公开(公告)号：US20080273752A1

公开(公告)日：2008-11-06

申请号：US12014397

申请日：2008-01-15

申请人： Ying Zhu ,  Gregory Baratoff ,  Thorsten Kohler

发明人： Ying Zhu ,  Gregory Baratoff ,  Thorsten Kohler

IPC分类号： G06K9/00

CPC分类号： B60W40/02 ,  G06T7/246 ,  G06T2207/20016 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30252 ,  G08G1/16 ,  G08G1/166 ,  G08G1/167

摘要： A method for vehicle detection and tracking includes acquiring video data including a plurality of frames, comparing a first frame of the acquired video data against a set of one or more vehicle detectors to form vehicle hypotheses, pruning and verifying the vehicle hypotheses using a set of course-to-fine constraints to detect a vehicle, and tracking the detected vehicle within one or more subsequent frames of the acquired video data by fusing shape template matching with one or more vehicle detectors.

摘要翻译： 一种用于车辆检测和跟踪的方法包括获取包括多个帧的视频数据，将所获取的视频数据的第一帧与一组一个或多个车辆检测器进行比较，以形成车辆假设，使用一组 通过融合与一个或多个车辆检测器的形状模板匹配来跟踪所获取的视频数据的一个或多个后续帧中的检测到的车辆。

公开(公告)号：US20050226471A1

公开(公告)日：2005-10-13

申请号：US11091142

申请日：2005-03-28

申请人： Maneesh Singh ,  Kazunori Okada ,  Benedicte Bascle ,  Dorin Comaniciu ,  Gregory Baratoff ,  Thorsten Kohler

发明人： Maneesh Singh ,  Kazunori Okada ,  Benedicte Bascle ,  Dorin Comaniciu ,  Gregory Baratoff ,  Thorsten Kohler

IPC分类号： G06K9/00

CPC分类号： G06K9/00228 ,  G06K9/00288

摘要： Methods for image processing for detecting and recognizing an image object include detecting an image object using pose-specific object detectors, and performing fusion of the outputs from the pose-specific object detectors. The image object is recognized using pose-specific object recognizers that use outputs from the pose-specific object detectors and the fused output of the pose-specific object detectors; and by performing fusion of the outputs of the pose-specific object recognizers to recognize the image object.

摘要翻译： 用于检测和识别图像对象的图像处理的方法包括使用姿势特定对象检测器检测图像对象，并且执行来自姿势特定对象检测器的输出的融合。 使用姿势特定对象识别器识别图像对象，所述对象识别器使用来自姿态特定对象检测器的输出和姿势特定对象检测器的融合输出; 并且通过执行姿态特定对象识别器的输出的融合来识别图像对象。

公开(公告)号：US20080024284A1

公开(公告)日：2008-01-31

申请号：US11628208

申请日：2005-05-13

申请人： Gregory Baratoff ,  Ludwig Ertl ,  Thorsten Kohler ,  Martin Pellkofer ,  Andre Rieder

发明人： Gregory Baratoff ,  Ludwig Ertl ,  Thorsten Kohler ,  Martin Pellkofer ,  Andre Rieder

IPC分类号： G08G1/16 ,  B62D15/02 ,  G05D1/02

CPC分类号： G08G1/161

摘要： An assistance system for motor vehicles has at least one monitoring unit monitoring a space external to a vehicle, in particular in a direction of travel of the motor vehicle, with a warning zone being defined in the monitored external space on each side of a lane. The warning zone is delimited by an earliest warning line and a latest warning line encompassing the respective lane marking or, as the case may be, boundary. An evaluation unit receives the data transmitted by the monitoring unit and generates a warning signal for an acoustic, visual and/or haptic warning and/or a steering intervention if the evaluation unit detects that a defined warning threshold lying within the warning zone is exceeded. The warning signal is issued only as a function of further planned driver-adaptive conditions.

