公开(公告)号：US07437006B2

公开(公告)日：2008-10-14

申请号：US10382437

申请日：2003-03-06

Applicant: Benedicte Bascle ,  Dorin Comaniciu ,  Anurag Mittal ,  Visvanathan Ramesh

Inventor： Benedicte Bascle ,  Dorin Comaniciu ,  Anurag Mittal ,  Visvanathan Ramesh

IPC: G06K9/62 ,  G06K9/74

CPC classification number: G06K9/4633 ,  G06K9/3233

Abstract: The present invention comprises using error propagation for building feature spaces with variable uncertainty and using variable-bandwidth mean shift for the analysis of such spaces, to provide peak detection and space partitioning. The invention applies these techniques to construct and analyze Hough spaces for line and geometrical shape detection, as well as to detect objects that are represented by peaks in the Hough space. This invention can be further used for background modeling by taking into account the uncertainty of the transformed image color and uncertainty of the motion flow. Furthermore, the invention can be used to segment video data in invariant spaces, by propagating the uncertainty from the original space and using the variable-bandwidth mean shift to detect peaks. The invention can be used in a variety of applications such as medical, surveillance, monitoring, automotive, augmented reality, and inspection.

Abstract translation: 本发明包括使用用于构建具有可变不确定性的特征空间的误差传播，并且使用可变带宽平均移位来分析这样的空间，以提供峰值检测和空间划分。 本发明应用这些技术来构建和分析用于线和几何形状检测的霍夫空间，以及检测由霍夫空间中的峰表示的对象。 通过考虑到变换图像颜色的不确定性和运动流的不确定性，本发明可以进一步用于背景建模。 此外，本发明可以用于通过从原始空间传播不确定性并使用可变带宽平均偏移来检测峰值来在不变空间中分割视频数据。 本发明可用于医疗，监视，监控，汽车，增强现实和检查等各种应用。

公开(公告)号：US20060142981A1

公开(公告)日：2006-06-29

申请号：US11360800

申请日：2006-02-23

Applicant: Michael Greiffenhagen ,  Visvanathan Ramesh ,  Dorin Comaniciu

Inventor： Michael Greiffenhagen ,  Visvanathan Ramesh ,  Dorin Comaniciu

IPC: G06F17/10

CPC classification number: H04N7/181 ,  G06T7/277 ,  G06T7/77 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30241 ,  G08B13/19604 ,  G08B13/19608 ,  G08B13/19628 ,  G08B13/19641 ,  G08B13/19643 ,  G08B13/19647 ,  H04N5/232

Abstract: The present invention relates to a method for visually detecting and tracking an object through a space. The method chooses modules for a restricting a search function within the space to regions with a high probability of significant change, the search function operating on images supplied by a camera. The method also derives statistical models for errors, including quantifying an indexing step performed by an indexing module, and tuning system parameters. Further the method applies a likelihood model for candidate hypothesis evaluation and object parameters estimation for locating the object.

公开(公告)号：US07027643B2

公开(公告)日：2006-04-11

申请号：US10345131

申请日：2003-05-15

Applicant: Dorin Comaniciu ,  Visvanathan Ramesh

Inventor： Dorin Comaniciu ,  Visvanathan Ramesh

IPC: G06K9/00

CPC classification number: G06K9/42 ,  G06K9/6226 ,  G06K9/6298 ,  G06K2209/01 ,  G06T7/13 ,  G06T7/90 ,  G06T2207/20016 ,  G06T2207/20048

Abstract: A system and method for automatic scale selection in real-time image and video processing and computer vision applications. In one aspect, a non-parametric variable bandwidth mean shift technique, which is based on adaptive estimation of a normalized density gradient, is used for detecting one or more modes in the underlying data and clustering the underlying data. In another aspect, a data-driven bandwidth (or scale) selection technique is provided for the variable bandwidth mean shift method, which estimates for each data point the covariance matrix that is the most stable across a plurality of scales. The methods can be used for detecting modes and clustering data for various types of data such as image data, video data speech data, handwriting data, etc.

