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. 发明授权

US08744122B2 System and method for object detection from a moving platform 有权
标题翻译：从移动平台进行物体检测的系统和方法
公开(公告)号：US08744122B2
公开(公告)日：2014-06-03
申请号：US12604298
申请日：2009-10-22
申请人： Garbis Salgian , John Benjamin Southall , Sang-Hack Jung , Vlad Branzoi , Jiangjian Xiao , Feng Han , Supun Samarasekera , Rakesh Kumar , Jayan Eledath
发明人： Garbis Salgian , John Benjamin Southall , Sang-Hack Jung , Vlad Branzoi , Jiangjian Xiao , Feng Han , Supun Samarasekera , Rakesh Kumar , Jayan Eledath
IPC分类号： G06K9/00
CPC分类号： G06K9/00369 , G06K9/00805
摘要： The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.
摘要翻译：本发明涉及一种用于在富3D环境中从移动平台检测属于第一类（例如移动和/或固定人物）的一个或多个目标的系统和方法。这里描述的框架使用分布在车辆周围的多个单目或立体摄像机来实现，以提供360度覆盖。此外，这里描述的框架利用许多过滤器来减少目标的假阳性识别的数量。

2. 发明申请

US20100328452A1 METHOD FOR POSE INVARIANT VESSEL FINGERPRINTING 有权
标题翻译：用于不定式船舶指纹的方法
公开(公告)号：US20100328452A1
公开(公告)日：2010-12-30
申请号：US12758507
申请日：2010-04-12
申请人： Sang-Hack Jung , Ajay Divakaran , Harpreet Singh Sawhney
发明人： Sang-Hack Jung , Ajay Divakaran , Harpreet Singh Sawhney
IPC分类号： H04N7/18 , G06K9/46
CPC分类号： G06K9/00771 , G06K9/6206 , G06K9/6211
摘要： A computer-implemented method for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.
摘要翻译：公开了一种用于匹配对象的计算机实现的方法。接收至少两个图像，其中至少两个图像中的一个具有第一目标对象，并且至少两个图像中的第二图像具有第二目标对象。提取来自第一目标对象的至少一个第一补丁和来自第二目标对象的至少一个第二补丁。构建基于包括部件类型和姿态中的至少一个的图像部件的对应码本的至少一个第一贴片和至少一个第二贴片中的每一个之间的基于距离的部件编码。所述至少一个第一贴片中的一个的视点弯曲到所述至少一个第二贴片的观点。应用基于对于至少一个第一贴片和至少一个第二贴片中的每一个的视图不变距离度量的零件级相似性度量来确定第一目标对象和第二目标对象是相同还是不同的对象。

3. 发明申请

US20090207257A1 CAMERA EGOMOTION ESTIMATION FROM AN INFRA-RED IMAGE SEQUENCE FOR NIGHT VISION 有权
标题翻译：来自夜视的红外图像序列的摄像机构估计
公开(公告)号：US20090207257A1
公开(公告)日：2009-08-20
申请号：US12203322
申请日：2008-09-03
申请人： Sang-Hack Jung , Jayan Eledath
发明人： Sang-Hack Jung , Jayan Eledath
IPC分类号： H04N5/225
CPC分类号： G06T7/246 , G06T7/73 , G06T2207/10016 , G06T2207/10048 , G06T2207/30244 , G06T2207/30252
摘要： A method for estimating egomotion of a camera mounted on a vehicle that uses infra-red images is disclosed, comprising the steps of (a) receiving a pair of frames from a plurality of frames from the camera, the first frame being assigned to a previous frame and an anchor frame and the second frame being assigned to a current frame; (b) extracting features from the previous frame and the current frame; (c) finding correspondances between extracted features from the previous frame and the current frame; and (d) estimating the relative pose of the camera by minimizing reprojection errors from the correspondences to the anchor frame. The method can further comprise the steps of (e) assigning the current frame as the anchor frame when a predetermined amount of image motion between the current frame and the anchor frame is observed; (f) assigning the current frame to the previous frame and assigning a new frame from the plurality of frames to the current frame; and (g) repeating steps (b)-(f) until there are no more frames from the plurality of frames to process. Step (c) is based on an estimation of the focus of expansion between the previous frame and the current frame.
摘要翻译：公开了一种用于估计安装在使用红外图像的车辆上的相机的自动运算的方法，包括以下步骤：（a）从相机从多个帧接收一对帧，将第一帧分配给先前的帧和锚帧，并且第二帧被分配给当前帧; （b）从前一帧和当前帧中提取特征; （c）从前一帧和当前帧之间提取的特征之间的对应; 以及（d）通过使从与对应帧对应的重新投射误差最小化来估计相机的相对姿态。该方法还可以包括以下步骤：（e）当观察到当前帧和锚帧之间的预定量的图像运动时，将当前帧分配为锚帧; （f）将当前帧分配给前一帧，并将新帧从多个帧分配给当前帧; 和（g）重复步骤（b） - （f），直到来自多个帧的帧不再有更多的处理。步骤（c）基于对前一帧和当前帧之间的扩展重点的估计。