摘要翻译： 用于机动车辆的辅助系统具有至少一个监视单元，其监视车辆外部的空间，特别是在机动车辆的行进方向上，在车道两侧的被监视的外部空间中限定警告区域。 警戒区由最早的警告线和包含相应车道标记的最新警告线（视情况而定）界定。 评估单元接收由监视单元发送的数据，并且如果评估单元检测到超出了警告区域内的定义的警告阈值，则生成用于声学，视觉和/或触觉警告和/或转向干预的警告信号。 警告信号仅作为进一步计划的驾驶员适应条件的函数发出。

公开(公告)号：US20050249401A1

公开(公告)日：2005-11-10

申请号：US11111640

申请日：2005-04-21

申请人： Claus Bahlmann ,  Ying Zhu ,  Dorin Comaniciu ,  Thorsten Kohler ,  Martin Pellkofer

发明人： Claus Bahlmann ,  Ying Zhu ,  Dorin Comaniciu ,  Thorsten Kohler ,  Martin Pellkofer

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/6228

摘要： A method for training a system for detecting multi-class objects in an image or a video sequence is described. A common ensemble of weak classifiers for a set of object classes is identified. For each object class, a separate weighting scheme is adapted for the ensemble of weak classifiers. A method for detecting objects of multiple classes in an image or a video sequence is also disclosed. Each class is assigned a detector that is implemented by a weighted combination of weak classifiers such that all of the detectors are based on a common ensemble of weak classifiers. Then weights are individually set for each class.

摘要翻译： 描述了一种用于训练用于检测图像或视频序列中的多类对象的系统的方法。 识别一组对象类的弱分类器的常见集合。 对于每个对象类，单独的加权方案适用于弱分类器的集合。 还公开了一种用于检测图像或视频序列中的多个类别的对象的方法。 每个类被分配一个由弱分类器的加权组合实现的检测器，使得所有检测器都基于弱分类器的共同集合。 然后，每个课程都可以单独设置权重。

公开(公告)号：US20070183651A1

公开(公告)日：2007-08-09

申请号：US10991684

申请日：2004-11-18

申请人： Dorin Comaniciu ,  Thorsten Kohler ,  Binglong Xie ,  Ying Zhu

发明人： Dorin Comaniciu ,  Thorsten Kohler ,  Binglong Xie ,  Ying Zhu

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/46

CPC分类号： G06K9/00832 ,  G06K9/00248 ,  G06K9/00362 ,  G06T7/74 ,  G06T2207/10012 ,  G06T2207/30201 ,  G06T2207/30248

摘要： A system and method for detecting an occupant and head pose using stereo detectors is disclosed. In the training stage, pairs of images taken simultaneously from a pair of stereo cameras are received and components in each pair of images are identified. Features are associated with each component and a value is associated with each feature. Among them, a subset of features with best discriminative capabilities is selected and forms a strong classifier for a given component in a pair of images. In the detection stage, the strong classifiers are used in the incoming image pairs to detect components. Identified components are used to detect occupants and head pose of the occupants. Stereo detection is combined with stereo matching in a systematic way to improve occupant detection and localization.

摘要翻译： 公开了一种使用立体声检测器检测乘员和头部姿势的系统和方法。 在训练阶段，接收从一对立体相机同时获取的图像对，并且识别每对图像中的成分。 功能与每个组件相关联，并且值与每个功能相关联。 其中，选择具有最佳辨别能力的特征的子集，并为一对图像中的给定分量形成强分类器。 在检测阶段，强分类器用于输入图像对以检测组件。 识别的组件用于检测乘员的乘客和头部姿势。 立体声检测与系统的立体匹配相结合，提高乘员检测和定位。

公开(公告)号：US20060177100A1

公开(公告)日：2006-08-10

申请号：US11313599

申请日：2005-12-21

申请人： Ying Zhu ,  Binglong Xie ,  Visvanathan Ramesh ,  Martin Pellkofer ,  Thorsten Kohler

