Automatic video surveillance can assist security personnel in the identification of threats. Generally, security personnel are monitoring multiple monitors and a system that would send an alert or warning could give the personnel extra time to scrutinize if a person is carrying a firearm. In this paper, we utilize Google’s Tensorflow API to create a digital framework that will identify handguns in real time video. By utilizing the MobileNetV1 Neural Network algorithm, our system is trained to identify handguns in various orientations, shapes, and sizes, then the intelligent gun identification system will automatically interpret if the subject is carrying a gun or other objects. Our experiments show the efficiency of implemented intelligent gun identification system.
CITATION STYLE
Singleton, M., Taylor, B., Taylor, J., & Liu, Q. (2018). Gun identification using tensorflow. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 251, pp. 3–12). Springer Verlag. https://doi.org/10.1007/978-3-030-00557-3_1
Mendeley helps you to discover research relevant for your work.