专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20130148904A1 POST-PROCESSING A MULTI-SPECTRAL IMAGE FOR ENHANCED OBJECT IDENTIFICATION 有权
标题翻译：后处理用于增强对象识别的多光谱图像
公开(公告)号：US20130148904A1
公开(公告)日：2013-06-13
申请号：US13324433
申请日：2011-12-13
申请人： Yao Rong WANG , Lalit Keshav MESTHA
发明人： Yao Rong WANG , Lalit Keshav MESTHA
IPC分类号： G06K9/62
CPC分类号： G06K9/72 , G06K9/4652
摘要： What is disclosed is a system and method for post-processing a multi-spectral image which has already been processed for pixel classification. A binary image is received which contains pixels that have been classified using a pixel classification method. Each pixel in the image has an associated intensity value and has a pixel value of 1 or 0 depending on whether the pixel has been classified as a material of interest or not. A block of size m×n is defined. Pixel values in a block are changed according to a threshold-based filtering criteria such that pixels in the same block all have the same binary value. The block is then shifted by k pixels and pixel processing repeats until all pixels have been processed. Once all blocks have been processed, contiguous pixels having the same binary value are grouped to form objects. In such a manner, pixel classification errors are reduced.
摘要翻译：所公开的是用于后处理已经被处理用于像素分类的多光谱图像的系统和方法。接收包含使用像素分类方法分类的像素的二进制图像。图像中的每个像素具有相关联的强度值，并且具有像素值为1或0的取决于像素是否被分类为感兴趣的材料。定义一个大小为m×n的块。块中的像素值根据基于阈值的滤波准则而改变，使得相同块中的像素都具有相同的二进制值。然后将块移动k个像素，并重复像素处理直到所有像素都被处理。一旦所有块都被处理，具有相同二进制值的连续像素被分组以形成对象。以这种方式，减少像素分类误差。

22. 发明申请

US20130141574A1 VEHICLE OCCUPANCY DETECTION VIA SINGLE BAND INFRARED IMAGING 有权
标题翻译：车辆通过单带红外成像检测车辆检测
公开(公告)号：US20130141574A1
公开(公告)日：2013-06-06
申请号：US13312414
申请日：2011-12-06
申请人： Edul N. DALAL , Peter PAUL , Lalit Keshav MESTHA , Abu Saeed ISLAM
发明人： Edul N. DALAL , Peter PAUL , Lalit Keshav MESTHA , Abu Saeed ISLAM
IPC分类号： H04N5/33
CPC分类号： G06K9/00362 , G06K9/2018 , H04N5/33
摘要： What is disclosed is a method for vehicle occupancy detection using a single band infrared imaging system. First, an infrared image of a vehicle intended to be processed for human occupancy detection is captured using a single band infrared camera set to a predefined wavelength band. A candidate sub-image is identified within the captured image. A cumulative histogram is formed using the reflectance values of each pixel in the candidate region. A threshold reflectance value is then determined from the cumulative histogram using a pre-defined cumulative occurrence fraction value which corresponds to a value equivalent to an average sized human face. Embodiments for setting the threshold reflectance value are disclosed. Thereafter, human occupants can be distinguished in the image from the vehicle's interior by comparing pixel reflectances in the sub-image against the threshold reflectance value.
摘要翻译：所公开的是使用单频带红外成像系统的车辆占用检测方法。首先，使用设定为预定波长带的单频带红外线摄像机来捕捉旨在进行人身携带检测的车辆的红外图像。在拍摄图像内识别候选子图像。使用候选区域中的每个像素的反射率值形成累积直方图。然后使用对应于等于平均大小的人脸的值的预定义累积出现分数值，从累积直方图确定阈值反射率值。公开了设定阈值反射率值的实施例。此后，通过将子图像中的像素反射率与阈值反射率值进行比较，可以将图像与车辆内部区分开。

