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

US20130058535A1 DETECTION OF OBJECTS IN AN IMAGE USING SELF SIMILARITIES 审中-公开
标题翻译：使用自我相似性检测图像中的对象
公开(公告)号：US20130058535A1
公开(公告)日：2013-03-07
申请号：US13697212
申请日：2011-02-28
申请人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Stefan Walk , Nikodem Majer , Konrad Schindler
发明人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Stefan Walk , Nikodem Majer , Konrad Schindler
IPC分类号： G06K9/00
CPC分类号： G06K9/6215 , G06K9/00369 , G06K9/4642 , G06K9/4647 , G06K9/4652 , G06K9/52 , G06K9/6267 , G06K2009/4666 , G06T7/60 , G06T7/90 , G06T2207/20021
摘要： An image processor (10) has a window selector for choosing a detection window within the image, and a self similarity computation part (40) for determining self-similarity information for a group of the pixels in any part of the detection window, to represent an amount of self-similarity of that group to other groups in any other part of the detector window, and for repeating the determination for groups in all parts of the detection window, to generate a global self similarity descriptor for the detection window. A classifier (50) is used for classifying whether an object is present based on the global self-similarity descriptor. By using global self-similarity rather than local similarities more information is captured which can lead to better classification. In particular, it helps enable recognition of more distant self-similarities inherent in the object, and self-similarities present at any scale.
摘要翻译：图像处理器（10）具有用于选择图像内的检测窗口的窗口选择器，以及用于确定检测窗口的任何部分中的一组像素的自相似度信息的自相似度计算部分（40），以表示该组与检测器窗口的任何其他部分中的其他组的自相似量，并且用于重复对检测窗口的所有部分中的组的确定，以生成用于检测窗口的全局自相似性描述符。分类器（50）用于基于全局自相似性描述符来分类对象是否存在。通过使用全局自相似性而不是局部相似性，可以获得更多的信息，从而导致更好的分类。特别地，它有助于识别对象中固有的更远的自相似性，以及任何规模存在的自相似性。

2. 发明申请

US20130142390A1 MONOCULAR 3D POSE ESTIMATION AND TRACKING BY DETECTION 有权
标题翻译：通过检测的单眼3D位置估计和跟踪
公开(公告)号：US20130142390A1
公开(公告)日：2013-06-06
申请号：US13702266
申请日：2011-06-14
申请人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Mykhaylo Andriluka , Stefan Roth
发明人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Mykhaylo Andriluka , Stefan Roth
IPC分类号： G06K9/00
CPC分类号： G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/251 , G06T2207/10016 , G06T2207/30196 , G06T2207/30232 , G06T2207/30244
摘要： Methods and apparatus are described for monocular 3D human pose estimation and tracking, which are able to recover poses of people in realistic street conditions captured using a monocular, potentially moving camera. Embodiments of the present invention provide a three-stage process involving estimating (10, 60, 110) a 3D pose of each of the multiple objects using an output of 2D tracking-by detection (50) and 2D viewpoint estimation (46). The present invention provides a sound Bayesian formulation to address the above problems. The present invention can provide articulated 3D tracking in realistic street conditions.The present invention provides methods and apparatus for people detection and 2D pose estimation combined with a dynamic motion prior. The present invention provides not only 2D pose estimation for people in side views, it goes beyond this by estimating poses in 3D from multiple viewpoints. The estimation of poses is done in monocular images, and does not require stereo images. Also the present invention does not require detection of characteristic poses of people.
摘要翻译：描述了用于单眼3D人体姿态估计和跟踪的方法和装置，其能够恢复使用单眼，潜在移动的相机拍摄的逼真的街道状况中的人的姿势。本发明的实施例提供一种三阶段过程，包括使用2D跟踪检测（50）和2D视点估计（46）的输出来估计（10,60,110）每个多个对象的3D姿态。本发明提供了一种解决上述问题的健全的贝叶斯公式。本发明可以在现实的街道条件下提供清晰的3D跟踪。本发明提供了与动态运动结合的人物检测和2D姿态估计的方法和装置。本发明不仅为侧视图中的人提供2D姿态估计，而且通过从多个视点估计3D的姿态来超越这一点。姿势的估计是在单目图像中进行的，不需要立体图像。此外，本发明不需要检测人的特征姿势。

