公开(公告)号：JP2006140952A

公开(公告)日：2006-06-01

申请号：JP2004330983

申请日：2004-11-15

Applicant: Nobuyuki Matsui ,  Sutetsupu One:Kk ,  Toa Corp ,  ティーオーエー株式会社 ,  伸之 松井 ,  株式会社ステップワン

Inventor： MATSUI NOBUYUKI ,  ISOGAWA TEIJIRO ,  SODO HIROMI ,  MAEDA KAZUAKI ,  OGAWA YUZO

IPC: H04N1/46 ,  G06N3/00 ,  G06T1/00 ,  H04N1/60

Abstract: PROBLEM TO BE SOLVED: To obtain a processing result as expected corresponding to the luminance of color image data, in an image processor which processes the color image data by a neutral network.
SOLUTION: The color image data Do are inputted to the network part 16 of the neutral network 14 of a BP-method learning type after normalized to values of 0 to 1 by a normalization part 12. The network part 16 applies luminance conversion processing to the color image data Do on the basis of parameters Wnm, Wpn, θn and θp set from a parameter setting part 18. At this time, the color image data Do are processed as a quaternion. Namely, three components, an R component, a G component and a B component constituting the color image data Do are collectively processed as three-dimensional vector data. Furthermore, the parameters Wnm, Wpn, θn and θp set in the network part 16 are selected according to the luminance of the color image data Do.
COPYRIGHT: (C)2006,JPO&NCIPI

Abstract translation: 要解决的问题：在通过中性网络处理彩色图像数据的图像处理器中获得与彩色图像数据的亮度相对应的预期的处理结果。 解决方案：通过归一化部分12将彩色图像数据Do输入到BP方法学习型中性网络14的网络部分16，其归一化为0至1的值。网络部分16应用亮度转换 基于从参数设定部18设定的参数Wnm，Wpn，θn，θp对彩色图像数据Do进行处理。此时，彩色图像数据Do被作为四元数进行处理。 即，将构成彩色图像数据Do的R成分，G成分和B成分的三个成分统称为三维矢量数据。 此外，根据彩色图像数据Do的亮度来选择网络部分16中设置的参数Wnm，Wpn，θn和θp。 版权所有（C）2006，JPO＆NCIPI

公开(公告)号：JP2004110280A

公开(公告)日：2004-04-08

申请号：JP2002270303

申请日：2002-09-17

Applicant: Hironobu Fujiyoshi ,  Toa Corp ,  ティーオーエー株式会社 ,  藤吉 弘亘

Inventor： FUJIYOSHI HIRONOBU ,  KANEIDE TAKEO ,  OGAWA YUZO

IPC: H04N5/14 ,  G06T7/20 ,  H04N7/18

Abstract: PROBLEM TO BE SOLVED: To enhance the sensitivity with which a moving object is detected where its movement, if any, does not easily appear as the magnitude of a brightness change.
SOLUTION: A T calculating part 2 detects a change in the brightness of a pixel within an image frame. A T determining part 6 compares the detected change with a T threshold, and if the detected change is greater than the T threshold, determines that the movement of the object exists at the pixel. A threshold setting part 8 which creates the T threshold sets the T threshold by using the dispersion of the brightness values of pixels which corresponds to the pixel in the previous frame.
COPYRIGHT: (C)2004,JPO

公开(公告)号：JP2009210331A

公开(公告)日：2009-09-17

申请号：JP2008052169

申请日：2008-03-03

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： OGAWA YUZO

IPC: G01B11/00 ,  G06T1/00 ,  H04N5/225 ,  H04N5/232 ,  H04N17/00

Abstract: PROBLEM TO BE SOLVED: To achieve camera calibration very simply. SOLUTION: In a camera calibration apparatus and method which determines camera parameters for associating two-dimensional image coordinates set on a photographed image by a fixed camera with three-dimensional world coordinates set in the real space, a map image which simulates a plane (x, y, 0) of which the height z in the real space is zero is provided. The two dimensional coordinates (α, β) of the map image and the world coordinates (x, y, 0) of the plane are associated with each other by a scaler 40. When the position of an indicator placed in the real space is designated on the map image, therefore, the world coordinates (x, y, 0) of the position is determined, and by adding the height of the indicator to this, the world coordinates (x, y, z) at the height position of the indicator is determined. The world coordinates (x, y, z) of the indicator are thus determined very simply, achieving camera calibration very simply. COPYRIGHT: (C)2009,JPO&INPIT

