Public transport security is one of the main priorities of the public authorities when fighting against crime and terrorism.
In this context, there is a great demand for autonomous systems able to detect abnormal events such as violent acts
aboard passenger cars and intrusions when the train is parked at the depot. To this end, we present an innovative
approach which aims at providing efficient automatic event detection by fusing video and audio analytics and reducing
the false alarm rate compared to classical stand-alone video detection. The multi-modal system is composed of two
microphones and one camera and integrates onboard video and audio analytics and fusion capabilities. On the one hand,
for detecting intrusion, the system relies on the fusion of “unusual” audio events detection with intrusion detections from
video processing. The audio analysis consists in modeling the normal ambience and detecting deviation from the trained
models during testing. This unsupervised approach is based on clustering of automatically extracted segments of
acoustic features and statistical Gaussian Mixture Model (GMM) modeling of each cluster. The intrusion detection is
based on the three-dimensional (3D) detection and tracking of individuals in the videos. On the other hand, for violent
events detection, the system fuses unsupervised and supervised audio algorithms with video event detection. The
supervised audio technique detects specific events such as shouts. A GMM is used to catch the formant structure of a
shout signal. Video analytics use an original approach for detecting aggressive motion by focusing on erratic motion
patterns specific to violent events. As data with violent events is not easily available, a normality model with structured
motions from non-violent videos is learned for one-class classification. A fusion algorithm based on Dempster-Shafer’s
theory analyses the asynchronous detection outputs and computes the degree of belief of each probable event.
In this work, we present the development of a multi-sensor system for the detection of objects concealed under clothes
using passive and active millimeter-wave (mmW) technologies. This study concerns both the optimization of a
commercial passive mmW imager at 94 GHz using a phase mask and the development of an active mmW detector at 77
GHz based on synthetic aperture radar (SAR).
A first wide-field inspection is done by the passive imager while the person is walking. If a suspicious area is detected,
the active imager is switched-on and focused on this area in order to obtain more accurate data (shape of the object,
nature of the material ...).
In the first part of this paper, we use a specially developed sensitive polymer (PLG) which belongs to the polysiloxane family. Thin layers of this polymer are deposited onto the surface of the optical transducers. Results will be presented on the response of diffraction-based optical transducers such as gratings and also on interferometric transducers and especially integrated Mach-Zehnder (MZ) interferometers. In the first case, a relief grating is coated with the sensitive polymer. A small variation of the refractive index of this layer, due to the presence of pollutant, induces a variation of the intensity of the diffracted orders which can be measured. In the second case, one arm of the integrated MZ interferometers is coated with the polymer. The variation of the refractive index of the polymer causes a phase shift in the measuring arm which can be measured by the modification of the output intensity. Assessment of sensitivity for the detection of nitro-aromatic compounds using a PLG sensitive layer on both sensors are presented and are also compared to the response of a SAW-based sensor coated with the same polymer.
In the second part of this paper, synthesis, spectroscopy and fluorescence quenching behaviour of a N-(2,5-ditertio-butylphenyl)-1,8-naphthalimide functionalised polystyrene (PST-NI) are reported. PST-NI was synthesized by free radical polymerisation of the corresponding monomer. The molecular weight (Mn) is 43 000 g.mol-1. Introduction of a bulky moiety on the naphthalimide chromophores avoids P-stacking of the polymer side chains as well as excimer formation and hence leads to very high fluorescence quantum yields in thin solid films (up to 60%). Upon 1 minute exposure to DNT vapour, it was shown that a 5.5 nm thick film of PST-NI exhibits a 45% drop in its fluorescence intensity, which makes this polymer very attractive for sensing applications.
We present a novel technique for engraving 2D patterns in one step with a UV pulsed laser by means of a versatile programmable approach. The spatial light modulation is actually performed by a reflective liquid crystal display instead of a mask. As these devices are unable to withstand the high energy throughput required for etching, the modulated beam is amplified by two-wave mixing in a nonlinear optical medium such as lithium niobate crystal optimized for the UV interaction. This technique provides a faster and more flexible alternative to laser marking with pixel by pixel raster-scan or fixed mask projection mode and e.g. can be applied to identify valuable items by imprinting a code onto the surface.
We present a novel technique for engraving microscopic 2D patterns in one step with a UV pulsed laser by means of a versatile programmable approach. The laser beam is divided to an expanded low energy signal beam which is spatially modulated by a LCD modulator and a higher energy pump beam with a plane homogeneous wave front. Both beams are superposed in a highly magnesium doped photorefractive lithium-niobate crystal where an energy transfer towards the weaker signal beam takes place. The spatially modulated and amplified signal beam is then de-magnified and imaged onto the surface where the image has to be engraved. The need for the coherent amplifier rises out of the fact that LCDs are unable to withstand the high energy throughput required for etching. The combination of the amplifier with the amplitude modulator leads to a faster and more flexible solution than laser marking with pixel-by-pixel raster-scan, or fixed mask projection mode. Such a technique can thus be applied to identify valuable items by imprinting a smart and personalized 2D code onto its surface.