公开(公告)号：US08189049B2

公开(公告)日：2012-05-29

申请号：US12690667

申请日：2010-01-20

申请人： Vitaly Alexandrovich Lopota ,  Alexander Sergeyevich Kondratyev ,  Victor Ivanovich Yudin ,  Sergey Anatoliyevich Polovko ,  Ekaterina Yurevna Smirnova ,  Kirill Nikolayevich Stupin ,  Lev Borisovich Kogan ,  Dmitry Nikolayevich Stepanov ,  Wataru Ito ,  Mitsue Ito ,  Kazunari Iwanaga ,  Miyuki Fujii

发明人： Vitaly Alexandrovich Lopota ,  Alexander Sergeyevich Kondratyev ,  Victor Ivanovich Yudin ,  Sergey Anatoliyevich Polovko ,  Ekaterina Yurevna Smirnova ,  Kirill Nikolayevich Stupin ,  Lev Borisovich Kogan ,  Dmitry Nikolayevich Stepanov ,  Wataru Ito ,  Mitsue Ito ,  Kazunari Iwanaga ,  Miyuki Fujii

IPC分类号： H04N7/18 ,  G06K9/34

CPC分类号： G08B13/1961 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/20044

摘要： Binarization is performed using a threshold image obtained by multiplying a variation in each pixel value of an input image with a coefficient. Although the variation is time-averaged based on an update coefficient for each pixel, the update coefficient is switched depending on whether or not a relevant pixel belongs to the object. Subsequently, from the binary image, an initial detection zone is formed and a spatial filtering process is performed thereto. The spatial filtering process includes at least one of skeleton analysis processing, object mask processing, morphology processing, and section analysis processing. For a tracking zone, the temporal positional change thereof is tracked, and the noise is reduced. Some of the tracking zones are removed, and the remaining zones are integrated into a cluster, and furthermore the cluster selection is performed based on the dimensions in real space.

摘要翻译： 使用通过将输入图像的每个像素值的变化与系数相乘而获得的阈值图像进行二值化。 虽然基于每个像素的更新系数对变化进行时间平均，但是根据相关像素是否属于对象来切换更新系数。 随后，从二进制图像中，形成初始检测区域并对其进行空间滤波处理。 空间滤波处理包括骨架分析处理，对象掩模处理，形态处理和截面分析处理中的至少一个。 对于跟踪区域，跟踪其时间位置变化，并且降低噪声。 一些跟踪区域被删除，其余区域被集成到集群中，此外，基于实际空间中的维度执行集群选择。

公开(公告)号：US08462211B2

公开(公告)日：2013-06-11

申请号：US12407606

申请日：2009-03-19

申请人： Vitaly Alexandrovich Lopota ,  Alexander Sergeyevich Kondratyev ,  Victor Ivanovich Yudin ,  Sergey Anatoliyevich Polovko ,  Ekaterina Yurevna Smirnova ,  Kirill Nikolayevich Stupin ,  Lev Borisovich Kogan ,  Dmitry Nikolayevich Stepanov

发明人： Vitaly Alexandrovich Lopota ,  Alexander Sergeyevich Kondratyev ,  Victor Ivanovich Yudin ,  Sergey Anatoliyevich Polovko ,  Ekaterina Yurevna Smirnova ,  Kirill Nikolayevich Stupin ,  Lev Borisovich Kogan ,  Dmitry Nikolayevich Stepanov

IPC分类号： H04N7/18

CPC分类号： G06T7/277 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2207/20012 ,  G06T2207/30196 ,  G06T2207/30236 ,  G06T2207/30241

摘要： The invention, at the first frame, records the background, as the threshold of detection-constant image with the predeterming minimum threshold, and with each subsequent frame, corrects the background and threshold with formulas while producing the adaptation of a renewal-constant in each pixel depending on the presence of the detected object, defines the difference between the current frame and background, compares it with the threshold, combines elements exceeding a threshold into detection zones, performs rejection of the detection zones, divides the zones in order to separate shadows, forms a tracking zone, searches already-detected segment of objects, forming clusters of the tracking zones. The coordinates of the obtained rectangles are assumed as the coordinates of the objects located in the frame.

摘要翻译： 本发明在第一帧中将背景记录为具有预定最小阈值的检测常数图像的阈值，并且随着每个随后的帧使用公式校正背景和阈值，同时在每一个中产生更新常数的适应 取决于检测对象的存在，定义当前帧和背景之间的差异，将其与阈值进行比较，将超过阈值的元素组合到检测区域中，执行检测区域的拒绝，划分区域以分离阴影 ，形成跟踪区域，搜索已经检测到的对象段，形成跟踪区域的群集。 所获得的矩形的坐标被假定为位于帧中的对象的坐标。