Active target recognition method based on sparse feature point cloud

The invention relates to the field of pattern recognition, in particular to an active target recognition method based on sparse feature point cloud. The purpose of active target recognition is to change the pose (viewpoint) of a visual sensor through planning to obtain sufficient information, so that the recognition efficiency and accuracy are improved. The active target recognition method based on the sparse feature point cloud comprises a target representation method based on the sparse feature point cloud and a feature point discrimination measurement method combining a visual dictionary and Bayesian. The method comprises the following steps: performing feature point detection and description on a target dense point cloud model, and constructing a sparse feature point cloud model of a target in combination with feature point model coordinates; and for the observable feature points in the candidate target, measuring the discrimination of each feature point by adopting a method of combining a visual dictiona