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. 发明专利

JP2015001901A 点群解析処理装置、点群解析処理方法、及びプログラム有权
标题翻译：点组分析处理装置，点组分析处理方法和程序
公开(公告)号：JP2015001901A
公开(公告)日：2015-01-05
申请号：JP2013126960
申请日：2013-06-17
申请人：日本電信電話株式会社 , Nippon Telegr & Teleph Corp
发明人： NIIGAKI JIN , SHIMAMURA JUN , ARAI HIROYUKI , TANIGUCHI YUKINOBU
IPC分类号： G06T7/60 , G06T1/00
摘要：【課題】電柱間の電線および引き込み線などの細線状物体について、複数の細線状物体が連結した状態でも細線状物体として高い精度で検出することを可能とする。【解決手段】3次元点群情報に含まれる点と、当該点の周囲の前記点との位置関係に基づいて、当該点が細線状物体を構成する構成点であるか否かについて判定を行い構成点を検出し、検出した構成点の各点の接線方向の情報に基づいて、構成点から直線要素を検出し、検出した直線要素を初期の細線状物体を示す細線状物体モデルとし、細線状物体モデル同士の近接状態と、予め定められる連結性指標とに基づいて、細線状物体モデルを連結していくことで再帰的に細線状物体モデルを生成し、細線状物体モデルに含まれる点の位置から細線状物体モデルの長さを推定し、推定した長さと、予め定められる閾値とに基づいて細線状物体モデルが適切なモデルであるか否かを判定する。【選択図】図1
摘要翻译：要解决的问题：为了高精度地检测诸如电极和引入线之间的电线的细线状物体，即使在细线状物体处于多条细线状物体的状态下连接。解决方案：点组分析处理装置通过基于三维点组信息中包含的点之间的物理关系，通过确定三维点组信息中包括的点是否构成细线状物体的构成点来检测构成点三维点组信息和点周围的点，基于检测到的构成点的每个点的切线方向上的信息，从构成点检测直线元素，将检测到的直线元素定义为细线形对象模型指示初始细线状物体，通过连接递归生成细线状对象模型基于细线状对象模型的接近状态和预定的连接指数，细线状对象模型从细线状对象模型的包围的点的位置估计细线状对象模型的长度，并根据估计的长度和预定的阈值来确定细线状对象模型是否是适当的模型。

2. 发明专利

JP2012238146A Color correction device, color correction method, and color correction program 有权
标题翻译：彩色校正装置，彩色校正方法和彩色校正程序
公开(公告)号：JP2012238146A
公开(公告)日：2012-12-06
申请号：JP2011106098
申请日：2011-05-11
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： KAWAMURA HARUMI , NOTO HAJIME , ISOGAI AI , NIIGAKI JIN , MATSUURA NOBUHIKO
IPC分类号： G06T3/00 , H04N9/04
摘要： PROBLEM TO BE SOLVED: To provide a color correction device, for solving a conventional problem in a panorama composite video, suppressing a color shift due to a camera individual difference and composing a panorama video from a user's view point.SOLUTION: The color correction device for correcting the color shift of a joining part due to the camera individual difference when joining videos of a plurality of view points includes: a color region specification section for specifying a region to an input video; a color correction information calculating section for calculating color correction information on the basis of the color information of the specified region obtained in the color region specification section; and a color correction section for correcting the color of the video based on the color correction information obtained by the color correction information calculating section.
摘要翻译：要解决的问题：为了提供一种用于解决全景复合视频中的常规问题的颜色校正装置，从用户的观点来抑制由于相机个体差异引起的颜色偏移和构成全景视频。解决方案：当连接多个视点的视频时，用于校正由于照相机个体差异导致的接合部分的色偏的颜色校正装置包括：颜色区域指定部分，用于指定输入视频的区域; 颜色校正信息计算部分，用于基于在颜色区域指定部分中获得的指定区域的颜色信息来计算颜色校正信息; 以及颜色校正部分，用于基于由颜色校正信息计算部分获得的颜色校正信息来校正视频的颜色。版权所有（C）2013，JPO＆INPIT

