to identify the threats, or mishaps beforehand. To achieve this goal, we are currently detecting weapons, firearms, and any suspicious activities, apart from that if any problem occurs, it is going to try to detect if any casualties had happened, and is producing the alert.

[1] Jaime Dever, Niels da Vitoria Lobo, and Mubarak Shah “Automated Visual Recognition of Armed Robbery”.[Online]. http://crcv.ucf.edu/papers/robbery.pdf.

[2]M.Grega, A. Matiolanski, P. Guzik and M. Leszczuk. “Automated detection of firearms and knives in a CCTV image”. Sensors 16(1), pp. 47. 2016.

[3] Saturnino Maldonado-Bascón, Cristian Iglesias-Iglesias, Pilar MartínMartín* and Sergio Lafuente-Arroyo.“Fallen People Detection Capabilities Using Assistive Robot”. Electronics 2019, 8(9), 915; 21 August 2019. [Online]. https://doi.org/10.3390/electronics8090915

[4] A. Bobick and S. Intille. Recognizing planned, multiperson action. Computer Vision and Image Understanding, 81(3):414–445, 2001.

[5] Kmiec M., Glowacz A. An Approach to Robust Visual Knife Detection. Mach. Graph. Vis. 2011; 20:215–227.

[6] Chen LH, Hsu HW, Wang LY, Su CW. Violence detection in movies. In: Computer Graphics, Imaging and Visualization (CGIV), 2011 Eighth International Conference on. IEEE; 2011. p. 119–124.

[7] Zhang, T.; Zhang, W.; Qi, L.; Zhang, L. Falling detection of lonely elderly people based on NAO humanoid robot. In Proceedings of the 2016 IEEE International Conference on Information and Automation (ICIA), Ningbo, China, 1–3 August 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 31–36.