Lighting invariant urban street classification

In this paper we propose the hybrid use of illuminant invariant and RGB images to perform image classification of urban scenes despite challenging variation in lighting conditions. Coping with lighting change (and the shadows thereby invoked) is a non-negotiable requirement for long term autonomy using vision. One aspect of this is the ability to reliably classify scene components in the presence of marked and often sudden changes in lighting. This is the focus of this paper. Posed with the task of classifying all parts in a scene from a full colour image, we propose that lighting invariant transforms can reduce the variability of the scene, resulting in a more reliable classification. We leverage the ideas of “data transfer” for classification, beginning with full colour images for obtaining candidate scene-level matches using global image descriptors. This is commonly followed by superpixellevel matching with local features. However, we show that if the RGB images are subjected to an illuminant invariant transform before computing the superpixel-level features, classification is significantly more robust to scene illumination effects. The approach is evaluated using three datasets. The first being our own dataset and the second being the KITTI dataset using manually generated ground truth for quantitative analysis. We qualitatively evaluate the method on a third custom dataset over a 750m trajectory.

Making scenes : Reggae, punk, and death metal in 1990s Bali

In 1996, Emma Baulch went to live in Bali to do research on youth culture. Her chats with young people led her to an enormously popular regular outdoor show dominated by local reggae, punk, and death metal bands. In this rich ethnography, she takes readers inside each scene: hanging out in the death metal scene among unemployed university graduates clad in black T-shirts and ragged jeans; in the punk scene among young men sporting mohawks, leather jackets, and hefty jackboots; and among the remnants of the local reggae scene in Kuta Beach, the island’s most renowned tourist area. Baulch tracks how each music scene arrived and grew in Bali, looking at such influences as the global extreme metal underground, MTV Asia, and the internationalization of Indonesia’s music industry. Making Scenes is an exploration of the subtle politics of identity that took place within and among these scenes throughout the course of the 1990s. Participants in the different scenes often explained their interest in death metal, punk, or reggae in relation to broader ideas about what it meant to be Balinese, which reflected views about Bali’s tourism industry and the cultural dominance of Jakarta, Indonesia’s capital and largest city. Through dance, dress, claims to public spaces, and onstage performances, participants and enthusiasts reworked “Balinese-ness” by synthesizing global media, ideas of national belonging, and local identity politics. Making Scenes chronicles the creation of subcultures at a historical moment when media globalization and the gradual demise of the authoritarian Suharto regime coincided with revitalized, essentialist formulations of the Balinese self.

After Darkly Catwalk Design, QUT Fashion Graduate Showcase 2013

QUT Fashion collaborated with QUT Interior Design to design the Catwalk for the After Darkly Graduate Fashion Show 2013. The ephemeral work (catwalk canopy) was developed through a collaboration between the authors based upon an undergraduate interior design unit 'Filmic Interiors'. The unit exploited the potential of film to influence, understand, and develop novel interior spaces – particularly through consideration of mise en scene, cinematic effects and atmospheric design strategies engaged by key film directors. The design outcome represented a hybridisation of student design proposals, contemplating both film and emerging fashion collections from QUT fashion graduate class of 2013. The creative work built upon material experimentation research explored by the designers either through prior QUT interior design units ('Strange Spaces') or through previous practice ‘Making Strange’(1). The work explored a number of iterations each testing material qualities and associated immaterial cinematic affects. The final catwalk proposed a unique design, which posited the spectators centrally within the space, encircled by a hand formed flexible material canopy used as an entrance for the fashion collections. The proposal exploited the malleable yet tensile character of the canopy to inform a temporary installation, intensified further through a varied program of sceno-graphic lighting. (1) Lindquist, M. & Pytel, A. (2013)

Getting away with murder: An examination of detected homicides staged as suicides

Staged crime scenes involve an offender deliberately altering evidence to simulate events to mislead investigators. Despite likely occurring more often than reported in the literature due to success in offender deception, the exact frequency of staged crime scenes is unknown. In an attempt to bridge this gap, a legal database was searched for detected staged scenes. A total of 115 cases were examined, and this study reports on 16 staged suicides that were examined through descriptive analysis. Findings indicate the frequent involvement of firearms, hanging, or asphyxia; and that offenders are usually known to victims, although not necessarily intimately.

