Multimodal Video Surveillance System

Abstract

Video Surveillance systems are used to monitor, observe and intercept the changes in activities, features and behavior of objects, people or places. A multimodal surveillance system incorporates a network of video cameras, acoustic sensors, pressure sensors, IR sensors and thermal sensors to capture the features of the entity under surveillance and send the recorded data to a base station for further processing. Multimodal surveillance systems are utilized to capture the required features and use them for pattern recognition, object identification, traffic management, object tracking, and so on. In the Indian scenario with the advent of the concept of ‘Smart Cities’, the need of an Intelligent Transportation System which is low-cost and limits power consumption is inevitable. The proposal is to develop an efficient camera placement algorithm for deciding placement of multiple video cameras at junctions and intersections in a multimodal surveillance system which will be capable of providing maximum coverage of the area under surveillance leading to complete elimination or reduction to a great extent the number of blind zones in a surveillance area, maximizing the view of subjects and minimizing occlusions in high vehicular traffic areas. Furthermore, the proposal is to develop a video summarization algorithm which can be used to create summaries of the videos captured in a multi-view surveillance system. Such a video summarization algorithm can be used further for object detection, motion tracking, traffic segmentation, etc. in a multi-view surveillance system. In addition to this, the use of video summarization algorithm can be extended in a multimodal surveillance system containing different types of sensors. The proposed algorithms have been designed while keeping into consideration the Indian transportation infrastructure scenario and will be able to reduce the cost of camera deployment, computational cost, power consumption; and provide efficient performance in a multi-view as well as multimodal surveillance system for an Intelligent Transportation System.