-
公开(公告)号：EP1339017A1
公开(公告)日：2003-08-27
申请号：EP01981087.8
申请日：2001-11-13
CPC分类号： G06K9/00127 , G06T7/0012 , G06T7/246 , G06T2200/04 , G06T2207/10016 , G06T2207/10056 , G06T2207/30024
摘要： A cell lineage can be constructed in a less labor intensive manner and in less time by using a computer. Areas, which are misidentified as nuclei, are efficiently removed. The invention comprises the steps of: selecting one or more nuclei for making a forward link from extracted nucleus candidates, in a plurality of 4D microscopic images in which the nucleus candidates are extracted; obtaining forward linkage information by sequentially extracting a nucleus candidate that meets a predetermined link condition with regard to the selected one or more nuclei from said 4D images; selecting one or more nuclei for making a reverse link from the forward linkage information; and obtaining backward linkage information by sequentially extracting a nucleus candidate that meets a predetermined link condition with regard to the selected one or more nuclei for backward link from said 4D images, removing misidentified nucleus candidates from the forward link information based on the reverse link information. The cell lineage is constructed simultaneously at the time of obtaining the forward link information and reverse link information.
-
公开(公告)号：EP1223547B1
公开(公告)日：2006-05-10
申请号：EP00940777.6
申请日：2000-06-21
CPC分类号： G06N3/126
摘要： A network structure (topology) capable of reproducing a target profile is produced and a topology pool (300) is produced (S102). A parameter capable of best reproducing a target profile is determined for each produced network structure, and the errors are calculated (S104). Triplets being combinations of the topologies, the parameters, and errors are stored in a triplet pool (400). These operations are carried out at a sampling step. The triplets in the triplet pool (400) are screened to select triplets conforming to the object. For the screening, for example, mutation analysis is used. These operations are carried out at a screening step. (S106). Upon completion of the screening step, a candidate triplet pool (500) is produced.
-
公开(公告)号：EP1375084A1
公开(公告)日：2004-01-02
申请号：EP02702847.1
申请日：2002-03-08
CPC分类号： G06T1/0014 , B25J13/00 , B25J13/003 , B25J19/023 , G10L2021/02087
摘要： A robot visuoauditory system that makes it possible to process data in real time to track vision and audition for an object, that can integrate visual and auditory information on an object to permit the object to be kept tracked without fail and that makes it possible to process the information in real time to keep tracking the object both visually and auditorily and visualize the real-time processing is disclosed. In the system, the audition module (20) in response to sound signals from microphones extracts pitches therefrom, separate their sound sources from each other and locate sound sources such as to identify a sound source as at least one speaker, thereby extracting an auditory event (28) for each object speaker. The vision module (30) on the basis of an image taken by a camera identifies by face, and locate, each such speaker, thereby extracting a visual event (39) therefor. The motor control module (40) for turning the robot horizontally extracts a motor event (49) from a rotary position of the motor. The association module (60) for controlling these modules forms from the auditory , visual and motor control events an auditory stream (65) and a visual stream (66) and then associates these streams with each other to form an association stream (67). The attention control module (6) effects attention control designed to make a plan of the course in which to control the drive motor, e. g., upon locating the sound source for the auditory event and locating the face for the visual event, thereby determining the direction in which each speaker lies. The system also includes a display (27, 37, 48, 68) for displaying at least a portion of auditory, visual and motor information. The attention control module (64) servo-controls the robot on the basis of the association stream or streams.
