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

JP2014042210A Projection type three-dimensional shape restoration device, projection type three-dimensional shape restoration method and projection type three-dimensional shape restoration program 有权
标题翻译：投影类型三维形状恢复装置，投影类型三维形状恢复方法和投影类型三维形状恢复程序
公开(公告)号：JP2014042210A
公开(公告)日：2014-03-06
申请号：JP2012184418
申请日：2012-08-23
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： MIYAGAWA ISAO , ARAI HIROYUKI , TANIGUCHI YUKINOBU
IPC分类号： H04N5/74 , G03B21/00 , G03B35/22 , G06T1/00 , H04N13/04
摘要： PROBLEM TO BE SOLVED: To restore an original three-dimensional shape from an image projected from a projector by using robust constraint conditions when a projector/camera system is used.SOLUTION: A projection type three-dimensional shape restoration device includes: shaded image generation means for generating a shaded image of an object, which is generated on the basis of a principle of an illuminance difference stereo from a three-dimensional shape of the object and direction information of illumination for illuminating the object for an image of the object which is to be projected by a projector; image output means for outputting the shaded image to the projector which projects the shaded image on a prescribed rectangular face; image input means for obtaining a captured image generated by allowing a camera to image the shaded image projected on the rectangular face; and three-dimensional shape restoration means which matrix-decomposes an image data matrix generated from the captured image into a temporary surface normal matrix and a temporary light source direction matrix, acquires a surface normal matrix by linearly transforming the temporary surface normal matrix by using a linearly transformed matrix and restores the three-dimensional shape of the object in response to the surface normal matrix.
摘要翻译：要解决的问题：当使用投影仪/照相机系统时，通过使用强大的约束条件，从投影仪投射的图像恢复原始的三维形状。解决方案：投影型三维形状恢复装置包括：阴影图像生成用于生成基于与物体的三维形状的照度差立体声的原理和用于照亮被摄体的图像的对象的照明的方向信息而生成的物体的阴影图像的装置，由投影仪投射; 图像输出装置，用于将阴影图像输出到将阴影图像投射到规定的矩形面上的投影仪; 图像输入装置，用于获得通过允许相机对投影在矩形面上的阴影图像进行成像而产生的拍摄图像; 以及将从拍摄图像生成的图像数据矩阵矩阵分解成临时表面法线矩阵和临时光源方向矩阵的三维形状恢复装置，通过使用临时表面法线矩阵线性变换来获取表面法线矩阵线性变换矩阵，并响应于表面法线矩阵恢复对象的三维形状。

3. 发明专利

JP2013101558A Image processing method, image processing apparatus and image processing program 有权
标题翻译：图像处理方法，图像处理装置和图像处理程序
公开(公告)号：JP2013101558A
公开(公告)日：2013-05-23
申请号：JP2011245768
申请日：2011-11-09
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ITO NAOKI , ARAI HIROYUKI , IGARASHI ISAMU , MORIMOTO MASASHI
IPC分类号： G06T1/00 , H04N5/232
摘要： PROBLEM TO BE SOLVED: To detect a person area while keeping temporal and spatial continuity, reducing erroneous detection and preventing individual identification.SOLUTION: An image processing method includes the steps of: on the basis of a processing target image, a background image generated in the last processing and a dispersion value image, updating the background image by subjecting respective pixel values of the background image and the processing target image to a weighing sum according to the dispersion value image; generating a low frequency component image by using a load average filter for the processing target image; generating a high frequency component image from a difference between the processing target image and the low frequency component image; calculating a person area candidate from a difference between the background image and the processing target image; suppressing values of respective pixels of the high frequency component image by using values of respective pixels of the calculated person area candidate; generating a result image by combining the suppressed high frequency component image and the low frequency component image; and outputting a resulting image as a processing result.
摘要翻译：要解决的问题：在保持时间和空间连续性的同时检测人员区域，减少错误检测并防止个人身份识别。解决方案：图像处理方法包括以下步骤：基于处理目标图像，在最后处理中产生的背景图像和色散值图像，通过对背景图像进行各自的像素值更新背景图像和所述处理目标图像根据所述色散值图像为加权和; 通过使用用于所述处理目标图像的负载平均滤波器来生成低频分量图像; 从处理对象图像和低频分量图像之间的差产生高频分量图像; 根据背景图像和处理对象图像之间的差异来计算人物区域候选; 通过使用所计算的人区域候选的各个像素的值来抑制高频分量图像的各个像素的值; 通过组合抑制的高频分量图像和低频分量图像来生成结果图像; 并输出作为处理结果的结果图像。版权所有（C）2013，JPO＆INPIT

