-
公开(公告)号：US09092863B2
公开(公告)日：2015-07-28
申请号：US13519510
申请日：2010-12-28
申请人： Xavier Baele , Julien Thollot
发明人： Xavier Baele , Julien Thollot
CPC分类号： G06T7/004 , A63F2300/1093 , A63F2300/6045 , G06F3/011 , G06F17/18 , G06K9/40 , G06T5/002 , G06T5/50 , G06T7/70 , G06T2200/24 , G06T2207/10016 , G06T2207/30196
摘要： The present invention relates to a method for stabilizing a series of measurements of a physical variable captured by a digital sensor. This method comprises the steps of: capturing at least a first measurement, a second measurement, and a third measurement of said physical variable and storing each measurement in a digital memory. The first and second measurements are compared and, if a difference between the first measurement and the second measurement is below a predetermined threshold, the second measurement is replaced in the memory by a corrected second measurement where the difference with respect to said first measurement has been reduced using a first filtering strength. The corrected second measurement and the third measurement are compared and, if a difference between the filtered value of the corrected second measurement and said third measurement is also below the threshold, said the third measurement is replaced by a corrected third measurement where a difference with respect to said corrected second measurement has been reduced using a second filtering strength that is lower than the first filtering strength. This method has the advantage of filtering noise while still allowing slow but relevant variations in the series of measurements.
摘要翻译： 本发明涉及一种用于稳定由数字传感器捕获的物理变量的一系列测量的方法。 该方法包括以下步骤：捕获所述物理变量的至少第一测量，第二测量和第三测量，并将每个测量值存储在数字存储器中。 对第一和第二测量进行比较，如果第一测量和第二测量之间的差值低于预定阈值，则通过校正的第二测量在存储器中替换第二测量，其中相对于所述第一测量的差已经被 减少使用第一过滤强度。 比较校正的第二测量和第三测量，并且如果校正的第二测量的滤波值与所述第三测量之间的差也低于阈值，则所述第三测量被校正的第三测量代替，其中与 使用低于第一滤波强度的第二滤波强度减小到所述校正的第二测量。 该方法具有过滤噪声的优点，同时仍然允许在一系列测量中缓慢而相关的变化。
-
公开(公告)号：US09081999B2
公开(公告)日：2015-07-14
申请号：US13519502
申请日：2010-12-28
IPC分类号： G06K9/00
CPC分类号： G06K9/00201 , G06K9/00234
摘要： Described herein is a method for recognizing a human head in a source image. The method comprises detecting a contour of at least part of a human body in the source image, calculating a depth of the human body in the source image. From the source image, a major radius size and a minor radius size of an ellipse corresponding to a human head at the depth is calculated, and, for at least several of a set of pixels of the detected contour, generating in an accumulator array at least one segment of an ellipse centered on the position of the contour pixel and having the major and minor radius sizes. Positions of local intensity maxima in the accumulator array are selected as corresponding to positions of the human head candidates in the source image.
摘要翻译： 这里描述了一种用于识别源图像中的人头的方法。 该方法包括检测源图像中的人体的至少一部分的轮廓，计算源图像中人体的深度。 从源图像中，计算对应于深度处的人头的椭圆的主半径尺寸和小半径尺寸，并且对于检测到的轮廓的一组像素中的至少几个，在累积器阵列中生成 以轮廓像素的位置为中心并且具有主半径和次半径尺寸的椭圆的至少一个部分。 选择累加器阵列中局部强度最大值的位置作为源图像中的人头候选者的位置。
-
公开(公告)号：US20130027293A1
公开(公告)日：2013-01-31
申请号：US13519510
申请日：2010-12-28
申请人： Xavier Baele , Julien Thollot
发明人： Xavier Baele , Julien Thollot
IPC分类号： G09G5/00
CPC分类号： G06T7/004 , A63F2300/1093 , A63F2300/6045 , G06F3/011 , G06F17/18 , G06K9/40 , G06T5/002 , G06T5/50 , G06T7/70 , G06T2200/24 , G06T2207/10016 , G06T2207/30196
摘要： The present invention relates to a method for stabilising a series of measurements of a physical variable captured by a digital sensor. This method comprises the steps of: capturing at least a first measurement, a second measurement, and a third measurement of said physical variable and storing each measurement in a digital memory. The first and second measurements are compared and, if a difference between the first measurement and the second measurement is below a predetermined threshold, the second measurement is replaced in the memory by a corrected second measurement where the difference with respect to said first measurement has been reduced using a first filtering strength. The corrected second measurement and the third measurement are compared and, if a difference between the filtered value of the corrected second measurement and said third measurement is also below the threshold, said the third measurement is replaced by a corrected third measurement where a difference with respect to said corrected second measurement has been reduced using a second filtering strength that is lower than the first filtering strength. This method has the advantage of filtering noise whilst still allowing slow but relevant variations in the series of measurements.
