公开(公告)号：US20070003148A1

公开(公告)日：2007-01-04

申请号：US11500977

申请日：2006-08-09

申请人： Shoji Muramatsu ,  Yuji Otsuka ,  Yoshiki Kobayashi ,  Hiroshi Takenaga ,  Jiro Takezaki ,  Tatsuhiko Monji ,  Isao Furusawa

发明人： Shoji Muramatsu ,  Yuji Otsuka ,  Yoshiki Kobayashi ,  Hiroshi Takenaga ,  Jiro Takezaki ,  Tatsuhiko Monji ,  Isao Furusawa

IPC分类号： G06K9/36

CPC分类号： G06T1/60 ,  G06T7/70

摘要： Information of light from a subject is converted into information of the electric charges to generate image data for one screen in an image pickup device, the image data is outputted to an image processing LSI, only the image data belonging to a plurality of areas is selected by a processing amount reduction unit, the selected image data is transferred to a RAM in a single chop by a data transfer unit, and the processing of recognizing a white line is executed by a CPU on the basis of the image data stored in the RAM.

摘要翻译： 将来自被摄体的光的信息转换成电荷的信息，以生成图像拾取装置中的一个屏幕的图像数据，将图像数据输出到图像处理LSI，仅选择属于多个区域的图像数据 通过处理量减少单元，所选择的图像数据由数据传送单元以单个切片传送到RAM，并且基于存储在RAM中的图像数据由CPU执行识别白线的处理 。

公开(公告)号：US07110613B2

公开(公告)日：2006-09-19

申请号：US10101052

申请日：2002-03-20

申请人： Shoji Muramatsu ,  Yuji Otsuka ,  Yoshiki Kobayashi ,  Hiroshi Takenaga ,  Jiro Takezaki ,  Tatsuhiko Monji ,  Isao Furusawa

发明人： Shoji Muramatsu ,  Yuji Otsuka ,  Yoshiki Kobayashi ,  Hiroshi Takenaga ,  Jiro Takezaki ,  Tatsuhiko Monji ,  Isao Furusawa

IPC分类号： G06K9/36

CPC分类号： G06T1/60 ,  G06T7/70

摘要： Information of light from a subject is converted into information of the electric charges to generate image data for one screen in an image pickup device, the image data is outputted to an image processing LSI, only the image data belonging to a plurality of areas is selected by a processing amount reduction unit, the selected image data is transferred to a RAM in a single chop by a data transfer unit, and the processing of recognizing a white line is executed by a CPU on the basis of the image data stored in the RAM.

公开(公告)号：US08730325B2

公开(公告)日：2014-05-20

申请号：US12365695

申请日：2009-02-04

申请人： Yuji Otsuka ,  Masayuki Takemura ,  Tatsuhiko Monji ,  Isao Furusawa

发明人： Yuji Otsuka ,  Masayuki Takemura ,  Tatsuhiko Monji ,  Isao Furusawa

IPC分类号： G09B9/04 ,  G06K9/00

CPC分类号： G06K9/00798 ,  G05D1/0246 ,  G05D2201/0213 ,  G06K9/3233

摘要： A traveling lane detector according to the present invention includes: an imaging unit mounted on a vehicle to take a road surface image; and an image processor performing image processing on the image to detect lane marks on the road surface. The image processor judges whether the vehicle is crossing the lane marks, and, when the vehicle is not crossing any of the lane marks, defines first and second windows, in the image, for detecting the lane marks located respectively on left and right parts of a road surface in front of or behind the vehicle, performs image processing on the image in each of the windows to detect the lane marks, and, when the vehicle is crossing any of the lane marks, defines a third window including the currently-crossed lane mark in the image, performs image processing on the image in the third window to detect the lane mark.

摘要翻译： 根据本发明的行车道检测器包括：安装在车辆上以拍摄路面图像的成像单元; 以及对所述图像执行图像处理的图像处理器，以检测路面上的车道标记。 图像处理器判断车辆是否越过车道标记，并且当车辆没有穿过任何车道标记时，在图像中限定第一和第二窗口，用于检测分别位于左侧和右侧的车道标记 在车辆前方或后方的路面上，对每个窗口中的图像执行图像处理以检测车道标记，并且当车辆正在穿过任何车道标记时，限定包括当前交叉的第三窗口 图像中的车道标记，对第三窗口中的图像执行图像处理以检测车道标记。

