Method and device for object recognition from depth-resolved image data

摘要

The invention relates to a method and a device for object recognition. The method comprises the steps: formation of at least one object from a depth image of a 3D camera evaluation and classification of the object (s) 2, 3 in a 2D image 5, which corresponds to the at least one formed object in the depth image (1 ) - possible sharing of the at least one object (1) formed from the depth image taking into account the classification of the object or objects (2, 3) in the 2D image (5) into a plurality of individual objects (2; 3). The method or the device can be used in particular in the context of a driver assistance system for the detection of objects in a vehicle environment.