Staged homicides: An examination of common features of faked burglaries, suicides, accidents and car accidents

A staged crime scene involves deliberate alteration of evidence by the offender to simulate events that did not occur for the purpose of misleading authorities (Geberth, 2006; Turvey, 2000). This study examined 115 staged homicides from the USA to determine common elements; victim and perpetrator characteristics; and specific features of different types of staged scenes. General characteristics include: multiple victims and offenders; a previous relationship be- tween parties involved; and victims discovered in their own home, often by the offender. Staged scenes were separated by type with staged burglaries, suicides, accidents, and car accidents examined in more detail. Each type of scene displays differently with separate indicators and common features. Features of staged burglaries were: no points of entry/exit staged; non-valuables taken; scene ransacking; offender self- injury; and offenders bringing weapons to the scene. Features of staged suicides included: weapon arrangement and simulating self-injury to the victim; rearranging the body; and removing valuables. Examples of elements of staged accidents were arranging the implement/weapon and re- positioning the deceased; while staged car accidents involved: transporting the body to the vehicle and arranging both; mutilation after death; attempts to secure an alibi; and clean up at the primary crime scene. The results suggest few staging behaviors are used, despite the credibility they may have offered the façade. This is the first peer-reviewed, published study to examine the specific features of these scenes, and is the largest sample studied to date.

Superpixel-based appearance change prediction for long-term navigation across seasons

Changing environments pose a serious problem to current robotic systems aiming at long term operation under varying seasons or local weather conditions. This paper is built on our previous work where we propose to learn to predict the changes in an environment. Our key insight is that the occurring scene changes are in part systematic, repeatable and therefore predictable. The goal of our work is to support existing approaches to place recognition by learning how the visual appearance of an environment changes over time and by using this learned knowledge to predict its appearance under different environmental conditions. We describe the general idea of appearance change prediction (ACP) and investigate properties of our novel implementation based on vocabularies of superpixels (SP-ACP). Our previous work showed that the proposed approach significantly improves the performance of SeqSLAM and BRIEF-Gist for place recognition on a subset of the Nordland dataset under extremely different environmental conditions in summer and winter. This paper deepens the understanding of the proposed SP-ACP system and evaluates the influence of its parameters. We present the results of a large-scale experiment on the complete 10 h Nordland dataset and appearance change predictions between different combinations of seasons.

Exploiting parallax in panoramic capture to construct light fields

We show that the parallax motion resulting from non-nodal rotation in panorama capture can be exploited for light field construction from commodity hardware. Automated panoramic image capture typically seeks to rotate a camera exactly about its nodal point, for which no parallax motion is observed. This can be difficult or impossible to achieve due to limitations of the mounting or optical systems, and consequently a wide range of captured panoramas suffer from parallax between images. We show that by capturing such imagery over a regular grid of camera poses, then appropriately transforming the captured imagery to a common parameterisation, a light field can be constructed. The resulting four-dimensional image encodes scene geometry as well as texture, allowing an increasingly rich range of light field processing techniques to be applied. Employing an Ocular Robotics REV25 camera pointing system, we demonstrate light field capture,refocusing and low-light image enhancement.

The Interview: Schnarking, Knob Jokes and the right to cause gross offence

Discussion of censorship and media freedom in the context of The Interview. A few weeks before the murderous attack by Islamic extremists on the satirical journal Charlie Hebdo, the Hollywood dream factory had its own encounter with would-be censors. The Interview (Evan Goldberg and Seth Rogen, 2014), as everyone with an interest in culture and current affairs cannot fail to be aware of by now, is a comedy in the “grossout” tradition exemplified by commercially successful movies such as Ted (Seth MacFarlane, 2012) and Bridesmaids (Paul Feig, 2011). Their humour is a combination of slapstick, physical comedy, and scatological jokes involving body fluids and the like— hence the “gross”. The best of them have been very funny, as well as bordering on the offensive (see Ted’s scene involving prostitutes, a foul-mouthed teddy bear and the entertainment value of someone taking a dump on the living room floor). They have often been controversial, as in the Farrelly brothers’ Me, Myself and Irene (2000), starring Jim Carrey as a schizophrenic police officer. At their most outrageous they have pushed the boundaries of political correctness to the limit.

An application of fuzzy DL-Based semantic perception to soil container classification

Semantic perception and object labeling are key requirements for robots interacting with objects on a higher level. Symbolic annotation of objects allows the usage of planning algorithms for object interaction, for instance in a typical fetchand-carry scenario. In current research, perception is usually based on 3D scene reconstruction and geometric model matching, where trained features are matched with a 3D sample point cloud. In this work we propose a semantic perception method which is based on spatio-semantic features. These features are defined in a natural, symbolic way, such as geometry and spatial relation. In contrast to point-based model matching methods, a spatial ontology is used where objects are rather described how they "look like", similar to how a human would described unknown objects to another person. A fuzzy based reasoning approach matches perceivable features with a spatial ontology of the objects. The approach provides a method which is able to deal with senor noise and occlusions. Another advantage is that no training phase is needed in order to learn object features. The use-case of the proposed method is the detection of soil sample containers in an outdoor environment which have to be collected by a mobile robot. The approach is verified using real world experiments.

