Jean-Luc Bruyelle

Intelligent Distributed Surveillance System for People Reidentification in a Transportation Environment

This article presents a solution to track people across a network of cameras with disjoint fields of vision. First, an appearance-based signature is extracted from each frame of the sequence characterizing the passage of a person. This feature, called color-position signature, merges spatial and color information for improved robustness. Moreover, an illuminant invariant procedure has been introduced to manage lighting and camera response changes. Second, the distance between 2 sequences is estimated with dimensionality reduction techniques. Two methods are implemented and compared. The first one is the classical, linear, principal components analysis, whereas the second is a recent nonlinear method called the Laplacian eigenmaps approach. Results from 2 databases acquired in difficult conditions show that the Laplacian eigenmaps method always yields the best results, which confirms the interest of nonlinear approaches in such applications. Moreover, these results show the relevance of this approach combining appearance-based signature and dimensionality reduction technique within the scope of people tracking across distinct fields of vision.

Intelligent Surveillance System Based on Stereo Vision for Level Crossings Safety Applications

Considered as a weak point in road and railway infrastructure, level crossings (LC) improvement safety became an important field of academic research and took increasingly railways undertakings concerns. Improving safety of persons and road-rail facilities is an essential key element to ensure a good operating of the road and railway transport. Statistically, nearly 44% of level crossings users have a bad perception of the environment which consequently increases the accidents risks Nelson (2002). However, the behavior of pedestrians, road vehicle drivers and railway operators cannot be previously estimated beforehand. According to Griffioen (2004), the human errors are the causes of 99% of accidents at LC whose 93% are caused by road users. It is important also to note the high cost related to each accident, approximately one hundredmillion euro per year in the EU for all level crossing accidents. For this purpose, road and railway safety professionals from several countries have been focused on providing a level crossings as safer as possible. Actions are planned in order to exchange information and provide experiments for improving the management of level crossing safety and performance. This has enabled us to discuss sharing knowledge gained from research into improving safety at level crossings.

Railway accident prevention and infrastructure protection

Railway accident prevention and protection are a key part of a wider picture of transport safety. The rail sector thus needs to improve its knowledge of trespassing and suicide, including at level crossing, in order to work out suitable responses by analyzing measures already taken in various countries. Governments, the rail industry and road organizations have been implementing a variety of countermeasures for many years to improve railway safety. These actions are substantial and have resulted in a continuing decrease in the number and the severity of accidents. This paper presents existing suitable techniques that are used in the preventative measures targeted to reduce railway suicides, trespassing and level crossing user accidents. It describes them in terms of their capability to effectively reduce accidents, their cost-effectiveness and their integration within the railway transport system as a whole. Language: en

Détection de chutes de personnes sur les voies et d'intrusions en tunnels dans les transports publics

This paper describes a detection system designed to detect persons or objects that fall onto tracks at transit stations . The system is also capable of detecting the presence of unauthorized individuals in train tunnels. Computer vision and image processing are used in the detection process.