A Generic Deformable Model for Vehicle Recognition

This paper reports the development of a highly parameterised 3-D model able to adopt the shapes of a wide variety of different classes of vehicles (cars, vans, buses, etc), and its subsequent specialisation to a generic car class which accounts for most commonly encountered types of car (includng saloon, hatchback and estate cars). An interactive tool has been developed to obtain sample data for vehicles from video images. A PCA description of the manually sampled data provides a deformable model in which a single instance is described as a 6 parameter vector. Both the pose and the structure of a car can be recovered by fitting the PCA model to an image. The recovered description is sufficiently accurate to discriminate between vehicle sub-classes.

A Filter for Visual Tracking Based on a Stochastic Model for Driver Behaviour

A driver controls a car by turning the steering wheel or by pressing on the accelerator or the brake. These actions are modelled by Gaussian processes, leading to a stochastic model for the motion of the car. The stochastic model is the basis of a new filter for tracking and predicting the motion of the car, using measurements obtained by fitting a rigid 3D model to a monocular sequence of video images. Experiments show that the filter easily outperforms traditional filters.

Visual surveillance using deformable models of vehicles

This paper presents recent developments to a vision-based traffic surveillance system which relies extensively on the use of geometrical and scene context. Firstly, a highly parametrised 3-D model is reported, able to adopt the shape of a wide variety of different classes of vehicle (e.g. cars, vans, buses etc.), and its subsequent specialisation to a generic car class which accounts for commonly encountered types of car (including saloon, batchback and estate cars). Sample data collected from video images, by means of an interactive tool, have been subjected to principal component analysis (PCA) to define a deformable model having 6 degrees of freedom. Secondly, a new pose refinement technique using “active” models is described, able to recover both the pose of a rigid object, and the structure of a deformable model; an assessment of its performance is examined in comparison with previously reported “passive” model-based techniques in the context of traffic surveillance. The new method is more stable, and requires fewer iterations, especially when the number of free parameters increases, but shows somewhat poorer convergence. Typical applications for this work include robot surveillance and navigation tasks.

Performance as social practice

Starting point for these outputs is a large scale research project in collaboration with the Zurich University for the Arts and the Kunstmuseum Thun, looking at a redefinition of Social Sculpture (Joseph Beuys/ Bazon Brock, 1970) as a functional device re-deployed to expand the art discourse into a societal discourse. Although Beuys‘ version of a social sculpture involved notions of abstruse mysticism and reformulations of a national identity these were never-the less part of a social transformation that shifted and re-arranged power relations. Following Laclau and Mouffe in their contention that democray is a fundamentally antagonistic process and contesting Grant Kester’s understanding of a ethically based relational practice, this work is alignes itself with Hirschhorn’s claim to an aesthetic practice within communities, following the possibility to view a socially based practice from both ends of the ethics debate, whereby ethical aspects fuels the aethetic to “create situations that are beautiful because they are ethical and shocking because they are ethical, thus in turn aesthetic because they are ethical” (O’Donnell). This project sets out to engage in activities which interact with surrounding communities and evoce new imaginations of site, thereby understanding site as a catalysts for subjective emergences. Performance is tested as a site for social practice. Archival research into local audio/visual resources, such as the Swiss Radio Archive, the Swiss Military Film Archives and zoological film archives of the Basel Zoo, was instrumental to the navigation of this work, under theme of crisis, catastrophy, landscape, fallout, in order to create a visual language for an active performance site. Commissioned by the Kunstmuseum Thun in collaboration with the University for the Arts in Zurich as part of a year long exhibition programme, (other artists are Jeanne Van Heeswijk (NL) and San Keller (CH), ) this project brings together a series of different works in a new performace installation. The performance process includes a performance workshop with 30 school children from local Swiss schools and their teachers, which was conducted publicly in the museum spaces. It enabled the children to engage with an unexpected set of tribal and animalistic behaviours, looking at situations of flight and rescue, resulting in a large performance choreography orchestration without an apparent conductor, it includes a collaboration with renowned Swiss zoologist, Prof Klaus Zuberbühler(University of St Andrews) and the Colonal General Haldimann commander of the military base in Thun. The installation included 2 static video images, shot in an around spectacular local cave site (Beatus Caves) including 3 children. The project will culminate in an edited edition of the Oncurating Journal, (issue no, tbc, in 2012) including interviews and essays from project collaborators. (Army Commander General, Thun, Jörg Hess, performance script, Timothy Long, and others)

