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.

Model-based vehicle detection and classification using orthographic approximations

This paper reports the current state of work to simplify our previous model-based methods for visual tracking of vehicles for use in a real-time system intended to provide continuous monitoring and classification of traffic from a fixed camera on a busy multi-lane motorway. The main constraints of the system design were: (i) all low level processing to be carried out by low-cost auxiliary hardware, (ii) all 3-D reasoning to be carried out automatically off-line, at set-up time. The system developed uses three main stages: (i) pose and model hypothesis using 1-D templates, (ii) hypothesis tracking, and (iii) hypothesis verification, using 2-D templates. Stages (i) & (iii) have radically different computing performance and computational costs, and need to be carefully balanced for efficiency. Together, they provide an effective way to locate, track and classify vehicles.

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.

A behavioral comparison between motorcyclists and a matched group of non-motorcycling car drivers: factors influencing accident risk

Motorcyclists and a matched group of non-motorcycling car drivers were assessed on behavioral measures known to relate to accident involvement. Using a range of laboratory measures, we found that motorcyclists chose faster speeds than the car drivers, overtook more, and pulled into smaller gaps in traffic, though they did not travel any closer to the vehicle in front. The speed and following distance findings were replicated by two further studies involving unobtrusive roadside observation. We suggest that the increased risk-taking behavior of motorcyclists was only likely to account for a small proportion of the difference in accident risk between motorcyclists and car drivers. A second group of motorcyclists was asked to complete the simulator tests as if driving a car. They did not differ from the non-motorcycling car drivers on the risk-taking measures but were better at hazard perception. There were also no differences for sensation seeking, mild social deviance, and attitudes to riding/driving, indicating that the risk-taking tendencies of motorcyclists did not transfer beyond motorcycling, while their hazard perception skill did. (C) 2002 Elsevier Science Ltd. All rights reserved.

Semantic-associative visual content labelling and retrieval: A multimodal approach

A novel framework referred to as collaterally confirmed labelling (CCL) is proposed, aiming at localising the visual semantics to regions of interest in images with textual keywords. Both the primary image and collateral textual modalities are exploited in a mutually co-referencing and complementary fashion. The collateral content and context-based knowledge is used to bias the mapping from the low-level region-based visual primitives to the high-level visual concepts defined in a visual vocabulary. We introduce the notion of collateral context, which is represented as a co-occurrence matrix of the visual keywords. A collaborative mapping scheme is devised using statistical methods like Gaussian distribution or Euclidean distance together with collateral content and context-driven inference mechanism. We introduce a novel high-level visual content descriptor that is devised for performing semantic-based image classification and retrieval. The proposed image feature vector model is fundamentally underpinned by the CCL framework. Two different high-level image feature vector models are developed based on the CCL labelling of results for the purposes of image data clustering and retrieval, respectively. A subset of the Corel image collection has been used for evaluating our proposed method. The experimental results to-date already indicate that the proposed semantic-based visual content descriptors outperform both traditional visual and textual image feature models. (C) 2007 Elsevier B.V. All rights reserved.

Visual surveillance for moving vehicles

An overview is given of a vision system for locating, recognising and tracking multiple vehicles, using an image sequence taken by a single camera mounted on a moving vehicle. The camera motion is estimated by matching features on the ground plane from one image to the next. Vehicle detection and hypothesis generation are performed using template correlation and a 3D wire frame model of the vehicle is fitted to the image. Once detected and identified, vehicles are tracked using dynamic filtering. A separate batch mode filter obtains the 3D trajectories of nearby vehicles over an extended time. Results are shown for a motorway image sequence.

Visual ambiguity in the oeuvre of the Gela Painter: a new lekythos from Thessaly

This paper presents a previously unpublished Attic lekythos and discusses visual ambiguity as an intentional drawing style used by a vase painter who conceptualised the many possible relationships between pot and user, object and subject. The Gela Painter endowed this hastily manufactured and decorated lekythos with visual effects that drew the viewer into an inherently ambivalent motif: a mounting Dionysos. This motif, like other Dionysian themes, had a vogue in late Archaic times but did not necessarily invoke chthonic associations. It had the potential to be consumed in diverse contexts, including religious festivals, by a wide range of audiences. Such images were not given to the viewer fully through visual perception but through interpretation.