4. 发明授权

US08861842B2 Method and apparatus for real-time pedestrian detection for urban driving 有权
标题翻译：城市驾驶实时行人检测方法与装置
公开(公告)号：US08861842B2
公开(公告)日：2014-10-14
申请号：US13022118
申请日：2011-02-07
申请人： Sang-Hack Jung , Mayank Bansal , Bogdan Calin Mihai Matei , Jayan Eledath , Harpreet Singh Sawhney , Rakesh Kumar , Raia Hadsell
发明人： Sang-Hack Jung , Mayank Bansal , Bogdan Calin Mihai Matei , Jayan Eledath , Harpreet Singh Sawhney , Rakesh Kumar , Raia Hadsell
IPC分类号： G06K9/00
CPC分类号： G06K9/00805 , G06K9/00369
摘要： A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.
摘要翻译：公开了一种用于检测车辆附近的一个或多个行人的存在的计算机实现方法。从至少一个图像捕获装置接收场景的图像。从图像中导出深度图。通过将多个ROI中的每一个与3D人体形状模型进行匹配，从深度图检测多个行人候选区域（ROI）。候选ROI的至少一部分通过采用针对多个深度带调谐的分级器级联进行分类，并且针对候选ROI部分内的数据的滤波表示进行训练，以确定至少一个行人是否靠近车辆。

5. 发明申请

US20120106800A1 3-D MODEL BASED METHOD FOR DETECTING AND CLASSIFYING VEHICLES IN AERIAL IMAGERY 有权
标题翻译：用于在航空影像中检测和分类车辆的基于3-D模型的方法
公开(公告)号：US20120106800A1
公开(公告)日：2012-05-03
申请号：US12913861
申请日：2010-10-28
申请人： Saad Masood Khan , Hui Cheng , Dennis Lee Matthies , Harpreet Singh Sawhney , Sang-Hack Jung , Chris Broaddus , Bogdan Calin Mihai Matei , Ajay Divakaran
发明人： Saad Masood Khan , Hui Cheng , Dennis Lee Matthies , Harpreet Singh Sawhney , Sang-Hack Jung , Chris Broaddus , Bogdan Calin Mihai Matei , Ajay Divakaran
IPC分类号： G06K9/68
CPC分类号： G06K9/00785 , B64C39/024 , B64C2201/123 , B64D47/08 , G06K9/00651 , G06K9/4671 , G06K9/6269 , G06K9/6282 , G06T7/11 , G06T7/20 , G06T2207/10012
摘要： A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.
摘要翻译：公开了一种用于确定在图像中检测到的车辆的车辆类型的计算机实现的方法。接收具有检测到的车辆的图像。在检测到的车辆上投影出具有显着特征点的多个车辆模型。将来自车辆模型的每个突出特征位置的第一组特征与从所检测到的车辆的相应突出特征位置导出的第二组特征进行比较，以形成一组正的匹配得分（p分数）和一组负面比赛得分（n分）。检测到的车辆至少部分地基于p分数集合和n分数集合被分类为车辆模型模型之一。

6. 发明申请

US20110255741A1 METHOD AND APPARATUS FOR REAL-TIME PEDESTRIAN DETECTION FOR URBAN DRIVING 有权
标题翻译：用于城市驾驶的实时检测方法和装置
公开(公告)号：US20110255741A1
公开(公告)日：2011-10-20
申请号：US13022118
申请日：2011-02-07
申请人： Sang-Hack Jung , Mayank Bansal , Bogdan Calin Mihai Matei , Jayan Eledath , Harpreet Singh Sawhney , Rakesh Kumar , Raia Hadsell
发明人： Sang-Hack Jung , Mayank Bansal , Bogdan Calin Mihai Matei , Jayan Eledath , Harpreet Singh Sawhney , Rakesh Kumar , Raia Hadsell
IPC分类号： G06K9/00
CPC分类号： G06K9/00805 , G06K9/00369
摘要： A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.
摘要翻译：公开了一种用于检测车辆附近的一个或多个行人的存在的计算机实现方法。从至少一个图像捕获装置接收场景的图像。从图像中导出深度图。通过将多个ROI中的每一个与3D人体形状模型进行匹配，从深度图检测多个行人候选区域（ROI）。候选ROI的至少一部分通过采用针对多个深度带调谐的分级器级联进行分类，并且针对候选ROI部分内的数据的滤波表示进行训练，以确定至少一个行人是否靠近车辆。