23. 发明申请

US20120262577A1 DETERMINING A NUMBER OF OBJECTS IN AN IR IMAGE 有权
标题翻译：确定IR图像中的一些对象
公开(公告)号：US20120262577A1
公开(公告)日：2012-10-18
申请号：US13086006
申请日：2011-04-13
申请人： Yao Rong WANG , Zhigang FAN , Lalit Keshav MESTHA
发明人： Yao Rong WANG , Zhigang FAN , Lalit Keshav MESTHA
IPC分类号： H04N5/33 , H04N7/18 , G06K9/00
CPC分类号： G06K9/00369 , G06K2009/4657 , G06T7/11 , G06T2207/10048 , G06T2207/30242
摘要： What is disclosed is a novel system and method for determining the number of objects in an IR image obtained using an IR imaging system. In one embodiment, a total of N intensity values are collected for each pixel in an IR image using a IR imaging system comprising an IR detection device and an IR Illuminator. Intensity values are retrieved from a database which have been estimated for a plurality of known materials, such as skin and hair. A classification is determined for each pixel in the IR image using either a best fitting method of a reflectance, or a correlation method. Upon classification, a total number of objects in the IR image can be determined. The present system and method finds its intended uses in of real world applications such as, determining the number of occupants in a vehicle traveling in a HOV/HOT lane.
摘要翻译：所公开的是用于确定使用IR成像系统获得的IR图像中的对象数量的新颖系统和方法。在一个实施例中，使用包括IR检测装置和IR照明器的IR成像系统对IR图像中的每个像素收集总共N个强度值。从已经为多种已知材料（例如皮肤和头发）估计的数据库检索强度值。使用反射率的最佳拟合方法或相关方法来确定IR图像中的每个像素的分类。在分类时，可以确定IR图像中的对象的总数。本系统和方法在现实应用中找到其预期用途，例如确定在HOV / HOT车道中行驶的车辆中的乘客人数。

24. 发明申请

US20110019212A1 BLACK POINT COMPENSATION IN A TIPP ARCHITECTURE 有权
标题翻译：烟囱建筑中的黑点补偿
公开(公告)号：US20110019212A1
公开(公告)日：2011-01-27
申请号：US12507515
申请日：2009-07-22
申请人： Yao Rong WANG , Lalit Keshav MESTHA
发明人： Yao Rong WANG , Lalit Keshav MESTHA
IPC分类号： H04N1/60
CPC分类号： H04N1/407
摘要： A method for calibrating an image printing system that includes a plurality of parallel printers, where each of the printers has a minimum luminance value. The method includes determining a minimum luminance value profile for the plurality of printers in the image printing system based on the minimum luminance values of each of the printers in the image printing system, determining a black point compensation function based on the determined minimum luminance value profile, adjusting luminance values for input image data using the determined black point compensation function, and rendering, with the parallel printers, images on substrates based on the input image data with adjusted luminance levels.
摘要翻译：一种用于校准包括多个平行打印机的图像打印系统的方法，其中每个打印机具有最小的亮度值。该方法包括基于图像打印系统中的每个打印机的最小亮度值确定图像打印系统中的多个打印机的最小亮度值分布，基于所确定的最小亮度值分布来确定黑点补偿功能使用确定的黑点补偿功能调整输入图像数据的亮度值，并且使用并行打印机，基于具有调整的亮度水平的输入图像数据来渲染基板上的图像。

25. 发明申请

US20100198368A1 METHODS AND SYSTEMS TO SCHEDULE GAINS IN PROCESS CONTROL LOOPS 有权
标题翻译：方法和系统在过程控制中排序增益
公开(公告)号：US20100198368A1
公开(公告)日：2010-08-05
申请号：US12363898
申请日：2009-02-02
申请人： Lalit Keshav MESTHA , Prudhvi K. GURRAM , Alvaro Enrique GIL
发明人： Lalit Keshav MESTHA , Prudhvi K. GURRAM , Alvaro Enrique GIL
IPC分类号： G05B13/04
CPC分类号： G03G15/065 , G03G15/0266 , G03G15/50
摘要： Methods and planning systems used to schedule gain matrices for process control loops and determine optimal values for manipulated variables according to a minimum cost function. A cost function is calculated for each of a predetermined number of plans as a sum of partial cost functions calculated over a predetermined number of projections in a horizon. Each partial cost function after the initial projection of a plan is calculated using a scheduled gain matrix. The gain matrix can be scheduled for each projection by selection from a predetermined set of gain matrices or can be calculated in real time during the calculation for each projection.
摘要翻译：用于计划过程控制回路的增益矩阵的方法和规划系统，并根据最小成本函数确定操纵变量的最佳值。对于预定数量的计划中的每一个计算成本函数，作为在水平线上预定数量的投影计算的部分成本函数的总和。使用调度增益矩阵计算平面图初始投影后的每个部分成本函数。增益矩阵可以通过从预定的增益矩阵组中选择来为每个投影进行调度，或者可以在每个投影的计算期间实时计算增益矩阵。

