公开(公告)号：US20110311108A1

公开(公告)日：2011-12-22

申请号：US13201241

申请日：2010-02-04

申请人： Hernan Badino ,  Uwe Franke

发明人： Hernan Badino ,  Uwe Franke

IPC分类号： G06K9/00

CPC分类号： G06K9/00805

摘要： A method for detecting objects, wherein two images of a surrounding (1) are taken and a disparity image is determined by means of stereo image processing, wherein a depth map of the surrounding (1) is determined from the determined disparities, wherein a free space delimiting line (2) is identified, delimiting an unobstructed region of the surrounding (1), wherein outside and along the free space delimiting line (1) the depth card is segmented by segments (3) of a suitable width formed by pixels of the same or similar distance to an image plane, wherein a height of each segment (3) is estimated as part of an object (4.1 to 4.6) located outside of the unobstructed region in a way, such that each segment (3) is characterized by the two-dimensional position of the base (for example the distance and angle to the longitudinal axis of the vehicle) and the height thereof.

摘要翻译： 一种用于检测物体的方法，其中拍摄周围（1）的两个图像，并且通过立体图像处理来确定视差图像，其中根据确定的差异确定周围（1）的深度图，其中， 空间限定线（2）被识别，限定周围（1）的无障碍区域，其中在自由空间限定线（1）的外部和沿着自由空间限定线（1），深度卡由具有适当宽度的段（3） 与图像平面相同或相似的距离，其中每个段（3）的高度被估计为位于无障碍区域外侧​​的对象（4.1至4.6）的一部分，使得每个段（3）被表征 通过基座的二维位置（例如，与车辆的纵向轴线的距离和角度）及其高度。

公开(公告)号：US08548229B2

公开(公告)日：2013-10-01

申请号：US13201241

申请日：2010-02-04

申请人： Hernan Badino ,  Uwe Franke

发明人： Hernan Badino ,  Uwe Franke

IPC分类号： G06K9/00

CPC分类号： G06K9/00805

摘要： A method for detecting objects, wherein two images of a surrounding (1) are taken and a disparity image is determined by means of stereo image processing, wherein a depth map of the surrounding (1) is determined from the determined disparities, wherein a free space delimiting line (2) is identified, delimiting an unobstructed region of the surrounding (1), wherein outside and along the free space delimiting line (1) the depth card is segmented by segments (3) of a suitable width formed by pixels of the same or similar distance to an image plane, wherein a height of each segment (3) is estimated as part of an object (4.1 to 4.6) located outside of the unobstructed region in a way, such that each segment (3) is characterized by the two-dimensional position of the base (for example the distance and angle to the longitudinal axis of the vehicle) and the height thereof.

摘要翻译： 一种用于检测物体的方法，其中拍摄周围（1）的两个图像，并且通过立体图像处理来确定视差图像，其中根据确定的差异确定周围（1）的深度图，其中， 空间限定线（2）被识别，限定周围（1）的无障碍区域，其中在自由空间限定线（1）的外部和沿着自由空间限定线（1），深度卡由具有适当宽度的段（3） 与图像平面相同或相似的距离，其中每个段（3）的高度被估计为位于无障碍区域外侧​​的对象（4.1至4.6）的一部分，使得每个段（3）被表征 通过基座的二维位置（例如，与车辆的纵向轴线的距离和角度）及其高度。

公开(公告)号：US20090297036A1

公开(公告)日：2009-12-03

申请号：US11993398

申请日：2006-01-03

申请人： Hernan Badino ,  Uwe Franke ,  Stefan Gehrig ,  Clemens Rabe

发明人： Hernan Badino ,  Uwe Franke ,  Stefan Gehrig ,  Clemens Rabe

IPC分类号： G06K9/62

CPC分类号： G06K9/00805 ,  G06K9/00818 ,  G06T7/215 ,  G06T7/277

摘要： The invention relates to a method for detecting objects on a pixel plane. Said movable object detection is frequently possible only by tracking the pre-segmented objects or the parts thereof. in this relation, the spatially adjacent objects often provoke problems, in particular in the case when a camera system or more precisely an observer is movable. The inventive method consists in determining a two-dimensional position of the relevant pixels inside a first image and in determining an associated remote value for each relevant pixel. Said pixels are tracked and localized on two ore more successive images, wherein the two-dimensional position or the pixel offset and the associated remote value are again determined for each pixel. The position and movement of the relevant pixels are also determined with the aid of a suitable filter. Finally, the relevant pixels are combined into objects under predefined conditions with respect to the position, moving direction and motion ratio thereof.

摘要翻译： 本发明涉及一种用于检测像素平面上的物体的方法。 所述可移动物体检测通常仅通过跟踪预分割对象或其部分而成为可能。 在这种关系中，空间相邻的物体经常引起问题，特别是在照相机系统或更精确地观察者是可移动的情况下。 本发明的方法在于确定第一图像内的相关像素的二维位置并确定每个相关像素的相关联的远程值。 所述像素被跟踪并定位在两个更连续的图像上，其中再次针对每个像素确定二维位置或像素偏移和相关联的远程值。 相关像素的位置和移动也借助于合适的滤波器来确定。 最后，相关像素在相对于其位置，移动方向和运动比的预定条件下组合成对象。