Feature extraction and recognition of landmine

Authors:
Wu Jian-bin;Tian Mao;Ling Yu-tao
Affiliations:
Department of Information Technology, HuaZhong Normal University, Wuhan, Hubei, China;School of Electronic Information, WuHan University, Wuhan, Hubei, China;Department of Information Technology, HuaZhong Normal University, Wuhan, Hubei, China
Venue:
WiCOM'09 Proceedings of the 5th International Conference on Wireless communications, networking and mobile computing
Year:
2009

Citing 3
Cited 0

Support-Vector Networks

Machine Learning
SVMTorch: support vector machines for large-scale regression problems

The Journal of Machine Learning Research
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

As a new detecting landmine method, Ground Penetrating Radar (GPR) is introduced into the field of detecting buried landmine. In order to improve the detection accuracy, A approach based on the Support Vector Machine (SVMs) is presented in the paper. The Support Vector Machines (SVMs) has solved the inevitable partial minimum problem and overcome the disadvantage which the traditional neural network cannot avoid, especially, it is suitable for the high dimension data space and sample less situations, it is used to extract feature vector and recognize landmine. In order to improve the accuracy of detection landmine, WP (wave packet)-based preprocessing algorithm is used to clutter reducing and the genetic algorithms (Gas) is used in the feature selection. The experiment result shows the feasibility and advantage of the presented algorithm.