Abstract translation: 要解决的问题：非常简单地实现相机校准。 解决方案：在相机校准装置和方法中，确定用于将通过固定照相机设置在拍摄图像上的二维图像坐标与设置在实际空间中的三维世界坐标相关联的相机参数，模拟 提供实际空间中的高度z为零的平面（x，y，0）。 地图图像的二维坐标（α，β）和平面的世界坐标（x，y，0）通过缩放器40彼此相关联。当指定在实际空间中的指示符的位置被指定 因此，在地图图像上，确定位置的世界坐标（x，y，0），并且通过将该指示符的高度相加，在该位置的高度位置处的世界坐标（x，y，z） 指标确定。 因此，非常简单地确定指示器的世界坐标（x，y，z），非常简单地实现相机校准。 版权所有（C）2009，JPO＆INPIT

公开(公告)号：JP2007235696A

公开(公告)日：2007-09-13

申请号：JP2006056268

申请日：2006-03-02

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： OGAWA YUZO

IPC: H04N5/232 ,  G06T1/00 ,  H04N5/225

CPC classification number: G06T3/60 ,  H04N5/23203

Abstract: PROBLEM TO BE SOLVED: To accurately control the direction of a camera on a photographed image as designated. SOLUTION: A monitor system 10 comprises a revolving camera 20 and a personal computer (PC) 30 as a control apparatus for controlling the direction of the camera 20. In such a monitor system 10, an image photographed by the camera 20 is displayed on a display 32 of the PC 30. When an arbitrary point is designated on the displayed photographed image by a mouse 34, the direction of the camera 20 is then controlled so that the designated point is positioned in the center of a screen. In such control, a mechanical axis coordinate system on the basis of a turning center of the camera 20 is conceptually introduced. In the mechanical axis coordinate system, the direction of the camera corresponding to the designated point is then determined, and the relevant camera is turned in the determined direction. As a result, the direction of the camera is accurately controlled to the direction corresponding to the designated point. COPYRIGHT: (C)2007,JPO&INPIT

Abstract translation: 要解决的问题：准确地控制照相机在指定的图像上的方向。 解决方案：监视器系统10包括作为用于控制照相机20的方向的控制装置的旋转照相机20和个人计算机（PC）30。在这种监视器系统10中，照相机20拍摄的图像是 显示在PC30的显示器32上。当通过鼠标34在所显示的拍摄图像上指定任意点时，然后控制照相机20的方向，使得指定点位于屏幕的中心。 在这种控制中，概念上引入了基于照相机20的转动中心的机械轴坐标系。 在机械轴坐标系中，然后确定与指定点对应的摄像机的方向，相关摄像机以确定的方向转动。 结果，相机的方向被精确地控制到与指定点相对应的方向。 版权所有（C）2007，JPO＆INPIT

公开(公告)号：JP2007078355A

公开(公告)日：2007-03-29

申请号：JP2005262650

申请日：2005-09-09

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： OGAWA YUZO

IPC: G01B11/02

Abstract: PROBLEM TO BE SOLVED: To precisely measure a height of a moving person, as to a height measuring instrument for measuring the height of the person based on a photographed image with the photographed person.
SOLUTION: A passerby 4 moving on a floor face 6 is photographed by a video camera 2. A personal computer 10 determines a height data of the passerby 4 from the floor face 6, in every of the plurality of images obtained from the video camera 2 photographing the passerby 4 moving in positions different respectively on the floor face 6. The personal computer 10 processes statistically the respective height data to determine the height of the passerby 4. An average value and a standard deviation of the respective height data are calculated, in the statistical processing, to settle the average value of the the height data having a value or more obtained by adding the standard deviation to the average value, as the height of the person.
COPYRIGHT: (C)2007,JPO&INPIT

