公开(公告)号：US20110074957A1

公开(公告)日：2011-03-31

申请号：US12859020

申请日：2010-08-18

申请人： Masahiro Kiyohara ,  Ryo Yumiba ,  Kota Irie ,  Tatsuhiko Monji

发明人： Masahiro Kiyohara ,  Ryo Yumiba ,  Kota Irie ,  Tatsuhiko Monji

IPC分类号： H04N7/18

CPC分类号： G06T3/4038 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/342

摘要： There is provided apparatus for vehicle surroundings monitorings that assists so as to make it possible for a driver to check the periphery of the vehicle with ease. Plural images are obtained by capturing the periphery of the vehicle with mutually differing exposure. A process of image recognition is then performed for a target within the thus obtained images. The images are then compared, and images for which the accuracy of image recognition of the target is favorable are selected from among the images. The selected images are joined and composited to generate a host vehicle periphery composite image. Thus, an image with a wide dynamic range and high visibility is generated, thereby making it easier for the driver to check the periphery of the vehicle.

摘要翻译： 提供了用于车辆环境监测的装置，其有助于使驾驶员容易地检查车辆周边。 通过以相互不同的曝光捕获车辆的周边来获得多个图像。 然后对由此获得的图像中的目标执行图像识别的处理。 然后比较图像，从图像中选择目标图像识别的准确性有利的图像。 所选择的图像被连接并合成以产生主车辆周边合成图像。 因此，产生具有宽动态范围和高可见度的图像，从而使驾驶员更容易地检查车辆的周边。

公开(公告)号：US08421863B2

公开(公告)日：2013-04-16

申请号：US12844439

申请日：2010-07-27

申请人： Ryo Yumiba ,  Masahiro Kiyohara ,  Tatsuhiko Monji ,  Kota Irie

发明人： Ryo Yumiba ,  Masahiro Kiyohara ,  Tatsuhiko Monji ,  Kota Irie

IPC分类号： H04N7/18 ,  H04N7/00

CPC分类号： B60R1/00 ,  B60R2300/105 ,  B60R2300/302 ,  B60R2300/303 ,  B60R2300/305 ,  B60R2300/306 ,  B60R2300/605 ,  B60R2300/607 ,  B60R2300/70 ,  B60R2300/806 ,  B62D15/029

摘要： Provided is an in-vehicle image display device capable of providing, from among images of the peripheral area of a vehicle that can change in accordance with the driving state, an image of a part needed by the driver at an appropriate timing so that the driver can recognize the positional relationship between the vehicle and the peripheral area of the vehicle. Images captured with in-vehicle cameras are acquired, and a vehicle periphery image is generated from such images. Then, a collision-warned part of the vehicle that has a possibility of hitting a nearby object is selected based on the vehicle driving state, and the acquired image is processed to generate an enlarged image of the peripheral area of the collision-warned part of the vehicle selected by the collision-warned part selection part. Then, a composite display image, in which the positions of the enlarged image and the vehicle periphery image are displayed in a correlated manner, is generated and displayed.

摘要翻译： 本发明提供一种车载图像显示装置，其能够在适当的定时从驾驶员能够根据驾驶状态变化的周边区域的图像中提供驾驶员所需要的部件的图像，使得驾驶员 可以识别车辆与车辆的周边区域之间的位置关系。 摄像机拍摄的图像被获取，并且从这些图像生成车辆周边图像。 然后，基于车辆行驶状态来选择具有撞击附近物体的可能性的车辆的碰撞警告部分，并且处理所获取的图像以产生碰撞警告部分的周边区域的放大图像 由碰撞警告部分选择部分选择的车辆。 然后，生成并显示以相关方式显示放大图像和车辆周边图像的位置的复合显示图像。

公开(公告)号：US20110234761A1

公开(公告)日：2011-09-29

申请号：US13133215

申请日：2009-12-07

申请人： Ryo Yumiba ,  Masahiro Kiyohara ,  Kota Irie ,  Tatsuhiko Monji

发明人： Ryo Yumiba ,  Masahiro Kiyohara ,  Kota Irie ,  Tatsuhiko Monji

IPC分类号： H04N13/02

CPC分类号： G06T3/0062 ,  B60R1/00 ,  B60R2300/605 ,  B60R2300/607 ,  B60R2300/8093 ,  G08G1/165 ,  G08G1/166

摘要： Provided is a three-dimensional object emergence detecting device capable of detecting the emergence of a three-dimensional object rapidly and correctly at low costs.Based on a bird's-eye view image 30 taken by a camera 21 mounted in a vehicle 20, the three-dimensional object emergence detecting device detects the emergence of a three-dimensional object 22 in the vicinity of the vehicle. From the bird's-eye view image 30, the three-dimensional object emergence detecting device extracts orthogonal-direction characteristic components 46 and 47, which are on the bird's-eye view image 30 and has directions 36 and 37 orthogonal to a view direction 33 of the camera 21, and based on amounts of the extracted orthogonal-direction characteristic components 46 and 47, detects the emergence of the three-dimensional object 22. This prevents from erroneously detecting incidental changes in the image, such as sway of sunshine or movement of a shadow, as the emergence of the three-dimensional object.

