Hidden Markov Model-Based Sense-Through-Foliage Target Detection Approach
In this paper, we propose sense-through-foliage targetdetection approach based on Hidden Markov Models (HMMs). Separate Hidden Markov Models are trained for signals containing target signature and no target (clutter), respectively. Less correlated features are selected as input of Hidden Markov Models for training and testing. Foliage data is collected from three different UWB radar locations, and experimental results show that position 1 data gives the best detection result. All three locations have above 0.8 AUC from the ROC curves.
KeywordsRadar target detection Foliage UWB HMM
This work was supported in part by NSFC under Grant 61731006, 61771342, 61711530132, Royal Society of Edinburgh, and Tianjin Higher Education Creative Team Funds Program.
- 5.Sauper C, Haghighi A, Barzilay R. Incorporating content structure into text analysis applications. In: Proceedings of the 2010 conference on empirical methods in natural language processing (EMNLP ’10). Stroudsburg, PA, USA: Association for Computational Linguistics; 2010. p. 377–87.Google Scholar
- 7.Dill C. Foliage Penetration (Phase II) Field Test: Narrowband versus Wideband Foliage Penetration. Final Report of Contract Number F41624-03-D-7001/04, July 2005 to Feb 2006.Google Scholar
- 8.Liang J, Liang Q, Samn SW. Foliage clutter modeling using the UWB radar. In: 2008 IEEE international conference on communications, Beijing, 2008; p. 1937–41.Google Scholar
- 9.Liang Q, Samn SW, Cheng X. UWB radar sensor networks for sense-through-foliage target detection. In: 2008 IEEE international conference on communications, Beijing, 2008; p. 2228–32.Google Scholar