公开(公告)号：US07006950B1

公开(公告)日：2006-02-28

申请号：US09592532

申请日：2000-06-12

Applicant: Michael Greiffenhagen ,  Visvanathan Ramesh ,  Dorin Comaniciu

Inventor： Michael Greiffenhagen ,  Visvanathan Ramesh ,  Dorin Comaniciu

IPC: G06F7/60 ,  G06F17/10 ,  G06F101/00

CPC classification number: H04N7/181 ,  G06T7/277 ,  G06T7/77 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30241 ,  G08B13/19604 ,  G08B13/19608 ,  G08B13/19628 ,  G08B13/19641 ,  G08B13/19643 ,  G08B13/19647 ,  H04N5/232

Abstract: The present invention relates to a method for visually detecting and tracking an object through a space. The method chooses modules for a restricting a search function within the space to regions with a high probability of significant change, the search function operating on images supplied by a camera. The method also derives statistical models for errors, including quantifying an indexing step performed by an indexing module, and tuning system parameters. Further the method applies a likelihood model for candidate hypothesis evaluation and object parameters estimation for locating the object.

Abstract translation: 本发明涉及一种用于通过空间目视检测和跟踪物体的方法。 该方法选择用于将空间内的搜索功能限制在具有很大变化概率的区域的模块，该搜索功能对由相机提供的图像进行操作。 该方法还导出错误的统计模型，包括量化由索引模块执行的索引步骤，以及调整系统参数。 此外，该方法应用候选假设评估的可行性模型和用于定位对象的对象参数估计。

公开(公告)号：US07881531B2

公开(公告)日：2011-02-01

申请号：US12198349

申请日：2008-08-26

Applicant: Benedicte Bascle ,  Dorin Comaniciu ,  Anurag Mittal ,  Visvanathan Ramesh

Inventor： Benedicte Bascle ,  Dorin Comaniciu ,  Anurag Mittal ,  Visvanathan Ramesh

IPC: G06K9/34 ,  G06K9/00 ,  G06K9/62 ,  G06K9/68

CPC classification number: G06K9/4633 ,  G06K9/3233

Abstract: The present invention comprises using error propagation for building feature spaces with variable uncertainty and using variable-bandwidth mean shift for the analysis of such spaces, to provide peak detection and space partitioning. The invention applies these techniques to construct and analyze Hough spaces for line and geometrical shape detection, as well as to detect objects that are represented by peaks in the Hough space. This invention can be further used for background modeling by taking into account the uncertainty of the transformed image color and uncertainty of the motion flow. Furthermore, the invention can be used to segment video data in invariant spaces, by propagating the uncertainty from the original space and using the variable-bandwidth mean shift to detect peaks. The invention can be used in a variety of applications such as medical, surveillance, monitoring, automotive, augmented reality, and inspection.

Abstract translation: 本发明包括使用用于构建具有可变不确定性的特征空间的误差传播，并且使用可变带宽平均移位来分析这样的空间，以提供峰值检测和空间划分。 本发明应用这些技术来构建和分析用于线和几何形状检测的霍夫空间，以及检测由霍夫空间中的峰表示的对象。 通过考虑到变换图像颜色的不确定性和运动流的不确定性，本发明可以进一步用于背景建模。 此外，本发明可以用于通过从原始空间传播不确定性并使用可变带宽平均偏移来检测峰值来在不变空间中分割视频数据。 本发明可用于医疗，监视，监控，汽车，增强现实和检查等各种应用。

公开(公告)号：US07458936B2

公开(公告)日：2008-12-02

申请号：US10703024

申请日：2003-11-06

Applicant: Xiang Sean Zhou ,  Dorin Comaniciu ,  Alok Gupta ,  Visvanathan Ramesh ,  Bhavani Duggirala ,  Diane Paine

Inventor： Xiang Sean Zhou ,  Dorin Comaniciu ,  Alok Gupta ,  Visvanathan Ramesh ,  Bhavani Duggirala ,  Diane Paine

