Abstract
Individuals react in response to internal or external stimuli, whether visual, auditory, gustatory, olfactory, cutaneous, kinesthetic, or vestibular. This behavior is not fully utilized to infer possible security incidents taking place or about to take place in a defined geographical area outside of the range or field-of-view of security systems. Sensors are in place in the form of human senses. If these natural sensors are utilized together with advances in deep learning technology, researchers will be equipped to build advanced security solutions. In this paper, we propose a security system based on the crowd behavior of synchronous head movement (SHMOV). The system provides an alert of a possible security incident if synchronous head movement occurs among a crowd in a specific area by analyzing the video stream from a camera. We assessed the proposed SHMOV system using an experiment on 20 participants in auditory, visual, and olfactory settings. This experiment demonstrated the technology's potential, with 100%, 100%, and 80% incident detection accuracy and alerts issued 9, 24, and 47 seconds after the start of each incident, respectively.