Motion planning of autonomous vehicles in a non-autonomous vehicle environment without speed lanes

Planning is one of the key problems for autonomous vehicles operating in road scenarios. Present planning algorithms operate with the assumption that traffic is organised in predefined speed lanes, which makes it impossible to allow autonomous vehicles in countries with unorganised traffic. Unorganised traffic is though capable of higher traffic bandwidths when constituting vehicles vary in their speed capabilities and sizes. Diverse vehicles in an unorganised exhibit unique driving behaviours which are analysed in this paper by a simulation study. The aim of the work reported here is to create a planning algorithm for mixed traffic consisting of both autonomous and non-autonomous vehicles without any inter-vehicle communication. The awareness (e.g. vision) of every vehicle is restricted to nearby vehicles only and a straight infinite road is assumed for decision making regarding navigation in the presence of multiple vehicles. Exhibited behaviours include obstacle avoidance, overtaking, giving way for vehicles to overtake from behind, vehicle following, adjusting the lateral lane position and so on. A conflict of plans is a major issue which will almost certainly arise in the absence of inter-vehicle communication. Hence each vehicle needs to continuously track other vehicles and rectify plans whenever a collision seems likely. Further it is observed here that driver aggression plays a vital role in overall traffic dynamics, hence this has also been factored in accordingly. This work is hence a step forward towards achieving autonomous vehicles in unorganised traffic, while similar effort would be required for planning problems such as intersections, mergers, diversions and other modules like localisation.

No Haus Like Bau

The project consists of a live performance taking the 2005 IKEA riot as the starting point for a speculative history of a fictional future, culminating in a choreographed re-enactment of the original event. It is accompanied by a film series explores the possibility of collective action emerging from the capitalist relations inherent in the consumer riot. The performance, staged at the Berlin Biennale, continues this research into re-enactment and post-1989 politics, using a stage set made of flatpack furniture. Using the aesthetics of Modernism and the avant garde, the project transposes early twentieth century utopian ideology to a present day setting where mass uprisings are motivated by cheap commodities. By re-evaluating biomechanics and Bauhaus theatre theory, these explorations of consumerism and revolution propose that the mechanized movement developed in conjunction with industrial labour survives as a historical re-enactment in the wake of manufacturing work in the west. In the absence of a visual language apt to the contemporary, No Haus Like Bau uses re-enactment as a retrogarde tactic. Its purpose on the one hand is to invoke trajectories for alternate futures that never materialized at an originary moment. On the other hand, the clash of past forms with present content serves to accentuate the historical changes that have thrown into question these forms. Rather than reflecting the present, the projection of the past into a fictional future aims to destabilize the dominant narrative that suggests the current configuration of art, politics and human nature has always been this way. The project has been widely exhibited internationally and supported by Film London and Arts Council England. A theoretical essay on re-enactment as a strategy for performance has been published in Art Papers and in Memory [MIT]. The project also formed the basis of a solo exhibition at Te Tuhi Art Centre, Auckland.

Vehicle-driver communication using off-the-shelf transceivers

Almost all modern cars can be controlled remotely using a personal communicator (keyfob). However, the degree of interaction between currently available personal communicators and cars is very limited. The communication link is unidirectional and the communication range is limited to a few dozen meters. However, there are many interesting applications that could be supported if a keyfob would be able to support energy efficient bidirectional longer range communication. In this paper we investigate off-the-shelf transceivers in terms of their usability for bidirectional longer range communication. Our evaluation results show that existing transceivers can generally support the required communication ranges but that links tend to be very unreliable. This high unreliability must be handled in an energy efficient way by the keyfob to car communication protocol in order to make off-the-shelf transceivers a viable solution.

