公开(公告)号：US20090129666A1

公开(公告)日：2009-05-21

申请号：US12233757

申请日：2008-09-19

申请人： Tobias GOEVERT ,  Lars Krueger ,  Christian Woehler

发明人： Tobias GOEVERT ,  Lars Krueger ,  Christian Woehler

IPC分类号： G06K9/00 ,  H04N13/02

CPC分类号： G06T7/593 ,  G06T7/97 ,  G06T2207/10012

摘要： Passive methods for three-dimensional reconstruction of a scene by means of image data are generally based on the determination of spatial correspondences between a number of images of the scene recorded from various directions and distances. A method and a device are disclosed which provide a high reliability in the solution of the correspondence problem in conjunction with a low computational outlay. Image areas for determining the correspondences are determined within a plurality of images forming at least two image sequences. In preferred embodiments, a parameterized function h(u,v,t) is matched to each of the image areas in a space R(uvgt) defined by pixel position (u, v), image value g and time t. The parameters of the parameterized functions are used to form a similarity measure between the image areas.

摘要翻译： 用于通过图像数据对场景进行三维重建的被动方法通常基于从各个方向和距离记录的场景的多个图像之间的空间对应性的确定。 公开了一种结合低计算支出在对应问题的解决方案中提供高可靠性的方法和装置。 在形成至少两个图像序列的多个图像内确定用于确定对应关系的图像区域。 在优选实施例中，参数化函数h（u，v，t）与由像素位置（u，v），图像值g和时间t定义的空间R（uvgt）中的每个图像区域匹配。 参数化函数的参数用于形成图像区域之间的相似性度量。

公开(公告)号：US08135211B2

公开(公告)日：2012-03-13

申请号：US12233757

申请日：2008-09-19

申请人： Tobias Goevert ,  Lars Krueger ,  Christian Woehler

发明人： Tobias Goevert ,  Lars Krueger ,  Christian Woehler

IPC分类号： G06K9/00

CPC分类号： G06T7/593 ,  G06T7/97 ,  G06T2207/10012

摘要： Passive methods for three-dimensional reconstruction of a scene by means of image data are generally based on the determination of spatial correspondences between a number of images of the scene recorded from various directions and distances. A method and a device are disclosed which provide a high reliability in the solution of the correspondence problem in conjunction with a low computational outlay. Image areas for determining the correspondences are determined within a plurality of images forming at least two image sequences. In preferred embodiments, a parameterized function h(u, v, t) is matched to each of the image areas in a space R(uvgt) defined by pixel position (u, v), image value g and time t. The parameters of the parameterized functions are used to form a similarity measure between the image areas.

摘要翻译： 用于通过图像数据对场景进行三维重建的被动方法通常基于从各个方向和距离记录的场景的多个图像之间的空间对应性的确定。 公开了一种结合低计算支出在对应问题的解决方案中提供高可靠性的方法和装置。 在形成至少两个图像序列的多个图像内确定用于确定对应关系的图像区域。 在优选实施例中，参数化函数h（u，v，t）与由像素位置（u，v），图像值g和时间t定义的空间R（uvgt）中的每个图像区域匹配。 参数化函数的参数用于形成图像区域之间的相似性度量。

公开(公告)号：US08154590B2

公开(公告)日：2012-04-10

申请号：US12362745

申请日：2009-01-30

申请人： Ulrich Kressel ,  Lars Krueger ,  Werner Progscha ,  Christian Woehler ,  Franz Kummert ,  Joachim Schmidt ,  Rainer Ott ,  Gerhard Sagerer

发明人： Ulrich Kressel ,  Lars Krueger ,  Werner Progscha ,  Christian Woehler ,  Franz Kummert ,  Joachim Schmidt ,  Rainer Ott ,  Gerhard Sagerer

IPC分类号： G06K9/00

CPC分类号： F16P3/142 ,  G05B2219/40202 ,  G06K9/00201 ,  G06K9/00342

摘要： A method for observing a person in an industrial environment using a multicamera system to acquire image data about the position and alignment of a person, including a person's body parts. These image data are then examined with regard to the imaging of a person so that whenever a person has been detected in the image data, an articulated virtual 3D model of the human body is matched to this person hypothesis. Subsequently, this virtual body model is continuously matched to the movement behavior of the person detected in the image data. A hazard potential is determined using knowledge of the position and the movement behavior of the virtual body model in space. The hazard potential thus determined is subjected to a threshold value comparison in order to act upon the movement control of the machine or the machine part in the event of this threshold value being exceeded.

