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

US20050069207A1 Method for detection and recognition of fog presence within an aircraft compartment using video images 有权
标题翻译：使用视频图像检测和识别飞机舱内的雾的方法
公开(公告)号：US20050069207A1
公开(公告)日：2005-03-31
申请号：US10702070
申请日：2003-11-05
申请人： Radoslaw Zakrzewski , Mokhtar Sadok , Jeffrey Shirer , Robert Zeliff
发明人： Radoslaw Zakrzewski , Mokhtar Sadok , Jeffrey Shirer , Robert Zeliff
IPC分类号： B64D45/00 , G06K9/52 , G06K9/62 , G06K9/66 , G06K9/68 , G06T7/20 , G08B17/12 , G06K9/46
CPC分类号： B64D45/0015 , B64D2045/0035 , G06K9/00771 , G06K9/626 , G06K9/629 , G06K9/6293 , G06T7/254 , G08B17/125
摘要： Detecting video phenomena, such as fire in an aircraft cargo bay, includes receiving a plurality of video images from a plurality of sources, compensating the images to provide enhanced images, extracting features from the enhanced images, and combining the features from the plurality of sources to detect the video phenomena. Extracting features may include determining an energy indicator for each of a subset of the plurality of frames. Detecting video phenomena may also include comparing energy indicators for each of the subset of the plurality of frames to a reference frame. The reference frame corresponds to a video frame taken when no fire is present, video frame immediately preceding each of the subset of the plurality of frames, or a video frame immediately preceding a frame that is immediately preceding each of the subset of the plurality of frames. Image-based and non-image based techniques are described herein in connection with fire detection and/or verification and other applications.
摘要翻译：检测诸如在飞机货舱中的火灾的视频现象包括从多个源接收多个视频图像，补偿图像以提供增强的图像，从增强的图像中提取特征，以及组合来自多个源的特征检测视频现象。提取特征可以包括确定多个帧的子集中的每一个的能量指示符。检测视频现象还可以包括将多个帧的子集中的每一个的能量指示符与参考帧进行比较。参考帧对应于不存在火焰时所拍摄的视频帧，紧接在多个帧的子集之前的视频帧，或紧邻在多个帧的子集之前的帧之前的视频帧。本文结合火灾探测和/或验证和其他应用来描述基于图像和非图像的技术。

22. 发明授权

US06853898B2 Occupant labeling for airbag-related applications 失效
标题翻译：乘客标签用于安全气囊相关应用
公开(公告)号：US06853898B2
公开(公告)日：2005-02-08
申请号：US10269308
申请日：2002-10-11
申请人： Michael E. Farmer , James M. Slicker
发明人： Michael E. Farmer , James M. Slicker
IPC分类号： B60R21/16 , B60R21/00 , B60R21/01 , B60R21/013 , B60R21/015 , G06K9/00 , G06K9/62 , G06T5/00 , G06T7/00 , G06T7/20 , G06F7/00
CPC分类号： B60R21/01542 , B60R21/01538 , B60R21/01552 , B60R21/01556 , B60R21/01558 , B60R2021/0044 , B60R2021/01315 , G06K9/00362 , G06K9/00369 , G06K9/00832 , G06K9/626 , G06T7/12 , G06T7/174 , G06T7/215 , G06T7/254 , G06T7/277 , G06T7/74 , G06T2207/10016 , G06T2207/10048 , G06T2207/30268
摘要： An invention is disclosed to divide a segmented image of an occupant into an upper torso image and a lower torso image. An occupant labeling heuristic can identify each pixel within the segmented image as an upper torso pixel or a lower torso pixel. A k-means module can provide an initial pixel classification by comparing the distance between the particular pixel and an estimated midpoint on the upper torso with the distance between the particular pixel and an estimated midpoint on the lower torso. The iterative parameters estimator can update the mean values for the upper torso and lower torso by performing a conditional likelihood heuristic. Pixels can then be classified as either upper or lower torso pixels by comparing a Mahalonobis distance for each torso. Airbag-related applications can then use the upper torso image to generate occupant characteristics relevant to airbag-related applications.
摘要翻译：公开了一种将乘客的分割图像划分为上躯干图像和下躯干图像的发明。乘员标签启发式可以将分割图像中的每个像素识别为上躯干像素或下躯干像素。 k-装置模块可以通过将特定像素之间的距离和上躯干上的估计中点与特定像素之间的距离与下躯干上的估计中点进行比较来提供初始像素分类。迭代参数估计器可以通过执行条件似然启发式来更新上躯干和下躯干的平均值。然后可以通过比较每个躯干的Mahalonobis距离将像素分类为上或下躯干像素。然后，安全气囊相关的应用可以使用上部躯干图像来产生与安全气囊相关的应用相关的乘员特征。