公开(公告)号：US20090201370A1

公开(公告)日：2009-08-13

申请号：US12365695

申请日：2009-02-04

申请人： Yuji OTSUKA ,  Masayuki Takemura ,  Tatsuhiko Monji ,  Isao Furusawa

发明人： Yuji OTSUKA ,  Masayuki Takemura ,  Tatsuhiko Monji ,  Isao Furusawa

IPC分类号： H04N7/18

CPC分类号： G06K9/00798 ,  G05D1/0246 ,  G05D2201/0213 ,  G06K9/3233

摘要： A traveling lane detector according to the present invention includes: an imaging unit mounted on a vehicle to take a road surface image; and an image processor performing image processing on the image to detect lane marks on the road surface. The image processor judges whether the vehicle is crossing the lane marks, and, when the vehicle is not crossing any of the lane marks, defines first and second windows, in the image, for detecting the lane marks located respectively on left and right parts of a road surface in front of or behind the vehicle, performs image processing on the image in each of the windows to detect the lane marks, and, when the vehicle is crossing any of the lane marks, defines a third window including the currently-crossed lane mark in the image, performs image processing on the image in the third window to detect the lane mark.

摘要翻译： 根据本发明的行车道检测器包括：安装在车辆上以拍摄路面图像的成像单元; 以及对所述图像执行图像处理的图像处理器，以检测路面上的车道标记。 图像处理器判断车辆是否越过车道标记，并且当车辆没有穿过任何车道标记时，在图像中限定第一和第二窗口，用于检测分别位于左侧和右侧的车道标记 在车辆前方或后方的路面上，对每个窗口中的图像执行图像处理以检测车道标记，并且当车辆正在穿过任何车道标记时，限定包括当前交叉的第三窗口 图像中的车道标记，对第三窗口中的图像执行图像处理以检测车道标记。

公开(公告)号：US08207834B2

公开(公告)日：2012-06-26

申请号：US12363129

申请日：2009-01-30

申请人： Masayuki Takemura ,  Shoji Muramatsu ,  Tatsuhiko Monji ,  Yuji Otsuka

发明人： Masayuki Takemura ,  Shoji Muramatsu ,  Tatsuhiko Monji ,  Yuji Otsuka

IPC分类号： B60Q1/00 ,  G08G1/00 ,  G06K9/00 ,  G01S13/88

CPC分类号： G06K9/00805 ,  B60W30/095 ,  B60W30/10 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30261 ,  G08G1/165 ,  G08G1/166

摘要： A virtual vehicle which approaches to a monitor-side vehicle and a virtual background are defined in a camera image, and a region in which a virtual vehicle moves fast with respect to a virtual background is defined as a first region F1, and a region in which a virtual vehicle moves slowly with respect to a virtual background is defined as a second region F2. Then, the first region F1 and the second region F2 combined with an actual camera image. In the first region F1, in which the virtual vehicle moves fast, a monitored vehicle is detected by a movement aspect of feature portions in the region, and in the second region F2, in which the virtual vehicle moves slowly, a monitored vehicle is detected by pattern recognition.

摘要翻译： 在摄像机图像中定义接近监视器侧车辆和虚拟背景的虚拟车辆，并且将虚拟车辆相对于虚拟背景快速移动的区域定义为第一区域F1，并且区域 将虚拟车辆相对于虚拟背景缓慢移动的物体被定义为第二区域F2。 然后，第一区域F1和第二区域F2与实际照相机图像组合。 在虚拟车辆快速移动的第一区域F1中，通过该区域中的特征部分的运动方面检测被监视的车辆，并且在虚拟车辆缓慢移动的第二区域F2中，检测被监视的车辆 通过模式识别。

公开(公告)号：US20090195410A1

公开(公告)日：2009-08-06

申请号：US12363129

申请日：2009-01-30

申请人： Masayuki TAKEMURA ,  Shoji Muramatsu ,  Tatsuhiko Monji ,  Yuji Otsuka

发明人： Masayuki TAKEMURA ,  Shoji Muramatsu ,  Tatsuhiko Monji ,  Yuji Otsuka

IPC分类号： G08G1/133 ,  G06T7/00

CPC分类号： G06K9/00805 ,  B60W30/095 ,  B60W30/10 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30261 ,  G08G1/165 ,  G08G1/166

摘要： A virtual vehicle which approaches to a monitor-side vehicle and a virtual background are defined in a camera image, and a region in which a virtual vehicle moves fast with respect to a virtual background is defined as a first region F1, and a region in which a virtual vehicle moves slowly with respect to a virtual background is defined as a second region F2. Then, the first region F1 and the second region F2 are applied to an actual camera image. In the first region F1 in which a virtual vehicle moves fast, a monitored vehicle is detected by a movement aspect of feature portions in the region, and in the second region F2 in which a virtual vehicle moves slowly, a monitored vehicle is detected by pattern recognition.

