Franco Oberti

Distributed architectures and logical-task decomposition in multimedia surveillance systems

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 (3 GSSs). 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 3 GSS physical architecture made up 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.

Robust tracking of humans and vehicles in cluttered scenes with occlusions

An algorithm for tracking multiple non-rigid objects in cluttered scenes is presented. The proposed approach models the shape of the objects by using corners. In particular, a learning algorithm is introduced in order to extract an adaptive model of the object automatically. The obtained adaptive model is used to individuate the object position and scale when occlusions are present. The method is used on an existing video-surveillance system in order to track moving objects in cluttered scenes. Results show that the proposed approach provides good performances with low processing times.

ROC curves for performance evaluation of video sequences processing systems for surveillance applications

Performance evaluation of image processing intermediate results in video based surveillance systems is extremely important due to the variety of approaches to this task. An approach based on the use of receiver operating characteristics (ROC) curves in order to evaluate the performance of a vision complex system for surveillance purposes is presented. The ROC curves have already been used in other research fields such as in the comparison of edge detection algorithms or in the evaluation of artificial neural networks: in this case they are used in order to compare different parameters selections within a system for the localization of moving objects. The presented results show the possibility of using ROC curves as a means for evaluation and comparison of video based surveillance systems.

Performance Evaluation Criterion for Characterizing Video-Surveillance Systems

In the last decade, video surveillance systems have been developed to guard remote environments in order to detect and prevent dangerous situations. In general, such systems are very complex and their performances rely strongly on the values taken on by the parameters regulating the behavior of surveillance algorithms. This makes it difficult to compare performances to select the most suitable system for the problem considered. Moreover, parameters are set during the installation phase, but a good selection requires time and experience. In this paper, we present an evaluation method for characterizing video-surveillance systems in order to provide an easy way of system installation. The proposed procedure is based on the definition of Receiver Operating Characteristic (ROC) curves traced for different parameter sets and for different system working conditions. Examples are given that concern an indoor video-based surveillance system for detecting, recognizing and tracking moving objects; the system has been characterized and evaluated for different scenarios. Results prove the validation of the proposed evaluation procedure though a comparison of the performances obtained in a laboratory with the ones achieved in real working environments, after system installation following the guidelines provided by the proposed methodology.

Change detection methods for automatic scene analysis by using mobile surveillance cameras

This paper proposes a video-surveillance system based on a mobile camera. In particular the developed system creates (during the off-line phase) a panoramic multilayer background image allowing one to use common change detection algorithms to search for a change detection binary image. Different approaches to get the change detection images are presented. The performances of the implemented algorithms are presented by using ROC curves.

A Comparison between Continuous And Burst, Recognition Driven Transmission Policies in Distributed 3GSS

This paper introduces an architecture of a third generation surveillance system (3GSS). In particular a method for choosing the optimal distribution of intelligence required by 3GSSs is presented. The effect of introducing recognition tasks, which can cause the interruption of flow in the system, is discussed. Experimental results over a simulated system illustrate the presented approach.

A real-time algorithm for error recovery in remote video-based surveillance applications

This work presents a real-time post-processing error-recovery algorithm explicitly devoted at enhancing the performances of outdoor video-surveillance systems working in remote modality. The aim of the proposed algorithm is to distinguish between changed blocks due to variations in the observed scene and noise-altered blocks that contain errors caused by channel noise. Such errors can be corrected by directly exploiting the considerable spatio-temporal redundancy of the encoded digital source without using any additional information. Experimental results, obtained through colour JPEG transmission simulations performed in the context of an actual remote video-surveillance system, compare the proposed scheme with different concealment schemes. It is proven that substantial improvements both in terms of perceptual quality and performance of the overall video-surveillance system are possible, by using the proposed algorithm as a stand-alone module or in conjunction with a relatively low-redundancy FEC coding.

Extending real time change-detection techniques to mosaic backgrounds and mobile camera sequences in surveillance systems

This paper shows a method for extending efficient algorithms for scene understanding already developed and tested for fixed cameras to a mobile camera environment. Real-time change detection methods for mobile-head cameras are introduced. The architecture of the system can be divided in two phases. During the off-line phase the system creates a panoramic multi-layer background image using a small number of static background images. In the on-line phase the system compares the acquired images with a portion of the panoramic background. Different approaches to produce the change detection images are analyzed. Experimental results are presented in order to validate the proposed methods; their evaluation is performed by using receiving operator characteristic (ROC) curves. The Neyman-Pearson statistical criterion has been used for selecting of optimal change detection threshold. The presented results, in terms of probabilities of false and correct detection rates and real-time behavior, show that one of the studied methods can be used as the basis for higher level modules of an automatic video-surveillance system.

Allocation strategies for distributed video surveillance networks

This paper discusses a typical architecture of a third-generation surveillance system (3GSS). In particular a method for choosing the optimal distribution of intelligence required by 3GSS is presented. Experimental results over a simulated system illustrate the presented approach.

Adaptive tracking of multiple non-rigid objects in cluttered scenes

Tracking of non-rigid objects (e.g. humans) is a crucial application for understanding the behavior of objects. Different methods have been presented in literature, whose main drawback is low robustness or high computational load in analysis of cluttered scenes. In the paper a low computational algorithm for tracking non-rigid objects in cluttered scenes is presented. The proposed approach models the shape of the objects by using corners. A learning algorithm is introduced in order to automatically extract the model of the object from a short video sequence acquired immediately before merging of more objects in the scene. The adaptive model extraction mechanism strongly improves method robustness. The method is tested on an existing video-surveillance system in order to track moving objects in cluttered scenes. Results show that the proposed approach gives good performances with low-processing times.