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

US20050013465A1 Method and apparatus for refining target position and size estimates using image and depth data 有权
标题翻译：使用图像和深度数据来提炼目标位置和尺寸估计的方法和装置
公开(公告)号：US20050013465A1
公开(公告)日：2005-01-20
申请号：US10617231
申请日：2003-07-10
申请人： John Southall , David Hirvonen , Theodore Camus
发明人： John Southall , David Hirvonen , Theodore Camus
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06K9/00624 , G06T7/55
摘要： A vehicle vision system that uses a depth map, image intensity data, and system calibration parameter to determine a target's dimensions and relative position. Initial target boundary information is projected onto the depth map and onto the image intensity. A visibility analysis determines whether the rear of a target is within the system's field of view. If so, the mapped image boundary is analyzed to determine an upper boundary of the target. Then, vertical image edges of the mapped image boundary are found by searching for a strongest pair of vertical image edges that are located at about the same depth. Then, the bottom of the mapped image boundary is found (or assumed from calibration parameters). Then, the target's position is found by an averaging technique. The height and width of the target are then computed.
摘要翻译：一种车辆视觉系统，其使用深度图，图像强度数据和系统校准参数来确定目标的尺寸和相对位置。初始目标边界信息被投影到深度图和图像强度上。可视性分析确定目标的后部是否在系统的视野内。如果是，则分析映射的图像边界以确定目标的上边界。然后，通过搜索位于大约相同深度的最强的一对垂直图像边缘来找到映射图像边界的垂直图像边缘。然后，找到映射图像边界的底部（或从校准参数假设）。然后，通过平均技术找到目标的位置。然后计算目标的高度和宽度。

2. 发明申请

US20050232463A1 Method and apparatus for detecting a presence prior to collision 审中-公开
标题翻译：用于在碰撞之前检测存在的方法和装置
公开(公告)号：US20050232463A1
公开(公告)日：2005-10-20
申请号：US11070356
申请日：2005-03-02
申请人： David Hirvonen , Theodore Camus , John Southall , Robert Mandelbaum
发明人： David Hirvonen , Theodore Camus , John Southall , Robert Mandelbaum
IPC分类号： B60Q1/00 , B62J3/00 , B62J6/00 , G06K9/00 , G06K9/32 , G06K9/54 , G06K9/60 , G06K9/62
CPC分类号： G06K9/3241 , G06K9/00805
摘要： A method and apparatus for detecting a target in an image is disclosed. A plurality of depth images is provided. A plurality of target templates is compared to at least one of the plurality of depth images. A scores image is generated based on the plurality of target templates and the at least one depth image.
摘要翻译：公开了一种用于检测图像中的目标的方法和装置。提供多个深度图像。将多个目标模板与多个深度图像中的至少一个进行比较。基于多个目标模板和至少一个深度图像生成分数图像。

3. 发明授权

US07697786B2 Method and apparatus for detecting edges of an object 有权
标题翻译：用于检测物体边缘的方法和装置
公开(公告)号：US07697786B2
公开(公告)日：2010-04-13
申请号：US11374732
申请日：2006-03-14
申请人： Theodore Camus , David Hirvonen
发明人： Theodore Camus , David Hirvonen
IPC分类号： G06K9/36 , G06K9/00 , G06K9/34 , G06K9/66 , G06K9/46
CPC分类号： G06K9/3241 , G06K9/00805 , G06K2209/23
摘要： The present invention provides a system and method for detecting edges of an object in a pre-crash sensing environment. The method includes extracting vertical edges from peaks in an array of column sums of absolute values of normalized horizontal derivates computed in the intensity image. The pixels with corresponding range image depths proximate the estimated object's closest surface contribute the column sums. The search is conducted for all likely combinations of left/right edge pairs preferably within a pre-determined horizontal range about the object's detected center. The left/right edge pairs that delimit a width within the pre-determined range of possible widths for the object are selected. Alternatively, an additional search is performed on each pair of edges to support any angular or inward slant on the edges of the object.
摘要翻译：本发明提供一种用于在预碰撞感测环境中检测物体的边缘的系统和方法。该方法包括从在强度图像中计算的归一化水平导数的绝对值的列和的数组中的峰中提取垂直边缘。具有邻近估计对象最近表面的对应范围图像深度的像素贡献列和。对于左/右边缘对的所有可能的组合优选地在关于对象检测到的中心的预定水平范围内进行搜索。选择在对象的可能宽度的预定范围内界定宽度的左/右边缘对。或者，对每对边缘执行附加搜索以支持物体边缘上的任何角度或向内倾斜。