摘要翻译： 在摄像机图像中定义接近监视器侧车辆和虚拟背景的虚拟车辆，并且将虚拟车辆相对于虚拟背景快速移动的区域定义为第一区域F1，并且区域 将虚拟车辆相对于虚拟背景缓慢移动的物体被定义为第二区域F2。 然后，将第一区域F1和第二区域F2应用于实际的摄像机图像。 在虚拟车辆快速移动的第一区域F1中，通过区域中的特征部分的运动方面检测被监视的车辆，并且在虚拟车辆缓慢移动的第二区域F2中，通过模式检测被监视的车辆 承认。

公开(公告)号：US08212878B2

公开(公告)日：2012-07-03

申请号：US11769986

申请日：2007-06-28

申请人： Takeshi Shima ,  Shoji Muramatsu ,  Yuji Otsuka ,  Tatsuhiko Monji ,  Kota Irie

发明人： Takeshi Shima ,  Shoji Muramatsu ,  Yuji Otsuka ,  Tatsuhiko Monji ,  Kota Irie

IPC分类号： H04N5/225

CPC分类号： G06T7/80 ,  G06T2207/30252

摘要： An on-vehicle camera calibration apparatus includes: an on-vehicle camera; a camera parameter calculation unit configured to calculate camera parameters from a characteristic amount of a road surface sign photographed by the on-vehicle camera and recognized by an image processing and to output the camera parameters, wherein the camera parameters include an installation height and installation angle of the on-vehicle camera in photographing; and a camera parameter calibration unit configured to perform optical axis calibration control of the on-vehicle camera by the camera parameters output from the camera parameter calculation unit.

摘要翻译： 车载摄像机校准装置包括：车载摄像机; 摄像机参数计算单元，被配置为根据由车载摄像机拍摄并通过图像处理识别的路面符号的特征量来计算摄像机参数并输出摄像机参数，其中摄像机参数包括安装高度和安装角度 的车载摄像头; 以及相机参数校准单元，被配置为通过从相机参数计算单元输出的相机参数来执行车载摄像机的光轴校准控制。

公开(公告)号：US07957559B2

公开(公告)日：2011-06-07

申请号：US11777585

申请日：2007-07-13

申请人： Takeshi Shima ,  Shoji Muramatsu ,  Yuji Otsuka ,  Kimiyoshi Machii ,  Mirai Higuchi ,  Tatsuhiko Monji ,  Kota Irie

发明人： Takeshi Shima ,  Shoji Muramatsu ,  Yuji Otsuka ,  Kimiyoshi Machii ,  Mirai Higuchi ,  Tatsuhiko Monji ,  Kota Irie

IPC分类号： G06K9/00

CPC分类号： G06K9/00798

摘要： In conventional systems using an onboard camera disposed rearward of a vehicle for recognizing an object surrounding the vehicle, the object is recognized by the camera disposed rearward of the vehicle. In the image recognized by the camera, a road surface marking taken by the camera appears at a lower end of a screen of the image, which makes it difficult to predict a specific position in the screen from which the road surface marking appears. Further, an angle of depression of the camera is large, and it is a short period of time to acquire the object. Therefore, it is difficult to improve a recognition rate and to reduce false recognition. Results of recognition (type, position, angle, recognition time) made by a camera disposed forward of the vehicle, are used to predict a specific timing and a specific position of a field of view of a camera disposed rearward of the vehicle, at which the object appears. Parameters of recognition logic of the rearwardly disposed camera and processing timing are then optimally adjusted. Further, luminance information of the image from the forwardly disposed camera is used to predict possible changes to be made in luminance of the field of view of the rearwardly disposed camera. Gain and exposure time of the rearwardly disposed camera are then adjusted.

摘要翻译： 在使用设置在车辆后方的车载照相机以识别车辆周围的物体的常规系统中，物体被设置在车辆后方的照相机识别。 在由相机识别的图像中，由相机拍摄的路面标记出现在图像的屏幕的下端，这使得难以预测出现路面标记的屏幕中的特定位置。 此外，相机的下压角度大，获取物体的时间短。 因此，难以提高识别率并减少错误识别。 使用布置在车辆前方的相机进行的识别（类型，位置，角度，识别时间）的结果用于预测设置在车辆后方的相机的视场的具体定时和特定位置， 该对象出现。 然后，最佳地调整后置摄像机的识别逻辑和处理定时的参数。 此外，来自前方照相机的图像的亮度信息用于预测在向后设置的相机的视场的亮度可能发生的变化。 然后调整向后放置的相机的增益和曝光时间。

