Minimization of Storage on Moving Objects in Video Surveillance
Navin Kumar. · International Journal for Research in Applied Science and Engineering Technology · 2019
Investigation and so the number of surveillance cameras installed in public space is increasing.Many cameras installed at fixed positions are required to observe a wide and complex area, so observation of the video pictures by human becomes difficult.So there is a need for automation and dynamism in such surveillance systems.In order to allow the different users (operators and administrators) to monitor the system selecting different Quality of Service (QoS) are required depending on the system status and to access live and recorded video from different localizations i.e. from their mobile devices.More concretely, in Internet Protocol (IP) surveillance systems some resources involved are limited or expensive.So a technology using automatic detection of intruders (using image processing systems) and automatic alert systems will provide competitive advantage for surveillance systems.Video surveillance systems are the most important for crime investigation.Detection of suspicious human action is of great practical importance.Due to random nature of human movements, reliable classification of suspicious human movements can be very difficult.Our primary aim is to bring out a solution for the memory consumption during video recording and the problem of automatically tracking people and detecting unusual or suspicious movements in Closed Circuit TV (CCTV) videos.Our work presents a frameworkthat processes video data obtained from a CCTV camera fixed at a particular location.It is also used to reduce the storage location of recording videos as the videos will be recorded statically.I.