3. 发明授权

US08958600B2 Monocular 3D pose estimation and tracking by detection 有权
标题翻译：单眼3D姿态估计和跟踪通过检测
公开(公告)号：US08958600B2
公开(公告)日：2015-02-17
申请号：US13702266
申请日：2011-06-14
申请人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Mykhaylo Andriluka , Stefan Roth
发明人： Gabriel Othmezouri , Ichiro Sakata , Bernt Schiele , Mykhaylo Andriluka , Stefan Roth
IPC分类号： G06K9/00 , G06T7/20 , G06E1/00
CPC分类号： G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/251 , G06T2207/10016 , G06T2207/30196 , G06T2207/30232 , G06T2207/30244
摘要： Methods and apparatus are described for monocular 3D human pose estimation and tracking, which are able to recover poses of people in realistic street conditions captured using a monocular, potentially moving camera. Embodiments of the present invention provide a three-stage process involving estimating (10, 60, 110) a 3D pose of each of the multiple objects using an output of 2D tracking-by detection (50) and 2D viewpoint estimation (46). The present invention provides a sound Bayesian formulation to address the above problems. The present invention can provide articulated 3D tracking in realistic street conditions.The present invention provides methods and apparatus for people detection and 2D pose estimation combined with a dynamic motion prior. The present invention provides not only 2D pose estimation for people in side views, it goes beyond this by estimating poses in 3D from multiple viewpoints. The estimation of poses is done in monocular images, and does not require stereo images. Also the present invention does not require detection of characteristic poses of people.
摘要翻译：描述了用于单眼3D人体姿态估计和跟踪的方法和装置，其能够恢复使用单眼，潜在移动的相机拍摄的逼真的街道状况中的人的姿势。本发明的实施例提供一种三阶段过程，包括使用2D跟踪检测（50）和2D视点估计（46）的输出来估计（10,60,110）每个多个对象的3D姿态。本发明提供了一种解决上述问题的健全的贝叶斯公式。本发明可以在现实的街道条件下提供清晰的3D跟踪。本发明提供了与动态运动结合的人物检测和2D姿态估计的方法和装置。本发明不仅为侧视图中的人提供2D姿态估计，而且通过从多个视点估计3D的姿态来超越这一点。姿势的估计是在单目图像中进行的，不需要立体图像。此外，本发明不需要检测人的特征姿势。

4. 发明授权

US08934666B2 Method and device for analyzing surrounding objects and/or surrounding scenes, such as for object and scene class segmenting 有权
标题翻译：用于分析周围物体和/或周围场景的方法和装置，例如用于对象和场景类分割
公开(公告)号：US08934666B2
公开(公告)日：2015-01-13
申请号：US13123017
申请日：2009-09-30
申请人： Stefan Lüke , Bernt Schiele , Christian Wojek
发明人： Stefan Lüke , Bernt Schiele , Christian Wojek
IPC分类号： G06K9/00 , G06K9/62 , G06T7/00
CPC分类号： G06K9/6297 , G06K9/00791 , G06T7/143
摘要： The invention relates to a method and an object detection device for analyzing objects in the environment and/or scenes in the environment. The object detection device includes a data processing and/or evaluation device. In the data processing and/or evaluation device, image data (xt) is evaluated on the basis of a Conditional Random Field (CRF) model and the CRF model provides additional object nodes (otn) which take into account information from an object detector.
摘要翻译：本发明涉及用于分析环境和/或环境中的物体的方法和物体检测装置。物体检测装置包括数据处理和/或评估装置。在数据处理和/或评估装置中，基于条件随机场（CRF）模型评估图像数据（xt），并且CRF模型提供考虑来自对象检测器的信息的附加对象节点（otn）。

