Unattended ground sensor (UGS) networks are intended to detect and localize the presence of strategic relocatable targets in the theater of operation over several kilometers. Passive acoustic sensors, an integral part of UGS, have achieved a high level of maturity and will allow acoustic target classification for tracked and wheeled vehicles. Of primary importance in the classification problem is the selection of a robust feature extraction technique, tolerant of both the environment and the nonstationary nature of the acoustic signatures. Several feature extraction techniques were used with experimental acoustic data collected from a small baseline, circular array. Results will be presented of the classification for acoustic features using a backpropagation neural network with simple power spectrum, harmonic line association [J. A. Robertson, IIT Research Institute, in-house report], principal components [J. Mao and A. K. Jain, IEEE Trans. Neural Networks 6 (2) (1995)], and wavelet packet [K. Etemad and R. Chellappa, Proc. First Intl. Conf. on Image Processing (November 1994)] feature extraction techniques.
The U.S. Army Research Laboratory (ARL) is developing an acoustic target classifier using a backpropagation neural network (BPNN) algorithm. Various techniques for extracting features have been evaluated to improve the confidence level and probability of correct identification. Some techniques used in the past include simple power spectral estimates (PSEs), split-window peak-picking, harmonic line association (HLA), principal component analysis (PCA), wavelet packet analysis,1'2'3'4 and others. In addition, improved results have been obtained when data are combined from other sensors co-located with the acoustic sensor. A three-axis seismic sensor has been configured as part of an acoustic sensor array that ARL uses on typical field experiments, with data collected and sampled simultaneously.The PSE, HLA, and shape statistic feature data are extracted from a group of vehicles and then split into testing and training files. The training file typically consists of 75 percent of the data set, and the performance of the trained neural network is evaluated with the remaining test data. Cross-validation is performed with vehicle data collected at different times of day and under various conditions. Results of the neural network from a few of the feature extraction algorithms under evaluation and from the fusion of the acoustic and seismic sensor data are presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.