摘要翻译： 一种使用多摄像系统观察工业环境中的人的方法，用于获取关于包括人体部分在内的人的位置和位置的图像数据。 然后，关于人的成像检查这些图像数据，使得每当在图像数据中检测到人时，将人体的关节虚拟3D模型与该人假设相匹配。 随后，该虚拟身体模型与图像数据中检测到的人的运动行为连续匹配。 使用空间中的虚拟身体模型的位置和运动行为的知识来确定危险潜力。 如此确定的危险潜力经受阈值比较，以便在超过该阈值的情况下对机器或机器部件的移动控制起作用。

公开(公告)号：US20090222134A1

公开(公告)日：2009-09-03

申请号：US12362733

申请日：2009-01-30

申请人： Andre Franke ,  Lars Krueger ,  Christian Woehler

发明人： Andre Franke ,  Lars Krueger ,  Christian Woehler

IPC分类号： G05B19/4061

CPC分类号： G05B19/4061 ,  G05B2219/39098 ,  G05B2219/49137

摘要： In modern industrial robots which move at considerable speeds, collisions generally cause serious damage to the robots and the collision objects. This can lead to injuries and expensive production stoppages. In a method for collision-free interaction between a machine having mobile machine elements and objects in its vicinity, safety regions are established and monitored using the knowledge of the current position and the dynamic behavior. In particular, image data of the mobile machine element are recorded by means of an image acquisition system and are correlated with a database, which has been compiled in a training phase with image data of at least one mobile machine element. The database contains image data relating to a plurality of movement phases within the movement process of the machine. In the scope of correlating the currently recorded image data with this database, both the current position of the mobile machine element is ascertained and a future position, reachable within the stopping time, is estimated. The dynamic behavior of the machine in the event of collision risk is optimized on the basis of this estimation.

摘要翻译： 在以相当大的速度移动的现代工业机器人中，碰撞通常会对机器人和碰撞物体造成严重损害。 这可能导致人身伤害和昂贵的生产停产。 在具有移动机器元件的机器和其附近的物体之间的无碰撞交互的方法中，使用当前位置和动态行为的知识来建立和监视安全区域。 特别地，通过图像采集系统记录移动机器元件的图像数据，并将其与已经在训练阶段编译的数据库相关联，该数据库具有至少一个移动机器元件的图像数据。 数据库包含与机器运动过程中的多个移动阶段有关的图像数据。 在将当前记录的图像数据与该数据库相关联的范围中，确定移动机器元件的当前位置，并且估计在停止时间内可到达的未来位置。 在碰撞风险的情况下机器的动态特性在此估计的基础上得到优化。

公开(公告)号：US20100310154A1

公开(公告)日：2010-12-09

申请号：US12756611

申请日：2010-04-08

申请人： Bjoern Barrois ,  Lars Krueger ,  Christian Woehler

发明人： Bjoern Barrois ,  Lars Krueger ,  Christian Woehler

IPC分类号： G06K9/00

CPC分类号： G01B11/245 ,  G01C11/06 ,  G06K9/00214 ,  G06T7/30 ,  G06T7/593 ,  G06T2200/04

摘要： The invention relates to a method for matching an object model to a three-dimensional point cloud, wherein the point cloud is generated from two images by means of a stereo method and a clustering method is applied to the point cloud in order to identify points belonging to respectively one cluster, wherein model matching is subsequently carried out, with at least one object model being superposed on at least one cluster and an optimum position of the object model with respect to the cluster being determined, and wherein a correction of false assignments of points is carried out by means of the matched object model. A classifier, trained by means of at least one exemplary object, is used to generate an attention map from at least one of the images. A number and/or a location probability of at least one object, which is similar to the exemplary object, is determined in the image using the attention map, and the attention map is taken into account in the clustering method and/or in the model matching.

