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

WO2005006254A3 SYSTEM OR METHOD FOR SEGMENTING IMAGES 审中-公开
公开(公告)号：WO2005006254A3
公开(公告)日：2005-01-20
申请号：PCT/IB2004/002267
申请日：2004-07-13
申请人： EATON CORPORATION , FARMER, Michael, E. , CHEN, Xunchang , WEN, Li
发明人： FARMER, Michael, E. , CHEN, Xunchang , WEN, Li
IPC分类号： G06T7/00
摘要： The disclosed system (20) identifies the images (40) of particular objects or organisms ("segmented image" (30) or "target image" (30)) from images (40) that include the segmented image (30) and the surrounding area (collectively, the "ambient image" (26)). Instead of attempting to merely segment the target image (30) from the ambient image (26), the system purposely "over-segments" the ambient image (26) into various image regions (42). Those image regions (42) are then selectively combined into the segmented image (30) using a predefined heuristic that incorporates logic relating to the particular context of the processed image. In some embodiments, different combinations of image regions (42) are evaluated on the basis of probability-weighted classifications (38).

2. 发明申请

WO2005008581A2 SYSTEM OR METHOD FOR CLASSIFYING IMAGES 审中-公开
标题翻译：用于分类图像的系统或方法
公开(公告)号：WO2005008581A2
公开(公告)日：2005-01-27
申请号：PCT/IB2004/002347
申请日：2004-07-20
申请人： EATON CORPORATION , FARMER, Michael, E. , CHEN, Xunchang
发明人： FARMER, Michael, E. , CHEN, Xunchang
IPC分类号： G06T
CPC分类号： G06K9/00832 , G06K9/00362
摘要： A system or method is disclosed for classifying sensor images into one of several pre-defined classifications (22). Mathematical moments (72) relating to various features (74) or attributes in the sensor image (26) are used to populated a vector of attributes (28), which are then compared to a corresponding template vector of attribute values (87). The template vector (87) contains values for known classifications (22) which are preferably predefined. By comparing the two vectors, various votes (92) and confidence metrics (85) are used to ultimately selct the appropriate classification (22). In some embodiments, preparation processing is performed before loading the attribute vector (87) with values. Image segmentation (69) is often desirable. The performance of heuristics (73) to adjust for environmental factors such as lighting can also be desirable. One embodiment of the system (29) is to prevent the deployment of an airbag when the occupant (34) in the seat (36) is a child, a rearfacing infant seat (36), or when the seat (36) is empty.
摘要翻译：公开了一种用于将传感器图像分类为若干预定义分类（22）之一的系统或方法。使用与传感器图像（26）中的各种特征（74）或属性相关的数学时刻（72）来填充属性（28）的向量，然后将其与属性值（87）的相应模板向量进行比较。模板向量（87）包含优选地预定义的已知分类（22）的值。通过比较两个向量，使用各种投票（92）和置信指标（85）来最终确定适当的分类（22）。在一些实施例中，在使用值加载属性向量（87）之前执行准备处理。图像分割（69）通常是可取的。启发式（73）的性能也适用于诸如照明等环境因素的调整。系统（29）的一个实施例是当座椅（36）中的乘员（34）是儿童，后排婴儿座椅（36）或座椅（36）为空时，防止气囊展开。

3. 发明申请

WO2005008581A3 SYSTEM OR METHOD FOR CLASSIFYING IMAGES 审中-公开
标题翻译：用于分类图像的系统或方法
公开(公告)号：WO2005008581A3
公开(公告)日：2005-04-14
申请号：PCT/IB2004002347
申请日：2004-07-20
申请人： EATON CORP , FARMER MICHAEL E , CHEN XUNCHANG
发明人： FARMER MICHAEL E , CHEN XUNCHANG
IPC分类号： B60R21/01 , G06K9/00
CPC分类号： G06K9/00832 , G06K9/00362
摘要： A system or method is disclosed for classifying sensor images into one of several pre-defined classifications (22). Mathematical moments (72) relating to various features (74) or attributes in the sensor image (26) are used to populated a vector of attributes (28), which are then compared to a corresponding template vector of attribute values (87). The template vector (87) contains values for known classifications (22) which are preferably predefined. By comparing the two vectors, various votes (92) and confidence metrics (85) are used to ultimately selct the appropriate classification (22). In some embodiments, preparation processing is performed before loading the attribute vector (87) with values. Image segmentation (69) is often desirable. The performance of heuristics (73) to adjust for environmental factors such as lighting can also be desirable. One embodiment of the system (29) is to prevent the deployment of an airbag when the occupant (34) in the seat (36) is a child, a rearfacing infant seat (36), or when the seat (36) is empty.
摘要翻译：公开了一种用于将传感器图像分类成几个预定义分类（22）中的一个的系统或方法。使用与传感器图像（26）中的各种特征（74）或属性有关的数学矩（72）来填充属性向量（28），然后将其与属性值（87）的对应模板向量进行比较。模板矢量（87）包含优选预定义的已知分类（22）的值。通过比较这两个向量，使用各种投票（92）和置信度度量（85）来最终选择适当的分类（22）。在一些实施例中，在向属性向量（87）加载值之前执行准备处理。图像分割（69）通常是可取的。启发式（73）调整环境因素（如照明）的性能也是可取的。系统（29）的一个实施例是当座椅（36）中的乘客（34）是儿童，面向后方的婴儿座椅（36）或座椅（36）为空时防止气囊展开。

