Classification of Live/Lifeless Assets with Laser Beams in Different Humidity Environments

Detecting the vitality of a certain distance person is important in natural disasters, search and rescue activities, urban warfare environments and in the fight against terrorism. In this study, a system is proposed that targets located at a certain distance are marked with a low-power laser beam, allowing them to be detected as live/lifeless. In addition, the performance of the proposed system in different relative humidity environments is analyzed. In this study, in a laboratory environment with 32%, 60%, 70% and 80% relative humidity, laser marks are obtained from the arms of 10 volunteer male subjects and 17 different objects, for each humidity rate. The signals obtained are trained in the developed deep learning network. In the literature, it is known that the performance of electronic devices at high relative humidity rates has decreased. As a result of experimental studies, it can be seen that the proposed system has a high classification performance even in the low humidity and very high humidity range. The fact that assets at a certain distance can be classified as live/lifeless with a high-performance rate, regardless of the humidity rate, demonstrates the applicability of the proposed system.