Backtracks: a devised performance

Backtracks aimed to investigate critical relationships between audio-visual technologies and live performance, emphasising technologies producing sound, contrasted with non-amplified bodily sound. Drawing on methodologies for studying avant garde theatre, live performance and the performing body, it was informed by work in critical and cultural theory by, for example, Steven Connor and Jonathan Rée, on the body's experience and interpretation of sound. The performance explored how shifting national boundaries, mobile workforces, complex family relationships, cultural pluralities and possibilities for bodily transformation have compelled a re-evaluation of what it means to feel 'at home' in modernity. Using montages of live and mediated images, disrupted narratives and sound, it evoked destablised identities which characterise contemporary lived experience, and enacted the displacement of certainties provided by family and nation, community and locality, body and selfhood. Homer's Odyssey framed the performance: elements could be traced in the mise-en-scène; in the physical presence of Athene, the narrator and Penelope weaving mementoes from the past into her loom; and in voice-overs from Homer's work. The performance drew on personal experiences and improvisations, structured around notions of journey. It presented incomplete narratives, memories, repressed anxieties and dreams through different combinations of sounds, music, mediated images, movement, voice and bodily sound. The theme of travel was intensified by performers carrying suitcases and umbrellas, by soundtracks incorporating travel effects, and by the distorted video images of forms of transport playing across 'screens' which proliferated across the space (sails, umbrellas, the loom, actors' bodies). The performance experimented with giving sound and silence performative dimensions, including presenting sound in visual and imagistic ways, for example by using signs from deaf sign language. Through-composed soundtracks of live and recorded song, music, voice-over, and noise exploited the viscerality of sound and disrupted cognitive interpretation by phenomenological, somatic experience, thereby displacing the impulse for closure/destination/home.

Modeling camera orientation and 3D structure from a sequence of images taken by a perambulating commercial video camera

In this paper we report the degree of reliability of image sequences taken by off-the-shelf TV cameras for modeling camera rotation and reconstructing 3D structure using computer vision techniques. This is done in spite of the fact that computer vision systems usually use imaging devices that are specifically designed for the human vision. Our scenario consists of a static scene and a mobile camera moving through the scene. The scene is any long axial building dominated by features along the three principal orientations and with at least one wall containing prominent repetitive planar features such as doors, windows bricks etc. The camera is an ordinary commercial camcorder moving along the axial axis of the scene and is allowed to rotate freely within the range +/- 10 degrees in all directions. This makes it possible that the camera be held by a walking unprofessional cameraman with normal gait, or to be mounted on a mobile robot. The system has been tested successfully on sequence of images of a variety of structured, but fairly cluttered scenes taken by different walking cameramen. The potential application areas of the system include medicine, robotics and photogrammetry.

The future of video analytics for surveillance and its ethical implications

The current state of the art and direction of research in computer vision aimed at automating the analysis of CCTV images is presented. This includes low level identification of objects within the field of view of cameras, following those objects over time and between cameras, and the interpretation of those objects’ appearance and movements with respect to models of behaviour (and therefore intentions inferred). The potential ethical problems (and some potential opportunities) such developments may pose if and when deployed in the real world are presented, and suggestions made as to the necessary new regulations which will be needed if such systems are not to further enhance the power of the surveillers against the surveilled.

Vehicle subtype, make and model classification from side profile video

This paper addresses the challenging domain of vehicle classification from pole-mounted roadway cameras, specifically from side-profile views. A new public vehicle dataset is made available consisting of over 10000 side profile images (86 make/model and 9 sub-type classes). 5 state-of-the-art classifiers are applied to the dataset, with the best achieving high classification rates of 98.7% for sub-type and 99.7- 99.9% for make and model recognition, confirming the assertion made that single vehicle side profile images can be used for robust classification.