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. 发明授权

US09025071B2 Method for contamination detection in a TOF range camera 有权
标题翻译： TOF范围摄像机污染检测方法
公开(公告)号：US09025071B2
公开(公告)日：2015-05-05
申请号：US12664025
申请日：2008-06-12
申请人： Bruno Mirbach , Romuald Ginhoux
发明人： Bruno Mirbach , Romuald Ginhoux
IPC分类号： H04N5/232 , G01S7/497 , G01S17/89 , H04N5/222
CPC分类号： H04N5/232 , G01S7/497 , G01S17/89 , G01S2007/4975 , H04N5/2226
摘要： A method for contamination detection in a time-of-flight (TOF) range imaging system is described, wherein the TOF range imaging system receives light reflected from a scene, through an optical interface, on an imager sensor having an array of pixels, and wherein distance information and amplitude information are determined for the sensor pixels. The presence of contamination on the optical interface is determined on the basis of amplitude information determined for the sensor pixels.
摘要翻译：描述了飞行时间（TOF）范围成像系统中的污染检测方法，其中TOF范围成像系统通过光学接口在具有像素阵列的成像器传感器上接收从场景反射的光，以及其中为传感器像素确定距离信息和幅度信息。基于为传感器像素确定的振幅信息来确定光学接口上的污染的存在。

2. 发明申请

US20110018967A1 RECORDING OF 3D IMAGES OF A SCENE 有权
标题翻译：记录场景三维图像
公开(公告)号：US20110018967A1
公开(公告)日：2011-01-27
申请号：US12747377
申请日：2008-12-09
申请人： Bruno Mirbach , Marta Castillo Franco , Thomas Solignac , Frederic Grandidier
发明人： Bruno Mirbach , Marta Castillo Franco , Thomas Solignac , Frederic Grandidier
IPC分类号： H04N13/02
CPC分类号： H04N13/106 , G01S7/497 , G01S17/36 , G01S17/89 , H04N2213/003
摘要： A method of recording 3D images of a scene based on the time-of-flight principle comprises illuminating a scene by emitting light carrying an intensity modulation, imaging the scene onto a pixel array using an optical system, detecting, in each pixel, intensity-modulated light reflected from the scene onto the pixel and determining, for each pixel, a distance value based on the phase of light detected in the pixel. The determination of the distance values comprises a phase-sensitive de-convolution of the scene imaged onto the pixel array such that phase errors induced by light spreading in the optical system are compensated for.
摘要翻译：基于飞行时间原理记录场景的3D图像的方法包括通过发射携带强度调制的光来照亮场景，使用光学系统将场景成像到像素阵列上，在每个像素中检测强度 - 将从场景反射的调制光调制到像素上，并针对每个像素确定基于在像素中检测到的光的相位的距离值。距离值的确定包括成像到像素阵列上的场景的相敏解卷积，以便补偿由光学系统中的光扩展引起的相位误差。

3. 发明申请

US20060220910A1 Parking aid for a vehicle 审中-公开
标题翻译：停车辅助车辆
公开(公告)号：US20060220910A1
公开(公告)日：2006-10-05
申请号：US10552788
申请日：2004-04-08
申请人： Guido Becker , Marta Castillo Franco , Bruno Mirbach , Thierry Mousel , Marc Schifflers
发明人： Guido Becker , Marta Castillo Franco , Bruno Mirbach , Thierry Mousel , Marc Schifflers
IPC分类号： G01S17/89 , G08G1/14
CPC分类号： G01S17/936 , B60Q9/006 , B60T2201/10 , G01S17/89 , G01S2015/934 , G01S2015/935 , G06K9/00805 , G06K9/00812
摘要： A method for providing parking aid for a vehicle, comprises the steps recording ambient data in the external area of a vehicle, calculation of the dimensions of a specific area using the recorded ambient data, and evaluation of the suitability of the specific area as a parking space taking into account the calculated dimensions and known, vehicle-specific reference values. According to the invention, the recording of ambient data comprises recording three-dimensional images of the surroundings by means of an optical 3-D system.
摘要翻译：一种用于为车辆提供停车辅助的方法，包括在车辆的外部区域记录环境数据的步骤，使用所记录的环境数据计算特定区域的尺寸，以及评估特定区域作为停车场的适用性考虑到计算的尺寸和已知的车辆特定参考值的空间。根据本发明，环境数据的记录包括通过光学3D-D系统记录周围环境的三维图像。

