公开(公告)号：US06658137B1

公开(公告)日：2003-12-02

申请号：US09534349

申请日：2000-03-24

申请人： Horimitsu Yuhara ,  Tomoyoshi Aoki

发明人： Horimitsu Yuhara ,  Tomoyoshi Aoki

IPC分类号： G06K900

CPC分类号： B60R16/0237 ,  G01S11/12 ,  G08G1/04

摘要： A road sensor system is provided which comprises at least one imaging sensor, an extraction means that captures brightness values for a plurality of windows corresponding to the area immediately in front of the vehicle from an image that is captured from the imaging sensor and is divided into a plurality of windows. It extracts a reference brightness value on the basis of the plurality of brightness values. The system includes a judgment means that compares the brightness value of at least one other window with the reference brightness value and judges that the window belongs to the road area if the difference is smaller than a predetermined value. The road area is determined by detecting the road surface based on brightness rather than the distance to the road surface.

摘要翻译： 提供了一种道路传感器系统，其包括至少一个成像传感器，提取装置，其从从成像传感器捕获的图像中捕获与车辆前面的区域对应的多个窗口的亮度值，并且被分成 多个窗口。 它基于多个亮度值提取参考亮度值。 该系统包括将至少一个其他窗口的亮度值与参考亮度值进行比较的判断装置，并且如果差值小于预定值，则判断该窗口属于道路区域。 通过基于亮度而不是到路面的距离检测路面来确定道路面积。

公开(公告)号：US20090284597A1

公开(公告)日：2009-11-19

申请号：US11995798

申请日：2006-07-06

申请人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

发明人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

IPC分类号： G06K9/00 ,  H04N7/18

CPC分类号： G06K9/00798 ,  G06T7/12 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/30256

摘要： An image processing system and the like capable of recognizing a lane mark in a road image with high accuracy are provided even if a light illumination state on a road surface is partially different. According to the image processing system (100) mounted on a vehicle (10), a color component (Rij, Gij, Bij) of the first pixel (Pij) included in an area (Aij) set in the road image is corrected with reference to a color component (Rik, Gik, Bik) of a second pixel (Pik) in view of a fact that it is highly probable that the color component of the second pixel included in the area along with the first pixel is affected by a shadow or light on the road surface. This reduces the effect of the shadow or light on the road surface and the actual color of a road surface portion corresponding to the first pixel can be sufficiently reflected in the color components (Rij, Gij, Bij) of the first pixel (Pij) and consequently in a feature value (Qij). Therefore, a lane mark (M) and its edge (E) are recognized in the road image on the basis of the feature value (Qij) of each pixel (Pij) in the road image.

摘要翻译： 即使路面上的光照射状态部分不同，也能够提供能够高精度地识别道路图像中的车道标记的图像处理系统等。 根据安装在车辆（10）上的图像处理系统（100），包括在道路图像中设置的区域（Aij）中的第一像素（Pij）的颜色分量（Rij，Gij，Bij）被校正参考 考虑到与第一像素一起包括在该区域中的第二像素的颜色分量非常可能受到阴影影响的事实，第二像素（Pik）的颜色分量（Rik，Gik，Bik） 或在路面上点亮。 这样可以减小阴影或光线对路面的影响，并且可以将与第一像素对应的路面部分的实际颜色充分地反映在第一像素（Pij）的颜色分量（Rij，Gij，Bij）中，并且 因此在特征值（Qij）中。 因此，基于道路图像中的各像素（Pij）的特征量（Qij），在道路图像中识别车道标记（M）及其边缘（E）。

公开(公告)号：US20080310679A1

公开(公告)日：2008-12-18

申请号：US11918453

申请日：2006-04-16

申请人： Tomoyoshi Aoki ,  Sachio Kobayashi ,  Naoki Mori ,  Takuma Nakamori

发明人： Tomoyoshi Aoki ,  Sachio Kobayashi ,  Naoki Mori ,  Takuma Nakamori

IPC分类号： G06K9/00

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

摘要： A vehicle capable of preventing detection of stud-type lane marks from being impossible and a vehicle having a lane mark recognizer are provided. The vehicle includes installation interval recognizing means (21) which recognizes an interval (L) between Botts Dots, vehicle speed recognizing means (22) which recognizes a traveling speed (v) of the vehicle, image synthesizing means (13) which generates synthesized image data (M3) by combining image data (M1) stored in an image memory (11) through an image input circuit (10) and image data (M2) stored in an image memory (12) through the same, imaging timing determining means (20) which determines the timing of imaging by a camera (2) on the basis of the interval (L) and the traveling speed (v) when acquiring the image data (M1, M2) in such a way that the positions of the Botts Dots in the image data (M1, M2) are different therebetween, and Botts Dots detecting means (14) which detects the Botts Dots from the synthesized image data (M3).