3. 发明专利

JP2014153336A Point group analysis processing device and point group analysis processing program 有权
标题翻译：点组分析处理设备和点组分析处理程序
公开(公告)号：JP2014153336A
公开(公告)日：2014-08-25
申请号：JP2013026070
申请日：2013-02-13
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , SHIMAMURA JUN , ARAI HIROYUKI , TANIGUCHI YUKINOBU
IPC分类号： G01B21/20 , G01B11/24 , G01B17/06 , G06T1/00 , G06T7/00
摘要： PROBLEM TO BE SOLVED: To allow detection of even a columnar object which has a small diameter and is short, even in the case where a measurement position of a subject is localized.SOLUTION: A three-dimensional point group storage unit 102 acquires three-dimensional point group information from a subject measurement unit 101 to supply this information to a columnar object detection unit 103. The columnar object detection unit 103 acquires three-dimensional point groups from the three-dimensional point group storage unit 102 and performs clustering based on local shapes of respective points and then uses fitting of a columnar object based on RANSAC to detect the position and inclination of the columnar object with respect to the acquired three-dimensional point groups and outputs a point group constituting the columnar object. A columnar object parameter output unit 104 converts columnar object parameter information (position and inclination) or the three-dimensional point group belonging to the columnar object into text data coded in ASCII or the like or binary data, and the data is outputted to a columnar object parameter display unit 105 as an image signal for display.
摘要翻译：要解决的问题：即使在对象的测量位置被定位的情况下，甚至能够检测甚至具有小直径的柱状物体。解决方案：三维点组存储单元102获取三维点组存储单元102，来自对象测量单元101的三维点组信息，以将该信息提供给柱状物体检测单元103.柱状物体检测单元103从三维点群存储单元102获取三维点群，并且基于局部然后使用基于RANSAC的柱状对象的拟合来检测柱状物体相对于所获取的三维点组的位置和倾斜度，并输出构成柱状物体的点群。柱状对象参数输出部104将列方式对象参数信息（位置和倾斜度）或属于柱状对象的三维点组转换成以ASCII等编码的文本数据或二进制数据，将数据输出到列对象参数显示单元105作为用于显示的图像信号。

4. 发明专利

JP2014106725A Point group analyzer, point group analysis method and point group analysis program 有权
标题翻译：点集合分析器，点集合分析方法和点组分析程序
公开(公告)号：JP2014106725A
公开(公告)日：2014-06-09
申请号：JP2012258941
申请日：2012-11-27
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , SHIMAMURA JUN , ARAI HIROYUKI , TANIGUCHI YUKINOBU
IPC分类号： G06T7/60
摘要： PROBLEM TO BE SOLVED: To provide a point group analyzer capable of accurately detecting a linear object by analyzing an obtained three-dimensional point group.SOLUTION: A point group analyzer includes: three-dimensional point group acquisition means of acquiring three-dimensional point group data; autocorrelation matrix calculation means of defining one of the three-dimensional point group data as a focus point, defining a point having a fixed distance or less from the focus point as a peripheral point, calculating importance of the peripheral point with respect to the focus point, and calculating a weighted autocorrelation matrix using the importance on the focus point; feature vector calculation means of calculating an eigenvalue feature vector in which an eigenvalue of the autocorrelation matrix is defined as an element; and identification means of determining whether the focus point constitutes a linear object by using the eigenvalue feature vector.
摘要翻译：要解决的问题：提供一种能够通过分析所获得的三维点组来精确地检测线性对象的点组分析器。解决方案：点组分析器包括：获取三维点组的三维点组获取装置数据; 自相关矩阵计算装置，其将三维点组数据之一定义为焦点，将从聚焦点固定距离或更小的点定义为周边点，计算外围点相对于焦点的重要性并且使用对焦点的重要性来计算加权自相关矩阵; 特征向量计算装置，其计算特征值特征向量，其中将所述自相关矩阵的特征值定义为元素; 以及通过使用特征值特征向量来确定焦点是否构成线性对象的识别装置。

