公开(公告)号：US07912251B2

公开(公告)日：2011-03-22

申请号：US12046715

申请日：2008-03-12

申请人： Tomoharu Suzuki ,  Jun Adachi ,  Shinichi Kojima ,  Kenichi Ohue ,  Yuji Ninagawa

发明人： Tomoharu Suzuki ,  Jun Adachi ,  Shinichi Kojima ,  Kenichi Ohue ,  Yuji Ninagawa

IPC分类号： G06K9/00 ,  H04N9/47 ,  G03B17/00

CPC分类号： A61B3/10 ,  A61B3/113 ,  G06K9/00604 ,  G06T7/12 ,  G06T2207/30201

摘要： An eyelid detection apparatus includes edge image generating means for generating an edge image representing a magnitude of pixel value change per pixel in a predetermined direction in a region including an eye, based upon an image of the region; local peak value point searching means for searching a local peak value point, where the magnitude of pixel value change reaches a local peak value in the predetermined direction, in the edge image; and boundary point detecting means for detecting at least one of a first boundary point indicating a boundary between an upper eyelid and an eyeball and a second boundary point indicating a boundary between a lower eyelid and the eyeball, based upon a point which is shifted from the local peak value point in a direction towards the eyeball.

摘要翻译： 眼睑检测装置包括边缘图像生成装置，用于基于该区域的图像，生成表示在包括眼睛的区域中的每个像素在每个像素上的像素值变化幅度的边缘图像; 局部峰值点搜索装置，用于在边缘图像中搜索像素值变化的幅度达到预定方向上的局部峰值的局部峰值点; 以及边界点检测装置，用于基于从所述眼睑和所述眼球偏移的点检测指示上眼睑和眼球之间的边界的第一边界点和指示下眼睑和眼球之间的边界的第二边界点中的至少一个 局部峰值点朝向眼球方向。

公开(公告)号：US08435188B2

公开(公告)日：2013-05-07

申请号：US12443775

申请日：2007-11-06

申请人： Kenichi Ohue ,  Yuji Ninagawa ,  Kentaro Takahashi ,  Shin-ichi Kojima ,  Jun Adachi ,  Tomoharu Suzuki

发明人： Kenichi Ohue ,  Yuji Ninagawa ,  Kentaro Takahashi ,  Shin-ichi Kojima ,  Jun Adachi ,  Tomoharu Suzuki

IPC分类号： A61B5/00

CPC分类号： G06K9/00248 ,  A61B3/14 ,  A61B5/18 ,  B60K28/06 ,  G06K9/00281 ,  G08B21/06

摘要： An eye opening detection system that includes an imaging mechanism that captures an image of the face of a detected subject, an edge extraction mechanism that extracts the edge of the image captured, and an upper and lower eyelid detection mechanism that detects the upper and lower eyelids of the detected subject according to the edge extracted, and that detects the eye opening of the detected subject with reference to a detected distance between the upper and lower eyelids. The upper and lower eyelid detection detects the upper eyelid and detects the lower eyelid with reference to the upper eyelid detected.

摘要翻译： 一种眼睛打开检测系统，其包括拍摄被检测对象的脸部的图像的成像机构，提取被捕获的图像的边缘的边缘提取机构，以及检测上下眼睑的上下眼睑检测机构 根据提取的边缘检测检测到的被检体，并且根据检测到的上眼睑和下眼睑之间的距离来检测被检测物体的眼睛开度。 上下眼睑检测检测上眼睑，并根据检测到的上眼睑检测下眼睑。

公开(公告)号：US20080226138A1

公开(公告)日：2008-09-18

申请号：US12046715

申请日：2008-03-12

申请人： Tomoharu Suzuki ,  Jun Adachi ,  Shinichi Kojima ,  Kenichi Ohue ,  Yuji Ninagawa