4. 发明专利

JP2013085182A Multiple projection brightness adjustment method, multiple projection brightness adjustment device, computer program, and recording media 有权
标题翻译：多项投影亮度调整方法，多项投影亮度调整装置，计算机程序和记录介质
公开(公告)号：JP2013085182A
公开(公告)日：2013-05-09
申请号：JP2011224920
申请日：2011-10-12
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： MIYAGAWA ISAO , ARAI HIROYUKI , MORIMOTO MASASHI
IPC分类号： H04N5/74 , G03B21/00 , G03B21/14 , G06T5/00 , G09G5/00 , G09G5/10
摘要： PROBLEM TO BE SOLVED: To provide a multiple projection brightness adjustment method, a multiple projection brightness adjustment device, a computer program, and a recording media, capable of compensating the brightness of a content image projected by a plurality of projectors, so as to make the content image almost equal to the original image even if the projectors response in a nonlinear manner.SOLUTION: An image input part 2 acquires image data from a camera 20. An image fluctuation detection part 3 acquires the image from the image input part 2 to detect a brightness fluctuation thereof using information on the image. A mode determination part 4 transmits synchronous signals for controlling all projectors, to instruct to process on brightness adjustment parts 5-1 through 5-N or brightness distribution parts 6-1 through 6-N. The brightness adjustment parts 5-1 through 5-N adjust the brightness output from projectors 10-1 through 10-N in accordance with the brightness fluctuation acquired in the image fluctuation detection part 3, and calculate a distribution coefficient to be used for multiple projection brightness compensation. The brightness distribution parts 6-1 through 6-N compensate the brightness of each projector using the distribution coefficient.
摘要翻译：要解决的问题：为了提供能够补偿多个投影仪投影的内容图像的亮度的多投影亮度调整方法，多投影亮度调节装置，计算机程序和记录介质，因此即使投影机以非线性方式响应，使得内容图像几乎等于原始图像。图像输入部分2从相机20获取图像数据。图像变动检测部分3从图像输入部分2获取图像，以使用关于图像的信息来检测其亮度波动。模式确定部分4发送用于控制所有投影仪的同步信号，指示处理亮度调节部分5-1至5-N或亮度分布部分6-1至6-N。亮度调整部5-1〜5-N根据在图像变动检测部3中取得的亮度变动来调整投影仪10-1〜10-N的亮度输出，并计算用于多个投影的分配系数亮度补偿。亮度分布部分6-1至6-N使用分布系数补偿每个投影仪的亮度。版权所有（C）2013，JPO＆INPIT