发明人： Ying Zhu ,  Binglong Xie ,  Visvanathan Ramesh ,  Martin Pellkofer ,  Thorsten Kohler

IPC分类号： G06K9/00 ,  H04N7/18

CPC分类号： G06K9/4609 ,  G06K2209/23

摘要： A method of detecting a feature of a vehicle in an image of a vehicle includes providing a digitized image of a vehicle, providing a first filter mask over a first subdomain of the image, where the filter mask is placed to detect a feature in the image, calculating a function of a gradient of the image inside the first masked subdomain, and detecting the presence or absence of a vehicle feature within the first masked subdomain based on the value of the gradient function.

公开(公告)号：US20060034484A1

公开(公告)日：2006-02-16

申请号：US11109106

申请日：2005-04-19

申请人： Claus Bahlmann ,  Ying Zhu ,  Visvanathan Ramesh ,  Martin Pellkofer ,  Thorsten Kohler

发明人： Claus Bahlmann ,  Ying Zhu ,  Visvanathan Ramesh ,  Martin Pellkofer ,  Thorsten Kohler

IPC分类号： G06K9/00

CPC分类号： G06K9/00818 ,  G06K9/4633 ,  G06K9/4652

摘要： A method for detecting and recognizing at least one traffic sign is disclosed. A video sequence having a plurality of image frames is received. One or more filters are used to measure features in at least one image frame indicative of an object of interest. The measured features are combined and aggregated into a score indicating possible presence of an object. The scores are fused over multiple image frames for a robust detection. If a score indicates possible presence of an object in an area of the image frame, the area is aligned with a model. A determination is then made as to whether the area indicates a traffic sign. If the area indicates a traffic sign, the area is classified into a particular type of traffic sign. The present invention is also directed to training a system to detect and recognize traffic signs.

摘要翻译： 公开了一种用于检测和识别至少一个交通标志的方法。 接收具有多个图像帧的视频序列。 使用一个或多个过滤器来测量指示感兴趣对象的至少一个图像帧中的特征。 测量的特征被组合并聚合成表示对象可能存在的分数。 分数融合在多个图像帧上以进行鲁棒检测。 如果分数表示在图像帧的区域中可能存在对象，则该区域与模型对齐。 然后确定该区域是否指示交通标志。 如果该区域指示交通标志，该区域被分类为特定类型的交通标志。 本发明还涉及训练用于检测和识别交通标志的系统。

公开(公告)号：US20050196020A1

公开(公告)日：2005-09-08

申请号：US11054996

申请日：2005-02-10

申请人： Dorin Comaniciu ,  Ying Zhu ,  Martin Pellkofer ,  Thorsten Kohler

发明人： Dorin Comaniciu ,  Ying Zhu ,  Martin Pellkofer ,  Thorsten Kohler

IPC分类号： G06K9/00 ,  G06T7/20

CPC分类号： G06K9/00805 ,  G06T7/254

摘要： A system and method for detecting a passing vehicle is disclosed. A video sequence comprising a plurality of image frames is received. Image intensity is measured and image motion is estimated in each image frame. A hypothesis model describing background dynamics is formulated. The measured image intensity and motion estimation is used to determine if the background dynamics has been violated in a given image frame. If the background dynamics has been violated, motion coherency is used to determine whether the violation of the background dynamics is caused by a passing vehicle.