4. 发明授权

US09025862B2 Range image pixel matching method 有权
标题翻译：范围图像像素匹配方法
公开(公告)号：US09025862B2
公开(公告)日：2015-05-05
申请号：US13879563
申请日：2011-10-07
申请人： Frederic Garcia Becerro , Bruno Mirbach
发明人： Frederic Garcia Becerro , Bruno Mirbach
IPC分类号： G06K9/00 , G06T15/00 , G06T7/00
CPC分类号： G06T15/00 , G06T7/30 , G06T2207/10028
摘要： A method for matching the pixels (10-1, 10-2) of a first range image of a scene (18) as seen from a first point of sight (14) with pixels (12-1, 12-2) of a second range image of the scene as seen from a second point of sight (16) comprises the following steps: providing the first range image as a grid of source pixels (10), on which the scene is mapped in accordance with a first projection associated with the first point of sight, wherein each source pixel has a point in the scene projected thereon in accordance with the first projection and has associated therewith a range value determined for that point in the scene; providing a grid of target pixels (12) for the second range image and a second projection associated with the second point of sight; and for each one of the target pixels, a) determining which source pixel would have the same point (P1, P2) in the scene projected thereon in accordance with the first projection as the target pixel would have projected thereon in accordance with the second projection if the imaged scene were a planar surface at a certain surface distance from the first point of sight; b) determining a depth coordinate of the point in the scene that the source pixel determined in step a) actually has projected thereon in accordance with the first projection; c) if the depth coordinate is greater than a threshold, which is itself greater than the surface distance, repeating steps a), b) and c) with an increased surface distance at step a) and an increased threshold at step c), and else associating the target pixel with the source pixel determined in step a).
摘要翻译：一种用于将从第一视点（14）观看的场景（18）的第一范围图像的像素（10-1,10-2）与像素（12-1,12-2）匹配的方法，从第二视点（16）观察的场景的第二范围图像包括以下步骤：将第一范围图像提供为源像素的网格，其上根据第一投影相关联地映射场景具有第一视点，其中每个源像素具有根据第一投影在其上投影的场景中的点，并且具有与其相关联地为该场景中的该点确定的范围值; 提供用于所述第二范围图像的目标像素（12）的网格和与所述第二视点相关联的第二投影; 并且对于目标像素中的每一个，a）根据第一投影确定在投影到其上的场景中哪个源像素将具有相同的点（P1，P2），因为目标像素将根据第二投影如果成像的场景是距离第一视点的某一表面距离处的平坦表面; b）根据第一投影确定在步骤a）中确定的源像素实际上已在其上投影的场景中的点的深度坐标; c）如果深度坐标大于其本身大于表面距离的阈值，则重复步骤a），b）和c），步骤a）处的表面距离增加，并且在步骤c）增加阈值，以及否则将目标像素与在步骤a）中确定的源像素相关联。

5. 发明授权

US08346684B2 Pattern classification method 有权
标题翻译：模式分类方法
公开(公告)号：US08346684B2
公开(公告)日：2013-01-01
申请号：US12374076
申请日：2007-07-17
申请人： Bruno Mirbach , Pandu Devarakota
发明人： Bruno Mirbach , Pandu Devarakota
IPC分类号： G06F15/18
CPC分类号： G06K9/6273 , G06K9/6262
摘要： For assigning a test pattern to a class chosen from a predefined set of classes, the class membership probability for the test pattern is calculated as well as the confidence interval for the class membership probability based upon a number of training patterns in a neighborhood of the test pattern in the feature space. The number of training patterns in the neighborhood of the test pattern is obtained from computing a convolution of a density function of the training patterns with a Gaussian smoothing function centered on the test pattern, where the density function of the training patterns is represented as a mixture of Gaussian functions. The convolution of the smoothing function and the mixture of Gaussian functions can be expressed analytically.
摘要翻译：为了将测试模式分配给从预定义的一组类中选择的类，测试模式的类成员概率以及基于测试邻域中的训练模式数量的类成员概率的置信区间进行计算特征空间中的图案。通过计算训练模式的密度函数的卷积与以测试模式为中心的高斯平滑函数获得测试模式附近的训练模式的数量，其中训练模式的密度函数被表示为混合的高斯函数。平滑函数的卷积和高斯函数的混合可以分析地表达。

