Vehicle Engine Classification Using Spectral Tone-Pitch Vibration Indexing and Neural Network

Introduction

The use of a Laser Doppler Vibrometer (LDV) as one important multi-modal imaging instrument has been consistently growing in recent years due to the unique advantage it can provide. An LDV sends out a laser beam to a reflective surface S which is then reflected back to the LDV, the amplitude and frequency of S’s vibrations are extracted from the Doppler shift of the reflected laser beam frequency due to the S’s vibrating motion. LDV sensors provide many advantages:

• 1.

  Non-contact and non-destructive measurements: No mass or pressure is applied during LDV’s measurement process; they are almost entirely harmless (only some high power types may cause damage to human eyes if viewed directly). LDV exerts no additional pain in non-invasive medical applications such as body temperature and pulse monitoring during medical operations, and causes no extra damages in non-intrusive civil engineering applications such as inspections of bridges, railways and buildings (Willemann, Castellini, Revel, & Tomasini, 2004) (Kubota, 2007) and delicate inspections of murals and antique fresco paintings in museums where LDV is the only viable means for inspection purposes (Castellini, Paone, & Tomasini, 1996). By contrast, the small dose of radiation from CT or X-ray in medical applications can have side effects to human cells; and the water penetration and/or corrosion are troublesome side effects in traditional ultrasonic tests.

• 2.

  High spatial and spectral resolution: the expansive and wide range of amplitudes and frequencies provided by LDV sensors confer researchers and developers with valuable information in both spatial and frequency domains for ensuing intensive analysis and classification.

The use of LDV in many research and development subjects has become increasingly more popular due precisely to the foregoing advantages. As a non-invasive and remote sensor with the afore-mentioned benefits, LDV measured data are an ideal modality/phenomenology to detect potential threats earlier and provides better protection to society, which is of utmost importance to military and law enforcement institutions. The use of LDV in vehicle classification using signature analysis is of crucial interest to military and law enforcement institutions, but is still in its infancy due to the lack of systematic investigations on its behavioral properties.