5. 发明专利

JP2012242947A Method for measuring number of passing objects, number-of-passing object measuring device, and program 有权
标题翻译：用于测量通过物件数量，通过数量的物体测量装置和程序的方法
公开(公告)号：JP2012242947A
公开(公告)日：2012-12-10
申请号：JP2011110341
申请日：2011-05-17
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： IGARASHI ISAMU , ITO NAOKI , ARAI HIROYUKI , KOIKE HIDEKI
IPC分类号： G06M7/00
摘要： PROBLEM TO BE SOLVED: To provide a method for measuring the number of passing objects capable of estimating the number of the passing objects in a region captured in a video.SOLUTION: A partial image generating section 10 generates a partial image from a continuous image sequence. A foreground detecting section 11 generates a foreground image representing a foreground region from the partial image. An on-image moving distance detecting section 12 detects a local moving distance on the image between frames in the detected foreground region. A moving distance coordinates conversion/representative moving distance calculating section 13 calculates a representative moving distance as a whole of an object group moving in each measuring direction of the number of passing objects by a method taking account of a relation between coordinates on the image and actual spatial coordinates on the basis of the local moving distance on the detected image. An in-image heads calculating section 14 estimates the number of objects captured in the image. A number of passers-by calculating section 15 calculates the number of passing objects between the frames in each measuring direction on the basis of the representative moving distance and the number of passing objects in each measuring direction.
摘要翻译：要解决的问题：提供一种用于测量能够估计在视频中捕获的区域中的通过对象的数量的通过对象的数量的方法。解决方案：部分图像生成部10从连续图像序列生成部分图像。前景检测部分11从部分图像生成表示前景区域的前景图像。图像上移动距离检测部分12检测检测到的前景区域中的帧之间的图像上的局部移动距离。移动距离坐标转换/代表性移动距离计算部13通过考虑图像上的坐标与实际的坐标之间的关系的方法，计算在通过对象的数量的每个测量方向上移动的对象组的整体的代表移动距离基于检测到的图像上的局部移动距离的空间坐标。图像内头部计算部分14估计在图像中捕获的对象的数量。多个路人计算部15基于代表移动距离和每个测量方向上的通过对象的个数来计算各测量方向上的帧之间的通过对象的数量。版权所有（C）2013，JPO＆INPIT

6. 发明专利

JP2012103742A Image processing apparatus, image processing method, and recording medium with recorded image processing program 有权
标题翻译：图像处理设备，图像处理方法和记录图像处理程序的记录介质
公开(公告)号：JP2012103742A
公开(公告)日：2012-05-31
申请号：JP2010248849
申请日：2010-11-05
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ITO NAOKI , KOIKE HIDEKI , ARAI HIROYUKI , IGARASHI ISAMU
IPC分类号： G06T1/00 , G06T7/20 , H04N5/262
摘要： PROBLEM TO BE SOLVED: To perform image conversion on a person-like area of a photographed time-series image so that an individual cannot be identified.SOLUTION: An image processing method includes the steps of:calculating an average value of respective pixels based upon images of a plurality of frames; removing a pixel value which deviates largely from the average value; calculating a dispersion value from the pixel; performing expansion processing and contraction processing on the dispersion value to generate a dispersion value image, and performing conversion using a multidimensional conversion expression; updating a background image; generating a low-frequency component image from the acquired image; generating a high-frequency component image from differences between the acquired image and low-frequency component image; calculating likelihood of a person from differences between the background image and the acquired image; generating a high-frequency component image by suppressing values of respective pixels of the high-frequency component image using values of respective pixels of likelihood of the person; and generating a result image by compounding the high-frequency component image after the suppression and the low-frequency component image.
摘要翻译：要解决的问题：对拍摄的时间序列图像的人物区域执行图像转换，使得不能识别个人。解决方案：图像处理方法包括以下步骤：基于多个帧的图像来计算各个像素的平均值; 去除偏离平均值的像素值; 从像素计算色散值; 对色散值执行扩展处理和收缩处理以产生色散值图像，并使用多维转换表达式进行转换; 更新背景图像; 从所获取的图像生成低频分量图像; 从所获取的图像和低频分量图像之间的差产生高频分量图像; 计算人的背景图像与所获取的图像之间的差异的可能性; 通过使用人的可能性的各个像素的值来抑制高频分量图像的各个像素的值来生成高频分量图像; 以及通过将抑制后的高频分量图像与低频分量图像进行混合来生成结果图像。版权所有（C）2012，JPO＆INPIT