MACHINE VISION FOR AUTOMATICVISUAL INSPECTION OF WOODENRAILWAY SLEEPERS USING UNSUPERVISED NEURAL NETWORKS

The motivation for this thesis work is the need for improving reliability of equipment and quality of service to railway passengers as well as a requirement for cost-effective and efficient condition maintenance management for rail transportation. This thesis work develops a fusion of various machine vision analysis methods to achieve high performance in automation of wooden rail track inspection.The condition monitoring in rail transport is done manually by a human operator where people rely on inference systems and assumptions to develop conclusions. The use of conditional monitoring allows maintenance to be scheduled, or other actions to be taken to avoid the consequences of failure, before the failure occurs. Manual or automated condition monitoring of materials in fields of public transportation like railway, aerial navigation, traffic safety, etc, where safety is of prior importance needs non-destructive testing (NDT).In general, wooden railway sleeper inspection is done manually by a human operator, by moving along the rail sleeper and gathering information by visual and sound analysis for examining the presence of cracks. Human inspectors working on lines visually inspect wooden rails to judge the quality of rail sleeper. In this project work the machine vision system is developed based on the manual visual analysis system, which uses digital cameras and image processing software to perform similar manual inspections. As the manual inspection requires much effort and is expected to be error prone sometimes and also appears difficult to discriminate even for a human operator by the frequent changes in inspected material. The machine vision system developed classifies the condition of material by examining individual pixels of images, processing them and attempting to develop conclusions with the assistance of knowledge bases and features.A pattern recognition approach is developed based on the methodological knowledge from manual procedure. The pattern recognition approach for this thesis work was developed and achieved by a non destructive testing method to identify the flaws in manually done condition monitoring of sleepers.In this method, a test vehicle is designed to capture sleeper images similar to visual inspection by human operator and the raw data for pattern recognition approach is provided from the captured images of the wooden sleepers. The data from the NDT method were further processed and appropriate features were extracted.The collection of data by the NDT method is to achieve high accuracy in reliable classification results. A key idea is to use the non supervised classifier based on the features extracted from the method to discriminate the condition of wooden sleepers in to either good or bad. Self organising map is used as classifier for the wooden sleeper classification.In order to achieve greater integration, the data collected by the machine vision system was made to interface with one another by a strategy called fusion. Data fusion was looked in at two different levels namely sensor-level fusion, feature- level fusion. As the goal was to reduce the accuracy of the human error on the rail sleeper classification as good or bad the results obtained by the feature-level fusion compared to that of the results of actual classification were satisfactory.

Visual perception of action categories and the "bowl-throw" decision in cricket.

Cricket umpires, cricket bowlers, and physical education students (who were knowledgeable about the rules of cricket), were shown 72 videotaped point-light displays of cricket deliveries with varying extents of elbow flexion such that they ranged from highly “bowl-like” to highly “throw-like”. The observers made a bowl-throw decision about each display, and the umpires and bowlers reported their confidence on a 5-point scale. The percentage of displays reported as a “bowl” was 59, 40, and 44 for the umpires, bowlers, and students respectively. Umpires made significantly more bowl decisions than both the bowlers and students, but there was no difference between the latter groups. Umpires were significantly more confident than the bowlers in both their bowl and throw decisions. Thus, in an experimental setting, with no apparent costs or benefits associated with their decision-makin, umpires “called” a bowler significantly less frequently for throwing than other knowledgeable observers. The procedures devised for this experiment demonstrate that psychophysical methods can be applied to the problem of discrete action-category nominations in sport (e.g., bowl or throw, walk or run).

