专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20170039434A1 External-Environment-Recognizing Apparatus 审中-公开
标题翻译：外部环境识别装置
公开(公告)号：US20170039434A1
公开(公告)日：2017-02-09
申请号：US15303228
申请日：2015-03-25
申请人： Hitachi Automotive Systems, Ltd.
发明人： Takeshi SHIMA , Toshiyuki AOKI , Haruki MATONO , Tatsuhiko MONJI , Rikiya KASHIMURA , Yasuto ARAKAKI
IPC分类号： G06K9/00 , H04N7/18 , G05D1/02 , G06T1/20 , B60W30/09 , B60W50/14 , H04N13/02 , G06K9/62
CPC分类号： G06K9/00791 , B60W30/09 , B60W50/14 , B60W2050/143 , B60W2050/146 , G05D1/0251 , G06K9/6267 , G06T1/00 , G06T1/20 , G06T2200/16 , G08G1/16 , H04N7/18 , H04N7/181 , H04N13/239
摘要： The objective of the present invention is to obtain an external environment-recognizing apparatus with which it is possible to obtain detection results having a necessary accuracy when a plurality of target objects from a captured image are detected. This external-environment-recognizing apparatus has: a plurality of processing units for processing an image; a recognition application-storing unit for storing, by object type, a plurality of recognition applications for recognizing an object by processing using at least one processing unit among the plurality of processing units; an external-information-acquiring unit for acquiring external information that includes at least external environmental information or vehicle behavior information; and a selecting unit for selecting at least one recognition application from the recognition-application-storing unit, and for selecting, on the basis of the external information, a processing unit among the plurality of processing units for processing the selected recognition application.
摘要翻译：本发明的目的是获得一种外部环境识别装置，当检测到来自拍摄图像的多个目标对象时，可以获得具有必要精度的检测结果的外部环境识别装置。该外部环境识别装置具有：用于处理图像的多个处理单元; 识别应用存储单元，用于通过对象类型存储用于通过使用所述多个处理单元中的至少一个处理单元进行处理来识别对象的多个识别应用; 外部信息获取单元，用于获取至少包括外部环境信息或车辆行为信息的外部信息; 以及选择单元，用于从所述识别应用存储单元中选择至少一个识别应用，并且用于根据所述外部信息选择所述多个处理单元中的处理所选择的识别应用的处理单元。

12. 发明申请

US20160005180A1 Imaging Apparatus and Vehicle Controller 审中-公开
标题翻译：成像设备和车辆控制器
公开(公告)号：US20160005180A1
公开(公告)日：2016-01-07
申请号：US14770033
申请日：2014-02-03
申请人： HITACHI AUTOMOTIVE SYSTEMS, LTD.
发明人： Haruki MATONO , Mirai HIGUCHI , Yuji OTSUKA
IPC分类号： G06T7/00 , H04N13/02 , B60W10/18 , B60R1/00 , B60W10/10 , G06T7/20 , B60W30/18
CPC分类号： G06T7/11 , B60R1/00 , B60R2300/105 , B60R2300/8086 , B60R2300/8093 , B60W2420/403 , G06K9/00362 , G06K9/00805 , G06T7/223 , G06T7/593 , G06T2207/10021 , G06T2207/20021 , G06T2207/20076 , G06T2207/30196 , G06T2207/30252 , G06T2207/30261 , H04N13/239 , H04N2013/0081
摘要： In order to provide an imaging apparatus which minimizes erroneous recognition of a moving body and prevent a braking operation from being erroneously performed, even if the moving body is likely to cross a road, the imaging apparatus includes a correlation value calculation unit that calculates a correlation value from two images captured by two imaging units, a three-dimensional object detection unit that detects a three-dimensional object from the two images, a region dividing unit that divides an image region including the three-dimensional object into multiple regions, a relative speed calculation unit that calculates relative speed for every region of the multiple regions, and a reliability calculation unit that calculates reliability of the three-dimensional object, based on the relative speed calculated for every region.
摘要翻译：为了提供一种使移动体的错误识别最小化并防止制动操作被错误地执行的成像装置，即使移动体容易跨越道路，成像装置包括相关值计算单元，其计算相关性由两个成像单元拍摄的两个图像的值，从两个图像检测三维物体的三维物体检测单元，将包括三维物体的图像区域划分成多个区域的区域分割单元，相对速度计算单元，其计算多个区域的每个区域的相对速度;以及可靠性计算单元，其基于针对每个区域计算的相对速度来计算三维对象的可靠性。

13. 发明申请

US20150310621A1 Image Processing Device 有权
标题翻译：图像处理装置
公开(公告)号：US20150310621A1
公开(公告)日：2015-10-29
申请号：US14439076
申请日：2013-10-07
申请人： Hitachi Automotive Systems, Ltd.
发明人： Haruki MATONO , Yuji OTSUKA
IPC分类号： G06T7/00 , H04N13/02
CPC分类号： H04N13/271 , G06K9/00201 , G06T7/593 , G06T2200/28 , H04N13/239 , H04N2013/0081
摘要： For reduced processing time involved in an image recognition process, correctors 26a and 26b corrects two source images, acquired by two cameras during the imaging of an object, so that when the two source images are arranged side by side in a lateral direction, the imaged object has the same height in both images. A parallax calculation section 28 calculates, by block matching process, a parallax on the basis of the two corrected source images. A parallax image generation section 30 generates a parallax image on the basis of the parallax calculated by the parallax calculation section 28. If a block that has been used during block matching has a rectangular shape including an ‘m’ number of pixels in a longitudinal direction and an ‘n’ number of pixels in a lateral direction, a first reduced-image generation section 32 generates a first reduced image from one of the two corrected source images so that the number of pixels in the longitudinal direction is 1/m and so that the number of pixels in the lateral direction is 1/n. Thus, resolution of the first reduced image equals that of the parallax image. An image recognition section 34 performs image recognition of the object, on the basis of the parallax image and the first reduced image.
摘要翻译：为了减少图像识别过程中的处理时间，校正器26a和26b校正在对象成像期间由两个摄像机获取的两个源图像，使得当两个源图像在横向方向上并排布置时，成像对象在两个图像中具有相同的高度。视差计算部28通过块匹配处理，基于两个校正的源图像来计算视差。视差图像生成部30基于由视差计算部28计算出的视差来生成视差图像。如果在块匹配期间使用的块具有包括纵向方向上的“m”个像素的矩形形状和横向方向上的“n”个像素，第一缩小图像生成部分32从两个校正的源图像之一生成第一缩小图像，使得纵向方向上的像素数为1 / m，因此横向方向的像素数为1 / n。因此，第一缩小图像的分辨率等于视差图像的分辨率。图像识别部分34基于视差图像和第一缩小图像执行对象的图像识别。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式