摘要翻译： 机器人视觉系统，使得可以实时处理数据以跟踪对象的视觉和试镜，从而可以将物体上的视觉和听觉信息集成在一起，以允许对象被保持跟踪，并且使得可以处理 公开了实时的信息，以视觉和听觉方式跟踪对象，并且可视化实时处理。 在系统中，响应于来自麦克风的声音信号的试听模块（20）从中提取音高，从而将它们的声源彼此分开，并且定位声源，例如将声源识别为至少一个扬声器，从而提取听觉事件 （28）。 基于由照相机拍摄的图像的视觉模块（30）通过面部识别并定位每个这样的扬声器，由此提取其视觉事件（39）。 用于转动机器人的马达控制模块（40）从马达的旋转位置水平地提取马达事件（49）。 用于控制这些模块的关联模块（60）从听觉，视觉和运动控制事件形成听觉流（65）和视觉流（66），然后将这些流彼此关联以形成关联流（67）。 注意力控制模块（6）实现设计的注意力控制，以制定控制驱动电机的过程的计划，例如， 例如，在定位用于听觉事件的声源并且定位用于视觉事件的面部，从而确定每个扬声器所在的方向。 该系统还包括用于显示听觉，视觉和运动信息的至少一部分的显示器（27,37,48,68）。 注意力控制模块（64）基于关联流或流来对机器人进行伺服控制。
-
4.发明公开ENTROPY FILTER, AND AREA EXTRACTING METHOD USING THE FILTER 审中-公开GETRIETS EXTRAKTIONS EXFAHREN MIT DEM过滤器
公开(公告)号：EP1339020A1
公开(公告)日：2003-08-27
申请号：EP01982768.2
申请日：2001-11-13
IPC分类号： G06T7/00
CPC分类号： G06T5/20 , G06T7/11 , G06T7/136 , G06T7/143 , G06T2207/10056 , G06T2207/30024
摘要： A smooth portion is efficiently extracted from an image. There is provided an entropy filter in which a noted pixel (x, y) is determined in an original image, said image is partitioned by a window of size (width, height) = (A, B) from the noted pixel, entropy of the partitioned window is calculated, and obtained entropy value is saved on the coordinates (x, y) of a resulting image. Here, in a noted pixel (x, y), x is ranged from 0 to (an image width minus a window width) and y is ranged from 0 to (an image height minus a window height). By using an entropy filter, a smooth portion in image quality is extracted from an original image. A preferred example of the smooth portion is a cell nucleus.
摘要翻译： 从图像中有效地提取平滑部分。 提供了一种熵滤波器，其中在原始图像中确定注意的像素（x，y），所述图像由所述像素的尺寸（宽度，高度）=（A，B）的窗口划分， 计算分割窗口，得到的熵值被保存在得到的图像的坐标（x，y）上。 这里，在所记录的像素（x，y）中，x为0〜（图像宽度减去窗口宽度），y为0〜（图像高度减去窗口高度）。 通过使用熵滤波器，从原始图像中提取图像质量的平滑部分。 平滑部分的优选实例是细胞核。
-
公开(公告)号：EP1267305A1
公开(公告)日：2002-12-18
申请号：EP00979080.9
申请日：2000-12-04
CPC分类号： G06K9/0014 , G01N33/5005 , G06T7/11 , G06T2200/04 , G06T2207/10016 , G06T2207/10056 , G06T2207/30024
摘要： The present invention provides a method for constructing cell lineage that is less labor intensive and requires less time as a result of using a computer. The method comprises the step for obtaining a plurality of 2D images different in focal plane and a time by taking a plurality of the 2D images by changing the focal plane and taking a plurality of the 2D images in a time series for a cell constituting the subject of observation. The method further comprises the steps of extracting a nucleus area by carrying out image processing for individual 2D images; unifying the nucleus area, which is derived from the identical nucleus, from the nucleus area extracted from the individual 2D images; and constructing the cell lineage from a time and a position, where the nucleus area appears and disappears in the image, in the unified nucleus area.