摘要翻译： 本发明涉及一种用于将对象模型与三维点云相匹配的方法，其中通过立体声方法从两个图像生成点云，并将聚类方法应用于点云，以便识别点属性 分配一个群，其中随后执行模型匹配，其中至少一个对象模型被叠加在至少一个群集上，并且所述对象模型相对于所述群集的最佳位置被确定，并且其中， 点通过匹配的对象模型进行。 通过至少一个示例性对象训练的分类器被用于从至少一个图像生成注意力图。 使用关注图在图像中确定与示例对象类似的至少一个对象的数量和/或位置概率，并且在聚类方法和/或模型中考虑关注图 匹配。

公开(公告)号：US09122266B2

公开(公告)日：2015-09-01

申请号：US12362733

申请日：2009-01-30

申请人： Andre Franke ,  Lars Krueger ,  Christian Woehler

发明人： Andre Franke ,  Lars Krueger ,  Christian Woehler

IPC分类号： G05B19/4061

CPC分类号： G05B19/4061 ,  G05B2219/39098 ,  G05B2219/49137

摘要： In a method for collision-free interaction between a machine having mobile machine elements and objects in its vicinity, safety regions are established and monitored using the knowledge of the current position and the dynamic behavior. In particular, image data of the mobile machine element are recorded by means of an image acquisition system and are correlated with a database compiled in a training phase with image data of at least one mobile machine element. The database contains image data relating to a plurality of movement phases within the movement process of the machine. Using the database, both the current position of the mobile machine element is ascertained and a future position, reachable within the stopping time, is estimated. The dynamic behavior of the machine in the event of collision risk is optimized on the basis of this estimation.

摘要翻译： 在具有移动机器元件的机器和其附近的物体之间的无碰撞交互的方法中，使用当前位置和动态行为的知识来建立和监视安全区域。 特别地，移动机器元件的图像数据通过图像采集系统被记录，并且与在至少一个移动机器元件的图像数据的训练阶段中编译的数据库相关。 数据库包含与机器运动过程中的多个移动阶段有关的图像数据。 使用数据库，确定移动机器元件的当前位置，并且估计在停止时间内可到达的未来位置。 在碰撞风险的情况下机器的动态特性在此估计的基础上得到优化。

公开(公告)号：US08379969B2

公开(公告)日：2013-02-19

申请号：US12756611

申请日：2010-04-08

申请人： Bjoern Barrois ,  Lars Krueger ,  Christian Woehler

发明人： Bjoern Barrois ,  Lars Krueger ,  Christian Woehler

IPC分类号： G06K9/00 ,  G06K9/34 ,  G06K9/62

CPC分类号： G01B11/245 ,  G01C11/06 ,  G06K9/00214 ,  G06T7/30 ,  G06T7/593 ,  G06T2200/04

摘要： The invention relates to a method for matching an object model to a three-dimensional point cloud, wherein the point cloud is generated from two images by means of a stereo method and a clustering method is applied to the point cloud in order to identify points belonging to respectively one cluster, wherein model matching is subsequently carried out, with at least one object model being superposed on at least one cluster and an optimum position of the object model with respect to the cluster being determined, and wherein a correction of false assignments of points is carried out by means of the matched object model. A classifier, trained by means of at least one exemplary object, is used to generate an attention map from at least one of the images. A number and/or a location probability of at least one object, which is similar to the exemplary object, is determined in the image using the attention map, and the attention map is taken into account in the clustering method and/or in the model matching.

摘要翻译： 本发明涉及一种用于将对象模型与三维点云相匹配的方法，其中通过立体声方法从两个图像生成点云，并将聚类方法应用于点云，以便识别点属性 分配一个群，其中随后执行模型匹配，其中至少一个对象模型被叠加在至少一个群集上，并且所述对象模型相对于所述群集的最佳位置被确定，并且其中， 点通过匹配的对象模型进行。 通过至少一个示例性对象训练的分类器被用于从至少一个图像生成注意力图。 使用关注图在图像中确定与示例对象类似的至少一个对象的数量和/或位置概率，并且在聚类方法和/或模型中考虑关注图 匹配。

公开(公告)号：US20090237499A1

公开(公告)日：2009-09-24

申请号：US12362745

申请日：2009-01-30

申请人： Ulrich Kressel ,  Lars Krueger ,  Werner Progscha ,  Christian Woehler ,  Franz Kummert ,  Joachim Schmidt ,  Rainer Ott

发明人： Ulrich Kressel ,  Lars Krueger ,  Werner Progscha ,  Christian Woehler ,  Franz Kummert ,  Joachim Schmidt ,  Rainer Ott