4. 发明申请

US20050270286A1 Method and apparatus for classifying an object 有权
标题翻译：分类物体的方法和装置
公开(公告)号：US20050270286A1
公开(公告)日：2005-12-08
申请号：US11070566
申请日：2005-03-02
申请人： David Hirvonen , Theodore Camus
发明人： David Hirvonen , Theodore Camus
IPC分类号： G06K9/00 , G06K9/32 , G06K9/62 , G06T15/00 , G06T15/40
CPC分类号： G06K9/00214 , G06K9/3241
摘要： A method and apparatus for classifying an object in an image is disclosed. A depth image is provided. At least one area of the depth image unsatisfactory for object identification are identified. A plurality of two-dimensional projections of surface normals in the depth image is determined without considering the unsatisfactory at least one area. One or more objects are classified based on the plurality of two-dimensional projections of surface normals.
摘要翻译：公开了一种用于对图像中的对象进行分类的方法和装置。提供深度图像。识别对物体识别不满足深度图像的至少一个区域。确定深度图像中的表面法线的多个二维投影，而不考虑不满意的至少一个区域。基于表面法线的多个二维投影来分类一个或多个物体。

5. 发明申请

US20060210117A1 Method and apparatus for ground detection and removal in vision systems 有权
标题翻译：视觉系统中地面检测和去除的方法和装置
公开(公告)号：US20060210117A1
公开(公告)日：2006-09-21
申请号：US11429865
申请日：2006-05-08
申请人： Peng Chang , David Hirvonen , Theodore Camus
发明人： Peng Chang , David Hirvonen , Theodore Camus
IPC分类号： G06K9/00
CPC分类号： G06K9/00624 , G06K9/00805 , G06K9/3241
摘要： A vision system that forms a map of a scene proximate a platform, e.g., a vehicle, that determines the actual ground plane form the map, and that corrects the map for differences between the actual ground plane and an assumed ground plane. The vision system may remove the actual ground plane from the map to prevent false positives. The vision system can further identify and classify objects and, if appropriate, take evasive action.
摘要翻译：形成靠近平台（例如，车辆）的场景的映射的视觉系统，其确定实际的接地平面形成地图，并且校正地图以了解实际接地平面与假定的接地平面之间的差异。视觉系统可以从地图中去除实际的地平面，以防止误报。视觉系统可以进一步识别和分类对象，如果适当，采取回避行动。

6. 发明申请

US20060245653A1 Method and apparatus for detecting edges of an object 有权
标题翻译：用于检测物体边缘的方法和装置
公开(公告)号：US20060245653A1
公开(公告)日：2006-11-02
申请号：US11374732
申请日：2006-03-14
申请人： Theodore Camus , David Hirvonen
发明人： Theodore Camus , David Hirvonen
IPC分类号： G06K9/48
CPC分类号： G06K9/3241 , G06K9/00805 , G06K2209/23
摘要： The present invention provides a system and method for detecting edges of an object in a pre-crash sensing environment. The method includes extracting vertical edges from peaks in an array of column sums of absolute values of normalized horizontal derivates computed in the intensity image. The pixels with corresponding range image depths proximate the estimated object's closest surface contribute the column sums. The search is conducted for all likely combinations of left/right edge pairs preferably within a pre-determined horizontal range about the object's detected center. The left/right edge pairs that delimit a width within the pre-determined range of possible widths for the object are selected. Alternatively, an additional search is performed on each pair of edges to support any angular or inward slant on the edges of the object.
摘要翻译：本发明提供一种用于在预碰撞感测环境中检测物体的边缘的系统和方法。该方法包括从在强度图像中计算的归一化水平导数的绝对值的列和的数组中的峰中提取垂直边缘。具有邻近估计对象最近表面的对应范围图像深度的像素贡献列和。对于左/右边缘对的所有可能的组合优选地在关于对象检测到的中心的预定水平范围内进行搜索。选择在对象的可能宽度的预定范围内界定宽度的左/右边缘对。或者，对每对边缘执行附加搜索以支持物体边缘上的任何角度或向内倾斜。

7. 发明授权

US08639000B2 Robust sparse image matching for robotic surgery 有权
标题翻译：用于机器人手术的鲁棒稀疏图像匹配
公开(公告)号：US08639000B2
公开(公告)日：2014-01-28
申请号：US13454297
申请日：2012-04-24
申请人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Tao Zhao , Brian D. Hoffman , Simon Di Maio
发明人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Tao Zhao , Brian D. Hoffman , Simon Di Maio
IPC分类号： G06T7/00
CPC分类号： G06K9/6211 , G06T7/33
摘要： Systems, methods, and devices are used to match images. Points of interest from a first image are identified for matching to a second image. In response to the identified points of interest, regions and features can be identified and used to match the points of interest to a corresponding second image or second series of images. Regions can be used to match the points of interest when regions of the first image are matched to the second image with high confidence scores, for example above a threshold. Features of the first image can be matched to the second image, and these matched features may be used to match the points of interest to the second image, for example when the confidence scores for the regions are below the threshold value. Constraint can be used to evaluate the matched points of interest, for example by excluding bad points.
摘要翻译：系统，方法和设备用于匹配图像。识别来自第一图像的兴趣点以匹配第二图像。响应于所识别的兴趣点，区域和特征可被识别并用于将感兴趣点与对应的第二图像或第二系列图像相匹配。当第一图像的区域与具有高置信度得分的第二图像匹配时，例如高于阈值，可以使用区域来匹配感兴趣点。第一图像的特征可以匹配第二图像，并且这些匹配的特征可以用于将感兴趣的点与第二图像匹配，例如当区域的置信度得分低于阈值时。约束可用于评估匹配的兴趣点，例如排除不良点。