公开(公告)号：US20080013789A1

公开(公告)日：2008-01-17

申请号：US11777585

申请日：2007-07-13

申请人： Takeshi SHIMA ,  Shoji Muramatsu ,  Yuji Otsuka ,  Kimiyoshi Machii ,  Mirai Higuchi ,  Tatsuhiko Monji ,  Kota Irie

发明人： Takeshi SHIMA ,  Shoji Muramatsu ,  Yuji Otsuka ,  Kimiyoshi Machii ,  Mirai Higuchi ,  Tatsuhiko Monji ,  Kota Irie

IPC分类号： G06K9/00

CPC分类号： G06K9/00798

摘要： In conventional systems using an onboard camera disposed rearward of a vehicle for recognizing an object surrounding the vehicle, the object is recognized by the camera disposed rearward of the vehicle. In the image recognized by the camera, a road surface marking taken by the camera appears at a lower end of a screen of the image, which makes it difficult to predict a specific position in the screen from which the road surface marking appears. Further, an angle of depression of the camera is large, and it is a short period of time to acquire the object. Therefore, it is difficult to improve a recognition rate and to reduce false recognition. Results of recognition (type, position, angle, recognition time) made by a camera disposed forward of the vehicle, are used to predict a specific timing and a specific position of a field of view of a camera disposed rearward of the vehicle, at which the object appears. Parameters of recognition logic of the rearwardly disposed camera and processing timing are then optimally adjusted. Further, luminance information of the image from the forwardly disposed camera is used to predict possible changes to be made in luminance of the field of view of the rearwardly disposed camera. Gain and exposure time of the rearwardly disposed camera are then adjusted.

摘要翻译： 在使用设置在车辆后方的车载照相机以识别车辆周围的物体的常规系统中，物体被设置在车辆后方的照相机识别。 在由相机识别的图像中，由相机拍摄的路面标记出现在图像的屏幕的下端，这使得难以预测出现路面标记的屏幕中的特定位置。 此外，相机的下压角度大，获取物体的时间短。 因此，难以提高识别率并减少错误识别。 使用布置在车辆前方的相机进行的识别（类型，位置，角度，识别时间）的结果用于预测设置在车辆后方的相机的视场的具体定时和特定位置， 该对象出现。 然后，最佳地调整后置摄像机的识别逻辑和处理定时的参数。 此外，来自前方照相机的图像的亮度信息用于预测在向后设置的相机的视场的亮度可能发生的变化。 然后调整向后放置的相机的增益和曝光时间。

公开(公告)号：US08885888B2

公开(公告)日：2014-11-11

申请号：US13474750

申请日：2012-05-18

申请人： Mirai Higuchi ,  Yuji Otsuka ,  Takeshi Shima ,  Kimiyoshi Machii ,  Shoji Muramatsu ,  Kota Irie ,  Tatsuhiko Monji

发明人： Mirai Higuchi ,  Yuji Otsuka ,  Takeshi Shima ,  Kimiyoshi Machii ,  Shoji Muramatsu ,  Kota Irie ,  Tatsuhiko Monji

IPC分类号： G06K9/00 ,  G08G1/16

CPC分类号： G08G1/16 ,  G06K9/00791 ,  G06K9/00798 ,  G08G1/166 ,  G08G1/167

摘要： An in-vehicle running-environment recognition apparatus including an input unit for inputting an image signal from in-vehicle imaging devices for photographing external environment of a vehicle, an image processing unit for detecting a first image area by processing the image signal, the first image area having a factor which prevents recognition of the external environment, an image determination unit for determining a second image area based on at least any one of size of the first image area, position thereof, and set-up positions of the in-vehicle imaging devices having the first image area, an environment recognition processing being performed in the second image area, the first image area being detected by the image processing unit, and an environment recognition unit for recognizing the external environment of the vehicle based on the second image area.

摘要翻译： 一种车载行驶环境识别装置，包括：输入单元，用于输入来自用于拍摄车辆的外部环境的车载成像装置的图像信号;图像处理单元，用于通过处理图像信号来检测第一图像区域;第一 图像区域具有防止识别外部环境的因素;图像确定单元，用于基于车辆的第一图像区域，其位置和设置位置中的至少一个尺寸来确定第二图像区域 具有第一图像区域的成像设备，在第二图像区域中执行的环境识别处理，由图像处理单元检测到的第一图像区域，以及用于基于第二图像识别车辆的外部环境的环境识别单元 区。