专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20070206865A1 Block-based Gaussian Mixture Model video motion detection 失效
标题翻译：基于块的高斯混合模型视频运动检测
公开(公告)号：US20070206865A1
公开(公告)日：2007-09-06
申请号：US11366318
申请日：2006-03-02
申请人： Lokesh Boregowda , Mohamed Ibrahim
发明人： Lokesh Boregowda , Mohamed Ibrahim
IPC分类号： G06K9/62
CPC分类号： G06K9/00771 , G06K9/38 , G06K9/56 , H04N5/144
摘要： A method for the detection of motion in video data is disclosed. In an embodiment, a method uses a background technique for the motion detection. In another embodiment, a Gaussian Mixture Model is applied to a neighborhood or block of pixels within an image frame, thereby identifying background and foreground in the image based on said blocks.
摘要翻译：公开了一种用于检测视频数据中的运动的方法。在一个实施例中，一种方法使用用于运动检测的背景技术。在另一实施例中，将高斯混合模型应用于图像帧内的邻域或像素块，从而基于所述块识别图像中的背景和前景。

2. 发明申请

US20070070365A1 Content-based image retrieval based on color difference and gradient information 审中-公开
标题翻译：基于色差和梯度信息的基于内容的图像检索
公开(公告)号：US20070070365A1
公开(公告)日：2007-03-29
申请号：US11234989
申请日：2005-09-26
申请人： Lokesh Boregowda , Sridevi Ganapathy , Mohamed Ibrahim , Mayur Jain
发明人： Lokesh Boregowda , Sridevi Ganapathy , Mohamed Ibrahim , Mayur Jain
IPC分类号： H04N1/60
CPC分类号： G06F16/5838
摘要： An image processing system and method uses color information and texture information to compare a first image and a second image. The color information and texture information are derived independently, and then combined to obtain robust comparison and image retrieval results. For the color features of the images, color component differences are calculated and compared. For the texture features of the images, a multi-dimensional K-means clustering of a gradient vectors are calculated and compared.
摘要翻译：图像处理系统和方法使用颜色信息和纹理信息来比较第一图像和第二图像。独立地导出颜色信息和纹理信息，然后组合以获得鲁棒的比较和图像检索结果。对于图像的颜色特征，计算和比较颜色分量差异。对于图像的纹理特征，计算和比较梯度向量的多维K均值聚类。

3. 发明申请

US20050226331A1 IDENTIFYING KEY VIDEO FRAMES 失效
标题翻译：识别主要视频框架
公开(公告)号：US20050226331A1
公开(公告)日：2005-10-13
申请号：US10708905
申请日：2004-03-31
申请人： Ibrahim Mohamed , Lokesh Boregowda
发明人： Ibrahim Mohamed , Lokesh Boregowda
IPC分类号： G06F17/30 , G11B27/28 , H04N5/14 , H04N7/12
CPC分类号： H04N5/147 , G06F17/30811 , G11B27/28
摘要： A rate of change of visual content (compared to an adjacent video frame) of a video frame is determined, and the video frame is selected as a key video frame if the rate exceeds a threshold value. In an embodiment, to compute the rate, the motion energy vector magnitude (square of displacement magnitude) of each moved pixel of the current frame is determined, and an average displacement magnitude is determined. The average displacement magnitude may also be used to determine the rate.
摘要翻译：确定视频帧的可视内容（与相邻视频帧相比）的变化率，并且如果速率超过阈值，则视频帧被选择为关键视频帧。在一个实施例中，为了计算速率，确定当前帧的每个移动像素的运动能量矢量幅度（位移幅度的平方），并且确定平均位移幅度。平均位移幅度也可用于确定速率。

4. 发明申请

US20070058863A1 Label Detection 有权
标题翻译：标签检测
公开(公告)号：US20070058863A1
公开(公告)日：2007-03-15
申请号：US11223885
申请日：2005-09-09
申请人： Lokesh Boregowda , Anupama Rajagopal , Krishnamoorthy Dornadula , Lalitha Eswara
发明人： Lokesh Boregowda , Anupama Rajagopal , Krishnamoorthy Dornadula , Lalitha Eswara
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/3258
摘要： A system and a method to detect a label are described herein. The system and method are to extract a horizontal region of interest based on the image; to extract a vertical region of interest based on the image; and to identify presence of the primary label in the image from the horizontal region of interest and from the vertical region of interest
摘要翻译：本文描述了用于检测标签的系统和方法。系统和方法是基于图像提取一个水平的感兴趣区域; 基于图像提取垂直的感兴趣区域; 并从感兴趣的水平区域和垂直感兴趣区域中识别图像中主要标签的存在

