Hidden Markov modeling for automatic target recognition

Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136) Pub Date : 1997-11-02 DOI:10.1109/ACSSC.1997.680565

D. Kottke, Jong-Kae Fwu, K. Brown

引用次数: 12

Abstract

A novel approach for applying hidden Markov models (HMM) to automatic target recognition (ATR) is proposed. The HMM-ATR captures target and background appearance variability by exploiting flexible statistical models. The method utilizes an unsupervised training procedure to estimate the statistical model parameters. Experiments upon a synthetic aperture radar (SAR) database were performed to test robustness over range of target pose, variation in target to background contrast, and mismatches in training and testing conditions. The results are compared against a template matching approach. The HMM captures target appearance variability well and significantly outperforms template matching in both robustness and flexibility.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

自动目标识别的隐马尔可夫建模

提出了一种将隐马尔可夫模型应用于自动目标识别的新方法。HMM-ATR通过利用灵活的统计模型捕获目标和背景的外观变化。该方法利用无监督训练过程来估计统计模型参数。在合成孔径雷达(SAR)数据库上进行了实验，测试了目标姿态范围、目标与背景对比度变化以及训练和测试条件下的不匹配情况下的鲁棒性。结果与模板匹配方法进行了比较。HMM可以很好地捕获目标的外观变化，并且在鲁棒性和灵活性方面都明显优于模板匹配。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136)

自引率

0.00%

发文量

期刊最新文献

A comparative study of multiple accessing schemes Self-affine modeling of speech signal in speech compression A progressive transmission image coder using linear phase paraunitary filter banks A canonical representation for distributions of adaptive matched subspace detectors Finite length equalization for FFT-based multicarrier systems-an error-whitening viewpoint