5. 发明专利

JP2013246674A Figure detection processing device, figure detection processing method and figure detection processing program 有权
标题翻译：图形检测处理装置，图形检测处理方法和图形检测处理程序
公开(公告)号：JP2013246674A
公开(公告)日：2013-12-09
申请号：JP2012120625
申请日：2012-05-28
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , SHIMAMURA JUN , MORIMOTO MASASHI , ARAI HIROYUKI
IPC分类号： G06T7/00 , G06F17/30 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To stably detect a figure to be detected from an input image.SOLUTION: A figure detection processing device is equipped with: means for setting a mask having a first region and a second region, which are predetermined corresponding to a figure to be detected, for a target pixel of an image; means for obtaining a first probability distribution which is a probability distribution of image feature quantity in the first region and a second probability distribution which is a probability distribution of image feature quantity in the second region, while moving the target pixel; means for, based on the first probability distribution and the second probability distribution, obtaining a separation level index indicating a difference level between the two probability distributions, and a self-similarity level index indicating a self-similarity level of the probability distribution in the first region and the second region, and calculating a figure index indicating likelihood of a figure to be detected from the separation level index and the self-similarity level index; and means for determining whether or not a figure positioned on the target pixel is a figure to be detected, by performing threshold value processing on the figure index.
摘要翻译：要解决的问题：为了从输入图像稳定地检测要检测的图像。解决方案：图形检测处理装置配备有：用于设置具有第一区域和第二区域的掩模的装置，所述第一区域和第二区域对应于图形被检测，用于图像的目标像素; 用于获取作为第一区域中的图像特征量的概率分布的第一概率分布和作为第二区域中的图像特征量的概率分布的第二概率分布的装置，同时移动目标像素; 用于基于所述第一概率分布和所述第二概率分布获得指示所述两个概率分布之间的差级别的分离级别索引以及指示所述第一概率分布中的概率分布的自相似度级别的自相似度级别索引区域和第二区域，并且从分离级别索引和自相似度级别索引计算指示要检测的图形的可能性的图形索引; 以及通过对图形索引执行阈值处理，确定位于目标像素上的图像是否是要检测的图形的装置。

6. 发明专利

JP2011165081A Method and apparatus for generating image, and program 有权
标题翻译：用于生成图像和程序的方法和装置
公开(公告)号：JP2011165081A
公开(公告)日：2011-08-25
申请号：JP2010029386
申请日：2010-02-12
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： KUNIDA YUTAKA , NIIGAKI JIN , ISOGAI AI , KIMATA HIDEAKI
IPC分类号： G06T1/00 , G06T19/00
摘要： PROBLEM TO BE SOLVED: To appropriately generate an image without worsening appearance of places except an object while saving computer resources. SOLUTION: An area where an important part of the subject is photographed is detected from the inside of an original image obtained by photographing the object from a plurality of viewpoint positions (step S2), an important part area in a space is estimated from the detected area where the important part is photographed and geometric conditions of the plurality of viewpoint positions (step S3), it is assumed that the important part area in the space is an object existence area where the object exists in the space, and an intermediate image of the object viewed from a reference viewpoint is generated (step S4). The important part area is segmented from the inside of the intermediate image as a segmented image (step S5). A base image is selected from the original image (step S6), and the segmented image is synthesized in an area where an important part of the base image exists (step S7). COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：在节省计算机资源的同时，适当地生成图像而不使对象外的位置的外观恶化。解决方案：从从多个视点位置拍摄对象获得的原始图像的内部检测拍摄对象的重要部分的区域（步骤S2），估计空间中的重要部分区域从拍摄重要部分的检测区域和多个视点位置的几何条件（步骤S3），假设空间中的重要部分区域是对象存在于空间中的对象存在区域，并且产生从参考视点观看的对象的中间图像（步骤S4）。重要部分区域作为分割图像从中间图像的内部分割（步骤S5）。从原始图像中选择基本图像（步骤S6），并且在存在基本图像的重要部分的区域中合成分割图像（步骤S7）。版权所有（C）2011，JPO＆INPIT