摘要翻译： 提供能够防止螺柱式车道标记的检测不可能的车辆和具有车道标识识别器的车辆。 车辆包括识别出点数之间的间隔（L）的安装间隔识别装置（21），识别车辆的行驶速度（v）的车速识别装置（22），产生合成图像的图像合成装置 数据（M3）通过组合通过图像输入电路（10）存储在图像存储器（11）中的图像数据（M1）和通过其存储在图像存储器（12）中的图像数据（M2），成像定时确定装置 20），其基于当获取图像数据（M1，M2）时的间隔（L）和行进速度（v），以相对于所述图像数据（B）的位置的方式确定摄像机（2）的成像定时 图像数据（M1，M2）中的点不同，以及从合成图像数据（M3）检测Botts点的Botts点检测装置（14）。

公开(公告)号：US06775395B2

公开(公告)日：2004-08-10

申请号：US09783613

申请日：2001-02-15

申请人： Morimichi Nishigaki ,  Tomoyoshi Aoki ,  Hiromitsu Yuhara ,  Masakazu Saka

发明人： Morimichi Nishigaki ,  Tomoyoshi Aoki ,  Hiromitsu Yuhara ,  Masakazu Saka

IPC分类号： G06K900

CPC分类号： G06K9/342 ,  G06K9/00201 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/3241 ,  G06T7/97

摘要： An object recognition system having at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of a n image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measure distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster and to recognize an object based on the clusters judged to be valid.

摘要翻译： 一种具有至少两个图像传感器和控制器的物体识别系统，该控制器适用于相对于由传感器捕获的n个图像的各个窗口来测量从系统到物理物体的距离。 控制器被进一步编程以通过使具有相似测量距离的相邻窗口相结合来形成簇。 控制器被编程为基于簇的属性来判断每个簇是有效还是无效，并且基于被判断为有效的簇来识别对象。

公开(公告)号：US08170285B2

公开(公告)日：2012-05-01

申请号：US11995798

申请日：2006-07-06

申请人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

发明人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

IPC分类号： G06K9/00

CPC分类号： G06K9/00798 ,  G06T7/12 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/30256

摘要： An image processing system and the like capable of recognizing a lane mark in a road image with high accuracy are provided even if a light illumination state on a road surface is partially different. According to the image processing system (100) mounted on a vehicle (10), a color component (Rij, Gij, Bij) of the first pixel (Pij) included in an area (Aij) set in the road image is corrected with reference to a color component (Rik, Gik, Bik) of a second pixel (Pik) in view of a fact that it is highly probable that the color component of the second pixel included in the area along with the first pixel is affected by a shadow or light on the road surface. This reduces the effect of the shadow or light on the road surface and the actual color of a road surface portion corresponding to the first pixel can be sufficiently reflected in the color components (Rij, Gij, Bij) of the first pixel (Pij) and consequently in a feature value (Qij). Therefore, a lane mark (M) and its edge (E) are recognized in the road image on the basis of the feature value (Qij) of each pixel (Pij) in the road image.

摘要翻译： 即使路面上的光照射状态部分不同，也能够提供能够高精度地识别道路图像中的车道标记的图像处理系统等。 根据安装在车辆（10）上的图像处理系统（100），包括在道路图像中设置的区域（Aij）中的第一像素（Pij）的颜色分量（Rij，Gij，Bij）被校正参考 考虑到与第一像素一起包括在该区域中的第二像素的颜色分量非常可能受到阴影影响的事实，第二像素（Pik）的颜色分量（Rik，Gik，Bik） 或在路面上点亮。 这样可以减小阴影或光线对路面的影响，并且可以将与第一像素对应的路面部分的实际颜色充分地反映在第一像素（Pij）的颜色分量（Rij，Gij，Bij）中，并且 因此在特征值（Qij）中。 因此，基于道路图像中的各像素（Pij）的特征量（Qij），在道路图像中识别车道标记（M）及其边缘（E）。

公开(公告)号：US20090080704A1

公开(公告)日：2009-03-26

申请号：US11919641

申请日：2006-06-20

申请人： Naoki Mori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Takuma Nakamori

发明人： Naoki Mori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Takuma Nakamori

IPC分类号： G06K9/00

CPC分类号： G06K9/00798 ,  B60W30/12 ,  B60W2420/42 ,  G08G1/167

摘要： There is provided an image acquisition means (2) for acquiring a color image of a road via an imaging means (9) mounted on a vehicle (8), a lane mark detection means (3, 4) for performing processing of detecting lane marks of a plurality of predetermined colors different from each other on the road based on color information of the color image, and outputting a result of the processing as lane mark candidate data, and a selection means (6) for selecting lane mark candidate data corresponding to a lane mark defining an actual lane on which the vehicle (8) is traveling from among at least the lane mark candidate data for the respective predetermined colors output from the lane mark detection means (3, 4), and determining and outputting lane data indicating information of the actual lane based on the selected lane mark candidate data. Therefore, even if there are lane marks of different colors on the road, the lane marks of the respective colors can be recognized appropriately from the color image of the road acquired via the imaging means such as a camera.

