Howard C. Choe

Wavelet-based ground vehicle recognition using acoustic signals

We present, in this paper, a wavelet-based acoustic signal analysis to remotely recognize military vehicles using their sound intercepted by acoustic sensors. Since expedited signal recognition is imperative in many military and industrial situations, we developed an algorithm that provides an automated, fast signal recognition once implemented in a real-time hardware system. This algorithm consists of wavelet preprocessing, feature extraction and compact signal representation, and a simple but effective statistical pattern matching. The current status of the algorithm does not require any training. The training is replaced by human selection of reference signals (e.g., squeak or engine exhaust sound) distinctive to each individual vehicle based on human perception. This allows a fast archiving of any new vehicle type in the database once the signal is collected. The wavelet preprocessing provides time-frequency multiresolution analysis using discrete wavelet transform (DWT). Within each resolution level, feature vectors are generated from statistical parameters and energy content of the wavelet coefficients. After applying our algorithm on the intercepted acoustic signals, the resultant feature vectors are compared with the reference vehicle feature vectors in the database using statistical pattern matching to determine the type of vehicle from where the signal originated. Certainly, statistical pattern matching can be replaced by an artificial neural network (ANN); however, the ANN would require training data sets and time to train the net. Unfortunately, this is not always possible for many real world situations, especially collecting data sets from unfriendly ground vehicles to train the ANN. Our methodology using wavelet preprocessing and statistical pattern matching provides robust acoustic signal recognition. We also present an example of vehicle recognition using acoustic signals collected from two different military ground vehicles. In this paper, we will not present the mathematics involved in this research. Instead, the focus of this paper is on the application of various techniques used to achieve our goal of successful recognition.

Novel identification of intercepted signals from unknown radio transmitters

We present a methodology for classifying and/or identifying unknown radio transmitters by analyzing turn-on transient signals. Since an expedited signal classification and identification is desirable, we developed an automated, fast signal classification and identification method using wavelet-based feature extraction combined with an artificial neural network (ANN). The environment we considered is that there are n radio frequency (rf) transmitters given m finite duration signals (m > n, several signals may be emitted from the same transmitter). We preprocess unknown transient signals using wavelet decomposition and extract multiresolution features (statistical and energy content) to provide efficient signal characterization. An ANN, trained on known signals and selected wavelets, is then used for classifying and identifying the extracted feature characteristics of the unknown signals. Our wavelet preprocessing combined with the ANN provide a robust and adaptive classifier and identifier. We also provide an example of transmitter classification and identification using transient signals collected from three different transmitters.

Wavelet analysis of ground vehicle acoustic signatures

In this paper we consider wavelet analyses of acoustic signatures of ground vehicles. We select two test cases, a squeak emanating from a tank track and the clatter of a tank running on pavement. We examine various cost functions that can be utilized in determining which set of wavelet basis functions give the most accurate representation of a given signal. We compare different orthogonal and biorthogonal wavelet transforms with each other and with the local cosine transform. We found that the local cosine transform performed better for the squeak than the particular wavelet packet transforms that we used, while they both gave approximately equivalent results for the clatter signal.

Sensor performance and weather effects modeling for intelligent transportation systems (ITS) applications

Optical sensors are used for several ITS applications, including lateral control of vehicles, traffic sign recognition, car following, autonomous vehicle navigation, and obstacle detection. This paper treats the performance assessment of a sensor/image processor used as part of an on-board countermeasure system to prevent single vehicle roadway departure crashes. Sufficient image contrast between objects of interest and backgrounds is an essential factor influencing overall system performance. Contrast is determined by material properties affecting reflected/radiated intensities, as well as weather and visibility conditions. This paper discusses the modeling of these parameters and characterizes the contrast performance effects due to reduced visibility. The analysis process first involves generation of inherent road/off- road contrasts, followed by weather effects as a contrast modification. The sensor is modeled as a charge coupled device (CCD), with variable parameters. The results of the sensor/weather modeling are used to predict the performance on an in-vehicle warning system under various levels of adverse weather. Software employed in this effort was previously developed for the U.S. Air Force Wright Laboratory to determine target/background detection and recognition ranges for different sensor systems operating under various mission scenarios.

