Detection and classification of concealed weapons using a magnetometer-based portal

摘要: A concealed weapons detection technology was developed through the support of National Institute Justice (NIJ) to provide a non intrusive means for rapid detection, location, and archiving data (including visual) potential suspects weapon threats. This technology, by Idaho Engineering Environmental Laboratory (INEEL), has been applied in portal style system using passive magnetic sensors as its basis. paper will report on enhancements enable classification discriminate threats from non-threats. Advanced signal processing algorithms were used analyze spectrum generated when person passes portal. These analyzed multiple variables including variance signature random placement and/or orientation. They perform pattern recognition calculate probability that collected correlates known database versus non-weapon responses. Neural networks further type identify controlled electronic items such cell phones pagers. False alarms reduced analyzing detector response Joint Time Frequency Analysis digital technique. The frequency components power given sensor derived. unique fingerprint provided additional information aid analysis. produce major improvements classification.