发明人： Tomoharu Suzuki ,  Jun Adachi ,  Shinichi Kojima ,  Kenichi Ohue ,  Yuji Ninagawa

IPC分类号： G06K9/00

CPC分类号： A61B3/10 ,  A61B3/113 ,  G06K9/00604 ,  G06T7/12 ,  G06T2207/30201

摘要： An eyelid detection apparatus includes edge image generating means for generating an edge image representing a magnitude of pixel value change per pixel in a predetermined direction in a region including an eye, based upon an image of the region; local peak value point searching means for searching a local peak value point, where the magnitude of pixel value change reaches a local peak value in the predetermined direction, in the edge image; and boundary point detecting means for detecting at least one of a first boundary point indicating a boundary between an upper eyelid and an eyeball and a second boundary point indicating a boundary between a lower eyelid and the eyeball, based upon a point which is shifted from the local peak value point in a direction towards the eyeball.

摘要翻译： 眼睑检测装置包括边缘图像生成装置，用于基于该区域的图像，生成表示在包括眼睛的区域中的每个像素在每个像素上的像素值变化幅度的边缘图像; 局部峰值点搜索装置，用于在边缘图像中搜索像素值变化的幅度达到预定方向上的局部峰值的局部峰值点; 以及边界点检测装置，用于基于从所述眼睑和所述眼球偏移的点检测指示上眼睑和眼球之间的边界的第一边界点和指示下眼睑和眼球之间的边界的第二边界点中的至少一个 局部峰值点朝向眼球方向。

公开(公告)号：US08606012B2

公开(公告)日：2013-12-10

申请号：US11509844

申请日：2006-08-25

申请人： Tomoharu Suzuki ,  Shinichi Eguchi

发明人： Tomoharu Suzuki ,  Shinichi Eguchi

IPC分类号： G06K9/46

CPC分类号： G06K9/00067 ,  G06K9/56 ,  G06K2009/00932 ,  G06T7/12 ,  G06T7/155 ,  G06T2207/20036 ,  G06T2207/20192 ,  G06T2207/30088 ,  G06T2207/30101

摘要： An image processing method extracts line segment elements from grayscale captured images, so that line segments are extracted at high-speed without being influenced by contrast ratio, even if morphology processing is used. A selection processing select an area where continuous line segments possibly exist from the captured image and a morphology processing detect line segment elements in the selected area by scanning an operator. Line segments can be extracted in a plurality of directions at high-speed. Also by an extraction target area selection processing, an area of which contrast ratio is low, continuing from an area of which contrast ratio is high in the line segment growth direction is also extracted as one line segment.

摘要翻译： 图像处理方法从灰度拍摄图像中提取线段元素，使得即使使用形态学处理也能以高速提取线段而不受对比度的影响。 选择处理从拍摄图像中选择可能存在连续线段的区域，并且形态学处理通过扫描操作者来检测所选区域中的线段元素。 可以高速地在多个方向上提取线段。 另外，通过提取目标区域选择处理，也提取对比度低的区域，从线段生长方向的对比度高的区域延续为一个线段。

公开(公告)号：US06603244B2

公开(公告)日：2003-08-05

申请号：US10082068

申请日：2002-02-26

申请人： Yoshihisa Sugiyama ,  Tomoharu Suzuki ,  Kenichi Kumagai

发明人： Yoshihisa Sugiyama ,  Tomoharu Suzuki ,  Kenichi Kumagai

IPC分类号： F02M5706

CPC分类号： H01T21/02 ,  H01T13/39

摘要： A spark plug includes: a central electrode; an insulator surrounding the central electrode radially; a metallic shell surrounding the insulator radially; and a ground electrode having a first end connected to the metallic shell and a second end defining a side face. The ground electrode is so bent that the side face of the second end faces the central electrode. The ground electrode contains: a nickel in a range from 58% to 71% by weight, a chromium in a range from 21% to 25% by weight, an iron in a range from 7% to 20% by weight, and an aluminum in a range from 1% to 2% by weight. The ground electrode has a Vickers hardness in a range from Hv 140 to Hv 220 through a Vickers hardness test specified in Japanese Industrial Standard Z2244. A load 9.8 N is applied to the ground electrode in the hardness test.

