Balls up : the converse blank canvas project

Research background: For decades the Chuck Taylor All Star basketball shoe (first designed in 1921 by Converse, an American shoe company), has been an iconic item of fashion apparel, particularly for the youth oriented market - as a form of self expression and identify, adolescents have for generations been customising their Converse sneakers to create innovative and unique footwear. Although originally developed purely for sport, sneakers gradually crossed over into fashion and the majority of athletic shoes are now purchased for street fashion or leisure wear. Artisan Gallery (Brisbane), in conjunction with the exhibition Reboot: Function, Fashion and the Sneaker, a history of the sneaker, selected 20 designers to customise and re-design the classic Converse Chuck Taylor All Stars shoe and in doing so highlighted the diversity of forms possible for creative outcomes. As Artisan Gallery Curator Kirsten Fitzpatrick states “the ‘sports show’, designed to coincide with the Olympics, is also about exploring the sneaker as a platform for creativity... and (one) of the more bazaar creations was Dean Brough's deconstructed shoes to make men’s underwear.” The exhibition ran from 21 June – 16 August 2012: http://artisan-ideaskillproduct.blogspot.com.au/2012/06/converse-blank-canvas-project.html Research question: Even though the sneaker is a fashion item, it still is fundamentally used for foot protection and historically was aligned to ball sports, principally Basketball - as a fashion designers/practitioner how can I connect (in a whimsical manner) this history of usage for ball sports to the sneaker and re-design and re-use all the physical elements of the shoe to produce a unique wearable item of clothing - the selected medium for this challenge and experimentation was the classic archetypal men’s white boxer shorts. Artisan Statement BALLS UP - The Converse Sneaker, it’s almost impossible to imagine a better rounded item to maintain peak performance for all types of ball sports. Gentlemen, your other most precious balls also deserve this level of comfort and support to sustain the hard times – the Converse Boxer, balls up, bats out, get ready to play hard. Research contribution: The project highlighted some of the unique and diverse creative manifestations that are possible from the classic sneaker. From a fashion practitioners’ perspective, the design outcomes (men’s boxer short made from converse sneakers) demonstrated the strong association to iconic fashion apparel, and recognised the connection to wearability and comfort that is requisite in both footwear and men’s underwear. Research significance: The exhibition was viewed by in excess of 1000 people and generated exceptional media coverage and public exposure/impact. As Artisan Gallery Curator Kirsten Fitzpatrick states “20 of Brisbane's best designers were given the opportunity to customise their own Converse Sneakers, with The Converse Blank Canvas Project.” And to be selected in this category demonstrates the calibre of importance for design prominence.

Combat sports analytics: Boxing punch classification using overhead depth imagery

In competitive combat sporting environments like boxing, the statistics on a boxer's performance, including the amount and type of punches thrown, provide a valuable source of data and feedback which is routinely used for coaching and performance improvement purposes. This paper presents a robust framework for the automatic classification of a boxer's punches. Overhead depth imagery is employed to alleviate challenges associated with occlusions, and robust body-part tracking is developed for the noisy time-of-flight sensors. Punch recognition is addressed through both a multi-class SVM and Random Forest classifiers. A coarse-to-fine hierarchical SVM classifier is presented based on prior knowledge of boxing punches. This framework has been applied to shadow boxing image sequences taken at the Australian Institute of Sport with 8 elite boxers. Results demonstrate the effectiveness of the proposed approach, with the hierarchical SVM classifier yielding a 96% accuracy, signifying its suitability for analysing athletes punches in boxing bouts.