23. 发明申请

US20040090439A1 Recognition and interpretation of graphical and diagrammatic representations 审中-公开
标题翻译：识别和解释图形和图解表示
公开(公告)号：US20040090439A1
公开(公告)日：2004-05-13
申请号：US10292416
申请日：2002-11-07
发明人： Holger Dillner
IPC分类号： G06F009/44 , G06T011/20
CPC分类号： G06K9/00402 , G06K9/00476 , G06K9/469 , G06K9/626
摘要： A system and method for recognizing and interpreting diagrammatic and graphical representations in a computer. A user specifies a problem by inputting a graphical or diagrammatic representation of the problem. A recognition process according to the invention identifies symbols in the representation, identifies relationships between the symbols, and generates an adjacency matrix corresponding to a graph that represents information obtained from the identified symbols and their relationships to each other. The adjacency matrix may be simplified and used to produce computer-readable output for execution by other program components to solve the problem. With this invention, users can easily use their Tablet PCs, smart pens, other pen-centric computers or any other such input mechanisms (such as WACOM tablets or mouse) to nulldrawnull their problem and solve it.
摘要翻译：一种用于在计算机中识别和解释图形和图形表示的系统和方法。用户通过输入问题的图形或图示来指定问题。根据本发明的识别过程识别表示中的符号，识别符号之间的关系，并且生成与表示从所识别的符号获得的信息及其彼此之间的关系的图形相对应的邻接矩阵。邻接矩阵可以被简化并用于产生用于由其他程序组件执行以解决问题的计算机可读输出。利用本发明，用户可以容易地使用他们的平板电脑，智能笔，其他以笔为中心的计算机或任何其他这样的输入机制（例如WACOM平板电脑或鼠标）来“绘制”他们的问题并解决它。

24. 发明授权

US06732119B2 Retrieval and matching of color patterns based on a predetermined vocabulary and grammar 有权
标题翻译：基于预定词汇和语法的颜色模式的检索和匹配
公开(公告)号：US06732119B2
公开(公告)日：2004-05-04
申请号：US10188687
申请日：2002-07-03
申请人： S. Kicha Ganapathy , Jianying Hu , Jelena Kovacevic , Aleksandra Mojsilovic , Robert James Safranek
发明人： S. Kicha Ganapathy , Jianying Hu , Jelena Kovacevic , Aleksandra Mojsilovic , Robert James Safranek
IPC分类号： G06F1730
CPC分类号： G06F17/30262 , G06F17/3025 , G06K9/626 , Y10S707/99932 , Y10S707/99933 , Y10S707/99936 , Y10S707/99945 , Y10S707/99948
摘要： The invention provides a perceptually-based system for pattern retrieval and matching, suitable for use in a wide variety of information processing applications. An illustrative embodiment of the system uses a predetermined vocabulary comprising one or more dimensions to extract color and texture information from an information signal, e.g., an image, selected by a user. The system then generates a distance measure characterizing the relationship of the selected image to another image stored in a database, by applying a grammar, comprising a set of predetermined rules, to the color and texture information extracted from the selected image and corresponding color and texture information associated with the stored image. The vocabulary may include dimensions such as overall color, directionality and orientation, regularity and placement, color purity, and pattern complexity and heaviness. The rules in the grammar may include equal pattern, overall appearance, similar pattern, and dominant color and general impression, with each of the rules expressed as a logical combination of values generated for one or more of the dimensions. The distance measure may include separate color and texture metrics characterizing the similarity of the respective color and texture of the two images being compared. The invention is also applicable to other types of information signals, such as sequences of video frames.
摘要翻译：本发明提供了一种基于感知的用于模式检索和匹配的系统，适用于各种各样的信息处理应用。系统的说明性实施例使用包括一个或多个维度的预定词汇表从用户选择的信息信号（例如，图像）中提取颜色和纹理信息。然后，系统通过将包括一组预定规则的语法应用于从所选择的图像提取的颜色和纹理信息以及相应的颜色和纹理，生成表征所选图像与存储在数据库中的另一图像的关系的距离度量与存储的图像相关联的信息。词汇可以包括诸如整体颜色，方向性和取向，规则性和放置，颜色纯度和图案复杂性和沉重性的尺寸。语法中的规则可以包括相等的模式，整体外观，类似的模式以及主要颜色和一般的印象，其中每个规则表示为为一个或多个维度生成的值的逻辑组合。距离测量可以包括表征正在比较的两个图像的相应颜色和纹理的相似性的分离的颜色和纹理度量。本发明也可应用于其他类型的信息信号，例如视频帧序列。