摘要翻译： 本发明提供了一种构建细胞谱系的方法，该方法由于使用计算机而耗费较少的劳动密集度并且需要更少的时间。 该方法包括以下步骤：通过改变焦平面并以构成该对象的单元的时间序列取多个2D图像来获取焦平面和时间上不同的多个2D图像的步骤 的观察。 该方法还包括以下步骤：通过对各个2D图像执行图像处理来提取核区域; 将从相同的核导出的核区域从从各个2D图像提取的核区域统一起来; 并且在统一的核区域中，从图像中的核区域出现并消失的时间和位置构建细胞谱系。
-
公开(公告)号：EP1248231A1
公开(公告)日：2002-10-09
申请号：EP00985897.8
申请日：2000-12-26
发明人： MOROHASHI, Mineo , KITANO, Hiroaki
摘要： The present invention provides a method for predicting a topology stepwise by producing candidate networks that can reproduce a given data profile, evaluating these candidate networks, and predicting a network structure and parameters that can provide the data profile. According to the present invention, a regulatory network for a gene that may induce a certain phenomenon or a metabolic network indicating enzyme and protein reactions can be predicted based on gene expression or protein concentration data.
摘要翻译： 本发明提供了一种用于通过产生可以再现给定数据简档的候选网络来逐步预测拓扑，评估这些候选网络以及预测可以提供数据简档的网络结构和参数的方法。 根据本发明，可以基于基因表达或蛋白质浓度数据来预测可以诱导特定现象的基因或指示酶和蛋白质反应的代谢网络的调节网络。
-
公开(公告)号：EP1306832A1
公开(公告)日：2003-05-02
申请号：EP01936921.4
申请日：2001-06-08
CPC分类号： G10L21/0208 , G10L2021/02165
摘要： A robot auditory apparatus and system are disclosed which are made capable of attaining active perception upon collecting a sound from an external target with no influence received from noises generated interior of the robot such as those emitted from the robot driving elements. The apparatus and system are for a robot having a noise generating source in its interior, and include: a sound insulating cladding (14) with which at least a portion of the robot is covered; at least two outer microphones (16 and 16) disposed outside of the cladding (14) for collecting an external sound primarily; at least one inner microphone (17) disposed inside of the cladding (14) for primarily collecting noises from the noise generating source in the robot interior; a processing section (23, 24) responsive to signals from the outer and inner microphones (16 and 16; and 17) for canceling from respective sound signals from the outer microphones (16 and 16), noises signal from the interior noise generating source and then issuing a left and a right sound signal; and a directional information extracting section (27) responsive to the left and light sound signals from the processing section (23, 24) for determining the direction from which the external sound is emitted. The processing section (23, 24) is adapted to detect burst noises owing to the noise generating source from a signal from the at least one inner microphone (17) for removing signal portions from the sound signals for bands containing the burst noises.
摘要翻译： 公开了一种机器人听觉装置和系统，其能够在从机器人驱动元件发射的那些从机器人内部产生的噪声不受任何影响的情况下从外部目标收集声音时获得主动感知。 该装置和系统用于在其内部具有噪声产生源的机器人，并且包括：覆盖机器人的至少一部分的隔音覆层（14）; 至少两个外部麦克风（16和16），其设置在所述包层（14）的外部，用于主要收集外部声音; 设置在所述包层（14）内部的至少一个内部麦克风（17），用于在所述机器人内部主要收集噪声产生源的噪声; 响应于来自外部麦克风（16和16）和17的信号的来自外部麦克风（16和16）的相应声音信号的来自内部噪声产生源的噪声信号的处理部分（23,24）和 然后发出左右声音信号; 以及响应于来自处理部分（23,24）的左声音信号和光声信号的方向信息提取部分（27），用于确定外部声音发射的方向。 处理部分（23,24）适于从来自至少一个内部麦克风（17）的信号中检测由于噪声发生源引起的突发噪声，用于从包含脉冲串噪声的波段的声音信号中去除信号部分。
-
8.发明公开APPARATUS WALKING WITH TWO LEGS; WALKING CONTROL APPARATUS; AND WALKING CONTROL METHOD THEREOF 有权两条腿行走装置; GEHST您的装置及方法您GEHST
公开(公告)号：EP1393866A1
公开(公告)日：2004-03-03
申请号：EP02730871.7
申请日：2002-06-03
发明人： FURUTA, Takayuki , TOMIYAMA, Ken , KITANO, Hiroaki
IPC分类号： B25J5/00
CPC分类号： B62D57/032
