Research on biomimetic pattern recognition for object adaptive tracking algorithm |
| |
Authors: | LIU Huanyun WANG Junning HE Di TU Shangbin |
| |
Affiliation: | (School of Telecommunication Engineering, Xidian Univ., Xi'an 710071, China) |
| |
Abstract: | A new method for image object recognition and tracking based on Biomimetic Pattern Recognition (BPR), which can automatically change the size of the object, is proposed. To accomplish the learning process of the sample objects with different sizes, an artificial neural network model is used to cover the training sample. The curve fitting method based on the Radial Basis Function (RBF) neural network is presented to approximate the size of the objects in the coverage of the network formed by BPR theory in order to change the size of the object automatically. The Quadratic Minimum Distance algorithm based on the Euclidean distance is applied to search the target in the process of object recognition and tracking. Experimental results and theoretical analysis show that the algorithm proposed in this paper is more effective and robust in object recognition and tracking of video image sequences than the BP neural network. |
| |
Keywords: | biomimetic pattern recognition target tracking curve fitting quadratic minimum distance neural network |
|
| 点击此处可从《西安电子科技大学学报》浏览原始摘要信息 |
|
点击此处可从《西安电子科技大学学报》下载全文 |