25. 发明授权

US06647379B2 Method and apparatus for interpreting information 有权
公开(公告)号：US06647379B2
公开(公告)日：2003-11-11
申请号：US10038103
申请日：2002-01-02
申请人： Gary Howard , Paul Colin Barson , Simon Field , Philip William Hobson
发明人： Gary Howard , Paul Colin Barson , Simon Field , Philip William Hobson
IPC分类号： G06N500
CPC分类号： G06K9/626 , G06N3/0427 , G06N5/025 , G06N7/005
摘要： A computer product for analyzing data representative of account usage, the computer product disposed on a computer readable medium and including instructions for causing a processor to provide a data classifier the data representative of account usage, wherein the data classifier produces in response to the data representative of account usage, classification outputs, provide to a rule inducer input data based on the data representative of account usage and the classification outputs, wherein the rule inducer produces rules descriptive of relationships between the data representative of account usage and the classification outputs. The data classifier can include a neural network and a Bayesian classifier. The input data based on the data representative of account usage can include a combination of the data representative of account usage and the classification outputs.

26. 发明申请

US20030165264A1 Part recognition data creation method and apparatus, electronic part mounting apparatus, and recorded medium 有权
公开(公告)号：US20030165264A1
公开(公告)日：2003-09-04
申请号：US10312772
申请日：2003-02-10
发明人： Atsushi Tanabe , Kimiaki Sano , Junichi Hada , Eiichi Hachiya , Seishiro Yanachi
IPC分类号： G06K009/00 , G06K009/46
CPC分类号： G06K9/32 , G06K9/626 , G06T7/0004 , G06T2207/30141 , G06T2207/30148 , H05K13/0413 , H05K13/0813 , H05K13/0882
摘要： It is an object of the present invention to provide a parts recognition data preparing method and a preparing device and an electronic parts mounting device and a recording medium, which are capable of preparing parts recognition data, which are set to respective electronic parts and are referred to when the electronic parts are to be recognized, precisely and quickly not to know particularly the characteristic of the recognition algorithm. In the present invention, there are provided an inputting means for inputting information of a body and electrodes of the electronic parts, a recognition algorithm selecting means for identifying a type of the electronic parts based on input information of the body and the electrodes and then selecting a recognition algorithm that is adaptive to the identified type, and a parts shape data extracting means for extracting automatically parts shape data, which are required for a recognizing process executed by the selected recognition algorithm, from the input information of the body and the electrodes, whereby parts recognition data in which recognition conditions of the electronic parts are recorded are prepared.

27. 发明申请

US20030135346A1 Occupant labeling for airbag-related applications 失效
标题翻译：乘客标签用于安全气囊相关应用
公开(公告)号：US20030135346A1
公开(公告)日：2003-07-17
申请号：US10269308
申请日：2002-10-11
申请人： Eaton Corporation
发明人： Michael E. Farmer , James M. Slicker
IPC分类号： G05D001/00 , G05D003/00 , G06F007/00 , E05F015/00 , G06F017/00 , B60R022/00 , G01C009/00 , G06F015/00 , G01C017/00 , G01C019/00 , B60R021/16
CPC分类号： B60R21/01542 , B60R21/01538 , B60R21/01552 , B60R21/01556 , B60R21/01558 , B60R2021/0044 , B60R2021/01315 , G06K9/00362 , G06K9/00369 , G06K9/00832 , G06K9/626 , G06T7/12 , G06T7/174 , G06T7/215 , G06T7/254 , G06T7/277 , G06T7/74 , G06T2207/10016 , G06T2207/10048 , G06T2207/30268
摘要： An invention is disclosed to divide a segmented image of an occupant into an upper torso image and a lower torso image. An occupant labeling heuristic can identify each pixel within the segmented image as an upper torso pixel or a lower torso pixel. A k-means module can provide an initial pixel classification by comparing the distance between the particular pixel and an estimated midpoint on the upper torso with the distance between the particular pixel and an estimated midpoint on the lower torso. The iterative parameters estimator can update the mean values for the upper torso and lower torso by performing a conditional likelihood heuristic. Pixels can then be classified as either upper or lower torso pixels by comparing a Mahalonobis distance for each torso. Airbag-related applications can then use the upper torso image to generate occupant characteristics relevant to airbag-related applications.
摘要翻译：公开了一种将乘客的分割图像划分为上躯干图像和下躯干图像的发明。乘员标签启发式可以将分割图像中的每个像素识别为上躯干像素或下躯干像素。 k-装置模块可以通过将特定像素之间的距离和上躯干上的估计中点与特定像素之间的距离与下躯干上的估计中点进行比较来提供初始像素分类。迭代参数估计器可以通过执行条件似然启发式来更新上躯干和下躯干的平均值。然后可以通过比较每个躯干的Mahalonobis距离将像素分类为上或下躯干像素。然后，安全气囊相关的应用可以使用上部躯干图像来产生与安全气囊相关的应用相关的乘员特征。

