Eads Deutschland Gmbh

Lfk-lenkflugkoerpersysteme Gmbh

Oliver Rockinger

Thomas Fechner

Christoph Stahl

Juergen A Topp

Image data of optically acquired input images () are processed for emphasizing at least two object classes. Each pixel is subjected to a rough classification () based on first criteria that determine whether or not a pixel is relevant for an object recognition. A reduced image () is formed from the relevant pixels and irrelevant pixels are omitted. The reduced image () is filtered () for forming at least two correlated filtered images () based on second criteria. Classified images (A,A,A) 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 (A,B,C), for each pixel whether the respective pixel belongs to an object class and if so to which object class.

Method for recognizing objects in an image pixel plane

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.

Growing community of inventors

Friedrichshafen, Germany

Oliver Rockinger