4. 发明申请

WO2005027047A2 SYSTEM OR METHOD FOR IDENTIFYING A REGION-OF-INTEREST IN AN IMAGE 审中-公开
标题翻译：用于识别图像中的利益区域的系统或方法
公开(公告)号：WO2005027047A2
公开(公告)日：2005-03-24
申请号：PCT/IB2004/002922
申请日：2004-09-08
申请人： EATON CORPORATION , FARMER, Michael, E. , CHEN, Xunchang , WEN, Li
发明人： FARMER, Michael, E. , CHEN, Xunchang , WEN, Li
IPC分类号： G06T7/00
CPC分类号： G06K9/3233 , G06T7/11 , G06T7/155 , G06T2207/10048 , G06T2207/20132 , G06T2207/20152 , G06T2207/30252
摘要： The disclosed segmentation method and system (collectively "system") identifies a region-of-interest within an ambient image captured by a sensor. The ambient image includes the target image (the "segmented image" of the target), as well as the area surrounding the target. The disclosed system purposely "under-segments" the ambient image and the process is typically followed by a subsequent segmentation process to remove the portions of the region-of-interest image that do not represent the segmented image. The system compares the ambient image captured by the sensor with a template ambient image without a target to assist in identifying the region-of-interest. They system performs a watershed heuristic to further remove portions of the ambient image from the region-of-interest. In a safety restraint embodiment of the system, the region-of-interest can be used by the safety restrain application to determine the classification of the vehicle occupant, and motion characteristics relating to the occupant.
摘要翻译：公开的分割方法和系统（统称为“系统”）识别由传感器捕获的环境图像内的感兴趣区域。环境图像包括目标图像（目标的“分割图像”）以及目标周围的区域。所公开的系统有意地“下划线”环境图像，并且该过程通常后跟随后的分割处理以去除不表示分割图像的感兴趣区域图像的部分。该系统将传感器捕获的环境图像与模板环境图像进行比较，而无需目标，以帮助识别感兴趣的区域。他们系统执行分水岭启发式，以进一步从感兴趣的区域中去除环境图像的部分。在系统的安全约束实施例中，安全限制应用可以使用感兴趣区域来确定车辆乘员的分类以及与乘客相关的运动特性。

5. 发明申请

WO2008148517A1 METHOD FOR DETERMINING THE POWER OF AN INTRAOCULAR LENS 审中-公开
标题翻译：确定内镜镜片功率的方法
公开(公告)号：WO2008148517A1
公开(公告)日：2008-12-11
申请号：PCT/EP2008/004406
申请日：2008-06-03
申请人： CARL ZEISS MEDITEC AG , VON BUENAU, Rudolf , WAGNER, Burkhard, Eric , MEYER, Scott , CHEN, Xunchang
发明人： VON BUENAU, Rudolf , WAGNER, Burkhard, Eric , MEYER, Scott , CHEN, Xunchang
IPC分类号： A61B3/117 , A61F2/16
CPC分类号： A61B3/0025 , A61B3/1005 , A61B3/117 , A61B3/1173 , A61F2/16 , A61F2/1605 , A61F2240/002
摘要： For the pre-operative calculation of the power of an intraocular lens, three input parameters are needed: the axial length of the eye (AL), the refractive power of the cornea, and the distance between the front of the cornea and the back focal plane of the intraocular lens, the so-called effective lens position (ELP). The invention shows a novel approach to the determination of the ELP.
摘要翻译：对于术前计算眼内透镜的功率，需要三个输入参数：眼睛的轴向长度（AL），角膜的屈光度以及角膜前部和背部焦点之间的距离眼内透镜的平面，所谓的有效透镜位置（ELP）。本发明显示了一种确定ELP的新方法。