摘要翻译： 提供了能够以低成本快速且正确地检测三维物体的出现的三维物体出射检测装置。 基于安装在车辆20中的照相机21拍摄的鸟瞰图30，三维物体出射检测装置检测车辆附近的三维物体22的出现。 从鸟瞰图30中，三维物体出射检测装置提取在鸟瞰图像30上的正交方向特征成分46和47，并且具有与视野方向33正交的方向36,37 照相机21，并且基于所提取的正交方向特征分量46和47的量来检测三维物体22的出现。这防止了错误地检测图像中的偶然变化，例如阳光的摇摆或运动 一个阴影，作为三维物体的出现。

公开(公告)号：US08289391B2

公开(公告)日：2012-10-16

申请号：US12859020

申请日：2010-08-18

申请人： Masahiro Kiyohara ,  Ryo Yumiba ,  Kota Irie ,  Tatsuhiko Monji

发明人： Masahiro Kiyohara ,  Ryo Yumiba ,  Kota Irie ,  Tatsuhiko Monji

IPC分类号： H04N9/47

CPC分类号： G06T3/4038 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/342

摘要： There is provided apparatus for vehicle surroundings monitorings that assists so as to make it possible for a driver to check the periphery of the vehicle with ease. Plural images are obtained by capturing the periphery of the vehicle with mutually differing exposure. A process of image recognition is then performed for a target within the thus obtained images. The images are then compared, and images for which the accuracy of image recognition of the target is favorable are selected from among the images. The selected images are joined and composited to generate a host vehicle periphery composite image. Thus, an image with a wide dynamic range and high visibility is generated, thereby making it easier for the driver to check the periphery of the vehicle.

摘要翻译： 提供了用于车辆环境监测的装置，其有助于使驾驶员容易地检查车辆周边。 通过以相互不同的曝光捕获车辆的周边来获得多个图像。 然后对由此获得的图像中的目标执行图像识别的处理。 然后比较图像，从图像中选择目标图像识别的准确性有利的图像。 所选择的图像被连接并合成以产生主车辆周边合成图像。 因此，产生具有宽动态范围和高可见度的图像，从而使驾驶员更容易地检查车辆的周边。

公开(公告)号：US20110025848A1

公开(公告)日：2011-02-03

申请号：US12844439

申请日：2010-07-27

申请人： Ryo YUMIBA ,  Masahiro Kiyohara ,  Tatsuhiko Monji ,  Kota Irie

发明人： Ryo YUMIBA ,  Masahiro Kiyohara ,  Tatsuhiko Monji ,  Kota Irie

IPC分类号： H04N7/18

CPC分类号： B60R1/00 ,  B60R2300/105 ,  B60R2300/302 ,  B60R2300/303 ,  B60R2300/305 ,  B60R2300/306 ,  B60R2300/605 ,  B60R2300/607 ,  B60R2300/70 ,  B60R2300/806 ,  B62D15/029

摘要： Provided is an in-vehicle image display device capable of providing, from among images of the peripheral area of a vehicle that can change in accordance with the driving state, an image of a part needed by the driver at an appropriate timing so that the driver can recognize the positional relationship between the vehicle and the peripheral area of the vehicle. Images captured with in-vehicle cameras are acquired, and a vehicle periphery image is generated from such images. Then, a collision-warned part of the vehicle that has a possibility of hitting a nearby object is selected based on the vehicle driving state, and the acquired image is processed to generate an enlarged image of the peripheral area of the collision-warned part of the vehicle selected by the collision-warned part selection part. Then, a composite display image, in which the positions of the enlarged image and the vehicle periphery image are displayed in a correlated manner, is generated and displayed.

