This paper presents a novel approach to sensing both suspicious, and task-specific behaviours through the use of advanced computational intelligence techniques. Locating suspicious activity in surveillance camera networks is an intensive task due to the volume of information and large numbers of camera sources to monitor. This results in countless hours of video data being streamed to disk without being screened by a human operator. To address this need, there are emerging video analytics solutions that have introduced new metrics such as people counting and route monitoring, alongside more traditional alerts such as motion detection. There are however few solutions that are sufficiently robust to reduce the need for human operators in these environments, and new approaches are needed to address the uncertainty in identifying and classifying human behaviours, autonomously, from a video stream. In this work we present an approach to address the autonomous identification of human behaviours derived from human pose analysis. Behavioural recognition is a significant challenge due to the complex subtleties that often make up an action; the large overlap in cues results in high levels of classification uncertainty. False alarms are significant impairments to autonomous detection and alerting systems, and over reporting can lead to systems being muted, disabled, or decommissioned. We present results on a Computational- Intelligence based Behaviour Recognition (CIBR) that utilises artificial intelligence to learn, optimise, and classify human activity. We achieve this through extraction of skeleton recognition of human forms within an image. A type-2 Fuzzy logic classifier then converts the human skeletal forms into a set of base atomic poses (standing, walking, etc.), after which a Markov-chain model is used to order a pose sequence. Through this method we are able to identify, with good accuracy, several classes of human behaviour that correlate with known suspicious, or anomalous, behaviours.
We introduce a system that exploits 3-D imaging technology as an enabler for the robust recognition of the human form. We combine this with pose and feature recognition capabilities from which we can recognise high-level human behaviours. We propose a hierarchical methodology for the recognition of complex human behaviours, based on the identification of a set of atomic behaviours, individual and sequential poses (e.g. standing, sitting, walking, drinking and eating) that provides a framework from which we adopt time-based machine learning techniques to recognise complex behaviour patterns.
KEYWORDS: Sensors, Environmental sensing, Chemical analysis, Data modeling, Atmospheric modeling, Environmental monitoring, Industrial chemicals, Chemical fiber sensors, Sensor networks, Biological and chemical sensing
We present findings of the DYCE project, which addresses the needs of military and blue light responders to provide a
rapid, reliable on-scene analysis of the dispersion of toxic airborne chemical threat agents following their release into the
environment. We describe the development and experimental results for a small network of ad-hoc deployable chemical
and meteorological sensors capable of identifying and locating the source of the contaminant release, as well as
monitoring and estimating the dispersion characteristics of the plume. We further present deployment planning
methodologies to optimize the data gathering mission given a constrained asset base.
We demonstrate the development and use of novel image processing methods to combine dual-band (MWIR and LWIR)
images from SELEX GALILEO's Condor II camera to extract characteristics of observed scenes comprising buried
mines and explosive objects. We discuss the development of a statistical processing technique to extract the different
characteristics of the two bands. We further present a statistical classifier used to detect targets on independently trained
images with a high detection probability and low false negative rates and discuss methods to mitigate the impact of false
positives through the selective processing of image regions and the contextual interpretation of the scene content.
KEYWORDS: Sensors, Luminescence, Solar energy, Pulsed laser operation, Receivers, Commercial off the shelf technology, Target detection, Nd:YAG lasers, Diode pumped solid state lasers, Laser energy
An active imaging system using UV fluorescence for target discrimination is proposed. The emission wavelength is
characteristic of the target material and allows spectral discrimination of targets from clutter.
The burst-illumination-LIDAR system transmits a laser pulse and the fluorescent return is detected with a synchronised
gated imaging receiver. The short gate length (~ns) allowed by a micro-channel plate CCD reduces solar clutter.
Detector noise is not the limiting factor because of the high MCP-CCD detectivity. Laser choice is constrained by the
required laser pulse energy, laser size and robustness. The COTS solution identified is a diode-pumped, 4th harmonic
converted, 1064nm laser. Nd:YAG, Nd:YLF and Nd:Alexandrite lasers have superior performance but require some
development for this application.
A pessimistic range model evaluates the optical powers. Comparison of the received fluorescent energy to the detector
noise equivalent energy and the solar energy received provides the detection range limit. Performance of the proposed
systems exceeds the detection range requirement for all samples evaluated and all varying conditions explored. The
lowest range is for black paint with the COTS laser system and is 2860m; the best ranges exceed 5km.
KEYWORDS: Sensors, Environmental sensing, Chemical analysis, Biological and chemical sensing, Data modeling, Buildings, Chemical fiber sensors, Atmospheric modeling, Environmental monitoring, Industrial chemicals
We present findings of the DYCE project, which addresses the needs of military and blue light responders in providing a
rapid, reliable on-scene analysis of the dispersion of toxic airborne contaminants following their malicious or accidental
release into a rural, urban or industrial environment. We describe the development of a small network of ad-hoc
deployable chemical and meteorological sensors capable of identifying and locating the source of the contaminant
release, as well as monitoring and estimating the dispersion characteristics of the plume. We further present deployment
planning methodologies to optimize the data gathering mission given a constrained asset base.
Jeroen Wellen, Rob Smets, Wim Hellenthal, Jason Lepley, Ioannis Tsalamanis, Stuart Walker, Anthony Ng'oma, Gert-Jan Rijckenberg, Ton Koonen, Kai Habel, Klaus-Dieter Langer
KEYWORDS: Coarse wavelength division multiplexing, Modulation, Radio over Fiber, Solar concentrators, Radon, Network architectures, Interfaces, Fiber to the x, Multiplexers, Prototyping
The European MUSE project, which aims to enable "MUlti Service and access Everywhere", studies architectures, technologies and business scenarios facilitating the deployment of new Broadband Access Networks and Services. This paper gives an overview and particularly discusses results of some of the high-speed access technologies that are developed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.