IPC分类号： H04N7/18

CPC分类号： F16P3/142 ,  G05B2219/40202 ,  G06K9/00201 ,  G06K9/00342

摘要： Manufacturing processes profit greatly from a close collaboration between human and machine. Whereas a human behaves flexibly and adaptively but is inclined to make mistakes during repetitive work operations, machines operate quickly and exactly but are static and not very flexible. In order to enable an improved hazard protection in the context of a safe human-machine interaction, a spatial- and time-dependent variable degree of hazard is allocated to monitored spatial areas as a function of the current position and the current movement state of a machine or a machine element, as well as of the observed person. For this purpose, a multicamera system is used to acquire image data of the person in order to obtain the most detailed information possible about the position and alignment of a person, in particular also with reference to the body parts thereof, in an industrial environment. These image data are then examined with regard to the imaging of a person so that whenever a person has been detected in the image data, an articulated virtual 3D model of the human body is matched to this person hypothesis. Subsequently, this virtual body model is continuously matched to the movement behavior of the person detected in the image data. A hazard potential is determined using knowledge of the position and the movement behavior of the virtual body model in space. The hazard potential thus determined is subjected to a threshold value comparison in order to act upon the movement control of the machine or the machine part in the event of this threshold value being exceeded.

摘要翻译： 制造流程从人与机器之间的密切合作中获益良多。 虽然人类的行为灵活自适，但倾向于在重复的作业过程中发生错误，机器运行速度快，但静止而且不是很灵活。 为了在安全的人机交互的背景下实现改进的危害保护，将空间和时间依赖的可变危险程度分配给监视的空间区域作为当前位置和当前运动状态的函数 机器或机器元件，以及观察者。 为此目的，使用多面体系统来获取人的图像数据，以便在工业环境中获得关于人的位置和排列的最详细信息，特别是参考其身体部分。 然后，关于人的成像检查这些图像数据，使得每当在图像数据中检测到人时，将人体的关节虚拟3D模型与该人假设相匹配。 随后，该虚拟身体模型与图像数据中检测到的人的运动行为连续匹配。 使用空间中的虚拟身体模型的位置和运动行为的知识来确定危险潜力。 如此确定的危险潜力经受阈值比较，以便在超过该阈值的情况下对机器或机器部件的移动控制起作用。

公开(公告)号：US20080004356A1

公开(公告)日：2008-01-03

申请号：US11701007

申请日：2007-02-01

申请人： Christoph Gurtler ,  Paula Rodrigues ,  Arno Nennemann ,  Lars Krueger

发明人： Christoph Gurtler ,  Paula Rodrigues ,  Arno Nennemann ,  Lars Krueger

IPC分类号： B01F3/08

CPC分类号： C01G39/00 ,  B82Y30/00 ,  C01D3/04 ,  C01P2004/62 ,  C01P2004/64

摘要： The present invention relates to innovative nanoparticles, to a process for preparing nanoparticles by recrystallization, and to the use thereof.

摘要翻译： 本发明涉及创新的纳米颗粒，涉及通过重结晶制备纳米颗粒的方法及其应用。

公开(公告)号：US20110237717A1

公开(公告)日：2011-09-29

申请号：US12943047

申请日：2010-11-10

申请人： Matthias Soddemann ,  Daniel Gordon Duff ,  Lars Krueger ,  Sigrun Stein

发明人： Matthias Soddemann ,  Daniel Gordon Duff ,  Lars Krueger ,  Sigrun Stein

IPC分类号： C08L33/20 ,  C08K5/07 ,  C08K5/1535 ,  C08K3/10 ,  C08K5/16 ,  C08K5/17 ,  C08L61/12

CPC分类号： C08L9/02 ,  C08J3/07 ,  C08J2309/04 ,  C08J2313/02 ,  C08J2315/00 ,  C08L9/04 ,  C09D109/04 ,  C09D133/18

摘要： Novel stable aqueous suspensions of a functionalized, completely or partially hydrogenated nitrite rubber are provided with very low emulsifier content and small particle diameter, furtheron a process for production thereof and the use thereof for producing composite materials via coating of substrate materials with the suspension.

摘要翻译： 功能化，完全或部分氢化的亚硝酸盐橡胶的新型稳定的水性悬浮液具有非常低的乳化剂含量和小的颗粒直径，还有其制备方法及其用于通过用悬浮液涂覆基材的方法制备复合材料的用途。