Distributed architectures and logical-task decomposition in multimedia surveillance systems

Abstract

In the past few years, the development of complex surveillance systems has captured the interest of both the research and industrial worlds. Strong and challenging requirements of modern society are involved in this problem, which aims to increase safety and security in several application domains such as transport, tourism, home and bank security, military applications, etc. At the same time, fast improvements in microelectronics, telecommunications, and computer science make it necessary to consider new perspectives in this field. The main objective of this paper is to investigate, discuss, and evaluate the impact of distributed processing and new communication techniques on multimedia surveillance systems, which represent the so-called third-generation surveillance systems (3GSSs). In particular aspects related to the distribution of intelligence among multiple-processing and wide-bandwidth resources are discussed in detail. It is shown how distribution of intelligence can be obtained by a hierarchical architecture that partitions, in a dynamic way, the main logical processing tasks (i.e., representation, recognition, and communication) performed in a 3GSS physical architecture made lip of intelligent cameras, hubs, and central control rooms. The advantages of this solution are pointed out in terms of: 1) increased flexibility and reconfigurability and 2) optimal allocation of available processing and bandwidth resources. Finally, a case study is analyzed that allows one to gain a deeper insight into a distributed surveillance system

A semantic-guided and self-configurable framework for video analysis

“…Replication of network nodes allows to increase their capabilities (e.g., additional computational power by including more algorithm severs mapped to dierent nodes). However, ecient coordination strategies are required for optimal usage of resources [25]. In addition, the distribution capability of the proposed approach is aected by the amount of data transmitted as it is frame-based.…”

“…For instance, [25] described the complexity of the tasks to perform as their number of instructions and each processing node by its computational power. The transmission time is also considered as the available bandwidth and data exchanged.…”

“…For instance, [38] proposed a framework for the video surveillance domain and [41] focused on the detection of stationary objects in underground stations. Another classication dierentiates between distributed [25] and nondistributed frameworks [36]. Furthermore, they can be categorized depending on the existence of a centralized server to monitor the framework components.…”

“…Nevertheless, their design is based on a human operator who has to accumulate a great amount of experience related with video processing, network design, data management and so on. To simplify this task, several approaches have been proposed based on performance evaluation [19], available resources [25] and knowledge descriptions [16]. However, they are not fully automatic requiring the human intervention in most of the design stages.…”

Source and physical‐layer network coding for correlated two‐way relaying

“…In many scenarios, such as wireless sensor networks (WSNs) [12]- [15], surveillance systems [16], [17] and multiview video systems [18]- [20], the measurements exhibit spatial correlations due to the space closeness of the measurements. Distributed source coding (DSC) has been shown as an efficient approach to exploit this inherent correlated property [21], [22].…”