公开(公告)号：US06818883B2

公开(公告)日：2004-11-16

申请号：US10421758

申请日：2003-04-24

申请人： Oliver Rockinger ,  Juergen A. Topp ,  Thomas Fechner

发明人： Oliver Rockinger ,  Juergen A. Topp ,  Thomas Fechner

IPC分类号： H01J516

CPC分类号： G01V8/10

摘要： A method for the detection of helicopters from a flying platform utilizes an imaging sensor. Relevant image regions of two successive images are subtracted from one another with respect to picture elements, and within the thus formed differential image, segments are identified by means of a threshold value process. Straight lines of the same orientation are adapted to the identified segments, and intersection points are determined for all such straight lines. Identification of a helicopter is made based on a bunching of the intersection points.

摘要翻译： 用于从飞行平台检测直升机的方法利用成像传感器。 相对于图像元素相减两个连续图像的相关图像区域，并且在如此形成的差分图像中，通过阈值处理来识别段。 相同方向的直线适用于所识别的片段，并且为所有这些直线确定交点。 直升机的识别基于交叉点的聚束。

公开(公告)号：US06944342B1

公开(公告)日：2005-09-13

申请号：US09721457

申请日：2000-11-20

申请人： Christoph Stahl ,  Thomas Fechner ,  Oliver Rockinger

发明人： Christoph Stahl ,  Thomas Fechner ,  Oliver Rockinger

IPC分类号： G06K9/62 ,  G06K9/68 ,  G06K9/36

CPC分类号： G06K9/6292

摘要： Image data of optically acquired input images (1) are processed for emphasizing at least two object classes. Each pixel is subjected to a rough classification (10) based on first criteria that determine whether or not a pixel is relevant for an object recognition. A reduced image (11) is formed from the relevant pixels and irrelevant pixels are omitted. The reduced image (11) is filtered (20) for forming at least two correlated filtered images (21, 22, 23) based on second criteria. Classified images (31A, 32A, 33A) are formed from the filtered images by classifiers that work in accordance with predetermined rules. Weighting factors are allocated to each object class. The classified images are merged in accordance with an algorithm to make a combined global evaluation for each object class. The global evaluation decides, based on the merged images (41A, 41B, 41C), for each pixel whether the respective pixel belongs to an object class and if so to which object class.

摘要翻译： 对光学获取的输入图像（1）的图像数据进行处理以强调至少两个对象类别。 基于确定像素是否与对象识别相关的第一标准，对每个像素进行粗略分类（10）。 从相关像素形成缩小图像（11），省略不相关的像素。 基于第二标准，对缩小图像（11）进行滤波（20）以形成至少两个相关滤波图像（21,22,23）。 分类图像（31A，32A，33A）由根据预定规则工作的分类器的滤波图像形成。 加权因子被分配给每个对象类。 分类图像根据算法合并，以对每个对象类进行组合的全局评估。 全局评估基于合并图像（41A，41B，41C），针对每个像素来确定各个像素是否属于对象类，如果是属于对象类则。