6. 发明申请

WO2005027047A3 SYSTEM OR METHOD FOR IDENTIFYING A REGION-OF-INTEREST IN AN IMAGE 审中-公开
标题翻译：用于识别图像中的利益区域的系统或方法
公开(公告)号：WO2005027047A3
公开(公告)日：2006-04-27
申请号：PCT/IB2004002922
申请日：2004-09-08
申请人： EATON CORP , FARMER MICHAEL E , CHEN XUNCHANG , WEN LI
发明人： FARMER MICHAEL E , CHEN XUNCHANG , WEN LI
IPC分类号： G06T7/00 , G06K9/32 , G06T5/00 , G06T7/20
CPC分类号： G06K9/3233 , G06T7/11 , G06T7/155 , G06T2207/10048 , G06T2207/20132 , G06T2207/20152 , G06T2207/30252
摘要： The disclosed segmentation method and system (collectively "system") identifies a region-of-interest within an ambient image captured by a sensor. The ambient image includes the target image (the "segmented image" of the target), as well as the area surrounding the target. The disclosed system purposely "under-segments" the ambient image and the process is typically followed by a subsequent segmentation process to remove the portions of the region-of-interest image that do not represent the segmented image. The system compares the ambient image captured by the sensor with a template ambient image without a target to assist in identifying the region-of-interest. They system performs a watershed heuristic to further remove portions of the ambient image from the region-of-interest. In a safety restraint embodiment of the system, the region-of-interest can be used by the safety restrain application to determine the classification of the vehicle occupant, and motion characteristics relating to the occupant.
摘要翻译：公开的分割方法和系统（统称为“系统”）识别由传感器捕获的环境图像内的感兴趣区域。环境图像包括目标图像（目标的“分割图像”）以及目标周围的区域。所公开的系统有意地“下划线”环境图像，并且该过程通常后跟随后的分割处理以去除不表示分割图像的感兴趣区域图像的部分。该系统将传感器捕获的环境图像与模板环境图像进行比较，而无需目标，以帮助识别感兴趣的区域。他们系统执行分水岭启发式，以进一步从感兴趣的区域去除环境图像的部分。在系统的安全约束实施例中，安全限制应用可以使用感兴趣区域来确定车辆乘员的分类以及与乘客相关的运动特性。

7. 发明申请

WO2005006254A2 SYSTEM OR METHOD FOR SEGMENTING IMAGES 审中-公开
标题翻译：用于分割图像的系统或方法
公开(公告)号：WO2005006254A2
公开(公告)日：2005-01-20
申请号：PCT/IB2004002267
申请日：2004-07-13
申请人： EATON CORP , FARMER MICHAEL E , CHEN XUNCHANG , WEN LI
发明人： FARMER MICHAEL E , CHEN XUNCHANG , WEN LI
IPC分类号： B60R21/01 , B60R21/015 , G06K9/00 , G06K9/64 , G06T5/00 , G06T7/00
CPC分类号： B60R21/01538 , G06K9/00362 , G06K9/6212 , G06T7/11 , G06T2207/10016 , G06T2207/30268
摘要： The disclosed system (20) identifies the images (40) of particular objects or organisms ("segmented image" (30) or "target image" (30)) from images (40) that include the segmented image (30) and the surrounding area (collectively, the "ambient image" (26)). Instead of attempting to merely segment the target image (30) from the ambient image (26), the system purposely "over-segments" the ambient image (26) into various image regions (42). Those image regions (42) are then selectively combined into the segmented image (30) using a predefined heuristic that incorporates logic relating to the particular context of the processed image. In some embodiments, different combinations of image regions (42) are evaluated on the basis of probability-weighted classifications (38).
摘要翻译：所公开的系统（20）从包括分割图像（30）和周围的图像（40）的图像（40）中识别特定对象或生物体（“分割图像”（30）或“目标图像”（30））的图像（40）区域（统称为“环境影像”（26））。代替尝试仅将目标图像（30）从环境图像（26）分割，系统有意地将环境图像（26）“过度分段”成各种图像区域（42）。然后使用包含与经处理的图像的特定上下文有关的逻辑的预定义启发式将那些图像区域（42）选择性地组合到分割图像（30）中。在一些实施例中，基于概率加权分类（38）来评估图像区域（42）的不同组合。

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