Improved combined invariant moment for moving targets classification

摘要

Invariant moment is a highly concentrated and distortion invariant image features. The goal of multi-moving object characterization and classification methods is to find a suitable description of different kinds of moving objects in the scene and match the similarity between unknown moving objects with invariant moment. This paper presents evolution and development of invariant moments family history, and designs a classification model to classify multi-moving objects. Experimental results show that this method can effectively improve the recognition rate of the moving object.