Evaluation of ΔT using statistical characteristics of the target and background

The conventional area weighted average temperature (AWAT) (Delta) T is a primary performance measure for characterizing target/background scenes. However, the AWAT definition is widely recognized as being inadequate for representing observer sensitivity in many target detection and acquisition tasks. This situation is particularly true for targets which are at short ranges relative to the observer or viewed through powered optics. In these cases the mid and high spatial frequency components provide distinctive cue features which dominate over the average or aggregate characteristics of the target. The authors examine alternative definitions of (Delta) T in order to identify more robust and accurate metrics for the evaluation of sensor and signature countermeasure performance. The analysis indicates that target/background scene descriptions using simple average parameters such as the mean and standard deviation are not sufficient for characterizing imaging sensor performance against targets with internal texture and contrast gradients in background clutter.

Comparative study of wavelet methods in ground vehicle signature analysis

In this paper we make a comparison between wavelet transforms and the local cosine transform of various types of images. This builds on our previous work involving acoustic signals, where we found that the local cosine transform gave a more compact representation for certain types of signals and performed as well as wavelets for others. This held even for signals that were transient in nature, where one might expect the wavelets to do better. We are interested in determining if the same holds true for images, which tend to include many transients, such as edges. We are also investigating the extent to which the rms error can be used to evaluate the perceptual quality of the reconstructed images.

Time-varying acoustic source identification using fusion of hidden Markov model and wavelet neural network

In this paper, we propose a first-order fused HMM-ANN (hidden Markov model and artificial neural net) classifier using feature vectors extracted from ground vehicle acoustic signals. The feature vectors applied in this paper are Fourier power spectrum and scale-invariant wavelet coefficients. Our fused classifier network robustly provides a better performance for a variety of ground vehicle acoustic signals when compared to a classifier with either HMM or ANN alone. We emphasize the use of scale-invariant wavelet transforms to extract scale-invariant wavelet coefficient features because they play a vital role in classifying and identifying unknown ground vehicle acoustic signals that are time-varying in scale structure.

IMPACT OF ADVERSE WEATHER ON SENSORS FOR VEHICLE COLLISION AVOIDANCE SYSTEMS

This paper treats the use of in-vehicle imaging sensors to achieve lateral control to avoid single vehicle roadway departure crashes. Since the sensor is expected to function under a variety of weather conditions, it is important to determine the overall performance envelope of the combined sensor/image processing algorithm. Initial roadway imagery was acquired under favorable ambient conditions and subsequently transformed to specified levels of adverse weather by means of software originally developed for military sensor applications. The transformed imagery was utilized to determine the relationship between adverse weather, measured in visibility ranges, versus the ability of the sensor/image processing algorithm to maintain lateral vehicle stability.

Scene/object classification using multispectral data fusion algorithms

Near-simultaneous, multispectral, coregistered imagery of ground target and background signatures were collected over a full diurnal cycle in visible, infrared, and ultraviolet spectrally filtered wavebands using Battelles portable sensor suite. The imagery data were processed using classical statistical algorithms, artificial neural networks and data clustering techniques to classify objects in the imaged scenes. Imagery collected at different times throughout the day were employed to verify algorithm robustness with respect to temporal variations of spectral signatures. In addition, several multispectral sensor fusion medical imaging applications were explored including imaging of subcutaneous vasculature, retinal angiography, and endoscopic cholecystectomy. Work is also being performed to advance the state of the art using differential absorption lidar as an active remote sensing technique for spectrally detecting, identifying, and tracking hazardous emissions. These investigations support a wide variety of multispectral signature discrimination applications including the concepts of automated target search, landing zone detection, enhanced medical imaging, and chemical/biological agent tracking.

Introduction of target, atmosphere, background, and sensor-specific (TABSS) ΔT metric: analysis, comparison, and applications

EO/IR/FLIR sensor performance models currently employ a thermal difference metric(s) to predict target detection, recognition, and identification ranges in conjunction with minimum resolvable temperature difference (MRT) curves. In this paper, we present a target, atmosphere, background, and sensor-specific (TABSS) thermal difference metric, minimizing shortcomings and deficiencies of other thermal difference metrics currently used in thermal imaging system performance models. This metric is parametrically compared with other (Delta) (Tau) metrics. We also investigate target, background, and scene pixel variances behavior as the scene maps to a fewer number of pixels, which reveals potential applications in clutter metrics as well as detection, recognition, and identification range predictions. Finally, we survey current status of sensor performance models to seek an application of the TABSS (Delta) (Tau) metrics. We find that this metric will enhance the current thermal imaging system performance models to accurately predict detection, recognition, and identification ranges not only when the thermal difference is large, but especially when the thermal difference is small.