The main need at University Residential Centre of Bertinoro (Ce.U.B. of the University of Bologna) was to integrate a Reco component into smart lighting poles produced by Ghisamestieri (into a product called Genius) installed in outdoor environment campus areas. The main target for this scenario was to:
“Integrate context recognition software into discrete environment”
Reco Context component has been installed using pre-existing cameras, preserving video surveillance infrastructure and configuring the system in order to:
“Smart City includes solutions to monitor large outdoor context, detecting abandoned or removed objects and crowded zones“
Abandoned object detection is one of the most useful areas of computer vision, due to its application in automated video surveillance systems for the detection of suspicious activities, that might endanger public safety. It is expecially important in sensitive and crowded places like universities, airports, railway stations, shopping centers, theatres and outdoor in private organizations.
Object detection becomes a more complex task due to occlusions, lighting changes, and other factors. Our framework allows to detect abandoned objects using adaptive background modeling generated based on pixel intensity. Once the object is detected, the system can classify the object characteristics such as the status (as removed or abandoned) and object dimension and then alert security staff (via mobile or directly to a control room).