摘要： Disclosed is a biped walking mobile system or apparatus, typically a biped walking robot, which achieves walk stability without altering a preestablished gait, namely path of movement for each of joint region, as well as a walk controller and a work control method therefor. The biped walking mobile apparatus, advantageously made as a humanoid robot with an upper body (11) as its main body having its head and a pair of hands, has in its lower part a pair of leg portions (13L, 13R) attached thereto so as to be each pivotally movable biaxially, each of the leg portions having a knee portion (12L, 12R) in its midway and a foot portion (14L, 14R) at its lower end, the foot portions being attached to its corresponding leg portion so as to be pivotally movable biaxially, and includes drive means associated with the leg, knee and foot portions for pivotally moving them, respectively, a gait former 8249 for forming gait data including data for a target angular path, data for a targeted angular velocity and data for a targeted angular acceleration, and a walk controller (30) for controlling respective driving actions of the drive means on the basis of the gait data, the walk controller including a ZMP compensator (32), the ZMP compensator including: a ZMP sensor (23L, 23R) for detecting ZMP for each the feet portions (14L, 14R), a ZMP converter (35) for computing a ZMP target value on the basis of the gait data from the gait former, and a ZMP compensating stage (36) for comparing the actual measurement value of ZMP detected by the ZMP sensor with the ZMP target value from the ZMP converter to modify the targeted angular velocity and acceleration in the gait data from the gait former and thereby to compensate or correct the ZMP target value. Thus, with the targeted angular path of movement in the gait data which remains unaltered when the ZMP target value is compensated, no case is there that the paths of movement of various parts of the mobile apparatus or robot such as its main body or legs come off those preestablished in the gait data Accordingly, even in case, e. g., a the biped mobile apparatus has its free foot landing positions unalterable such as in stepping-stones, or an obstacle needed to be stepped over or passed under, it an achieve walk control with certainty.
摘要翻译： 公开了一种双足步行移动系统或装置，通常，双足步行机器人，这实现步行稳定性而不改变预先建立的步态，运动的每一个接合区域即路径，以及散步控制器和用于其的工作控制方法。 的双足步行移动装置，有利地制成具有在上部主体（11）作为其主体具有其头部和一双手的人形机器人，已经在其下部连接到其上，从而一对腿部分（13L，13R）的 为能够各自枢转地移动双轴，每一个都具有在其中途膝盖部分（12L，12R），并在其下端的底座部分（14L，14R）的腿部，放脚部分被附接至其对应的部分，从而 以能够枢转地移动双轴，并且包括驱动装置与腿，膝盖和脚部分相关联的用于枢转地移动它们分别是步态前8249用于为目标角路径形成步态数据包括数据，用于目标角速度数据和 步态数据的基础上，对目标角加速度，和散步控制器（30），用于控制驱动器的respectivement驱动动作的数据的手段，所述的步行控制装置包括一个ZMP补偿器（32）时，ZMP补偿器包括：一个ZMP传感器 （2 3L，23R），用于检测ZMP为各支脚部分（14L，14R），一ZMP转换器（35），用于计算从所述步态前步态数据的基础上的ZMP目标值，和一个ZMP补偿级（36） 用于比较由ZMP传感器与来自ZMP变换器的ZMP目标值从步态前者并由此来补偿或校正ZMP目标值修改在步态数据目标角速度和加速度检测ZMP的实际测量值。 因此，与当ZMP目标值补偿哪个保持不变在步态数据移动的目标角度路径，任何情况下，是在那里的移动装置或机器人的各个部分的移动路径做：例如它的主体或腿过来 那些在相应的步态数据预先建立关，即使在的情况下，即 。克，一两足动物移动设备都有其自由脚落地的位置：如垫脚石不可改变的，或者需要被跨过或下穿过障碍，它实现步行controlwith确定性。
-
公开(公告)号：EP1223547A1
公开(公告)日：2002-07-17
申请号：EP00940777.6
申请日：2000-06-21
IPC分类号： G06N3/00
CPC分类号： G06N3/126
摘要： Topology pool 300 is produced by generating network structures (topologies) potentially being able to reproduce a target profile (S102). Best parameters to be able to reproduce the target profile are determined for the respective generated network structures, and the margin of error thereof is calculated (S104). Triplets that have been combined from the parameters and the margin of error for the topologies are stored in triplet pool 400. Up to this point is the sampling stage and from this point is the stage where the triplets in triplet pool 400 adapted to the objective are screened; mutation data, for example, is used for this screening (S106). Candidate triplet pool 500 is achieved once the screening stage has ended.
