A number of recent statistics show that the rate of crime caused by firearms is of great concern in many parts of the world, especially in countries where firearms are legally permitted. One of the ways to reduce the threat of violence caused by firearms is early detection of their presence with sufficient time for officers or vigilantes to act. An innovative and effective solution in this context would be to equip surveillance cameras with intelligence.
The main weapon detection systems are based on metal detectors found in airports and at public events in enclosed areas. These systems are very expensive and not very effective for the particularities of today’s world, but their robustness makes them necessary in certain places (airports, public buildings, …). Nowadays, there is a need for a system that can reinforce and improve the current systems and be used in a greater number of environments.
The ultimate goal of this project is to develop an accurate and robust intelligent system for the detection of weapons on video especially suitable for the security field.
The outstanding results are:
- A model for firearms detection in videos using Deep Learning (https://www.sciencedirect.com/science/article/pii/S0925231217308196).
- A model of knife detection in surveillance video using pre-processing and Deep Learning techniques (https://www.sciencedirect.com/science/article/pii/S0925231218313365)
- An image fusion technique that minimises the number of false positives in the detection of weapons in real video surveillance scenarios (https://www.sciencedirect.com/science/article/pii/S1566253518300393).
Period
Enero 2017- current
Researchers
Francisco Herrera, Siham Tabik, Roberto Olmos, Alberto Castillo, and Francisco Pérez of the Instituto Interuniversitario de Investigación en Data Science and Computational Intelligence, Granada, Spain.
Awards
- Premio Security Forum I+D+i en el 2017 al proyecto de innovación UGR: “Sistema de detección de armas de fuego en vídeo en tiempo real”( https://www.securityforum.es/premios/).
- Recognition by MIT Technology Review of the arxiv version of the article “Automatic Handgun Detection Alarm in Videos Using Deep Learning” as one of the five most stimulating articles of the first week of March 2017 worldwide (https://www.technoloSecurity Forum R&D&I Award in 2017 to the UGR innovation project: “Real-time video firearms detection system” (https://www.securityforum.es/premios/).gyreview.com/s/603786/the-best-of-the-physics-arxiv-week-ending-march-4-2017/).
