Xinde Li, Yilin Dong, Chaomin Luo, and Yingzi Tan
Aircraft target recognition, locally linear embedding, Markov chain,HMM
Aiming to the problem of low recognition rate for aircraft target recognition caused by the change of postures, an aircraft target recognition based on locally linear embedding (LLE) and hidden Markov model (HMM) is proposed in this paper. Firstly, we extract features from the single frame image. Secondly, we use the LLE method for the nonlinear dimension reduction. To obtain a set of sequence information, preliminary identification is used in the low-dimensional embedding space. To make up for the loss of the information in the dimension reduction, meanwhile, due to the similarity of images for the different aircrafts in some attitudes, the sequence information fusion based on the HMM is used to complete the aircraft target recognition. Finally, the experiment result shows the validity of this method.
Important Links:
Go Back