7. 发明申请

US20100202657A1 SYSTEM AND METHOD FOR OBJECT DETECTION FROM A MOVING PLATFORM 有权
标题翻译：用于移动平台对象检测的系统和方法
公开(公告)号：US20100202657A1
公开(公告)日：2010-08-12
申请号：US12604298
申请日：2009-10-22
申请人： Garbis Salgian , John Benjamin Southall , Sang-Hack Jung , Vlad Branzoi , Jiangjian Xiao , Feng Han , Supun Samarasekera , Rakesh Kumar , Jayan Eledath
发明人： Garbis Salgian , John Benjamin Southall , Sang-Hack Jung , Vlad Branzoi , Jiangjian Xiao , Feng Han , Supun Samarasekera , Rakesh Kumar , Jayan Eledath
IPC分类号： G06K9/48 , G06K9/00
CPC分类号： G06K9/00369 , G06K9/00805
摘要： The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.
摘要翻译：本发明涉及一种用于在富3D环境中从移动平台检测属于第一类（例如移动和/或固定人物）的一个或多个目标的系统和方法。这里描述的框架使用分布在车辆周围的多个单目或立体摄像机来实现，以提供360度覆盖。此外，这里描述的框架利用许多过滤器来减少目标的假阳性识别的数量。

8. 发明授权

US08913783B2 3-D model based method for detecting and classifying vehicles in aerial imagery 有权
标题翻译：基于3-D模型的航空图像检测和分类车辆的方法
公开(公告)号：US08913783B2
公开(公告)日：2014-12-16
申请号：US12913861
申请日：2010-10-28
申请人： Saad Masood Khan , Hui Cheng , Dennis Lee Matthies , Harpreet Singh Sawhney , Sang-Hack Jung , Chris Broaddus , Bogdan Calin Mihai Matei , Ajay Divakaran
发明人： Saad Masood Khan , Hui Cheng , Dennis Lee Matthies , Harpreet Singh Sawhney , Sang-Hack Jung , Chris Broaddus , Bogdan Calin Mihai Matei , Ajay Divakaran
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00785 , B64C39/024 , B64C2201/123 , B64D47/08 , G06K9/00651 , G06K9/4671 , G06K9/6269 , G06K9/6282 , G06T7/11 , G06T7/20 , G06T2207/10012
摘要： A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.
摘要翻译：公开了一种用于确定在图像中检测到的车辆的车辆类型的计算机实现的方法。接收具有检测到的车辆的图像。在检测到的车辆上投影出具有显着特征点的多个车辆模型。将来自车辆模型的每个突出特征位置的第一组特征与从所检测到的车辆的相应突出特征位置导出的第二组特征进行比较，以形成一组正的匹配得分（p分数）和一组负面比赛得分（n分）。检测到的车辆至少部分地基于p分数集合和n分数集合被分类为车辆模型模型之一。

9. 发明授权

US08634638B2 Real-time action detection and classification 有权
标题翻译：实时动作检测与分类
公开(公告)号：US08634638B2
公开(公告)日：2014-01-21
申请号：US12488911
申请日：2009-06-22
申请人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
发明人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
IPC分类号： G06K9/62
CPC分类号： G06K9/00342
摘要： The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
摘要翻译：本发明涉及一种用于基于运动模式创建强分类器的方法和系统，其中强分类器可用于确定由运动中的身体执行的动作。当创建强分类器时，通过测量运动模式中的特征之间的相似度来执行动作分类。本发明的实施例可以利用基于候选部分的动作集和训练样本来训练一个或多个弱分类器，然后将其用于创建强分类器。

10. 发明授权

US08330819B2 Method for pose invariant vessel fingerprinting 有权
标题翻译：姿态不变血管指纹方法
公开(公告)号：US08330819B2
公开(公告)日：2012-12-11
申请号：US12758507
申请日：2010-04-12
申请人： Sang-Hack Jung , Ajay Divakaran , Harpreet Singh Sawhney
发明人： Sang-Hack Jung , Ajay Divakaran , Harpreet Singh Sawhney
IPC分类号： H04N7/18
CPC分类号： G06K9/00771 , G06K9/6206 , G06K9/6211
摘要： A computer-implemented method for for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invariant distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.
摘要翻译：公开了一种用于匹配对象的计算机实现的方法。接收至少两个图像，其中至少两个图像中的一个具有第一目标对象，并且至少两个图像中的第二图像具有第二目标对象。提取来自第一目标对象的至少一个第一补丁和来自第二目标对象的至少一个第二补丁。构建基于包括部件类型和姿态中的至少一个的图像部件的对应码本的至少一个第一贴片和至少一个第二贴片中的每一个之间的基于距离的部件编码。所述至少一个第一贴片中的一个的视点弯曲到所述至少一个第二贴片的观点。应用基于对于至少一个第一贴片和至少一个第二贴片中的每一个的视图不变距离度量的零件级相似性度量来确定第一目标对象和第二目标对象是相同还是不同的对象。

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