28. 发明授权

US6014461A Apparatus and method for automatic knowlege-based object identification 失效
标题翻译：自动基于知识的对象识别的装置和方法
公开(公告)号：US6014461A
公开(公告)日：2000-01-11
申请号：US998315
申请日：1997-12-24
申请人： Audrey Kathleen Hennessey , YouLing Lin , Veera V. S. Khaja , Ramakrishna Pattikonda , Rajasekar Reddy , Huitian Lu , Ramachandra Katragadda
发明人： Audrey Kathleen Hennessey , YouLing Lin , Veera V. S. Khaja , Ramakrishna Pattikonda , Rajasekar Reddy , Huitian Lu , Ramachandra Katragadda
IPC分类号： G06K9/62
CPC分类号： G06K9/626
摘要： An apparatus and method for automatic knowledge-based object or anomaly classification is provided by capturing a pixel map of an image and from that generating high level descriptors of the object or anomaly such as size, shape, color and sharpness. These descriptors are compared with sets of descriptors in a knowledge-base to classify the object or anomaly.
摘要翻译：通过捕获图像的像素图和从生成对象或异常的高级描述符（例如大小，形状，颜色和锐度）的方式提供用于自动基于知识的对象或异常分类的装置和方法。将这些描述符与知识库中的描述符集进行比较，以对对象或异常进行分类。

29. 发明授权

US5966683A Apparatus and method for analyzing chemical system data 失效
公开(公告)号：US5966683A
公开(公告)日：1999-10-12
申请号：US929618
申请日：1997-09-15
申请人： Peter J. Millett , Gary D. Burns , Gary E. Brobst
发明人： Peter J. Millett , Gary D. Burns , Gary E. Brobst
IPC分类号： F22B37/38 , C02F1/00 , F01K21/00 , G01N1/10 , G01N33/18 , G06K9/62 , G06Q10/00 , G06Q50/00 , G21C17/02
CPC分类号： G01N33/18 , G06K9/626 , G06F2219/00 , Y10S706/914 , Y10S706/915
摘要： A power plant water chemistry analysis apparatus and method relies upon water chemistry sensors to obtain power plant water chemistry data characterizing the chemical activity of a power plant water system. An analytical model processor is used to generate model predictions for the power plant water system. A statistical data fitting processor selects screened data from the power plant water chemistry data that corresponds to the model predictions. The screened data is processed by an artificial intelligence processor to derive power plant water chemistry diagnostic information. The artificial intelligence processor includes an expert system, rule base, plant water chemistry system simulator, and pattern recognition module.

30. 发明授权

US5748850A Knowledge base system and recognition system 失效
标题翻译：知识库系统和识别系统
公开(公告)号：US5748850A
公开(公告)日：1998-05-05
申请号：US464208
申请日：1995-06-05
申请人： Akito Sakurai
发明人： Akito Sakurai
IPC分类号： G06K9/72 , G06F9/44 , G06K9/62 , G06N5/02 , G06N5/04 , G10L15/08 , G10L15/18 , G10L15/28 , G06F15/18
CPC分类号： G06K9/626 , G06N5/02 , G10L15/083
摘要： In a recognition system using a knowledge base in which there is required tolerance for ambiguity and noises in a knowledge expressing system not having the cause-and-effect relation existing, for example, in a knowledge base system employed for pattern recognition. The knowledge base supported recognition system includes as an inference engine an apparatus in which a hypergraph is added to the data structure of the knowledge base to obtain a minimum cost tree or the like by use of costs assigned to hyperedges of the hypergraph. With this provision, there can be attained tolerance for ambiguity of the knowledge base and noises superimposed on input data.
摘要翻译：在使用知识库的识别系统中，例如在用于模式识别的知识库系统中，存在对不存在因果关系的知识表达系统中的歧义和噪声的要求容忍的识别系统。知识库支持的识别系统包括作为推理引擎的装置，其中通过使用分配给超图的超帧的成本将超图添加到知识库的数据结构以获得最小成本树等。通过这一规定，可以实现对知识库的模糊度和对输入数据叠加的噪声的容限。

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