8. 发明授权

US07068815B2 Method and apparatus for ground detection and removal in vision systems 有权
公开(公告)号：US07068815B2
公开(公告)日：2006-06-27
申请号：US10813768
申请日：2004-03-31
申请人： Peng Chang , David Hirvonen , Theodore Armand Camus
发明人： Peng Chang , David Hirvonen , Theodore Armand Camus
IPC分类号： G06K9/00
CPC分类号： G06K9/00624 , G06K9/00805 , G06K9/3241
摘要： A vision system that forms a map of a scene proximate a platform, e.g., a vehicle, that determines the actual ground plane form the map, and that corrects the map for differences between the actual ground plane and an assumed ground plane. The vision system may remove the actual ground plane from the map to prevent false positives. The vision system can further identify and classify objects and, if appropriate, take evasive action.

9. 发明授权

US08830224B2 Efficient 3-D telestration for local robotic proctoring 有权
标题翻译：有效的3-D远程监控用于本地机器人监视
公开(公告)号：US08830224B2
公开(公告)日：2014-09-09
申请号：US12465020
申请日：2009-05-13
申请人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Christopher J. Hasser , Brian E. Miller , Catherine J. Mohr , Myrian J. Curet , Tao Zhao , Simon Di Maio , Brian D. Hoffman
发明人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Christopher J. Hasser , Brian E. Miller , Catherine J. Mohr , Myrian J. Curet , Tao Zhao , Simon Di Maio , Brian D. Hoffman
IPC分类号： G06T15/00 , G06K9/68
CPC分类号： A61B34/25 , A61B34/20 , A61B2034/2057 , A61B2034/2065 , A61B2090/371 , A61B2090/373 , G06T7/593 , G06T11/00 , G06T2207/10068 , G06T2207/20096 , G06T2207/20101 , G06T2207/30004 , H04N13/10 , H04N13/20 , H04N13/30 , H04N2013/0092
摘要： An apparatus is configured to show telestration in 3-D to a surgeon in real time. A proctor is shown one side of a stereo image pair, such that the proctor can draw a telestration line on the one side with an input device. Points of interest are identified for matching to the other side of the stereo image pair. In response to the identified points of interest, regions and features are identified and used to match the points of interest to the other side. Regions can be used to match the points of interest. Features of the first image can be matched to the second image and used to match the points of interest to the second image, for example when the confidence scores for the regions are below a threshold value. Constraints can be used to evaluate the matched points of interest, for example by excluding bad points.
摘要翻译：一种装置被配置为实时地向外科医生示出3-D的远程化。监视器被显示为立体图像对的一侧，使得监视器可以在一侧用输入装置绘制远距离信号线。识别兴趣点以匹配立体图像对的另一侧。响应于所识别的兴趣点，区域和特征被识别并用于将感兴趣点与另一侧匹配。区域可用于匹配兴趣点。第一图像的特征可以匹配第二图像，并且用于将感兴趣的点与第二图像匹配，例如当区域的置信度得分低于阈值时。限制可用于评估匹配的兴趣点，例如排除不良点。

10. 发明授权

US08184880B2 Robust sparse image matching for robotic surgery 有权
标题翻译：用于机器人手术的鲁棒稀疏图像匹配
公开(公告)号：US08184880B2
公开(公告)日：2012-05-22
申请号：US12465029
申请日：2009-05-13
申请人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Tao Zhao , Brian D. Hoffman , Simon Di Maio
发明人： Wenyi Zhao , Chenyu Wu , David Hirvonen , Tao Zhao , Brian D. Hoffman , Simon Di Maio
IPC分类号： G06T7/00
CPC分类号： G06K9/6211 , G06T7/33
摘要： Systems, methods, and devices are used to match images. Points of interest from a first image are identified for matching to a second image. In response to the identified points of interest, regions and features can be identified and used to match the points of interest to a corresponding second image or second series of images. Regions can be used to match the points of interest when regions of the first image are matched to the second image with high confidence scores, for example above a threshold. Features of the first image can be matched to the second image, and these matched features may be used to match the points of interest to the second image, for example when the confidence scores for the regions are below the threshold value. Constraint can be used to evaluate the matched points of interest, for example by excluding bad points.
摘要翻译：系统，方法和设备用于匹配图像。识别来自第一图像的兴趣点以匹配第二图像。响应于所识别的兴趣点，区域和特征可被识别并用于将感兴趣点与对应的第二图像或第二系列图像相匹配。当第一图像的区域与具有高置信度得分的第二图像匹配时，例如高于阈值，可以使用区域来匹配感兴趣点。第一图像的特征可以匹配第二图像，并且这些匹配的特征可以用于将感兴趣的点与第二图像匹配，例如当区域的置信度得分低于阈值时。约束可用于评估匹配的兴趣点，例如排除不良点。

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