26. 发明申请

US20090190966A1 ACTIVE IMAGE STATE CONTROL WITH LINEAR DISTRIBUTED ACTUATORS ON DEVELOPMENT ROLLS 有权
标题翻译：线性分布式执行器在开发滚动条件下的主动图像状态控制
公开(公告)号：US20090190966A1
公开(公告)日：2009-07-30
申请号：US12208078
申请日：2008-09-10
申请人： Lalit Keshav MESTHA , Palghat RAMESH , John G. SHAW , Dale R. MASHTARE , Joel A. KUBBY
发明人： Lalit Keshav MESTHA , Palghat RAMESH , John G. SHAW , Dale R. MASHTARE , Joel A. KUBBY
IPC分类号： G03G15/08
CPC分类号： G03G15/0818 , G03G2215/00957 , G03G2215/0653 , G03G2215/1614
摘要： Exemplary embodiments provide a roll member that includes one or more linear arrays of actuator cells and methods for making and using the roll member. In one embodiment, each linear array of the roll member can be controllably actuated as a group by, e.g., an oscillating voltage, to release toner particles adhered thereto and to form a uniform toner cloud in the development area between the roll member and an image receiving member. The controllable actuation can also aid in the unloading process of the residual toner particles from the roll member. In various embodiments, the uniform toner cloud and/or the controllable unloading process can enable a non-interactive development system for image-on-image full-color printing.
摘要翻译：示例性实施例提供了包括一个或多个致动器单元的线性阵列的辊构件以及用于制造和使用辊构件的方法。在一个实施例中，辊构件的每个线性阵列可以通过例如振荡电压作为一组进行可控地致动，以释放附着在其上的调色剂颗粒，并在辊构件和图像之间的显影区域中形成均匀的调色剂云接收成员。可控制的致动还可以帮助来自辊构件的剩余调色剂颗粒的卸载过程。在各种实施例中，均匀调色剂云和/或可控卸载过程可以实现用于图像上全色打印的非交互式显影系统。

27. 发明申请

US20080007802A1 PITCH TO PITCH ONLINE GRAY BALANCE CALIBRATION 有权
标题翻译：点击在线灰度平衡校准
公开(公告)号：US20080007802A1
公开(公告)日：2008-01-10
申请号：US11428489
申请日：2006-07-03
申请人： R. Enrique VITURRO , Lalit Keshav MESTHA , Joseph D. HANCOCK , Tonya L. LOVE
发明人： R. Enrique VITURRO , Lalit Keshav MESTHA , Joseph D. HANCOCK , Tonya L. LOVE
IPC分类号： H04N1/46
CPC分类号： H04N1/46
摘要： A printer or other marking engine includes a marking material transfer device, such as a photoreceptor drum or belt, that includes a plurality of pitches. Each pitch receives an individual color of marking material and conveys the marking material to a substrate. The marking engine forms a desired image in a main image area of the substrate using marking material from one or more of the pitches, and produces a target patch pattern for each of the pitches in a margin area located outside the main image area. A measuring device such as a spectrophotometer is used to measure each target patch pattern, and based on the measured values, an individual color calibration is performed for each pitch for use in a subsequent marking operation. The color calibration may include generating or modifying a tone reproduction curve for each pitch based on the measured values. The margin area may be later trimmed off, thereby removing the portion of the substrate on which the target patch pattern is formed.
摘要翻译：打印机或其他标记引擎包括包括多个间距的标记材料传送装置，例如感光鼓或皮带。每个音调接收标记材料的单独颜色，并将标记材料传送到基底。标记引擎使用来自一个或多个间距的标记材料在基板的主图像区域中形成期望的图像，并且在位于主图像区域外部的边缘区域中产生用于每个间距的目标贴图。使用诸如分光光度计的测量装置来测量每个目标贴片图案，并且基于测量值，对于每个间距执行单独的颜色校准以用于随后的标记操作。颜色校准可以包括基于测量值产生或修改每个音高的色调再现曲线。可以稍后修剪边缘区域，从而去除其上形成有目标贴片图案的基板的部分。

28. 发明申请

US20130236073A1 WEB-BASED SYSTEM AND METHOD FOR VIDEO ANALYSIS 有权
标题翻译：基于WEB的系统和视频分析方法
公开(公告)号：US20130236073A1
公开(公告)日：2013-09-12
申请号：US13417979
申请日：2012-03-12
申请人： Nischal M. PIRATLA , Lalit Keshav MESTHA , Meera SAMPATH
发明人： Nischal M. PIRATLA , Lalit Keshav MESTHA , Meera SAMPATH
IPC分类号： G06K9/46 , G06F3/048
CPC分类号： G06K9/00979
摘要： What is disclosed is a web-based system which comprises, in part, video analysis modules for performing different types of analysis services on a video, and a server in network communication with a user's computing device. A user selects one or more menu options displayed on a webpage. Each of the menu options is associated with a respective video analysis available to the user. The user makes their election and, within the same session, uploads to the server a video desired to be analyzed with respect to each of the video analysis services selected by the user. Once the server has obtained the user's selection(s) and has received the uploaded video, the server communicates the video to each video analysis module associated with each of the respective analysis services. Upon each completion of the video analysis, the results are communicated back to the user. Various embodiments are disclosed.
摘要翻译：公开的是基于网络的系统，其部分地包括用于在视频上执行不同类型的分析服务的视频分析模块，以及与用户的计算设备进行网络通信的服务器。用户选择网页上显示的一个或多个菜单选项。每个菜单选项与用户可用的各自的视频分析相关联。用户进行选举，并且在同一会话内，向服务器上传相对于由用户选择的每个视频分析服务而要分析的视频。一旦服务器获得用户的选择并已经接收到上传的视频，服务器将该视频传送到与每个相应的分析服务相关联的每个视频分析模块。在每次完成视频分析时，将结果传回给用户。公开了各种实施例。