摘要翻译： 本发明提供一种车载图像显示装置，其能够在适当的定时从驾驶员能够根据驾驶状态变化的周边区域的图像中提供驾驶员所需的部位的图像，使得驾驶员 可以识别车辆与车辆的周边区域之间的位置关系。 摄像机拍摄的图像被获取，并且从这些图像生成车辆周边图像。 然后，基于车辆行驶状态来选择具有撞击附近物体的可能性的车辆的碰撞警告部分，并且处理所获取的图像以产生碰撞警告部分的周边区域的放大图像 由碰撞警告部分选择部分选择的车辆。 然后，生成并显示以相关方式显示放大图像和车辆周边图像的位置的复合显示图像。

公开(公告)号：US20120269382A1

公开(公告)日：2012-10-25

申请号：US12918042

申请日：2009-04-24

申请人： Masahiro Kiyohara ,  Kota Irie ,  Naoki Kourogi ,  Tatsuhiko Monji ,  Yoshitaka Takahashi ,  Shoji Muramatsu

发明人： Masahiro Kiyohara ,  Kota Irie ,  Naoki Kourogi ,  Tatsuhiko Monji ,  Yoshitaka Takahashi ,  Shoji Muramatsu

IPC分类号： G06K9/00

CPC分类号： G01C21/26 ,  G06K9/00798 ,  G06T5/006 ,  G06T7/254 ,  G06T2207/30256 ,  G08G1/09623 ,  G08G1/165

摘要： An object recognition device includes; an image-capturing unit mounted to a mobile body; an image generation unit that converts images captured by the image-capturing unit at different time points to corresponding synthesized images as seen vertically downwards from above; a detection unit that compares together a plurality of the synthesized images and detects corresponding regions; and a recognition unit that recognizes an object present upon the road surface from a difference between the corresponding regions.

摘要翻译： 物体识别装置包括： 安装到移动体的图像捕获单元; 图像生成单元，其将从不同时间点的图像拍摄单元拍摄的图像转换成从上方垂直向下观看的对应合成图像; 检测单元，其将多个合成图像进行比较并检测相应的区域; 以及识别单元，从相应区域之间的差异识别路面上存在的物体。

公开(公告)号：US08818026B2

公开(公告)日：2014-08-26

申请号：US12918042

申请日：2009-04-24

申请人： Masahiro Kiyohara ,  Kota Irie ,  Naoki Kourogi ,  Tatsuhiko Monji ,  Yoshitaka Takahashi ,  Shoji Muramatsu

发明人： Masahiro Kiyohara ,  Kota Irie ,  Naoki Kourogi ,  Tatsuhiko Monji ,  Yoshitaka Takahashi ,  Shoji Muramatsu

IPC分类号： G06K9/00

CPC分类号： G01C21/26 ,  G06K9/00798 ,  G06T5/006 ,  G06T7/254 ,  G06T2207/30256 ,  G08G1/09623 ,  G08G1/165

摘要： An object recognition device includes; an image-capturing unit mounted to a mobile body; an image generation unit that converts images captured by the image-capturing unit at different time points to corresponding synthesized images as seen vertically downwards from above; a detection unit that compares together a plurality of the synthesized images and detects corresponding regions; and a recognition unit that recognizes an object present upon the road surface from a difference between the corresponding regions.

摘要翻译： 物体识别装置包括： 安装到移动体的图像捕获单元; 图像生成单元，其将从不同时间点的图像拍摄单元拍摄的图像转换成从上方垂直向下观看的对应合成图像; 检测单元，其将多个合成图像进行比较并检测相应的区域; 以及识别单元，从相应区域之间的差异识别路面上存在的物体。

公开(公告)号：US20140028873A1

公开(公告)日：2014-01-30

申请号：US14110679

申请日：2012-04-04

申请人： Mirai Higuchi ,  Masahiro Kiyohara ,  Takeshi Shima ,  Tatsuhiko Monji

发明人： Mirai Higuchi ,  Masahiro Kiyohara ,  Takeshi Shima ,  Tatsuhiko Monji

IPC分类号： H04N5/235

CPC分类号： H04N5/2352 ,  G06K9/2054 ,  G08B13/19647 ,  H04N5/232 ,  H04N5/23229 ,  H04N5/2353

摘要： There is provided an image processing apparatus that can implement image recognition processing on all of objects to be recognized, and can reduce a load of capturing and transferring images. The image processing apparatus includes: an image capturing unit that captures image information picked up by an imaging element; a processing region setting unit that sets a plurality of processing regions for the image information; a processing sequence/frequency determination unit that determines at least any one of a sequence, a frequency, and a timing of capturing the respective image information in a plurality of set processing regions, and at least any one of a sequence, a frequency, and a timing of processing the respective image information; and an image processing unit that captures the image information for each of the processing regions according to the sequence, the frequency, or the timing which has been determined, and processes the captured image information according to the sequence, the frequency, or the timing which has been determined.