Abstract translation: 要解决的问题：为了精确地测量移动人物的高度，关于用于根据拍摄的人拍摄的图像来测量人的身高的高度测量仪器。

解决方案：通过摄像机2拍摄在地面6上移动的路人4。个人计算机10从从地板面6确定的从多个图像获得的每个图像中确定路人4的高度数据 视频摄像机2拍摄在不同于地面6上的位置移动的路人4.个人计算机10对各个高度数据进行统计处理，以确定路人4的高度。各个高度数据的平均值和标准偏差为 在统计处理中，将通过将标准偏差与平均值相加而获得的值的多个高度数据的平均值作为人的高度来计算。 版权所有（C）2007，JPO＆INPIT

公开(公告)号：JP2006245795A

公开(公告)日：2006-09-14

申请号：JP2005056150

申请日：2005-03-01

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： OGAWA YUZO

IPC: H04N7/18 ,  G06T7/20

Abstract: PROBLEM TO BE SOLVED: To track the movement of a mobile and displaying the result on one screen on the basis of images photographed by a plurality of cameras.
SOLUTION: Mobile detection and 3D conversion sections 28, 30 detect the mobile depending on imaging signals generated from a camera 12 for imaging an imaging region 18 and a camera 14 for imaging an imaging region 20 which is partly overlapped with the imaging region 18, and generate labels including mobile body positional information representing the position of the mobile and mobile position accuracy information representing the accuracy of the mobile positional information. An integration server 36 integrates the positional information items of the labels on the basis of the mobile position accuracy information of both the labels when the labels correspond to one and same mobile. Images corresponding to the imaging regions 18, 20 are displayed on one display screen of clients 38, 42, indicators corresponding to the labels are displayed at positions corresponding to the positional information items of the labels, and after the labels are integrated, an indicator is displayed on the basis of the integrated label.
COPYRIGHT: (C)2006,JPO&NCIPI

Abstract translation: 要解决的问题：基于由多个照相机拍摄的图像来跟踪移动体的移动并在一个屏幕上显示结果。 解决方案：移动检测和3D转换部分28,30根据从相机12产生的成像信号来检测移动体，用于对成像区域18进行成像和照相机14，用于对与成像区域部分重叠的成像区域20成像 并且生成包括表示移动体的位置信息的移动体位置信息和表示移动位置信息的精度的移动位置精度信息的标签。 当标签对应于同一移动站时，集成服务器36基于两个标签的移动位置精度信息来集成标签的位置信息项。 对应于成像区域18,20的图像被显示在客户端38,42的一个显示屏幕上，与标签对应的指示符显示在与标签的位置信息项相对应的位置处，并且在标签被集成之后， 在综合标签的基础上显示。 版权所有（C）2006，JPO＆NCIPI

公开(公告)号：JP2005003377A

公开(公告)日：2005-01-06

申请号：JP2003163718

申请日：2003-06-09

Applicant: Hironobu Fujiyoshi ,  Toa Corp ,  ティーオーエー株式会社 ,  弘亘 藤吉

Inventor： FUJIYOSHI HIRONOBU ,  KANEIDE TAKEO ,  OGAWA YUZO

IPC: G01B11/00 ,  G06T1/00 ,  G06T3/00 ,  H04N7/18

Abstract: PROBLEM TO BE SOLVED: To automatically acquiring the height of an object to be sensed by specifying the object to be sensed in a two-dimensional image acquired by one camera. SOLUTION: A master camera 2 two-dimensionally photographs both a reference plane 4 in a three-dimensional space and the object to be sensed in the reference plane. The object to be sensed is determined on the basis of a two-dimensional image of the camera 2. Both first two-dimensional coordinates of the image of the object to be sensed in a two-dimensional reference plane 4a corresponding to a reference plane 4 in the two-dimensional image and second two-dimensional coordinates of the object to be sensed at a distance from the two-dimensional reference plane 4a on the basis of the two-dimensional coordinates are determined by a personal computer 8. The personal computer 8 converts the first two-dimensional coordinates into first three-dimensional coordinates in a reference plane 4 in a three-dimensional space and converts the second coordinates into second three-dimensional coordinates. The conversion into the second three-dimensional coordinates is performed by arranging the location of a first or second three-dimensional coordinate axis in the second three-dimensional coordinates at the location of first or second three-dimensional coordinates of the first three-dimensional coordinates. COPYRIGHT: (C)2005,JPO&NCIPI