6. 发明申请

US20120229646A1 REAL-TIME DYNAMIC REFERENCE IMAGE GENERATION FOR RANGE IMAGING SYSTEM 有权
标题翻译：实时动态成像系统的动态参考图像生成
公开(公告)号：US20120229646A1
公开(公告)日：2012-09-13
申请号：US13497100
申请日：2010-09-16
申请人： Frédéric Grandidier , Bruno Mirbach , Thomas Solignac
发明人： Frédéric Grandidier , Bruno Mirbach , Thomas Solignac
IPC分类号： H04N5/232 , H04N7/18
CPC分类号： G06K9/00201 , G06K9/00771 , G06K2209/015 , G06T7/254 , G06T2207/10028 , G06T2207/30236
摘要： A dynamic reference range image generation method comprises providing a reference range image, to be dynamically updated, composed of pixels, each of which contains a reference range value. An acquired range image is provided, the pixels of which contain each a measured range value, the measured range values being updated at a predetermined rate. Pixels of the acquired range image containing an invalid measured range value are accordingly marked. The measured range value of each pixel of the acquired range image not marked as containing an invalid measured range value is compared with the reference range value of the corresponding pixel of the reference range image. The reference range value of that pixel of the reference range image is updated e.g. to the measured range value or to an average of the measured range value and one or more prior measured range values if a) the measured range value is considered less than the reference range value and has remained substantially constant for a first time period, or if b) the measured range value is considered greater than the reference range value and has remained substantially constant for a second time period smaller than the first time period. If neither of conditions a) and b) is fulfilled, the reference range value is kept substantially constant instead.
摘要翻译：动态参考范围图像生成方法包括提供要被动态更新的，由像素组成的参考范围图像，每个像素包含参考范围值。提供获取的范围图像，其像素包含每个测量范围值，测量的范围值以预定速率更新。相应地标记包含无效测量范围值的所获取范围图像的像素。将未被标记为包含无效测量范围值的所获取的范围图像的每个像素的测量范围值与参考范围图像的对应像素的参考范围值进行比较。参考范围图像的该像素的参考范围值被更新。如果a）测量的范围值被认为小于参考范围值并且在第一时间段内保持基本上恒定，或者如果在一个或多个测量范围值中， b）测量的范围值被认为大于参考范围值，并且在小于第一时间段的第二时间段内保持基本上恒定。如果条件a）和b）都不满足，则参考范围值保持基本上不变。

7. 发明申请

US20090319451A1 PATTERN CLASSIFICATION METHOD 有权
标题翻译：模式分类方法
公开(公告)号：US20090319451A1
公开(公告)日：2009-12-24
申请号：US12374076
申请日：2007-07-17
申请人： Bruno Mirbach , Pandu Devarakota
发明人： Bruno Mirbach , Pandu Devarakota
IPC分类号： G06F15/18 , G06N5/04 , G06N7/04
CPC分类号： G06K9/6273 , G06K9/6262
摘要： For assigning a test pattern to a class chosen from a predefined set of classes, the class membership probability for the test pattern is calculated as well as the confidence interval for the class membership probability based upon a number of training patterns in a neighbourhood of the test pattern in the feature space. The number of training patterns in the neighbourhood of the test pattern is obtained from computing a convolution of a density function of the training patterns with a Gaussian smoothing function centred on the test pattern, where the density function of the training patterns is represented as a mixture of Gaussian functions. The convolution of the smoothing function and the mixture of Gaussian functions can be expressed analytically.
摘要翻译：为了将测试模式分配给从预定义的一组类中选择的类，测试模式的类成员概率以及基于测试邻域中的训练模式数量的类成员概率的置信区间进行计算特征空间中的图案。通过计算训练模式的密度函数的卷积与以测试模式为中心的高斯平滑函数获得测试模式附近的训练模式的数量，其中训练模式的密度函数被表示为混合的高斯函数。平滑函数的卷积和高斯函数的混合可以分析地表达。