摘要翻译： 本发明涉及一种用于稳定由数字传感器捕获的物理变量的一系列测量的方法。 该方法包括以下步骤：捕获所述物理变量的至少第一测量，第二测量和第三测量，并将每个测量值存储在数字存储器中。 对第一和第二测量进行比较，如果第一测量和第二测量之间的差值低于预定阈值，则通过校正的第二测量在存储器中替换第二测量，其中相对于所述第一测量的差已经被 减少使用第一过滤强度。 比较校正的第二测量和第三测量，并且如果校正的第二测量的滤波值与所述第三测量之间的差也低于阈值，则所述第三测量被校正的第三测量代替，其中与 使用低于第一滤波强度的第二滤波强度减小到所述校正的第二测量。 该方法具有过滤噪声的优点，同时仍然允许在一系列测量中缓慢而相关的变化。
-
公开(公告)号：US20130022262A1
公开(公告)日：2013-01-24
申请号：US13519502
申请日：2010-12-28
CPC分类号： G06K9/00201 , G06K9/00234
摘要： Described herein is a method for recognising a human head in a source image. The method comprises detecting a contour of at least part of a human body in the source image, calculating a depth of the human body in the source image. From the source image, a major radius size and a minor radius size of an ellipse corresponding to a human head at the depth is calculated, and, for at least several of a set of pixels of the detected contour, generating in an accumulator array at least one segment of an ellipse centred on the position of the contour pixel and having the major and minor radius sizes. Positions of local intensity maxima in the accumulator array are selected as corresponding to positions of the human head candidates in the source image.
摘要翻译： 这里描述了一种用于识别源图像中的人头的方法。 该方法包括检测源图像中的人体的至少一部分的轮廓，计算源图像中人体的深度。 从源图像中，计算对应于深度处的人头的椭圆的主半径尺寸和小半径尺寸，并且对于检测到的轮廓的一组像素中的至少几个，在累积器阵列中生成 以轮廓像素的位置为中心并且具有主半径和次半径尺寸的椭圆的至少一个部分。 选择累加器阵列中局部强度最大值的位置作为源图像中的人头候选者的位置。
-
公开(公告)号：US08175374B2
公开(公告)日：2012-05-08
申请号：US12596604
申请日：2007-04-20
申请人： Gilles Pinault , Jeremie Roy , Laurent Desmecht , Xavier Baele
发明人： Gilles Pinault , Jeremie Roy , Laurent Desmecht , Xavier Baele
CPC分类号： G06K9/00362 , G06K9/00201
摘要： The present invention relates to a volume recognition method comprising the steps of: a) capturing three-dimensional image data using a 3D imaging system 3, wherein said image data represent a plurality of points 5, each point 5 having at least a set of coordinates in a three-dimensional space; b) grouping at least some of the points 5 in a set of clusters 6; c) selecting, according to a first set of parameters such as position and size, a cluster 6 corresponding to an object of interest 1 located in range of said imaging system 3; d) grouping at least some of the points 5 of the selected cluster 6 in a set of sub-clusters according to a second set of parameters comprising their positions in the three-dimensional space, wherein each sub-cluster has a centroid 11 in the three-dimensional space; and e) associating a volume 12 to each of at least some of said sub-clusters, wherein said volume 12 is fixed to the centroid 11 of said sub-cluster. The present invention also relates to a volume recognition system for carrying out this method.