Abstract translation: 要解决的问题：通过在由一个摄像机获取的二维图像中指定要感测的对象来自动获取要感测的对象的高度。 解决方案：主摄像机2二维地照相三维空间中的参考平面4和在参考平面中要被感测的对象。 基于相机2的二维图像来确定要被感测的物体。在对应于参考平面4的二维参考平面4a中要被感测的对象的图像的第一二维坐标 在二维坐标的基础上，距离二维基准面4a距离被感测物体的二维图像和二维坐标由个人计算机8确定。个人计算机8 将第一二维坐标转换为三维空间中的参考平面4中的第一三维坐标，并将第二坐标转换为第二三维坐标。 通过在第一三维坐标的第一或第三三维坐标的位置处将第一或第二三维坐标轴的位置布置在第二三维坐标中来执行到第二三维坐标的转换 。 版权所有（C）2005，JPO＆NCIPI

公开(公告)号：JP2009105802A

公开(公告)日：2009-05-14

申请号：JP2007277419

申请日：2007-10-25

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： OGAWA YUZO

IPC: H04N7/18 ,  H04N5/225 ,  H04N5/232

Abstract: PROBLEM TO BE SOLVED: To simulate which range can be photographed before installing a camera.
SOLUTION: A top view (6) of a prescribed area is displayed on an upper surface window 4 and a camera upper surface display 10 arranged on an optional position in the upper surface window 4 is displayed on the arrangement position. According to the display of the camera upper surface display 14, a camera horizontal visual field display 18 is displayed in the upper surface window 4. Simultaneously, a camera elevation display 16 and a camera vertical visual field display 20 are displayed in an elevation window 12. In a 3D image display window 46, a 3D image supposed to be photographed by the camera is displayed.
COPYRIGHT: (C)2009,JPO&INPIT

Abstract translation: 要解决的问题：模拟在安装相机之前可以拍摄哪个范围。

解决方案：在上表面窗4上显示规定区域的顶视图（6），并且布置在上表面窗4中的可选位置的照相机上表面显示器10被显示在布置位置。 根据照相机上表面显示器14的显示，在上表面窗口4中显示照相机水平视野显示器18.同时，在仰角窗12中显示照相机仰视显示器16和照相机垂直视野显示器20 在3D图像显示窗口46中，显示由相机拍摄的3D图像。 版权所有（C）2009，JPO＆INPIT

公开(公告)号：JP2008102589A

公开(公告)日：2008-05-01

申请号：JP2006282496

申请日：2006-10-17

Applicant: Toa Corp ,  ティーオーエー株式会社

Inventor： MATSUI NOBUYUKI ,  KAMIURA NAOTAKE ,  ISOGAWA TEIJIRO ,  OGAWA YUZO ,  OTSUKA AKITSUGU ,  IWATANI KENJI

IPC: G06T7/00 ,  G06N3/00 ,  H04N5/232 ,  H04N7/18

CPC classification number: H04N5/262 ,  G06T7/277 ,  H04N19/537

Abstract: PROBLEM TO BE SOLVED: To provide a novel moving image processor detecting a moving object in an moving image using a self-organizing map. SOLUTION: A composite video signal output from a camera 20 is converted into color image data by an input conversion part 50. The color image data is input to a feature extraction part 58 through an image dividing part 52 and a frame setting part 56. The feature extraction part 58 extracts n-dimensional features of the input color image data, and the extracted feature data is input to a control part 60. The control part 60 constitutes a block unit learning type self-organizing map together with a map 62, and identifies whether each pixel forms a moving object region or a background region by applying the feature data to the map 62. Based on the identified result, the control part 60 controls an output conversion part 70 to display only the moving object region on a monitor 40. COPYRIGHT: (C)2008,JPO&INPIT

Abstract translation: 要解决的问题：提供使用自组织图来检测运动图像中的移动物体的新颖的运动图像处理器。 解决方案：从相机20输出的复合视频信号通过输入转换部分50转换为彩色图像数据。彩色图像数据通过图像分割部分52和帧设置部分被输入到特征提取部分58 特征提取部分58提取输入彩色图像数据的n维特征，并将所提取的特征数据输入到控制部分60.控制部分60构成块单元学习型自组织图与地图 并且通过将特征数据应用于地图62来识别每个像素是否形成移动物体区域或背景区域。基于所识别的结果，控制部分60控制输出转换部分70以仅显示移动物体区域 监视器40.版权所有（C）2008年，JPO＆INPIT