摘要翻译： 提供了一种能够对要被识别的所有对象执行图像识别处理的图像处理装置，并且可以减少捕获和传送图像的负担。 该图像处理设备包括：图像捕获单元，其捕获由成像元件拾取的图像信息; 处理区域设定单元，对所述图像信息设定多个处理区域; 处理序列/频率确定单元，其确定在多个集合处理区域中捕获各个图像信息的序列，频率和定时中的至少一个，以及序列，频率和 处理各图像信息的定时; 以及图像处理单元，其根据已经确定的顺序，频率或定时捕获每个处理区域的图像信息，并且根据序列，频率或时间来处理所捕获的图像信息 已经确定

公开(公告)号：US09077907B2

公开(公告)日：2015-07-07

申请号：US14110679

申请日：2012-04-04

申请人： Mirai Higuchi ,  Masahiro Kiyohara ,  Takeshi Shima ,  Tatsuhiko Monji

发明人： Mirai Higuchi ,  Masahiro Kiyohara ,  Takeshi Shima ,  Tatsuhiko Monji

IPC分类号： H04N5/235 ,  G06K9/20 ,  H04N5/232 ,  G08B13/196

CPC分类号： H04N5/2352 ,  G06K9/2054 ,  G08B13/19647 ,  H04N5/232 ,  H04N5/23229 ,  H04N5/2353

摘要： There is provided an image processing apparatus that can implement image recognition processing on all of objects to be recognized, and can reduce a load of capturing and transferring images. The image processing apparatus includes: an image capturing unit that captures image information picked up by an imaging element; a processing region setting unit that sets a plurality of processing regions for the image information; a processing sequence/frequency determination unit that determines at least any one of a sequence, a frequency, and a timing of capturing the respective image information in a plurality of set processing regions, and at least any one of a sequence, a frequency, and a timing of processing the respective image information; and an image processing unit that captures the image information for each of the processing regions according to the sequence, the frequency, or the timing which has been determined, and processes the captured image information according to the sequence, the frequency, or the timing which has been determined.

摘要翻译： 提供了一种能够对要被识别的所有对象执行图像识别处理的图像处理装置，并且可以减少捕获和传送图像的负担。 该图像处理设备包括：图像捕获单元，其捕获由成像元件拾取的图像信息; 处理区域设定单元，对所述图像信息设定多个处理区域; 处理序列/频率确定单元，其确定在多个集合处理区域中捕获各个图像信息的序列，频率和定时中的至少一个，以及序列，频率和 处理各图像信息的定时; 以及图像处理单元，其根据已经确定的顺序，频率或定时捕获每个处理区域的图像信息，并且根据序列，频率或时间来处理所捕获的图像信息 已经确定

公开(公告)号：US07948397B2

公开(公告)日：2011-05-24

申请号：US12292887

申请日：2008-11-28

申请人： Masaki Nakamura ,  Tomoaki Ishikawa ,  Osamu Aisaka ,  Kota Irie ,  Naoki Kourogi ,  Takeshi Shima ,  Masahiro Kiyohara

发明人： Masaki Nakamura ,  Tomoaki Ishikawa ,  Osamu Aisaka ,  Kota Irie ,  Naoki Kourogi ,  Takeshi Shima ,  Masahiro Kiyohara

IPC分类号： G08G1/16

CPC分类号： G06K9/00798

摘要： Image information apparatuses, methods, and programs acquire image information of a plurality of frames of images sensed at predetermined regular time intervals. The apparatuses, methods, and programs detect a leading and trailing end of a lane mark included in a detection area defined in each frame of the image information. The apparatuses, methods, and programs detect a detected distance from one of the leading and trailing end of the lane mark to the other one as a detected distance based on the speed of the vehicle and the number of frames between a frame in which one of the leading end and the trailing end of the lane mark is detected and a frame in which the other one of the leading end and the trailing end of the lane mark is detected and determine a lane mark type of the lane mark on the basis of the detected distance.

摘要翻译： 图像信息装置，方法和程序获取以预定的规则时间间隔感测的多个图像帧的图像信息。 设备，方法和程序检测包括在图像信息的每个帧中定义的检测区域中的车道标记的前端和后端。 装置，方法和程序根据车辆的速度和帧之间的帧数检测从车道标记的前端和后端之一到另一车道标记的检测距离， 检测车道标记的前端和尾端，并且检测车道标记的前端和后端中的另一个被检测到的帧，并基于该车道标记确定车道标记的车道标记类型 检测距离。