摘要翻译： 公开了一种用于检测过往车辆的系统和方法。 接收包括多个图像帧的视频序列。 测量图像强度，并在每个图像帧中估计图像运动。 制定描述背景动力学的假设模型。 测量的图像强度和运动估计用于确定在给定图像帧中是否违反了背景动力学。 如果背景动力学被违反，则使用运动一致性来确定背景动力学的违反是否由过去的车辆引起。

公开(公告)号：US20060023918A1

公开(公告)日：2006-02-02

申请号：US10532151

申请日：2004-04-01

申请人： Ludwig Ertl ,  Thorsten Kohler

发明人： Ludwig Ertl ,  Thorsten Kohler

IPC分类号： G01C11/36 ,  G01K9/00

CPC分类号： B60R21/01538 ,  B60R21/01552 ,  G06K9/00362 ,  G06T7/73

摘要： The invention relates to a method for determining the current position (A, B, C, D) of a head (9) of an occupant (8) in the passenger compartment (2) of a motor vehicle (1), said head moving toward an automatic dynamic disabling zone (6) in front of an airbag module (5). To this end, the invention makes use of the idea that the best position for a measurement with regard thereto is the point in space where the ideal direction of movement (14) of the head (9) is perpendicular to an ideal line of sight (17) of the camera (160. The measurement is then preferably carried out when the geometric center (10) of the head (9) crosses this point. In a preferred embodiment, the calculation of the actual movement vector of the head (9) is taken as a basis, said head being preferably perpendicular in a current line of sight (18) of the camera (16). The invention advantageously increases the potential for protecting an occupant (8) in a motor vehicle (1). It is thus suited, in particular, for use in occupant protection systems of modern motor vehicles (1).

摘要翻译： 本发明涉及一种用于确定机动车辆（1）的乘客舱（2）中的乘客（8）的头部（9）的当前位置（A，B，C，D）的方法，所述头部移动 朝向在气囊模块（5）前面的自动动态禁用区域（6）。 为此，本发明利用以下思想：关于其的测量的最佳位置是头部（9）的理想的运动方向（14）垂直于理想的视线（10）的空间点 首先，当头部（9）的几何中心（10）穿过该点时，优选地进行测量。在优选实施例中，头部（9）的实际运动矢量的计算， 作为基准，所述头部优选地在相机（16）的当前视线（18）中垂直，本发明有利地增加了保护机动车辆（1）中的乘员（8）的潜力， 因此特别适用于现代汽车的乘员保护系统（1）。

公开(公告)号：US20080027607A1

公开(公告)日：2008-01-31

申请号：US11587198

申请日：2005-04-18

申请人： Ludwig Ertl ,  Thorsten Kohler ,  Hans-Wilhelm Ruehl ,  Dirk Zittlau

发明人： Ludwig Ertl ,  Thorsten Kohler ,  Hans-Wilhelm Ruehl ,  Dirk Zittlau

IPC分类号： G06G7/76 ,  G01C21/30 ,  G06G7/78 ,  G06F7/00

CPC分类号： B60W40/06 ,  B60W30/16 ,  B60W50/14 ,  B60W2550/402

摘要： An assistance system for motor vehicles, in particular an electronic rally-copilot, an over-taking assistant, or right-of-way assistant, includes at least one control unit, which selects data from at least three groups of global, local, and internal data. The selection is by way of a specification of a driver known by the control unit and they are connected together in such a manner that an output signal can be produced relating to the driving dynamics of the motor vehicle. Further, there is provided an assistance system, which simultaneously processes, in an advantageous manner, data prepared by three groups (and/or with the specification of the driver from four groups). Redundancy can be established in an advantageous manner, which is determined, in particular for security-related uses. It can be used, in particular, as a rally-copilot, an over-taking assistant and/or right-of-way assistant for modern vehicles.

摘要翻译： 机动车辆的辅助系统，特别是电子集会副驾驶，超车助手或右路助手，包括至少一个控制单元，该控制单元从至少三组全球，局部和 内部数据。 该选择是通过控制单元已知的驱动器的指定，并且它们以可以产生与机动车辆的驾驶动态相关的输出信号的方式连接在一起。 此外，提供了一种辅助系统，其以有利的方式同时处理由三组（和/或具有来自四组的驾驶员的指定）准备的数据。 可以以有利的方式建立冗余，特别是针对与安全有关的用途。 它可以用于特别是作为一个集会副驾驶，过份助手和/或现代车辆的右路助手。