摘要翻译： 提供了一种用于通过安装在车辆（8）上的成像装置（9）获取道路彩色图像的图像获取装置（2），用于执行检测车道标记的处理的车道标记检测装置（3,4） 基于彩色图像的颜色信息在道路上彼此不同的多个预定颜色的多个预定颜色，并将处理结果作为车道标记候选数据输出;以及选择装置（6），用于选择对应于 从车道标记检测装置（3,4）输出的各个预定颜色的至少车道标记候补数据中定义车辆（8）正在行进的实际车道的车道标记，并且确定并输出指示 基于所选择的车道标记候选数据的实际车道的信息。 因此，即使在道路上存在不同颜色的车道标记，也可以从通过诸如照相机的摄像装置获得的道路的彩色图像适当地识别各种颜色的车道标记。

公开(公告)号：US08144926B2

公开(公告)日：2012-03-27

申请号：US11919641

申请日：2006-06-20

申请人： Naoki Mori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Takuma Nakamori

发明人： Naoki Mori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Takuma Nakamori

IPC分类号： G06K9/00

CPC分类号： G06K9/00798 ,  B60W30/12 ,  B60W2420/42 ,  G08G1/167

摘要： There is provided an image acquisition means (2) for acquiring a color image of a road via an imaging means (9) mounted on a vehicle (8), a lane mark detection means (3, 4) for performing processing of detecting lane marks of a plurality of predetermined colors different from each other on the road based on color information of the color image, and outputting a result of the processing as lane mark candidate data, and a selection means (6) for selecting lane mark candidate data corresponding to a lane mark defining an actual lane on which the vehicle (8) is traveling from among at least the lane mark candidate data for the respective predetermined colors output from the lane mark detection means (3, 4), and determining and outputting lane data indicating information of the actual lane based on the selected lane mark candidate data. Therefore, even if there are lane marks of different colors on the road, the lane marks of the respective colors can be recognized appropriately from the color image of the road acquired via the imaging means such as a camera.

摘要翻译： 提供了一种用于通过安装在车辆（8）上的成像装置（9）获取道路彩色图像的图像获取装置（2），用于执行检测车道标记的处理的车道标记检测装置（3,4） 基于彩色图像的颜色信息在道路上彼此不同的多个预定颜色的多个预定颜色，并将处理结果作为车道标记候选数据输出;以及选择装置（6），用于选择对应于 从车道标记检测装置（3,4）输出的各个预定颜色的至少车道标记候补数据中定义车辆（8）正在行进的实际车道的车道标记，并且确定并输出指示 基于所选择的车道标记候选数据的实际车道的信息。 因此，即使在道路上存在不同颜色的车道标记，也可以从通过诸如照相机的摄像装置获得的道路的彩色图像适当地识别各种颜色的车道标记。

公开(公告)号：US08036427B2

公开(公告)日：2011-10-11

申请号：US11919657

申请日：2006-05-18

申请人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

发明人： Takuma Nakamori ,  Sachio Kobayashi ,  Tomoyoshi Aoki ,  Naoki Mori

IPC分类号： G06K9/00

CPC分类号： G06K9/4652 ,  G06K9/00798

摘要： The present invention includes: image capturing means (2) which captures a color image of a road via imaging means (7); area extraction means (3) which extracts areas having a similar color feature value from the captured color image of the road; white balance processing means (5) which performs, for each of the extracted areas, a white balance process of correcting each pixel data in the extracted area so as to reduce the degree of divergence in the level between color components according to a level balance between the color components of the pixel data in the extracted area; and road sign detection means (6) which detects a road sign on the road from the color image subjected to the white balance process. Thus, even if the road illumination state is partially different, it is possible to accurately detect a road sign such as a lane mark from the captured color image of the road via the imaging means such as a camera.