Visual perception of movement kinematics and the acquisition of "action prototypes"

Recognizing a class of movements as belonging to a "nominal" action category, such as walking, running, or throwing, is a fundamental human ability. Three experiments were undertaken to test the hypothesis that common ("prototypical") features of moving displays could be learned by observation. Participants viewed moving stick-figure displays resembling forearm flexion movements in the saggital plane. Four displays (presentation displays) were first presented in which one or more movement dimensions were combined with 2 respective cues: direction (up, down), speed (fast, slow), and extent (long, short). Eight test displays were then shown, and the observer indicated whether each test display was like or unlike those previously seen. The results showed that without corrective feedback, a single cue (e.g., up or down) could be correctly recognized, on average, with the proportion correct between .66 and .87. When two cues were manipulated (e.g., up and slow), recognition accuracy remained high, ranging between .72 and .89. Three-cue displays were also easily identified. These results provide the first empirical demonstration of action-prototype learning for categories of human action and show how apparently complex kinematic patterns can be categorized in terms of common features or cues. It was also shown that probability of correct recognition of kinematic properties was reduced when the set of 4 presentation displays were more variable with respect to their shared kinematic property, such as speed or amplitude. Finally, while not conclusive, the results (from 2 of the 3 experiments) did suggest that similarity (or "likeness") with respect to a common kinematic property (or properties) is more easily recognized than dissimilarity.

Picturing Australian history: visual texts in nonfiction for children

Time is one of the most prominent themes in the relatively young genre of children's literature, for the young, like adults, want to know about the past. The historical novel of the West grew out of Romanticism, with its exploration of the inner world of feeling, and it grew to full vigor in the era of imperialism and the exploration of the physical world. From the end of the 18th century, children's books flourished, partly in response to these cultural and political influences. After Darwin, Freud, and Einstein, literary works began to grapple with skepticism about the nature of time itself. This book explores how children's writers have presented the theme and concept of time past. While the book looks primarily at literature of the 19th and 20th centuries, it considers a broad range of historical material treated in works from that period. Included are discussions of such topics as Joan of Arc in children's literature, the legacy of Robinson Crusoe, colonial and postcolonial children's literature, the Holocaust, and the supernatural. International in scope, the volume examines history and collective memory in Portuguese children's fiction, Australian history in picture books, Norwegian children's literature, and literary treatments of the great Irish famine. So too, the expert contributors are from diverse countries and backgrounds.

There's no place like home : unhomely moments in three postcolonial picture books

One of the principal strands of postcolonial theory and critical practice is the interrogation of received versions of colonial history. This paper investigates the extent to which three contemporary picture books, Gavin Bishop's The House that Jack Built, John Marsden and Shaun Tan's The Rabbits, and Thomas King and William Kent Monkman's A Coyote Columbus Story, mobilise postcolonial strategies in their representations of place. In particular, it focuses on how postcolonial textuality unsettles and transgresses notions of "homeliness" in narratives involving the displacement of colonised and colonising peoples. As the shifting power relations of colonialism render unhomely what has previously been homely (especially for colonised peoples), so they involve a contrary move in which unhomely spaces are changed into simulacra of lost or abandoned homes. Drawing upon Walter Benjamin's formulation of materialist historiography, Homi Bhabha describes what he terms 'the unhomely moment' as that in which personal and psychic histories intersect with the violent dislocations of colonialism. This paper will argue that such unhomely moments shape the visual and verbal narratives of The House that Jack Built, The Rabbits and A Coyote Columbus Story, all of which deal with the trauma which occurs when cultures previously geographically and psychically distant are brought into close contact with each other. Written to and for children who are citizens of postcolonial cultures, these texts disclose the unease which persists in contemporary societies where colonial histories are rehearsed and revisioned. However, the paper will argue that the three texts position readers in quite different ways; for instance, while the verbal text of The Rabbits constructs an implied author capable of speaking for the colonised and offering readers a very circumscribed subject position, Thomas King's narrative in A Coyote Columbus Story engages in a dialogic playfulness which allows readers to adopt a variety of reading positions. For each text, some key representations of unhomely moments will be considered, and the paper will explore the extent to which they construct forms of temporality which negotiate the space between history and its significances within crosscultural and intercultural formations.