公开(公告)号：US08013758B2

公开(公告)日：2011-09-06

申请号：US12441863

申请日：2007-09-20

申请人： Tomoharu Suzuki

发明人： Tomoharu Suzuki

IPC分类号： G08G1/16

CPC分类号： G06K9/00805 ,  G06K9/00221 ,  G06K9/00604 ,  G06T7/73 ,  G06T2207/30264 ,  G08G1/166

摘要： An obstacle detecting portion (11) on a vehicle detects an obstacle behind the vehicle. A CPU (20) detects the direction of the driver's line of sight based on a driver's face image captured by a camera (12). The CPU (20) determines whether the direction of the driver's line of sight directed to mirrors (51L, 51R) reflecting an image of the obstacle behind the vehicle. According to the result of the determination, the CPU (20) sets the level of an alarm to be outputted by warning signal outputting portions (15, 16).

摘要翻译： 车辆上的障碍物检测部（11）检测车辆后方的障碍物。 CPU（20）基于由照相机（12）拍摄的驾驶员的脸部图像来检测驾驶员的视线的方向。 CPU（20）判断驾驶员的视线方向是否反映车辆后方的障碍物的反射镜（51L，51R）。 根据判定结果，CPU（20）设定要由警告信号输出部（15,16）输出的报警电平。

公开(公告)号：US20100060440A1

公开(公告)日：2010-03-11

申请号：US12441863

申请日：2007-09-20

申请人： Tomoharu Suzuki

发明人： Tomoharu Suzuki

IPC分类号： B60Q1/00

CPC分类号： G06K9/00805 ,  G06K9/00221 ,  G06K9/00604 ,  G06T7/73 ,  G06T2207/30264 ,  G08G1/166

摘要： An obstacle detecting portion (11) on a vehicle detects an obstacle behind the vehicle. A CPU (20) detects the direction of the driver's line of sight based on a driver's face image captured by a camera (12). The CPU (20) determines whether the direction of the driver's line of sight directed to mirrors (51L, 51R) reflecting an image of the obstacle behind the vehicle. According to the result of the determination, the CPU (20) sets the level of an alarm to be outputted by warning signal outputting portions (15, 16).

摘要翻译： 车辆上的障碍物检测部（11）检测车辆后方的障碍物。 CPU（20）基于由照相机（12）拍摄的驾驶员的脸部图像来检测驾驶员的视线的方向。 CPU（20）判断驾驶员的视线方向是否反映车辆后方的障碍物的反射镜（51L，51R）。 根据判定结果，CPU（20）设定要由警告信号输出部（15,16）输出的报警电平。

公开(公告)号：US08229250B2

公开(公告)日：2012-07-24

申请号：US12368506

申请日：2009-02-10

申请人： Tomoharu Suzuki ,  Shinichi Eguchi

发明人： Tomoharu Suzuki ,  Shinichi Eguchi

IPC分类号： G06K9/40

CPC分类号： G06K9/6211 ,  G06K9/6212

摘要： A pattern alignment method performs alignment of the comparison source pattern or the comparison target pattern that has been subjected to the angle-scale conversion with the comparison source pattern. Angular deviations and scale factors between the comparison source pattern and the comparison target pattern are computed separately, after angle and scale conversion, the measured template matching is performed. Therefore, parallel-displacement alignment can be made faster and precise alignment is possible. Template matching processing can be minimized, and aligning can be performed precisely and rapidly.