5. 发明申请

US20070058836A1 Object classification in video data 审中-公开
标题翻译：视频数据中的对象分类
公开(公告)号：US20070058836A1
公开(公告)日：2007-03-15
申请号：US11227505
申请日：2005-09-15
申请人： Lokesh Boregowda , Anupama Rajagopal
发明人： Lokesh Boregowda , Anupama Rajagopal
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00771
摘要： A method to classify objects labels objects as human, vehicle, multiple human, or other based on output from a motion detection algorithm. Features that are extracted from the blob, such as size, shape, and area, form a basis of the classification. The extracted features are subjected to various mathematical analyses that distinguish the classes that are available for labeling an object.
摘要翻译：根据运动检测算法的输出，将对象分类为人类，车辆，多人或其他对象的方法。从斑点中提取的特征，如大小，形状和面积，构成分类的基础。提取的特征经受各种数学分析，区分可用于标记对象的类。

6. 发明申请

US20060204082A1 Fusion of color space data to extract dominant color 有权
标题翻译：色彩空间数据融合提取主色
公开(公告)号：US20060204082A1
公开(公告)日：2006-09-14
申请号：US11223224
申请日：2005-09-09
申请人： Lokesh Boregowda , Lalitha Eswara
发明人： Lokesh Boregowda , Lalitha Eswara
IPC分类号： G06K9/00 , G06K9/40
CPC分类号： G06K9/4652
摘要： A system and a method to extract dominant color information using fusion of color space data may include Red, Green, Blue (RGB) color space data and may include (H), Saturation (S), and Intensity Value (V) color space data. Red, Green and Blue color space histograms may be computed and maximum count values of each color space may be obtained, which may help finding ‘shine’ information in the object. Normalized HSV color space may be fused with Normalized RGB color space for dominant color determination. The dominant color decision conditions involved in the fusion process may change based on a ‘shine’ flag.
摘要翻译：使用彩色空间数据融合提取主色信息的系统和方法可以包括红色，绿色，蓝色（RGB）色彩空间数据，并且可以包括（H），饱和度（S）和强度值（V）颜色空间数据。可以计算红色，绿色和蓝色颜色空间直方图，并且可以获得每个颜色空间的最大计数值，这可以帮助在对象中找到“闪耀”信息。归一化的HSV颜色空间可以与归一化RGB颜色空间融合，用于主要颜色确定。融合过程中涉及的主要颜色决策条件可能会根据“闪耀”标志而改变。

7. 发明申请

US20070061727A1 Adaptive key frame extraction from video data 审中-公开
标题翻译：从视频数据提取自适应关键帧
公开(公告)号：US20070061727A1
公开(公告)日：2007-03-15
申请号：US11227386
申请日：2005-09-15
申请人： Lokesh Boregowda , Anupama Rajagopal
发明人： Lokesh Boregowda , Anupama Rajagopal
IPC分类号： G11B27/00 , H04N5/14 , H04N5/445
CPC分类号： H04N5/147
摘要： In some embodiments, the present invention is related to a method that includes determining difference frames between successive frames in video data and determining an energy value of each difference frame. The method further includes determining a cumulative energy mean for each difference frame and a predetermined number of previous difference frames and updating the energy value of each frame by removing the cumulative energy mean from the energy value of each difference frame. In addition, the method further includes identifying a temporal change in the energy value of each difference frame to extract key frames from video data. Identifying a temporal change in the energy value of each difference frame to extract key frames from the video data may include identifying difference frames that have an energy value greater than zero after the cumulative energy mean has been removed from the energy value of each difference frame.
摘要翻译：在一些实施例中，本发明涉及一种方法，其包括确定视频数据中的连续帧之间的差分帧并确定每个差分帧的能量值。该方法还包括确定每个差分帧的累积能量平均值和预定数量的先前差分帧，并且通过从每个差分帧的能量值去除累积能量平均值来更新每个帧的能量值。此外，该方法还包括识别每个差分帧的能量值的时间变化以从视频数据中提取关键帧。识别每个差分帧的能量值的时间变化以从视频数据中提取关键帧可以包括在从每个差分帧的能量值去除累积能量均值之后，识别具有大于零的能量值的差异帧。