摘要翻译： 本发明涉及一种音量识别方法，包括以下步骤：a）使用3D成像系统3拍摄三维图像数据，其中所述图像数据表示多个点5，每个点5至少具有一组坐标 在三维空间中 b）将一组簇6中的点5中的至少一些分组; c）根据第一组参数（诸如位置和大小）选择对应于位于所述成像系统3的范围内的感兴趣对象1的簇6; d）根据包括其在三维空间中的位置的第二组参数，将所选择的群集6的点5中的至少一些分组在一组子群集中，其中每个子群集中的质心11 三维空间; 以及e）将体积12与至少一些所述子集群中的每一个相关联，其中所述体积12被固定到所述子集群的质心11。 本发明还涉及一种用于执行该方法的音量识别系统。
-
公开(公告)号：US08891825B2
公开(公告)日：2014-11-18
申请号：US13518989
申请日：2010-12-28
CPC分类号： G06T7/0079 , G06K9/00201 , G06K9/6223 , G06T7/10
摘要： The present invention relates to a method for tracking at least one object in a sequence of frames, each frame comprising a pixel array, wherein a depth value is associated to each pixel. The method comprises grouping at least some of said pixels of each frame into several regions, grouping said regions into clusters (B1, . . . , B5) of interconnected regions; and determining that a cluster (B2, . . . , B5) which is adjacent to another cluster (B1) in a two-dimensional projection belongs to an object partially occluded by said other cluster (B1) if it has a different depth value than said other cluster (B1).
摘要翻译： 本发明涉及一种用于跟踪帧序列中的至少一个对象的方法，每个帧包括像素阵列，其中深度值与每个像素相关联。 该方法包括将每个帧的至少一些所述像素分组成多个区域，将所述区域分组成互连区域的簇（B1 ...，B5）; 并且如果二维投影中的另一个簇（B1）相邻的一个簇（B2，...，B5）具有与所述另一个簇（B1）不同的深度值 其他集群（B1）。
-
公开(公告)号：US20130016879A1
公开(公告)日：2013-01-17
申请号：US13518989
申请日：2010-12-28
IPC分类号： G06K9/62
CPC分类号： G06T7/0079 , G06K9/00201 , G06K9/6223 , G06T7/10
摘要： The present invention relates to a method for tracking at least one object in a sequence of frames, each frame comprising a pixel array, wherein a depth value is associated to each pixel. The method comprises grouping at least some of said pixels of each frame into several regions, grouping said regions into clusters (B1, . . . , B5) of interconnected regions; and determining that a cluster (B2, . . . , B5) which is adjacent to another cluster (B1) in a two-dimensional projection belongs to an object partially occluded by said other cluster (B1) if it has a different depth value than said other cluster (B1).
摘要翻译： 本发明涉及一种用于跟踪帧序列中的至少一个对象的方法，每个帧包括像素阵列，其中深度值与每个像素相关联。 该方法包括将每个帧的至少一些所述像素分组成多个区域，将所述区域分组成互连区域的簇（B1 ...，B5）; 并且如果二维投影中的另一个簇（B1）相邻的一个簇（B2，...，B5）具有与所述另一个簇（B1）不同的深度值 其他集群（B1）。
-
公开(公告)号：US20100208035A1
公开(公告)日：2010-08-19
申请号：US12596604
申请日：2007-04-20
申请人： Gilles Pinault , Jeremie Roy , Laurent Desmecht , Xavier Baele
发明人： Gilles Pinault , Jeremie Roy , Laurent Desmecht , Xavier Baele
CPC分类号： G06K9/00362 , G06K9/00201
摘要： The present invention relates to a volume recognition method comprising the steps of:a) capturing three-dimensional image data using a 3D imaging system 3, wherein said image data represent a plurality of points 5, each point 5 having at least a set of coordinates in a three-dimensional space; b) grouping at least some of the points 5 in a set of clusters 6; c) selecting, according to a first set of parameters such as position and size, a cluster 6 corresponding to an object of interest 1 located in range of said imaging system 3; d) grouping at least some of the points 5 of the selected cluster 6 in a set of sub-clusters according to a second set of parameters comprising their positions in the three-dimensional space, wherein each sub-cluster has a centroid 11 in the three-dimensional space; and e) associating a volume 12 to each of at least some of said sub-clusters, wherein said volume 12 is fixed to the centroid 11 of said sub-cluster. The present invention also relates to a volume recognition system for carrying out this method.
摘要翻译： 本发明涉及一种音量识别方法，包括以下步骤：a）使用3D成像系统3拍摄三维图像数据，其中所述图像数据表示多个点5，每个点5至少具有一组坐标 在三维空间中 b）将一组簇6中的点5中的至少一些分组; c）根据第一组参数（诸如位置和大小）选择对应于位于所述成像系统3的范围内的感兴趣对象1的簇6; d）根据包括其在三维空间中的位置的第二组参数，将所选择的群集6的点5中的至少一些分组在一组子群集中，其中每个子群集中的质心11 三维空间; 以及e）将体积12与至少一些所述子集群中的每一个相关联，其中所述体积12被固定到所述子集群的质心11。 本发明还涉及一种用于执行该方法的音量识别系统。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.015 秒)
