/394
摘要： A system for remote quantitative detection of fluid leaks from a natural gas or oil pipeline by use of an airborne platform; including at least one laser light source for nearly simultaneous illuminating two or more target fluids and a background, wherein the two or more target fluids are characterized by two or more absorption wavelengths, and wherein the background has a different wavelength than either of the two or more target fluids. The illumination source is pointed based on a positioning system while in a geometric area along a path two or more target fluids are scanned for using the illumination sources. A signal detector detects the two or more target fluids using quantitative signal processing. Also included are a controller, a path planning and path finding tool for the positioning of the airborne platform, and a communicator for communicating the presence of the detected leak.
摘要翻译： 用于通过使用空中平台从天然气或石油管道远程定量检测流体泄漏的系统; 包括用于几乎同时照射两种或更多种目标流体和背景的至少一种激光源，其中所述两种或更多种目标流体的特征在于两个或更多个吸收波长，并且其中背景具有不同于两个或更多个目标流体中的任一个的波长 更多的目标液体。 照明源基于定位系统被指向，而沿着路径的几何区域中，扫描两个或更多个目标流体以使用照明源。 信号检测器使用定量信号处理来检测两个或更多个目标流体。 还包括用于定位机载平台的控制器，路径规划和路径查找工具，以及用于传达检测到的泄漏的存在的通信器。
-
9.发明授权
公开(公告)号：US5579409A
公开(公告)日：1996-11-26
申请号：US159641
申请日：1993-11-30
IPC分类号： G01B11/24 , G06K9/00 , G06K9/48 , G06T1/00 , G06T5/00 , G06T5/40 , G06T7/00 , G06T7/60 , G06T9/20 , G06T11/40 , G06K9/46
CPC分类号： G06T7/0083 , G06K9/00127 , G06K9/48 , G06T11/40 , G06T7/0012 , G06T9/20 , G06T2207/10016 , G06T2207/10056 , G06T2207/20148 , G06T2207/30024
摘要： Accessing the exterior points of an object is used in the area of object identification when it is important to use the information in the local exterior environment of an object in order to extract a feature which may be useful for object recognition. Examples of this type of feature which are important for recognizing and classifying objects occur in the area if bacterial detection. Adaptive classification is a way of making the analysis independent of variations in imaging conditions, such as lighting, positioning, electronic amplification, etc. Two general methods can be used to access the local exterior environment of an object, knowing the perimeter points of the object. In the first method, the shape of an annular exterior region around the object of interest can be made to follow the shape of the object itself. In the second method, an known exterior shape, such as a circle, is used to characterize the exterior contour region, approximating the shape of the object.
摘要翻译： 在对象识别的区域中使用对象的外部点来访问对象的本地外部环境中的信息是重要的，以便提取可能对对象识别有用的特征。 如果细菌检测，这种对识别和分类对象重要的这种特征的实例发生在该区域中。 自适应分类是使得分析独立于诸如照明，定位，电子放大等的成像条件的变化的方式。可以使用两种一般方法来访问对象的局部外部环境，知道对象的周边点 。 在第一种方法中，可以使感兴趣物体周围的环形外部区域的形状遵循物体本身的形状。 在第二种方法中，使用已知的外部形状（例如圆形）来表征外部轮廓区域，近似对象的形状。
-
公开(公告)号：US20100002927A1
公开(公告)日：2010-01-07
申请号：US12167373
申请日：2008-07-03
申请人： Hooshmand M. Kalayeh
发明人： Hooshmand M. Kalayeh
IPC分类号： G06K9/00
CPC分类号： G06K9/3233 , G06K2209/05
摘要： A method to identify a Region Of Interest (ROI) within an image includes the steps of: reading a digital image; finding predetermined brightness values; analyzing lines near a plurality of outer edges of the digital image; identifying an entire area of the digital image as the ROI if the found brightness values are also found in lines near the plurality of outer edges of the digital image; computing Radon transforms to generate one dimensional (1D) projections of the digital image if the found brightness values are not found in the lines; detecting a set of edges within the 1D projections; selecting edges from the set of edges; validating the selected edges to identify a set of validated edges; computing the ROI from the set of validated edges of the 1D projections; and saving the computed ROI to memory. A system to perform the method is also described.
摘要翻译： 识别图像内的感兴趣区域（ROI）的方法包括以下步骤：读取数字图像; 找到预定的亮度值; 分析数字图像的多个外边缘附近的线; 如果在数字图像的多个外边缘附近的线中也发现所发现的亮度值，则将数字图像的整个区域识别为ROI; 如果在行中没有找到发现的亮度值，则计算Radon变换以产生数字图像的一维（1D）投影; 检测一维投影内的一组边缘; 从该组边缘中选择边缘; 验证所选择的边缘以识别一组经验证的边缘; 从1D投影的验证边缘的集合计算ROI; 并将计算出的ROI保存到存储器中。 还描述了执行该方法的系统。
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.018 秒)