IPC: A61B8/00

CPC classification number: G06K9/6276 ,  A61B8/0883 ,  G06F19/00 ,  G06K9/6256 ,  G06K2209/05 ,  G06Q50/22 ,  G16H50/20 ,  Y10S128/92 ,  Y10S128/924

Abstract: A system and method for providing decision support to a physician during a medical examination is disclosed. Data is received from a sensor representing a particular medical measurement. The received data includes image data. The received data and context data is analyzed with respect to one or more sets of training models. Probability values for the particular medical measurement and other measurements to be taken are derived based on the analysis and based on identified classes. The received image data is compared with training images. Distance values are determined between the received image data and the training images, and the training images are associated with the identified classes. Absolute value feature sensitivity scores are derived for the particular medical measurement and other measurements to be taken based on the analysis. The probability values, distance values and absolute value feature sensitivity scores are outputted to the user.

Abstract translation: 公开了一种用于在医学检查期间向医师提供决策支持的系统和方法。 从代表特定医疗测量的传感器接收数据。 所接收的数据包括图像数据。 相对于一组或多组训练模型分析接收到的数据和上下文数据。 特定医疗测量和其他测量的概率值基于分析并基于识别的类别导出。 将接收到的图像数据与训练图像进行比较。 在接收的图像数据和训练图像之间确定距离值，并且训练图像与所识别的类别相关联。 基于分析，针对特定医疗测量和其他测量得出绝对值特征灵敏度得分。 将概率值，距离值和绝对值特征灵敏度得分输出给用户。

公开(公告)号：US07167519B2

公开(公告)日：2007-01-23

申请号：US10325413

申请日：2002-12-20

Applicant: Dorin Comaniciu ,  Alessio Del Bue ,  Visvanathan Ramesh

Inventor： Dorin Comaniciu ,  Alessio Del Bue ,  Visvanathan Ramesh

IPC: H04N7/12 ,  G06K9/00

CPC classification number: H04N19/23 ,  H04N7/141 ,  H04N7/183 ,  H04N19/124 ,  H04N19/126 ,  H04N19/14 ,  H04N19/146 ,  H04N19/149 ,  H04N19/17 ,  H04N19/172 ,  H04N19/174 ,  H04N19/196 ,  H04N19/61

Abstract: An apparatus and method for video object generation and selective encoding is provided. The apparatus includes a detection module for detecting a first object in at least one image frame of a series of image frames; a tracking module for tracking the first object in successive image frames and segmenting the first object from a background, the background being a second object; and an encoder for encoding the first and second objects to be transmitted to a receiver, wherein the first object is compressed at a high compression rate and the second object is compressed at a low compression rate. The receiver merges the first and second object to form a composite image frame. The method provides for detecting, tracking and segmenting one or more objects, such as a face, from a background to be encoded at the same or different compression rates to conserve bandwidth.

公开(公告)号：US06999004B2

公开(公告)日：2006-02-14

申请号：US10463912

申请日：2003-06-17

Applicant: Dorin Comaniciu ,  Visvanathan Ramesh ,  Nikolaos Paragios

Inventor： Dorin Comaniciu ,  Visvanathan Ramesh ,  Nikolaos Paragios

IPC: G08G1/017 ,  G08G1/054

CPC classification number: G06K9/3241 ,  G06K9/00805 ,  G06T7/246 ,  G08G1/04

Abstract: A system and method for vehicle detection and tracking in tunnels is provided. The method comprises the steps of capturing a plurality of image frames viewing at least one traffic lane; extracting at least one feature from the plurality of image frames; detecting at least one object indicative of a vehicle from the extracted feature; and tracking the detected vehicle over time to determine the detected vehicle's velocity. The system comprising at least one image capture device for capturing a plurality of image frames viewing at least one traffic lane; and a processor adapted for extracting at least one feature from the plurality of image frames, detecting at least one object indicative of a vehicle from the extracted feature, and tracking the detected vehicle over time to determine the detected vehicle's velocity.

