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

WO2012093147A1 NATURAL GESTURE BASED USER INTERFACE METHODS AND SYSTEMS 审中-公开
标题翻译：基于自然语言的用户界面方法和系统
公开(公告)号：WO2012093147A1
公开(公告)日：2012-07-12
申请号：PCT/EP2012/050115
申请日：2012-01-04
申请人： SOFTKINETIC SOFTWARE , TOCINOS DIAZ, Juan Carlos , SIMONS, Kevin , PINAULT, Gilles , BAELE, Xavier , THOLLOT, Julien , DAL ZOT, David
发明人： TOCINOS DIAZ, Juan Carlos , SIMONS, Kevin , PINAULT, Gilles , BAELE, Xavier , THOLLOT, Julien , DAL ZOT, David
IPC分类号： G06T7/20 , G06F3/01 , G06F3/03
CPC分类号： G06F3/017 , A63F13/06 , A63F2300/1087 , A63F2300/6045 , G06F3/0304 , G06K9/00355
摘要： Described herein is a user interface that provides contextual feedback, controls and interface elements on a display screen of an interactive three-dimensional imaging system. A user (2410) interacts with the interface to provide control signals in accordance with those recognised by the system to a makes use of at least one point of interes (2310, 2320) in a three-dimensional scene that is imaged by the imaging system to provide control signals for the user interface. Control signals are provided by means of gestures (2420, 2430) which are analysed in real-time by gesture recognition processes that analyse statistical and geometrical properties of point of interest motion and trajectories.
摘要翻译：这里描述的是在交互式三维成像系统的显示屏幕上提供上下文反馈，控制和界面元素的用户界面。用户（2410）与界面交互以根据由系统识别的那些提供控制信号，利用由成像系统成像的三维场景中的至少一个点（2310,2320）为用户界面提供控制信号。通过手势（2420,2430）提供控制信号，这些手势通过手势识别过程实时分析，该过程分析兴趣点运动和轨迹的统计和几何特性。

2. 发明申请

WO2011080280A1 HEAD RECOGNITION METHOD 审中-公开
标题翻译：头识别方法
公开(公告)号：WO2011080280A1
公开(公告)日：2011-07-07
申请号：PCT/EP2010/070817
申请日：2010-12-28
申请人： SOFTKINETIC , BAELE, Xavier , THOLLOT, Julien , MARTINEZ GONZALEZ, Javier , SIMONS, Kevin
发明人： BAELE, Xavier , THOLLOT, Julien , MARTINEZ GONZALEZ, Javier , SIMONS, Kevin
IPC分类号： G06K9/00
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。

3. 发明申请

WO2011080282A1 TRACKING METHOD 审中-公开
标题翻译：跟踪方法
公开(公告)号：WO2011080282A1
公开(公告)日：2011-07-07
申请号：PCT/EP2010/070821
申请日：2010-12-28
申请人： SOFTKINETIC , BAELE, Xavier , GUIGUES, Laurent , MARTINEZ GONZALEZ, Javier
发明人： BAELE, Xavier , GUIGUES, Laurent , MARTINEZ GONZALEZ, Javier
IPC分类号： G06T7/00 , G06K9/00
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 (B 1 ,..., B 5 ) of interconnected regions; and determining that a cluster (B 2 ,..., B 5 ) which is adjacent to another cluster (B 1 ) in a two-dimensional projection belongs to an object partially occluded by said other cluster (B 1 ) if it has a different depth value than said other cluster (B 1 ).
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若干区域，将所述区域分组成互连区域的簇（B1，...，B5）; 并且如果与所述另一个集群（B1）具有不同的深度值，则确定与二维投影中的另一个集群（B1）相邻的集群（B2，...，B5）属于由所述另一个集群（B1）部分闭塞的对象其他集群（B1）。

4. 发明申请

WO2011080281A1 STABILISATION METHOD AND COMPUTER SYSTEM 审中-公开
标题翻译：稳定方法和计算机系统
公开(公告)号：WO2011080281A1
公开(公告)日：2011-07-07
申请号：PCT/EP2010/070819
申请日：2010-12-28
申请人： SOFTKINETIC , BAELE, Xavier , THOLLOT, Julien
发明人： BAELE, Xavier , THOLLOT, Julien
IPC分类号： G06T5/00 , G06T7/00
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： A method for stabilising a series of measurements of a physical variable comprises the steps of : capturing at least a first, second, and third measurement of said physical variable and storing each measurement in a digital memory. 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. If a difference between the filtered value of the corrected second measurement and said third measurement is also below the threshold, said 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：用于稳定物理变量的一系列测量的方法包括以下步骤：捕获所述物理变量的至少第一，第二和第三测量，并将每个测量值存储在数字存储器中。如果第一测量和第二测量之间的差异低于预定阈值，则通过校正的第二测量在存储器中替换第二测量，其中使用第一滤波强度已经减少了相对于所述第一测量的差。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，则所述第三测量被替换为校正的第三测量值，其中相对于所述校正的第二测量值的差已经被使用第二滤波强度即低于第一过滤强度。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。

5. 发明申请

WO2008128568A1 VOLUME RECOGNITION METHOD AND SYSTEM 审中-公开
标题翻译：体积识别方法和系统
公开(公告)号：WO2008128568A1
公开(公告)日：2008-10-30
申请号：PCT/EP2007/053895
申请日：2007-04-20
申请人： SOFIKINETIC S.A. , PINAULT, Gilles , ROY, Jérémie , DESMECHT, Laurent , BAELE, Xavier
发明人： PINAULT, Gilles , ROY, Jérémie , DESMECHT, Laurent , BAELE, Xavier
IPC分类号： G06K9/20
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）捕获三维图像数据，其中所述图像数据表示多个点（5），每个点（5）具有在三维空间中至少有一组坐标; b）将一组聚类（6）中的至少一些点（5）分组; c）根据第一组参数（诸如位置和大小），选择与位于所述成像系统（3）的范围内的感兴趣对象（1）相对应的簇（6）; d）根据包括其在三维空间中的位置的第二组参数，将所选择的集群（6）的至少一些点（5）分组在一组子集群中，其中每个子集群具有质心（11）在三维空间中; 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）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。

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