8. 发明申请

US20070058837A1 Video motion detection using block processing 审中-公开
标题翻译：视频运动检测采用块处理
公开(公告)号：US20070058837A1
公开(公告)日：2007-03-15
申请号：US11227588
申请日：2005-09-15
申请人： Lokesh Boregowda , Mayur Jain , Anupama Rajagopal
发明人： Lokesh Boregowda , Mayur Jain , Anupama Rajagopal
IPC分类号： G06K9/00
CPC分类号： G06T7/223 , G06T2207/10016 , G06T2207/10024
摘要： A system detects motion in video data. In an embodiment, a difference frame is created by comparing the pixels from a first frame and a second frame. The difference frame is divided up into blocks of pixels, and the system calculates standard deviations on a block basis. A threshold value is calculated based on the standard deviation, and the presence or absence of motion is determined based on that threshold value.
摘要翻译：系统检测视频数据中的运动。在一个实施例中，通过比较来自第一帧和第二帧的像素来创建差异帧。差分帧被划分成像素块，并且系统以块为基础计算标准偏差。基于标准偏差计算阈值，并且基于该阈值确定运动的存在或不存在。

9. 发明申请

US20070140547A1 System and method for prediction of pitting corrosion growth 失效
标题翻译：点腐蚀生长预测的系统和方法
公开(公告)号：US20070140547A1
公开(公告)日：2007-06-21
申请号：US11314903
申请日：2005-12-21
申请人： Lalitha Eswara , Lokesh Boregowda , Thirumaran Ekambaram
发明人： Lalitha Eswara , Lokesh Boregowda , Thirumaran Ekambaram
IPC分类号： G06K9/00
CPC分类号： G06K9/00 , G06K2209/19
摘要： A system and method predicts pitting corrosion growth using imaging technology. In an embodiment, a first module preprocesses images to locate seed points, and a second module models a corrosion life cycle of the seed points. In another embodiment, the seed points are identified with defined confidence levels, and the rate of change of features in corrosion images is analyzed to identify dominant life-cycle phases of corrosion and defining corrosion impact factor for corrosion quantification.
摘要翻译：系统和方法使用成像技术预测点腐蚀生长。在一个实施例中，第一模块预处理图像以定位种子点，并且第二模块模拟种子点的腐蚀寿命周期。在另一个实施方案中，用定义的置信水平识别种子点，并且分析腐蚀图像中的特征的变化率，以识别腐蚀的主要生命周期阶段并且定义用于腐蚀定量的腐蚀影响因子。

10. 发明申请

US20070058856A1 Character recoginition in video data 审中-公开
标题翻译：视频数据中的角色识别
公开(公告)号：US20070058856A1
公开(公告)日：2007-03-15
申请号：US11227016
申请日：2005-09-15
申请人： Lokesh Boregowda , Anupama Rajagopal
发明人： Lokesh Boregowda , Anupama Rajagopal
IPC分类号： G06K9/62 , G06K9/18 , G06K9/34 , G06K9/00
CPC分类号： G06K9/628 , G06K9/3258 , G06K9/6814 , G06K2209/01 , G06K2209/15
摘要： An example method of recognizing characters in video data includes (i) Obtaining a binary image from a scene in video data; (ii) segmenting characters in the binary image (e.g., by using region labeling); and (iii) using a character recognition model to recognize the segmented characters. The method may be incorporated into an existing video system or newly developed video systems to perform character recognition tasks on a variety of different objects. In some embodiments, the character recognition module uses a learning-based neural network to recognize characters. In other embodiments, the character recognition module uses a non-learning-based progressive shape analysis process for character recognition.
摘要翻译：识别视频数据中的字符的示例方法包括：（i）从视频数据中的场景获取二进制图像; （ii）分割二进制图像中的字符（例如，通过使用区域标记）; 和（iii）使用字符识别模型来识别分段字符。该方法可以并入现有的视频系统或新开发的视频系统中，以在各种不同的对象上执行字符识别任务。在一些实施例中，字符识别模块使用基于学习的神经网络来识别字符。在其他实施例中，字符识别模块使用用于字符识别的基于非学习的渐进形状分析处理。

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