摘要翻译： 通过生成潜在地能够再现目标简档的网络结构（拓扑）来产生拓扑池300（S102）。 对于各个生成的网络结构确定能够再现目标简档的最佳参数，并且计算其误差余量（S104）。 从参数和拓扑的误差边界组合的三重态存储在三元组池400中。到此为止，是采样阶段，从这一点来看，三联池400中适用于目标的三元组是 筛选; 突变数据例如用于该筛选（S106）。 一旦筛选阶段结束，就可以实现候选三联池500。
-
10.发明公开METHOD AND APPARATUS FOR DETERMINING SOUND SOURCE 有权VERFAHREN UNDGERÄTZUR BESTIMMUNG EINER TONQUELLE
公开(公告)号：EP1205762A1
公开(公告)日：2002-05-15
申请号：EP00935570.2
申请日：2000-06-07
摘要： Provided in accordance with the invention are a sound source identifying apparatus and method whereby objects as sound sources can be determined as to their locations with higher accuracy by using sound information and image information thereof and are separated from mixed sounds with certainty by using position information thereof. The sound source identifying apparatus (10) is constructed to include a sound collecting means (11) for capturing sounds from a plurality of sound sources (A, B, C)with a pair of sound collecting microphones (11a, 11b) juxtaposed with each other across a preselected spacing D and opposed to the sound sources (A, B, C) and for processing the captured sounds; an imaging means (12) for consecutively imaging the sound sources (A, B, C); a sensing means for sensing objects; an image processing means (13) for deriving information as to locations of the objects possibly being the sound sources, from either or both of image pictures imaged by the imaging means (12) and directional information of the objects sensed by the sensing means; a sound processing means (14) for localizing the locations of the sound sources based on sound information of the sounds captured by the sound collecting means (11) and position information derived by the image processing means (13); and a control means (15) for controlling operations of the sound collecting means (11), the imaging means (12), the sensing means, the image processing means (13), and the sound processing means (14).
摘要翻译： 根据本发明提供的是一种声源识别装置和方法，通过使用声音信息及其图像信息，可以通过使用声音信息及其图像信息，通过使用其位置信息来确定地与混合声音分离，从而可以以更高的精确度来确定作为声源的对象作为声源 。 声源识别装置（10）被构造成包括用于从多个声源（A，B，C）捕获声音的声音收集装置（11），其中一对收集话筒（11a，11b）与每个声源 另一个在预选间距D上并与声源（A，B，C）相对并且用于处理所捕获的声音; 用于对声源（A，B，C）连续成像的成像装置（12）; 用于感测物体的感测装置; 用于从由成像装置（12）成像的图像图像中的一个或两个以及由感测装置感测的物体的方向信息，导出关于可能是声源的物体的位置的信息的图像处理装置（13） 声音处理装置（14），用于基于由声音采集装置（11）捕获的声音的声音信息和由图像处理装置（13）导出的位置信息来定位声源的位置; 以及用于控制声音收集装置（11），成像装置（12），感测装置，图像处理装置（13）和声音处理装置（14）的操作的控制装置（15）。
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.02 秒)