Abstract translation: 提供了一种用于隧道中车辆检测和跟踪的系统和方法。 该方法包括以下步骤：捕获观看至少一个行车道的多个图像帧; 从所述多个图像帧中提取至少一个特征; 从所提取的特征中检测指示车辆的至少一个物体; 并随着时间跟踪所检测到的车辆以确定检测到的车辆的速度。 该系统包括用于捕获观看至少一个行车道的多个图像帧的至少一个图像捕获装置; 以及处理器，适于从所述多个图像帧中提取至少一个特征，从所提取的特征中检测指示车辆的至少一个物体，以及跟踪所检测到的车辆随时间的变化，以确定所检测到的车辆的速度。

公开(公告)号：US20050001013A1

公开(公告)日：2005-01-06

申请号：US10842802

申请日：2004-05-11

Applicant: Binglong Xie ,  Dorin Comaniciu ,  Visvanathan Ramesh ,  Markus Simon

Inventor： Binglong Xie ,  Dorin Comaniciu ,  Visvanathan Ramesh ,  Markus Simon

IPC: G06K9/00 ,  B23K1/00

CPC classification number: G06K9/00281

Abstract: A system and method for object detection are provided where the system includes a component detection unit for detecting components in an image, a component fusion unit in signal communication with the component detection unit for fusing the components into an object, and a CPU in signal communication with the detection and fusion units for comparing the fused components with a statistical model; and the method includes receiving observation data for a plurality of training images, forming at least one statistical model from the plurality of training images, receiving an input image having a plurality of pixels, detecting a plurality of components in the input image, determining a fusion of the detected components, comparing the fusion with the statistical model, and detecting an object in accordance with the comparison.

Abstract translation: 提供了一种用于对象检测的系统和方法，其中系统包括用于检测图像中的分量的分量检测单元，与分量检测单元进行信号通信的分量融合单元，用于将分量融合到对象中，以及在信号通信中的CPU 用检测和融合单元比较融合成分与统计模型; 并且该方法包括接收多个训练图像的观测数据，从多个训练图像中形成至少一个统计模型，接收具有多个像素的输入图像，检测输入图像中的多个分量，确定融合 的检测组件，将融合与统计模型进行比较，并根据比较来检测对象。

公开(公告)号：US08060178B2

公开(公告)日：2011-11-15

申请号：US12243199

申请日：2008-10-01

Applicant: Xiang Zhou ,  Dorin Comaniciu ,  Alok Gupta ,  Visvanathan Ramesh ,  Bhavani Duggirala ,  Diane Paine

Inventor： Xiang Zhou ,  Dorin Comaniciu ,  Alok Gupta ,  Visvanathan Ramesh ,  Bhavani Duggirala ,  Diane Paine

IPC: A61B5/00

CPC classification number: G06K9/6276 ,  A61B8/0883 ,  G06F19/00 ,  G06K9/6256 ,  G06K2209/05 ,  G06Q50/22 ,  G16H50/20 ,  Y10S128/92 ,  Y10S128/924

Abstract: A system and method for providing decision support to a physician during a medical examination is disclosed. Data is received from a sensor representing a particular medical measurement. The received data includes image data. The received data and context data is analyzed with respect to one or more sets of training models. Probability values for the particular medical measurement and other measurements to be taken are derived based on the analysis and based on identified classes. The received image data is compared with training images. Distance values are determined between the received image data and the training images, and the training images are associated with the identified classes. Absolute value feature sensitivity scores are derived for the particular medical measurement and other measurements to be taken based on the analysis. The probability values, distance values and absolute value feature sensitivity scores are outputted to the user.

Abstract translation: 公开了一种用于在医学检查期间向医师提供决策支持的系统和方法。 从代表特定医疗测量的传感器接收数据。 所接收的数据包括图像数据。 相对于一组或多组训练模型分析接收到的数据和上下文数据。 特定医疗测量和其他测量的概率值基于分析并基于识别的类别导出。 将接收到的图像数据与训练图像进行比较。 在接收的图像数据和训练图像之间确定距离值，并且训练图像与所识别的类别相关联。 基于分析，针对特定医疗测量和其他测量得出绝对值特征灵敏度得分。 将概率值，距离值和绝对值特征灵敏度得分输出给用户。