7. 发明专利

JP2013012045A Image processing method, image processing system, and computer program 审中-公开
标题翻译：图像处理方法，图像处理系统和计算机程序
公开(公告)号：JP2013012045A
公开(公告)日：2013-01-17
申请号：JP2011144417
申请日：2011-06-29
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , ISOGAI AI , NOTO HAJIME , KAWAMURA HARUMI , MATSUURA NOBUHIKO
IPC分类号： G06T1/00
摘要： PROBLEM TO BE SOLVED: To synthesize a high-quality virtual viewpoint image while suppressing a depth estimation error, even if mapping between images is difficult.SOLUTION: An image processing method is for synthesizing an image of a subject viewed from a given virtual viewpoint position, referring to a multi-viewpoint image obtained by imaging the subject from a plurality of different viewpoints. The image processing method comprises: calculating a likelihood to a depth of each pixel with regard to the multi-viewpoint image; estimating the depth of each pixel according to the likelihood; calculating an estimation function for estimating a likelihood to the depth from an image feature using a depth estimation result of a high accuracy estimation pixel; correcting the likelihood to a correction targeting pixel using the estimation function; re-estimating the depth of the whole image using the corrected likelihood; and synthesizing the image of the subject in accordance with the virtual viewpoint position, referring to the re-estimated depth and the multi-viewpoint image.
摘要翻译：要解决的问题：为了在抑制深度估计误差的同时合成高质量虚拟视点图像，即使图像之间的映射困难。解决方案：参考从多个不同视点对被摄体进行成像而获得的多视点图像，用于合成从给定虚拟视点位置观看的被摄体的图像的图像处理方法。图像处理方法包括：针对多视点图像计算每个像素的深度的可能性; 根据似然估计每个像素的深度; 使用高精度估计像素的深度估计结果计算用于估计来自图像特征的深度的可能性的估计函数; 使用所述估计函数来校正修正目标像素的可能性; 使用校正的可能性重新估计整个图像的深度; 以及根据重新估计的深度和多视点图像，根据虚拟视点位置合成被摄体的图像。版权所有（C）2013，JPO＆INPIT

8. 发明专利

JP2014109555A Point group analysis processing apparatus, point group analysis processing method and program 审中-公开
标题翻译：点组分析处理装置，点组分析处理方法和程序
公开(公告)号：JP2014109555A
公开(公告)日：2014-06-12
申请号：JP2012265618
申请日：2012-12-04
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , SHIMAMURA JUN , ARAI HIROYUKI , TANIGUCHI YUKINOBU
IPC分类号： G01B21/00 , G01B11/00 , G01B11/08 , G01B11/26 , G01B21/10 , G01B21/22 , G06T7/60
摘要： PROBLEM TO BE SOLVED: To detect a three-dimensional point group composing a columnar object with high accuracy even when the columnar object is obliquely inclined or the columnar object is adjacent to the other object.SOLUTION: A columnar object detection apparatus 100 includes: a columnar object parameter estimation part 105 which estimates a columnar parameter of a columnar object by round column application to a three-dimensional point group to be an apparatus processing target by RANSAC; and a columnar object identification part 106 which identifies whether or not a point group existing on a position of the estimated columnar object is a columnar object on the basis of the columnar object parameter estimated by the columnar object parameter estimation part 105 and outputs a determination result of the presence/absence of the columnar object, and when determining that the columnar object exists, outputs center positions and radiuses of respective columnar objects in a plurality of small areas obtained by dividing the three-dimensional point group.
摘要翻译：要解决的问题：即使当柱状物体倾斜倾斜或柱状物体与另一物体相邻时，也可以高精度地检测构成柱状物体的三维点组。解决方案：柱状物体检测装置100包括：圆柱对象参数估计部105，其通过圆列应用将柱状对象的列参数通过RANSAC作为装置处理对象的三维点组进行估计; 以及柱状物体识别部106，其基于由柱状物体参数估计部105估计出的柱状物参数来识别存在于所述推定柱状物体的位置上的点群是否为柱状物体，并输出确定结果柱状对象的存在/不存在，并且当确定柱状对象存在时，在通过划分三维点组获得的多个小区域中输出各个柱状对象的中心位置和半径。

