摘要
This paper discusses recognition of three dimensional (3D) moving object from multiple views, which is based on 2D processed frames of a video sequence, view categories (feature aspects) of object, and their transitions. Log polar mapping (LPM) and discrete Fourier transformation (DFM) are used to obtain position, scale and rotation invariant feature vectors of 2D characteristic views. ART 2 model is used as memory and classifier of the feature information of the object. ART 2 neural network is improved in experiment with satisfactory results.
ＶｉｓｉｏｎＲｅｃｏｇｎｉｔｉｏｎｏｆＴｈｒｅｅＤｉｍｅｎｓｉｏｎａｌＯｂｊｅｃｔＵｓｉｎｇＡｓｐｅｃｔＧｒａｐｈＬＵＡＮＸｉｎＺＨＵＴｉｅｙｉＴＡＯＱｉｚｈｉ（栾新）（朱铁一）（陶奇志）（ＲｏｂｏｔＲｅｓｅａｒｃｈＩｎｓｔｉｔｕｔｅ，Ｈａｒｂｉｎ...
