Automatic Surveillance System for Video Sequences
Abstract of the project
Video surveillance systems are quite common these days. Surveillance data has increased exponentially in last couple of years. This rate of increase has been gathering speed in underdeveloped and developed countries. Only in United Kingdom, there are 4.2million closed circuit TV cameras are installed, one per every 14 people. This procedure is becoming common in Pakistan too. CPO office Lahore has more than 100 surveillance cameras while Punjab institute of Cardiology has 80 cameras to monitor activities of patients and their relatives. A huge amount of data is collected by these cameras every day, but question remains, if all of this data is useful. It seems insane to store the whole day data if it was a serene day, or even if some suspicious activity is observed in some part of the day. The storage mechanism should be robust to log only the most relevant coverage of the video stream. If further creates the problem of storing huge amount of data which is expensive in relation to storage media required. This project is a step towards remedy of above mentioned problems, i.e. using image processing methods for secured and safer atmosphere for our country men and keeping a check on storage of video streams data. The system will use surveillance cameras installed in security sensitive areas which will capture and store videos of daily life activities being happening in that area. Automatic understanding of these videos will be performed using image processing methods which will trigger alarms in case of any unusual event occurrences. Textual description of the video sequence will be generated using natural language processing which will save storage size since textual storage is less storage intensive as compared to video sequences. A web based utility for videos searching and summarization will be provided to search most relevant videos in accordance with the security needs,
This project can provide support to law enforcement agencies in reducing events of terrorism. This project mainly encompasses automatic understanding of visual scenes based on individual contents/High Level Features (HLFs)  present in the videos. By extracting high-level features, such as the human’s face, age, gender, actions and objects etc., we can distinguish the mobility of suspects and offenders. The peaceful purposes of this project are monitoring crowd, restricted access points and counting occurrence of specific persons. Project knowingly substitutes for human intervention for monitoring of surveillance cameras. Such human intervention can cause drowsiness or over work scenarios, while our system is running all day without human intervention.