8. 发明授权

US10795006B2 3D time-of-flight camera system and position/orientation calibration method therefor 有权
公开(公告)号：US10795006B2
公开(公告)日：2020-10-06
申请号：US13058962
申请日：2009-04-27
申请人： Frederic Garcia , Frederic Grandidier , Bruno Mirbach , Roberto Orsello , Thomas Solignac
发明人： Frederic Garcia , Frederic Grandidier , Bruno Mirbach , Roberto Orsello , Thomas Solignac
IPC分类号： G01S7/497 , G01S17/89 , G01S17/08 , G06T7/80
摘要： A camera system comprises a 3D TOF camera for acquiring a camera-perspective range image of a scene and an image processor for processing the range image. The image processor contains a position and orientation calibration routine implemented therein in hardware and/or software, which position and orientation calibration routine, when executed by the image processor, detects one or more planes within a range image acquired by the 3D TOF camera, selects a reference plane among the at least one or more planes detected and computes position and orientation parameters of the 3D TOF camera with respect to the reference plane, such as, e.g., elevation above the reference plane and/or camera roll angle and/or camera pitch angle.

9. 发明授权

US09400917B2 Real-time dynamic reference image generation for range imaging system 有权
标题翻译：范围成像系统的实时动态参考图像生成
公开(公告)号：US09400917B2
公开(公告)日：2016-07-26
申请号：US13497100
申请日：2010-09-16
申请人： Frédéric Grandidier , Bruno Mirbach , Thomas Solignac
发明人： Frédéric Grandidier , Bruno Mirbach , Thomas Solignac
IPC分类号： H04N7/18 , H04N5/232 , G06K9/00 , G06T7/20
CPC分类号： G06K9/00201 , G06K9/00771 , G06K2209/015 , G06T7/254 , G06T2207/10028 , G06T2207/30236
摘要： A dynamic reference range image generation method comprises providing a reference range image, to be dynamically updated, composed of pixels, each of which contains a reference range value. An acquired range image is provided, the pixels of which contain each a measured range value, the measured range values being updated at a predetermined rate. Pixels of the acquired range image containing an invalid measured range value are accordingly marked. The measured range value of each pixel of the acquired range image not marked as containing an invalid measured range value is compared with the reference range value of the corresponding pixel of the reference range image. The reference range value of that pixel of the reference range image is updated e.g. to the measured range value or to an average of the measured range value and one or more prior measured range values if a) the measured range value is considered less than the reference range value and has remained substantially constant for a first time period, or if b) the measured range value is considered greater than the reference range value and has remained substantially constant for a second time period smaller than the first time period. If neither of conditions a) and b) is fulfilled, the reference range value is kept substantially constant instead.
摘要翻译：动态参考范围图像生成方法包括提供要被动态更新的，由像素组成的参考范围图像，每个像素包含参考范围值。提供获取的范围图像，其像素包含每个测量范围值，测量的范围值以预定速率更新。相应地标记包含无效测量范围值的所获取范围图像的像素。将未被标记为包含无效测量范围值的所获取的范围图像的每个像素的测量范围值与参考范围图像的对应像素的参考范围值进行比较。参考范围图像的该像素的参考范围值被更新。如果a）测量的范围值被认为小于参考范围值并且在第一时间段内保持基本上恒定，或者如果在一个或多个测量范围值中， b）测量的范围值被认为大于参考范围值，并且在小于第一时间段的第二时间段内保持基本上恒定。如果条件a）和b）都不满足，则参考范围值保持基本恒定。

10. 发明授权

US08396251B2 Method for determining the position of an object from a digital image 有权
标题翻译：用于从数字图像确定对象的位置的方法
公开(公告)号：US08396251B2
公开(公告)日：2013-03-12
申请号：US11720473
申请日：2005-11-28
申请人： Bruno Mirbach , Marta Castillo Franco , Romuald Ginhoux
发明人： Bruno Mirbach , Marta Castillo Franco , Romuald Ginhoux
IPC分类号： G06K9/00
CPC分类号： G06T7/73
摘要： Method for determining the position of an object point in a scene from a digital image thereof acquired through an optical system is presented. The image comprises a set of image points corresponding to object points and the position of the object points are determined by means of predetermined vectors associated with the image points. The predetermined vector represents the inverted direction of a light ray in the object space that will produce this image point through the optical system comprising all distortion effects of the optical system.
摘要翻译：提出了从通过光学系统获得的数字图像中确定场景中物体的位置的方法。图像包括与对象点对应的一组图像点，并且通过与图像点相关联的预定向量来确定对象点的位置。预定矢量表示通过包括光学系统的所有失真效应的光学系统产生该图像点的对象空间中的光线的反转方向。

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