摘要翻译： 本发明包括：通过成像装置（7）捕捉道路的彩色图像的图像捕获装置（2）。 区域提取装置（3），其从所捕获的道路彩色图像中提取具有相似颜色特征值的区域; 白平衡处理装置（5）对于每个提取区域执行校正所提取的区域中的每个像素数据的白平衡处理，以便根据色彩分量之间的水平平衡来降低色彩分量之间的差异程度 提取区域中的像素数据的颜色分量; 以及从经过白平衡处理的彩色图像检测道路上的道路标志的道路标志检测单元（6）。 因此，即使道路照明状态是部分不同的，也可以通过诸如照相机的摄像装置从所拍摄的道路彩色图像中准确地检测诸如车道线的路标。

公开(公告)号：US06963657B1

公开(公告)日：2005-11-08

申请号：US09640928

申请日：2000-08-17

申请人： Morimichi Nishigaki ,  Tomoyoshi Aoki ,  Masakazu Saka ,  Hiromitsu Yuhara

发明人： Morimichi Nishigaki ,  Tomoyoshi Aoki ,  Masakazu Saka ,  Hiromitsu Yuhara

IPC分类号： H04N7/18 ,  B60R21/00 ,  B60W30/00 ,  G01B11/00 ,  G01C3/00 ,  G01C3/06 ,  G01C22/00 ,  G01S11/12 ,  G01S17/93 ,  G05D1/00 ,  G06K9/00 ,  G06T1/00 ,  G06T7/00 ,  G08G1/00 ,  G08G1/16

CPC分类号： G01S11/12 ,  G01S17/936 ,  G06K9/00201 ,  G06K9/00805 ,  G06T7/593 ,  G06T7/70 ,  G08G1/166

摘要： An object recognition system mounted on a vehicle comprises a camera and a controller. The camera captures an image in front of the vehicle. The controller divides the image into a plurality of windows. The controller measures distance to the road surface for each of the plurality of windows and thereby obtains a plurality of distances. The controller estimates a relative inclination of the road surface against the vehicle based on the plurality of distances. The controller judges, for each of the plurality of windows, based on the estimated inclination, whether the object is an obstacle or the road surface and thereby obtains a judgment result. The controller recognizes the object based on the judgment result. The system recognizes objects in front of the vehicle even when the vehicle is lopsided by pitching, rolling or else.

摘要翻译： 安装在车辆上的物体识别系统包括相机和控制器。 相机拍摄车辆前方的图像。 控制器将图像分成多个窗口。 控制器针对多个窗口中的每个窗口测量与路面的距离，从而获得多个距离。 控制器基于多个距离估计路面相对于车辆的相对倾斜度。 控制器基于所估计的倾斜度，判断对象是障碍物还是路面，从而获得判断结果。 控制器根据判断结果识别对象。 该系统识别车辆前方的物体，即使车辆通过俯仰，滚动或其他方式偏移。

公开(公告)号：US06792147B1

公开(公告)日：2004-09-14

申请号：US09691124

申请日：2000-10-18

申请人： Masakazu Saka ,  Hiromitsu Yuhara ,  Tomoyoshi Aoki ,  Morimichi Nishigaki

发明人： Masakazu Saka ,  Hiromitsu Yuhara ,  Tomoyoshi Aoki ,  Morimichi Nishigaki

IPC分类号： G06K948

CPC分类号： G06K9/3241 ,  G06K9/00805 ,  G06K2209/23 ,  G06T7/12 ,  G06T7/74 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20132 ,  G06T2207/30256 ,  G06T2207/30261

摘要： An object recognition system including a position sensor, an image sensor and a controller is provided. The position sensor determines the position of an object, and the image sensor captures an image of the object. The controller sets a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized. The controller extracts horizontal edges from the processing area, and judges whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized. More practically, the controller can check if each of the extracted edges contains a pixel on a boundary of the processing area. If so, the controller judges to the edge to belong to an object other than the object. The controller can also examine the linearity of each of the extracted edges. If the linearity is larger than a predetermined value, the controller judges the edge to belong to an object other than the object. The controller can also examine the slope of each of the extracted edges. If the slope is larger than a predetermined value, the controller judges the edge to belong to an object other than the object. Thus, the edges judged to belong to an object other than the object are removed. The controller recognizes the outline of the object based on the edges judged to belong to the object.

摘要翻译： 提供了一种包括位置传感器，图像传感器和控制器的对象识别系统。 位置传感器确定对象的位置，并且图像传感器捕获对象的图像。 控制器基于由位置传感器确定的对象的位置和要识别的对象的预定大小来设置由图像传感器捕获的图像内的处理区域。 控制器从处理区域中提取水平边缘，并且基于要被识别的对象的特性来判断每个提取的边缘是否属于对象。 更实际地，控制器可以检查每个提取的边缘是否包含处理区域的边界上的像素。 如果是这样，则控制器判断边缘属于对象以外的对象。 控制器还可以检查每个提取的边缘的线性。 如果线性度大于预定值，则控制器判定边缘属于对象以外的对象。 控制器还可以检查每个提取的边缘的斜率。 如果斜率大于预定值，则控制器判断该边缘属于除该对象之外的对象。 因此，判断为属于对象以外的对象的边缘被去除。 控制器基于被判定为属于对象的边缘来识别对象的轮廓。