Noise in my head: Voices from the ugly Australian underground

The Ugly Australian Underground documents the music, songwriting, aesthetics and struggles of fifty of Australia’s most innovative and significant bands and artists currently at the creative peak of their careers. The book provides a rare insight into the critically heralded cult music scene in Australia. The author, Jimi Kritzler, is both a journalist and a musician, and is personally connected to the musicians he interviews through his involvement in this music subculture. The interviews are extremely personal and reveal much more than any interview granted to street press or blogs. They deal with not only the music and songwriting processes of each band, but in some circumstances their struggles with drugs, involvement in crime and the death of band members.

Automatic image scaling for place recognition in changing environments

Robustness to variations in environmental conditions and camera viewpoint is essential for long-term place recognition, navigation and SLAM. Existing systems typically solve either of these problems, but invariance to both remains a challenge. This paper presents a training-free approach to lateral viewpoint- and condition-invariant, vision-based place recognition. Our successive frame patch-tracking technique infers average scene depth along traverses and automatically rescales views of the same place at different depths to increase their similarity. We combine our system with the condition-invariant SMART algorithm and demonstrate place recognition between day and night, across entire 4-lane-plus-median-strip roads, where current algorithms fail.

Place recognition with ConvNet landmarks: Viewpoint-robust, condition-robust, training-free

Place recognition has long been an incompletely solved problem in that all approaches involve significant compromises. Current methods address many but never all of the critical challenges of place recognition – viewpoint-invariance, condition-invariance and minimizing training requirements. Here we present an approach that adapts state-of-the-art object proposal techniques to identify potential landmarks within an image for place recognition. We use the astonishing power of convolutional neural network features to identify matching landmark proposals between images to perform place recognition over extreme appearance and viewpoint variations. Our system does not require any form of training, all components are generic enough to be used off-the-shelf. We present a range of challenging experiments in varied viewpoint and environmental conditions. We demonstrate superior performance to current state-of-the- art techniques. Furthermore, by building on existing and widely used recognition frameworks, this approach provides a highly compatible place recognition system with the potential for easy integration of other techniques such as object detection and semantic scene interpretation.

An Intelligent Driver Warning System

This chapter is focussed on the research and development of an intelligent driver warning system (IDWS) as a means to improve road safety and driving comfort. Two independent IDWS case studies are presented. The first study examines the methodology and implementation for attentive visual tracking and trajectory estimation for dynamic scene segmentation problems. In the second case study, the concept of driver modelling is evaluated which can be used to provide useful feedback to drivers. In both case studies, the quality of IDWS is largely determined by the modelling capability for estimating multiple vehicle trajectories and modelling driving behaviour. A class of modelling techniques based on neural-fuzzy systems, which exhibits provable learning and modelling capability, is proposed. For complex modelling problems where the curse of dimensionality becomes an issue, a network construction algorithm based on Adaptive Spline Modelling of Observation Data (ASMOD) is also proposed.

The sweet aroma of success: Modification of products for new markets in the case of TORQ by Di Bella Coffee

In 2002, Phillip Di Bella’s childhood passion for coffee and keen entrepreneurial spirit led him to establish a small coffee roasting warehouse in in the inner suburbs of Brisbane (Di Bella, 2012). With a keen sense of direction and passion for his coffee products and providing unparalleled customer service, Di Bella Coffee quickly grew to become a key player in the coffee roasting scene. This passion for the ultimate coffee experience is evident in the firm’s logo ‘Di Bella Coffee Inspires Passion’. Phillip Di Bella stated that ‘the common denominator of this company is about inspiration and passion. We are not a coffee company, we are a people company. You know, are we inspiring you from the moment you walk in the door to the moment you leave. If you are not feeling inspired then we haven’t done our job properly as a company’. Fundamentally, providing the ultimate coffee experience, as detailed in the following case is one in which focuses on the coffee consumption experience, not the coffee itself. Over that last 10 years Di Bella Coffee has constantly strived for the ultimate coffee, while expanding business operations into the booming Asian coffee market, establishing headquarters in Shanghai in 2010. In 2011, Di Bella Coffee commenced their second international venture with the launch of operations in India (Di Bella Coffee, 2012); followed shortly by the creation of a new category of coffee, set to revolutionise to coffee industry. The fusion of two traditional forms of coffee; espresso coffee and instant coffee, to create a third category- espresso instant, led to the development of TORQ by Di Bella.