摘要翻译： 图案对准方法执行比较源图案或经过角度比例变换的比较对象图案与比较源图案的对准。 在比较源图案和比较目标图案之间的角度偏差和比例因子分别计算，在角度和尺度转换之后，执行测量的模板匹配。 因此，能够进行平行位移对准，并且可以进行精确的对准。 可以最小化模板匹配处理，并且可以精确而快速地进行对齐。

公开(公告)号：US07486801B2

公开(公告)日：2009-02-03

申请号：US11236591

申请日：2005-09-28

申请人： Tomoharu Suzuki ,  Kazuya Watanabe ,  Kosuke Sato ,  Jun Amano ,  Katsuhiko Umeno

发明人： Tomoharu Suzuki ,  Kazuya Watanabe ,  Kosuke Sato ,  Jun Amano ,  Katsuhiko Umeno

IPC分类号： G06K9/00

CPC分类号： G06T3/0081 ,  G01C11/02 ,  G06T15/20 ,  H04N7/181

摘要： A monitoring system for monitoring surroundings of a vehicle by displaying images taken by a plurality of cameras provided at the vehicle on a display apparatus provided in a vehicle compartment includes an image processing portion. The image processing portion includes a boundary-determining portion for determining a boundary of the neighboring images taken by the plurality of cameras for synthesizing the neighboring images in a horizontal direction by approximating the boundary to an exponential curve, a horizontally normalizing portion for normalizing the neighboring images in a horizontal direction so that the boundary approximated to the exponential curve is converted into a linear vertical boundary, a vertically compensating portion for compensating a vertical displacement between the neighboring images on the linear vertical boundary, and a pixel-adjusting portion for adjusting the number of pixels of the synthesized image to the number of pixels suitable for displaying the synthesized image produced by the image processing portion on the display apparatus.

摘要翻译： 通过将设置在车辆上的多个摄像机拍摄的图像显示在设置在车厢中的显示装置上来监视车辆的环境的监视系统包括图像处理部分。 图像处理部分包括：边界确定部分，用于通过近似指向曲线的边界来确定用于合成水平方向上的相邻图像的多个相机拍摄的相邻图像的边界;水平归一化部分，用于对相邻的图像进行归一化 图像沿水平方向，使得近似于指数曲线的边界被转换为线性垂直边界，用于补偿线性垂直边界上的相邻图像之间的垂直位移的垂直补偿部分和用于调整图像的像素调整部分 合成图像的像素数与适合于显示由显示装置上的图像处理部分产生的合成图像的像素数目相对应。

公开(公告)号：US20070177825A1

公开(公告)日：2007-08-02

申请号：US11509844

申请日：2006-08-25

申请人： Tomoharu Suzuki ,  Shinichi Eguchi

发明人： Tomoharu Suzuki ,  Shinichi Eguchi

IPC分类号： G06K9/56

CPC分类号： G06K9/00067 ,  G06K9/56 ,  G06K2009/00932 ,  G06T7/12 ,  G06T7/155 ,  G06T2207/20036 ,  G06T2207/20192 ,  G06T2207/30088 ,  G06T2207/30101

摘要： An image processing method extracts line segment elements from grayscale captured images, so that line segments are extracted at high-speed without being influenced by contrast ratio, even if morphology processing is used. A selection processing select an area where continuous line segments possibly exist from the captured image and a morphology processing detect line segment elements in the selected area by scanning an operator. Line segments can be extracted in a plurality of directions at high-speed. Also by an extraction target area selection processing, an area of which contrast ratio is low, continuing from an area of which contrast ratio is high in the line segment growth direction is also extracted as one line segment.

摘要翻译： 图像处理方法从灰度拍摄图像中提取线段元素，使得即使使用形态学处理也能以高速提取线段而不受对比度的影响。 选择处理从拍摄图像中选择可能存在连续线段的区域，并且形态学处理通过扫描操作者来检测所选区域中的线段元素。 可以高速地在多个方向上提取线段。 另外，通过提取目标区域选择处理，也提取对比度低的区域，从线段生长方向的对比度高的区域延续为一个线段。