29. 发明申请

US20130218028A1 DERIVING ARTERIAL PULSE TRANSIT TIME FROM A SOURCE VIDEO IMAGE 有权
标题翻译：从源视频图像导出动脉脉冲时间
公开(公告)号：US20130218028A1
公开(公告)日：2013-08-22
申请号：US13401286
申请日：2012-02-21
申请人： Lalit Keshav MESTHA
发明人： Lalit Keshav MESTHA
IPC分类号： A61B5/024 , A61B6/00
CPC分类号： G06T7/0012 , A61B5/0075 , A61B5/02125 , G06T2207/30076 , G06T2207/30104
摘要： What is disclosed is a system and method for determining an arterial pulse transit time of a subject of interest in a remote sensing environment. A video imaging system is used to capture a time varying source images of a proximal and distal region of a subject intended to be analyzed for arterial pulse transit time. A time series signal for each of the proximal and distal regions is extracted from the source images and a phase of each of the extracted time series signals is computed. A difference is then computed between these phases. This phase difference is a monotonic function of frequencies in the signals. From the monotonic function, an arterial pulse transit time of the subject is extracted. The subject's arterial pulse transit time is then communicated to a computer system. The computer system determines blood pressure, blood vessel blockage, blood flow velocity, or a peripheral neuropathy.
摘要翻译：公开的是用于确定遥感环境中感兴趣的对象的动脉脉冲传播时间的系统和方法。视频成像系统用于捕获旨在分析动脉脉冲传播时间的受试者的近端和远端区域的时变源图像。从源图像提取每个近端和远端区域的时间序列信号，并且计算每个提取的时间序列信号的相位。然后在这些阶段之间计算差异。该相位差是信号中频率的单调函数。从单调功能，提取对象的动脉脉冲传播时间。然后将受试者的动脉脉冲传播时间传达到计算机系统。计算机系统确定血压，血管阻塞，血流速度或周围神经病变。

30. 发明申请

US20130181836A1 IMAGE-BASED DETERMINATION OF CO AND CO2 CONCENTRATIONS IN VEHICLE EXHAUST GAS EMISSIONS 有权
标题翻译：基于图像的车辆排放气体CO和CO2浓度的确定
公开(公告)号：US20130181836A1
公开(公告)日：2013-07-18
申请号：US13419856
申请日：2012-03-14
申请人： George Cunha CARDOSO , Lalit Keshav MESTHA
发明人： George Cunha CARDOSO , Lalit Keshav MESTHA
IPC分类号： G06K9/62 , G08B21/00 , H04N7/18
CPC分类号： G01M15/108
摘要： What is disclosed is a system and method for image-based determination of concentration of CO and CO2 in a vehicle's exhaust gas in an emissions testing environment. In one embodiment, the present method involves receiving an IR image of the exhaust plume of a motor vehicle intended to be tested for CO and CO2 concentrations. The IR image has been captured using a mid-wave infrared camera with at least one optical filter tuned to the infrared absorption band of CO and CO2. The images are pre-processed to isolate pixels which contain the exhaust plume. The intensity values of pixels in those isolated regions are normalized and concentrations of CO and CO2 are determined via a calibration curve which relates pixel intensities to concentrations. The concentrations are compared to an emissions standard set for the vehicle to determine whether the vehicle is a gross polluter.
摘要翻译：所公开的是用于在排放测试环境中基于图像确定车辆废气中CO和CO 2浓度的系统和方法。在一个实施例中，本方法包括接收旨在被测试CO和CO 2浓度的机动车辆的排气羽流的IR图像。使用中波红外摄像机捕获IR图像，其中至少一个光滤波器被调谐到CO和CO 2的红外吸收带。图像被预处理以分离包含排气羽流的像素。将这些孤立区域中的像素的强度值归一化，并通过将像素强度与浓度相关联的校准曲线来确定CO和CO 2的浓度。将浓度与车辆的排放标准进行比较，以确定车辆是否是总污染物。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式