Evidence reasoning for event inference in smart transport video surveillance

In this paper we present a new event recognition framework, based on the Dempster-Shafer theory of evidence, which combines the evidence from multiple atomic events detected by low-level computer vision analytics. The proposed framework employs evidential network modelling of composite events. This approach can effectively handle the uncertainty of the detected events, whilst inferring high-level events that have semantic meaning with high degrees of belief. Our scheme has been comprehensively evaluated against various scenarios that simulate passenger behaviour on public transport platforms such as buses and trains. The average accuracy rate of our method is 81% in comparison to 76% by a standard rule-based method.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.

Islands of pain in a sea of change: Behaviour analysis and bereavement,

The paper Bereavement: A behavioural process (Dillenburger & Keenan, 1994) was first published within a vacuum of behaviour analytic thinking or research in this field. The paper was meant to be a first step in stimulating others to contribute to the understanding of one of the most complex, yet most universal, human behavioural processes. The only behaviour analyst addressing the issues directly was Calkin (1990). Recently, after reading our original 1994 paper, Beth Sulzer-Azaroff suggested that we should solicit comments directly from the behaviour analytic community. This we did with the help of Erik Arntzen and now the reprint and the commentaries in this edition of the European Journal of Behaviour Analysis (EJBA) fully embrace and extend the contribution of behaviour analysis to the understanding of the behavioural process that is bereavement.

Teaching and learning technologies in Higher Education: Applied behaviour analysis and autism.

Professionals on both international and national levels who work with children with autism are expressing the need for graduate-level training in applied behaviour analysis. The implementation of effective instruction in higher education for professionals working with children with autism and their families is a complex undertaking: the learner needs to acquire an understanding of the principles and procedures of applied behaviour analysis and also adapt this knowledge to the learning prerequisites of individuals with autism. In this paper we outline some current thinking about adult education and blended learning technologies and then describe and illustrate with examples emerging possibilities of multimedia technology in the development of teaching materials. We conclude that synergies between graduate-level curriculum requirements, knowledge of adult learning, and communication technology are necessary to establish comprehensive learning environments for professionals who specialize in autism intervention.

Understanding applied behaviour analysis: An introduction to ABA for parents, teachers, and other professionals

book review

Millimeter-wave and submillimeter-wave imaging for security and surveillance

Passive equipments operating in the 30-300 GHZ (millimeter wave) band are compared to those in the 300 GHz-3 THz (submillimeter band). Equipments operating in the submillimeter band can measure distance and also spectral information and have been used to address new opportunities in security. Solid state spectral information is available in the submillimeter region making it possible to identify materials, whereas in millimeter region bulk optical properties determine the image contrast. The optical properties in the region from 30 GHz to 3 THz are discussed for some typical inorganic and organic solids. in the millimeter-wave region of the spectrum, obscurants such as poor weather, dust, and smoke can be penetrated and useful imagery generated for surveillance. in the 30 GHZ-3 THZ region dielectrics such as plastic and cloth are also transparent and the detection of contraband hidden under clothing is possible. A passive millimeter-wave imaging concept based on a folded Schmidt camera has been developed and applied to poor weather navigation and security. The optical design uses a rotating mirror and is folded using polarization techniques. The design is very well corrected over a wide field of view making it ideal for surveillance, and security. This produces a relatively compact imager which minimizes the receiver count.