9. 发明专利

JP2012194751A Image processing method, image processing system and computer program 审中-公开
标题翻译：图像处理方法，图像处理系统和计算机程序
公开(公告)号：JP2012194751A
公开(公告)日：2012-10-11
申请号：JP2011057897
申请日：2011-03-16
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NIIGAKI JIN , ISOGAI AI , KAWAMURA HARUMI , NOTO HAJIME , WAKABAYASHI KAORI , MATSUURA NOBUHIKO
IPC分类号： G06T3/00 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To provide a virtual viewpoint image synthesizer capable of suppressing a depth estimated error and synthesizing a high quality virtual viewpoint image even when mapping between images is difficult.SOLUTION: A depth estimation part acquires a camera parameter and image data from a camera image/camera parameter storage part and outputs a depth estimation result. At the time, as for a pixel for which the depth estimation is difficult, a subject to which the pixel belongs is estimated and a correction is performed using the depth information on the subject. When mapping is difficult as for a pixel at a portion where a depth in the vicinity of a boundary of the subject is rapidly changed, the depth information on the same subject is given. An image synthesizing part outputs a composite image viewed from a virtual viewpoint based on the camera parameter, the image data and the depth estimation result.
摘要翻译：要解决的问题：即使在图像之间的映射困难的情况下，也能够提供能够抑制深度估计误差并合成高品质虚拟视点图像的虚拟视点图像合成器。解决方案：深度估计部分从相机图像/相机参数存储部分获取相机参数和图像数据，并输出深度估计结果。此时，对于难以进行深度估计的像素，估计像素属于的被摄体，并且使用关于被摄体的深度信息进行校正。当与受试者的边界附近的深度急剧变化的部分的像素难以进行映射时，给出相同被摄体的深度信息。图像合成部根据摄像机参数，图像数据和深度估计结果输出从虚拟视点观看的合成图像。版权所有（C）2013，JPO＆INPIT

10. 发明专利

JP2012173858A Omnidirectional image generation method, image generation device and program 有权
标题翻译： OMNIDIRECTIONAL图像生成方法，图像生成装置和程序
公开(公告)号：JP2012173858A
公开(公告)日：2012-09-10
申请号：JP2011033402
申请日：2011-02-18
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ISOGAI AI , KAWAMURA HARUMI , NOTO HAJIME , NIIGAKI JIN , MATSUURA NOBUHIKO
IPC分类号： G06T19/00 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To generate an omnidirectional image of deep scene from multiple images.SOLUTION: An omnidirectional image generation method for generating an omnidirectional image of deep scene from multiple images includes: a step for acquiring images of a subject taken from multiple viewing locations; a step for projecting each of the acquired images on multiple predefined layer surfaces; a step for calculating color information or brightness information of the subject on the layer surfaces where the images are projected; a step for calculating reliability, which shows an existence probability of the subject at each point on the layer surfaces, by obtaining a similarity between each point of the subject on the acquired images and each point of images projected on the layer surfaces; a step for selecting multiple layers with a central focus on a layer having the highest reliability of the subject, based on the reliability; and a step for generating an omnidirectional image of deep scene based on the color information or brightness information of the subject on the surfaces of the selected layers and on reliability information.
摘要翻译：要解决的问题：从多个图像生成深色场景的全向图像。解决方案：一种用于从多个图像生成深度场景的全向图像的全向图像生成方法包括：从多个观看位置获取被摄体的图像的步骤; 将所获取的图像中的每一个投影到多个预定义的层表面上的步骤; 用于计算投影图像的层表面上的被摄体的颜色信息或亮度信息的步骤; 用于计算可靠性的步骤，其通过获得所获取的图像上的对象的每个点与投影在层表面上的每个图像点之间的相似度来示出在层表面上的每个点处的被摄体的存在概率; 基于可靠性选择具有对象的最高可靠性的层的具有中心焦点的多个层的步骤; 以及基于所选择的层的表面上的被摄体的颜色信息或亮度信息以及可靠性信息来生成深色场景的全向图像的步骤。版权所有（C）2012，JPO＆INPIT

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