Pregled bibliografske jedinice broj: 1277755
AUTONOMOUS SECURITY SYSTEM BASED ON ARTIFICIAL INTELLIGENCE
AUTONOMOUS SECURITY SYSTEM BASED ON ARTIFICIAL INTELLIGENCE // Zbornik radova XV. konferencije Dani kriznog upravljanja / Toth, Ivan (ur.).
Velika Gorica, 2022. str. 574-580 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), stručni)
CROSBI ID: 1277755 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
AUTONOMOUS SECURITY SYSTEM BASED ON ARTIFICIAL
INTELLIGENCE
Autori
Radovan, Aleksander ; Pajas, Matija ; Gligora, Tomislav ; Mihaljević, Branko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), stručni
Izvornik
Zbornik radova XV. konferencije Dani kriznog upravljanja
/ Toth, Ivan - Velika Gorica, 2022, 574-580
Skup
XV. Međunarodna znanstveno-stručna konferencija Dani kriznog upravljanja
Mjesto i datum
Velika Gorica, Hrvatska, 26.10.2022. - 27.10.2022
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
security system, autonomous, artificial intelligence, image processing, mobile network
Sažetak
By significantly improving technological capabilities and the power of artificial intelligence, traditional security systems controlled by humans can be improved considerably, primarily in ensuring safety for citizens in populated areas, where the timely distribution of information can prevent the spread of danger and protect human lives. This paper will show a proposal for the implementation of an autonomous security system that, using the infrastructure of security cameras and mobile operators, enables autonomous notification of citizens about threats and the provision of basic information on how to behave. Image processing algorithms combined with algorithms for recognizing dangerous situations form the basis of the autonomy of the proposed system. These algorithms have the ability to learn and improve in order to detect objects and situations better, and they are based on the use of existing data sets, i.e., images, enabling continuous improvement. The features extracted from the images are then normalized, formatted, and prepared to be sent to an integrated system that manages the mobile network, which notifies mobile users of the emerging situation and instructs them on how to behave. Since it can retrieve information about users who are in a certain area and connected to the base stations of the telecommunications network, the mobile network can also automatically act to provide the user with key information. In this paper, the details of such a system and the combined experiences of the authors in the construction of such systems are given, as well as usage scenarios and best practices are described.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Tehničko veleučilište u Zagrebu,
Veleučilište Velika Gorica,
Visoko učilište Algebra, Zagreb ,
RIT Croatia, Dubrovnik