专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20110262009A1 METHOD AND APPARATUS FOR IDENTIFYING OBSTACLE IN IMAGE 有权
标题翻译：用于识别图像中的障碍物的方法和装置
公开(公告)号：US20110262009A1
公开(公告)日：2011-10-27
申请号：US13133546
申请日：2009-04-30
申请人： Bobo Duan , Wei Liu , Huai Yuan
发明人： Bobo Duan , Wei Liu , Huai Yuan
IPC分类号： G06K9/00
CPC分类号： G06K9/00805
摘要： A method for identifying barriers in images is disclosed. In the method, images of a current frame and N frame which is nearest to the current frame are obtained, the obtained images of the frames are divided in the same way, and the image of each frame obtains a plurality of divided block regions; the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame is calculated; whether each block region in the image of the current frame is decided successively according to the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame; the barriers in the images are determined according to each block region.
摘要翻译：公开了一种用于识别图像中的障碍物的方法。在该方法中，获得与当前帧最近的当前帧和N帧的图像，以相同的方式划分所获得的帧的图像，并且每帧的图像获得多个分割块区域; 计算对应于当前帧的每个块区域和最接近当前帧的N帧的运动屏障置信度; 根据与当前帧对应的每个块区域的运动屏障置信度和最接近当前帧的N帧，连续确定当前帧图像中的每个块区域; 根据每个块区域确定图像中的屏障。

2. 发明授权

US08463039B2 Method and device for partitioning barrier 有权
标题翻译：分隔屏障的方法和装置
公开(公告)号：US08463039B2
公开(公告)日：2013-06-11
申请号：US13133068
申请日：2009-04-30
申请人： Wei Liu , Yingying Zhang , Bobo Duan , Huai Yuan
发明人： Wei Liu , Yingying Zhang , Bobo Duan , Huai Yuan
IPC分类号： G06K9/34
CPC分类号： G06K9/00805 , G06T7/13 , G06T7/70 , G06T2207/20021 , G06T2207/30261
摘要： A barrier partitioning method and device are used for partitioning a barrier area from an image. The method includes: performing edge detecting and partitioning blocks to the image to obtain multiple edge image blocks; performing beeline detection to each edge image block to obtain beelines respectively; for each beeline, determining the line direction of the beeline corresponding to a standard road plane, and determining the edge image block to be a barrier block according to the line direction; forming all the determined barrier blocks to be a barrier area according to a connection principle.
摘要翻译：屏障划分方法和装置用于从图像分割屏障区域。该方法包括：对图像执行边缘检测和划分块以获得多个边缘图像块; 对每个边缘图像块执行线性检测以分别获得目标; 对于每个直线，确定对应于标准道路平面的直线的线方向，并根据线方向将边缘图像块确定为障碍块; 根据连接原理将所有确定的阻挡块形成为阻挡区域。

3. 发明授权

US08406474B2 Method and apparatus for identifying obstacle in image 有权
标题翻译：用于识别图像中的障碍物的方法和装置
公开(公告)号：US08406474B2
公开(公告)日：2013-03-26
申请号：US13133546
申请日：2009-04-30
申请人： Bobo Duan , Wei Liu , Huai Yuan
发明人： Bobo Duan , Wei Liu , Huai Yuan
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/00805
摘要： A method for identifying barriers in images is disclosed. In the method, images of a current frame and N frame which is nearest to the current frame are obtained, the obtained images of the frames are divided in the same way, and the image of each frame obtains a plurality of divided block regions; the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame is calculated; whether each block region in the image of the current frame is decided successively according to the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame; the barriers in the images are determined according to each block region.
摘要翻译：公开了一种用于识别图像中的障碍物的方法。在该方法中，获得与当前帧最近的当前帧和N帧的图像，以相同的方式划分所获得的帧的图像，并且每帧的图像获得多个分割块区域; 计算对应于当前帧的每个块区域和最接近当前帧的N帧的运动屏障置信度; 根据与当前帧对应的每个块区域的运动屏障置信度和最接近当前帧的N帧，连续确定当前帧图像中的每个块区域; 根据每个块区域确定图像中的屏障。

4. 发明申请

US20110235913A1 METHOD AND DEVICE FOR PARTITIONING BARRIER 有权
标题翻译：用于分隔障碍物的方法和装置
公开(公告)号：US20110235913A1
公开(公告)日：2011-09-29
申请号：US13133068
申请日：2009-04-30
申请人： Wei Liu , Yingying Zhang , Bobo Duan , Huai Yuan
发明人： Wei Liu , Yingying Zhang , Bobo Duan , Huai Yuan
IPC分类号： G06K9/34
CPC分类号： G06K9/00805 , G06T7/13 , G06T7/70 , G06T2207/20021 , G06T2207/30261
摘要： A barrier partitioning method and device are used for partitioning a barrier area from an image. The method includes: performing edge detecting and partitioning blocks to the image to obtain multiple edge image blocks; performing beeline detection to each edge image block to obtain beelines respectively; for each beeline, determining the line direction of the beeline corresponding to a standard road plane, and determining the edge image block to be a barrier block according to the line direction; forming all the determined barrier blocks to be a barrier area according to a connection principle.
摘要翻译：屏障划分方法和装置用于从图像分割屏障区域。该方法包括：对图像执行边缘检测和划分块以获得多个边缘图像块; 对每个边缘图像块执行线性检测以分别获得目标; 对于每个直线，确定对应于标准道路平面的直线的线方向，并根据线方向将边缘图像块确定为障碍块; 根据连接原理将所有确定的阻挡块形成为阻挡区域。

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