Multiple-object tracking in cluttered and crowded public spaces

This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly difficult by the nature of objects encountered in such scenes: these too change in appearance and scale, and are often articulated (e.g. humans). We propose a method which uses fast motion detection and segmentation as a constraint for both building appearance models and their robust propagation (matching) in time. The appearance model is based on sets of local appearances automatically clustered using spatio-kinetic similarity, and is updated with each new appearance seen. This integration of all seen appearances of a tracked object makes it extremely resilient to errors caused by occlusion and the lack of permanence of due to low data quality, appearance change or background clutter. These theoretical strengths of our algorithm are empirically demonstrated on two hour long video footage of a busy city marketplace.

Scenes from another life (the paper)

What is my dance now? My body is saturated with images and details. My choreography has become an exorcism of ghosts of “opening-nights past” as I dance out memories and events inscribed on my body. A chorus of my other selves now accompanies my stage performance, live and virtual, real and imagined, past and present.

Scenes from another life

What is my dance now? My body is saturated with images and details. My choreography has become an exorcism of ghosts of “opening-nights past” as I dance out memories and events inscribed on my body. A chorus of my other selves now accompanies my stage performance, live and virtual, real and imagined, past and present.

A method for automatically creating 3D animated scenes from annotated fiction text

This paper describes a strategy for automatically converting fiction text into 3D animations. It assumes the existence of fiction text annotated with avatar, object, setting, transition and relation annotations, and presents a transformation process that converts annotated text into quantified constraint systems, the solutions to which are used in the population of 3D environments. Constraint solutions are valid over temporal intervals, ensuring that consistent dynamic behaviour is produced. A substantial level of automation is achieved, while providing opportunities for creative manual intervention in animation process. The process is demonstrated using annotated examples drawn from popular fiction text that are converted into animation sequences, confirming that the desired results can be achieved with only highlevel human direction.

Learning about dynamic scenes

Incremental learning allows modification of developed concepts without the need for prior knowledge of all data. An incremental algorithm is developed to focus on the problems of memory size, forgetting and concept drift. The evidence based forgetting procedure minimizes the concept size and maintains its consistency with respect to the incoming data. An age value associated with the data determines its reinforcement or removal from a concept.

On the incremental learning and recognition of the pattern of movement of multiple labelled objects in dynamic scenes

In this paper we discuss combining incremental learning and incremental recognition to classify patterns consisting of multiple objects, each represented by multiple spatio-temporal features. Importantly the technique allows for ambiguity in terms of the positions of the start and finish of the pattern. This involves a progressive classification which considers the data at each time instance in the query and thus provides a probable answer before all the query information becomes available. We present two methods that combine incremental learning and incremental recognition: a time instance method and an overall best match method.

Film grammar based refinements to extracting scenes in motion pictures

To enable high-level semantic indexing of video, we tackle the problem of automatically structuring motion pictures into meaningful story units, namely scenes. In our recent work, drawing guidance from film grammar, we proposed an algorithmic solution for extracting scenes in motion pictures based on a shot neighborhood color coherence measure. In this paper, we extend our work by presenting various refinement mechanisms, inspired by the knowledge of film devices that are brought to bear while crafting scenes, to further improve the results of the scene detection algorithm. We apply the enhanced algorithm to ten motion pictures and demonstrate the resulting improvements in performance.

The reflexive museum : opening the door to behind the scenes

In this paper I argue for a shift in conceptualising exhibitions: from products to be presented to processes to be revealed. I will explore how museum theory and practice are inextricably intertwined and can be brought into fruitful dialogue within an exhibition setting. By revealing the processes leading to the definition of categories and the interpretation of identities, and by giving ‘faces’ to decisions made, the ‘reflexive museum’ can become an embodiment of democracy, which does not silence controversies but gives diversity public voices. The ‘reflexive museum’ as I envisage it, by referring to Beck and Bonss’ ‘reflexive modernity’ (2001) is not only self-aware, but confronts, critiques, questions and ultimately transforms itself and invites the visitor to democratically participate in this process.

First, I sketch out recent academic musings on museological approaches. Then I present some examples of exhibitions in Germany in which these theories have been put into practice. I conclude by arguing for a symbiotic relationship between museum theory and practice, enabling the museum to realise its unique potential as a dynamic ‘playground’ located between scholarly thinking and the public.

The reflexive museum - opening the door to behind the scenes

In this paper I argue for a shift in conceptualising exhibitions: from products to be presented to processes to be revealed. I will explore how museum theory and praxis are inextricably intertwined and can be brought into fruitful dialogue within an exhibition setting. By revealing the processes leading to the definition of categories and the interpretation of identities, and by giving faces to decisions made, the ‘reflexive museum’ can become an embodiment of democracy, which does not silence controversies but gives diversity public voices. First, I sketch out recent academic musings on museological approaches. Then I present some examples of exhibitions in Germany in which these theories have been put into praxis. I conclude by arguing for a symbiotic relationship of museum theory and praxis enabling the museum to realise its unique potential as a dynamic ‘playground’ between academia and the public.

Contextually Learnt Detection of Unusual Motion-Based Behaviour in Crowded Public Spaces

In this paper we are interested in analyzing behaviour in crowded publicplaces at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of ‘‘normal behaviour’’ for a particular scene and thus alert to novelty in unseen footage. The first contribution is a low-level motion model based on what we term tracklet primitives, which are scenespecific elementary motions. We propose a clustering-based algorithm for tracklet estimation from local approximations to tracks of appearance features. This is followed by two methods for motion novelty inference from tracklet primitives: (a) an approach based on a non-hierarchial ensemble of Markov chains as a means of capturing behavioural characteristics at different scales, and (b) a more flexible alternative which exhibits a higher generalizing power by accounting for constraints introduced by intentionality and goal-oriented planning of human motion in a particular scene. Evaluated on a 2 h long video of a busy city marketplace, both algorithms are shown to be successful at inferring unusual behaviour, the latter model achieving better performance for novelties at a larger spatial scale.