5. 发明申请

US20110313665A1 Method for Automatically Detecting a Driving Maneuver of a Motor Vehicle and a Driver Assistance System Comprising Said Method 审中-公开
公开(公告)号：US20110313665A1
公开(公告)日：2011-12-22
申请号：US13201020
申请日：2010-03-04
申请人： Stefan Lueke , Ken Schmitt , Rolf Isermann , Stefan Habenicht , Andree Hohm , Roman Mannale , Christian Wojek , Hermann Winner , Bernt Schiele
发明人： Stefan Lueke , Ken Schmitt , Rolf Isermann , Stefan Habenicht , Andree Hohm , Roman Mannale , Christian Wojek , Hermann Winner , Bernt Schiele
IPC分类号： B60W30/08
CPC分类号： G01S13/931 , G01S2013/9325 , G01S2013/9346 , G01S2013/9353
摘要： The invention relates to a method for automatically detecting a driving maneuver of a motor vehicle (A), in particular an overtaking maneuver or an evasive maneuver, in which the surroundings of the vehicle are covered and an electronic image thereof is created, the electronic image is used for the detection of a traffic lane and/or of a road as well as of-objects (B, C) in the surroundings of the vehicle, longitudinal-dynamics and lateral-dynamics movement information ({dot over (ψ)}, αy, δH, ωFL, ωFR, ωRL, ωRR) of motor vehicle (A) is determined, and the position ({circumflex over (X)}) of motor vehicle (A) is odometrically estimated on the basis of the data (bLane, yLane, θ, c0) of lane detection and/or road detection and/or of the movement information ({dot over (ψ)}, αy, δH, ωFL, ωFR, ωRL, ωRR) of motor vehicle (A), wherein the invention provides that a) the following indicator quantities are formed from the estimated position data ({circumflex over (X)}) of motor vehicle (A): a value of the lateral distance (LOL, LOR) of motor vehicle (A) from a road marking or traffic line (L), a time-to-collision value (TTCA,B) relative to the distance (d) from the object (B) located in the direction of motion, in particular from the vehicle driving ahead (B), a longitudinal-dynamics overtaking-or-evasive-maneuver indicator (I) formed from the indicator quantity (TTCA,B) of the time-to-collision value and from a value that corresponds to the position (FPS) of the gas pedal of motor vehicle (A), and b) that threshold values (Ith, TTCA,B,th) are determined for said indicator quantities (LOL, LOR, TTCA,B, I), which threshold values are used as criteria for detecting partial maneuvers of an overtaking or evasive maneuver, in particular a maneuver to follow a vehicle driving ahead, a lane change, a maneuver to pass the stationary or moving object (B) and a maneuver to cut into the lane of the overtaken object (B), as well as for detecting transitions between said partial maneuvers.

6. 发明申请

US20110200230A1 METHOD AND DEVICE FOR ANALYZING SURROUNDING OBJECTS AND/OR SURROUNDING SCENES, SUCH AS FOR OBJECT AND SCENE CLASS SEGMENTING 有权
标题翻译：用于分析环境对象和/或环境的方法和设备，如对象和场景分类
公开(公告)号：US20110200230A1
公开(公告)日：2011-08-18
申请号：US13123017
申请日：2009-09-30
申请人： Stefan Lüke , Bernt Schiele , Christian Wojek
发明人： Stefan Lüke , Bernt Schiele , Christian Wojek
IPC分类号： G06K9/00
CPC分类号： G06K9/6297 , G06K9/00791 , G06T7/143
摘要： The invention relates to a method and an object detection device for analysing objects in the environment and/or scenes in the environment. The object detection device includes a data processing and/or evaluation device. In the data processing and/or evaluation device, image data (xt) is evaluated on the basis of a Conditional Random Field (CRF) model and the CRF model provides additional object nodes (otn) which take into account information from an object detector.
摘要翻译：本发明涉及用于分析环境和/或环境中的物体的方法和物体检测装置。物体检测装置包括数据处理和/或评估装置。在数据处理和/或评估装置中，基于条件随机场（CRF）模型评估图像数据（xt），并且CRF模型提供考虑来自对象检测器的信息的附加对象节点（otn）。

7. 发明申请

US20110243376A1 METHOD AND A DEVICE FOR DETECTING OBJECTS IN AN IMAGE 审中-公开
标题翻译：用于检测图像中的对象的方法和装置
公开(公告)号：US20110243376A1
公开(公告)日：2011-10-06
申请号：US12672007
申请日：2008-08-04
申请人： Stefan Lüke , Edgar Semann , Bernt Schiele , Christan Wojek
发明人： Stefan Lüke , Edgar Semann , Bernt Schiele , Christan Wojek
IPC分类号： G06K9/00
CPC分类号： G06K9/4647 , G06K9/3241
摘要： Detection of an object of a specified object category in an image. With the method, it is provided that: (1) at least two detectors are provided which are respectively set up for the purpose of detecting an object of the specified object category with a specified object size, wherein object sizes differ for the detectors, (2) the image is evaluated by the detectors in order to check whether an object of the specified object category is located in the image, and (3) an object of the specified object category is detected in the image when on the basis of the evaluation of the image by at least one of the detectors it is determined that an object of the specified object category is located in the image. A system suitable for implementing the method for detecting an object of a specified object category in an image is also described.
摘要翻译：检测图像中指定对象类别的对象。使用该方法，提供：（1）提供至少两个检测器，其分别设置用于以指定的对象尺寸检测指定对象类别的对象，其中对于检测器的对象大小不同（ 2）图像由检测器评估，以便检查指定对象类别的对象是否位于图像中，并且（3）当基于评估在图像中检测到指定对象类别的对象时由至少一个检测器检测图像，确定指定对象类别的对象位于图像中。还描述了适于实现用于检测图像中的指定对象类别的对象的方法的系统。

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