7. 发明专利

JP2011186719A Apparatus, method and program for detecting object 审中-公开
标题翻译：检测对象的装置，方法和程序
公开(公告)号：JP2011186719A
公开(公告)日：2011-09-22
申请号：JP2010050417
申请日：2010-03-08
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ITO NAOKI , IGARASHI ISAMU , MIYAGAWA ISAO , ARAI HIROYUKI , KOIKE HIDEKI
IPC分类号： G06T7/20 , G06T1/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To count the accurate number of objects by controlling adaptation of an object to a background model even when the object (person) rests for a comparatively long period. SOLUTION: An object detection processing part 3 divides an input image photographed by a fixed camera 1 and a background model into blocks each of which is composed of a plurality of pixels and extracts an object area corresponding to a contour of the object in each block. Further, the object detection processing part 3 performs expansion processing to fill an area corresponding to the inside of the contour part and performs contraction processing for controlling excess detection of the object area due to the expansion processing. A load value table generation part 5 obtains a load value expressing a contribution ratio of each pixel to the number of objects to generate a load value table. An object counting part 6 integrates the load values of pixels in the object area to count the number of objects. COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：即使当对象（人）休息较长的时间段时，也可以通过控制对象到背景模型的适应来计数对象的准确数量。解决方案：对象检测处理部分3将由固定照相机1和背景模型拍摄的输入图像划分为由多个像素组成的块，并且提取与该对象的轮廓相对应的对象区域每个块。此外，对象检测处理部3进行扩展处理，以填充对应于轮廓部分的内部的区域，并执行缩放处理，以控制由于扩展处理而导致的对象区域的过度检测。负载值表生成部5获取表示各像素的贡献率与生成负载值表的对象数的负载值。对象计数部6将对象区域中的像素的负载值进行积分，以对对象的数量进行计数。版权所有（C）2011，JPO＆INPIT

8. 发明专利

JP2010187130A Camera calibrating device, camera calibration method, camera calibration program, and recording medium having the program recorded therein 审中-公开
标题翻译：相机校准设备，摄像机校准方法，摄像机校准程序以及记录有程序的记录介质
公开(公告)号：JP2010187130A
公开(公告)日：2010-08-26
申请号：JP2009029082
申请日：2009-02-10
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： OSAWA TATSUYA , ARAI HIROYUKI , KOIKE HIDEKI
IPC分类号： H04N5/228 , G01B11/00 , G01B11/26 , G06T1/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To facilitate measurement of internal and external parameters of a camera.
SOLUTION: A silhouette image creation means 12 creates a silhouette image resulting from extracting an area of an object from an image inputted from an image acquisition means 11 like a camera. A parameter estimation means 14 selects a preliminarily prepared change type of the object in accordance with an arbitrary probability and generates a state candidate according with the selected change type. A simulation image is created by projecting the silhouette image on a virtual camera having the same camera internal and external parameters as the generated state candidate on the basis of the state candidate and simulating the silhouette image. An evaluation value is obtained which results from product operation between a result of comparison between both images and a determination result of likelihood of the object itself based on prior knowledge. It is determined whether the state candidate can be accepted as the final change state or not in accordance with the evaluation value. Internal and external parameters of the camera are estimated from the accepted change state.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：为了便于测量相机的内部和外部参数。解决方案：剪影图像创建装置12创建从从诸如照相机的图像获取装置11输入的图像中提取对象的区域而产生的剪影图像。参数估计单元14根据任意概率选择预先准备好的对象的改变类型，并根据所选择的改变类型生成状态候补。通过基于状态候选来将轮廓图像投影到具有与生成的状态候选相同的摄像机内部和外部参数的虚拟摄像机上并且模拟轮廓图像来创建模拟图像。获得由两个图像之间的比较结果与基于现有知识的对象本身的可能性的确定结果之间的产品操作产生的评估值。根据评估值确定状态候选者是否可以被接受为最终改变状态。相机的内部和外部参数是从可接受的更改状态估计的。版权所有（C）2010，JPO＆INPIT

9. 发明专利

JP2010186265A Camera calibration device, camera calibration method, camera calibration program, and recording medium with the program recorded threin 有权
标题翻译：相机校准装置，相机校准方法，相机校准程序以及记录有THREIN的记录介质
公开(公告)号：JP2010186265A
公开(公告)日：2010-08-26
申请号：JP2009029084
申请日：2009-02-10
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： MIYAGAWA ISAO , ARAI HIROYUKI , KOIKE HIDEKI
IPC分类号： G06T1/00 , G01B11/00 , G01B11/26 , H04N5/225
摘要： PROBLEM TO BE SOLVED: To provide a camera calibration device for easily calibrating a camera.
SOLUTION: This camera calibration device is provided with a reference point adjustment part 104 for setting a prescribed two-dimensional coordinate system in an image acquired by photographing a reference object wherein geometric information of a reference point is known by use of a camera 102 of a calibration target, and extracting a prepared two-dimensional coordinate value of the reference point, and a reference point measurement part 105, and is provided with a camera calibration processing part 106 for adjusting a position or an attitude of the reference object until a part of the obtained reference points satisfies a specific geometric restraint condition, and calibrating external information or internal information of the camera 102 from the coordinate value of the reference point obtained on two-dimensional coordinates and the geometric information of the reference point according to calculation derived from a perspective projection condition when three-dimensional points of all the reference points on the reference object are projected to the two-dimensional coordinate system.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于轻松校准相机的相机校准装置。解决方案：本相机校准装置设置有参考点调整部分104，用于在通过使用照相机拍摄参考点的几何信息已知的参考对象拍摄的图像中设置规定的二维坐标系 102，并且提取准备的参考点的二维坐标值和参考点测量部分105，并且设置有用于调整参考对象的位置或姿态的相机校准处理部分106，直到所获得的参考点的一部分满足特定的几何约束条件，并且根据二维坐标获得的参考点的坐标值和参考点的几何信息根据计算校准外部信息或摄像机102的内部信息从三维点的透视投影状态得出将参考对象上的所有参考点投影到二维坐标系。版权所有（C）2010，JPO＆INPIT

10. 发明专利

JP2010015472A Pedestrian sex determination device, pedestrian sex determination method, pedestrian sex determination program, and recording medium therefor 审中-公开
标题翻译： PEDESTRIAN SEX确定装置，PEDESTRIAN SEX确定方法，PEDESTRIAN SEX确定方案及其记录介质
公开(公告)号：JP2010015472A
公开(公告)日：2010-01-21
申请号：JP2008176434
申请日：2008-07-07
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： TANAKA HIDENORI , WU XIAOJUN , ARAI HIROYUKI , KOIKE HIDEKI
IPC分类号： G06T7/20 , G06T1/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To determine the sex of a pedestrian correctly using images picked up from various angles by image pickup devices.
SOLUTION: The images obtained by imaging the pedestrian by a plurality of image pickup devices are input in a sex determination device 1 in time series. A pedestrian region extraction part 12 of the sex determination device 1 generates a silhouette image from the difference of values between the pixels at the position of the pedestrian in an input image and the pixels at the position corresponding to the pedestrian in a background image. A person model construction part 13 configures a three-dimensional person model using the silhouette image and acquires the angle of each joint and the length between joints as parameters. A walking cycle cutoff part 15 calculates a walking cycle from the parameters. A feature quantity extraction part 16 acquires the feature of sex from the relation between the shoulder part and the waist part from a parameter string cut out for each walking cycle. A sex determination part 18 determines the sex by comparing the feature quantity with the feature quantity to which a special label is added in advance.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：使用通过图像拾取装置从各种角度拾取的图像来正确地确定行人的性别。
解决方案：通过多个图像拾取装置对行人进行成像而获得的图像以时间序列输入到性别确定装置1中。性别判定装置1的行人区域提取部12根据输入图像中的行人的位置的像素与对应于背景图像中的行人的位置的像素之间的值的差异，生成轮廓图像。个人模型构造部13使用剪影图像来构造三维人物模型，并且获取每个关节的角度和关节之间的长度作为参数。步行循环切断部15根据参数计算步行周期。特征量提取部16从针对每个行走周期切断的参数串中从肩部与腰部的关系获取性别的特征。性别确定部分18通过将特征量与预先添加特殊标签的特征量进行比较来确定性别。版权所有（C）2010，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