Robust automatic face clustering in news video

Clustering identities in a video is a useful task to aid in video search, annotation and retrieval, and cast identification. However, reliably clustering faces across multiple videos is challenging task due to variations in the appearance of the faces, as videos are captured in an uncontrolled environment. A person's appearance may vary due to session variations including: lighting and background changes, occlusions, changes in expression and make up. In this paper we propose the novel Local Total Variability Modelling (Local TVM) approach to cluster faces across a news video corpus; and incorporate this into a novel two stage video clustering system. We first cluster faces within a single video using colour, spatial and temporal cues; after which we use face track modelling and hierarchical agglomerative clustering to cluster faces across the entire corpus. We compare different face recognition approaches within this framework. Experiments on a news video database show that the Local TVM technique is able effectively model the session variation observed in the data, resulting in improved clustering performance, with much greater computational efficiency than other methods.

Development of a robust framework for an outdoor mobile manipulation UAV

There is a growing interest to autonomously collect or manipulate objects in remote or unknown environments, such as mountains, gullies, bush-land, or rough terrain. There are several limitations of conventional methods using manned or remotely controlled aircraft. The capability of small Unmanned Aerial Vehicles (UAV) used in parallel with robotic manipulators could overcome some of these limitations. By enabling the autonomous exploration of both naturally hazardous environments, or areas which are biologically, chemically, or radioactively contaminated, it is possible to collect samples and data from such environments without directly exposing personnel to such risks. This paper covers the design, integration, and initial testing of a framework for outdoor mobile manipulation UAV. The framework is designed to allow further integration and testing of complex control theories, with the capability to operate outdoors in unknown environments. The results obtained act as a reference for the effectiveness of the integrated sensors and low-level control methods used for the preliminary testing, as well as identifying the key technologies needed for the development of an outdoor capable system.

Human action recognition from video sequences

This PhD research has proposed new machine learning techniques to improve human action recognition based on local features. Several novel video representation and classification techniques have been proposed to increase the performance with lower computational complexity. The major contributions are the construction of new feature representation techniques, based on advanced machine learning techniques such as multiple instance dictionary learning, Latent Dirichlet Allocation (LDA) and Sparse coding. A Binary-tree based classification technique was also proposed to deal with large amounts of action categories. These techniques are not only improving the classification accuracy with constrained computational resources but are also robust to challenging environmental conditions. These developed techniques can be easily extended to a wide range of video applications to provide near real-time performance.

Human mesenchymal stem cells retain multilineage differentiation capacity including neural marker expression after extended in vitro expansion

The suitability of human mesenchymal stem cells (hMSCs) in regenerative medicine relies on retention of their proliferative expansion potential in conjunction with the ability to differentiate toward multiple lineages. Successful utilisation of these cells in clinical applications linked to tissue regeneration requires consideration of biomarker expression, time in culture and donor age, as well as their ability to differentiate towards mesenchymal (bone, cartilage, fat) or non-mesenchymal (e.g., neural) lineages. To identify potential therapeutic suitability we examined hMSCs after extended expansion including morphological changes, potency (stemness) and multilineage potential. Commercially available hMSC populations were expanded in vitro for > 20 passages, equating to > 60 days and > 50 population doublings. Distinct growth phases (A-C) were observed during serial passaging and cells were characterised for stemness and lineage markers at representative stages (Phase A: P+5, approximately 13 days in culture; Phase B: P+7, approximately 20 days in culture; and Phase C: P+13, approximately 43 days in culture). Cell surface markers, stem cell markers and lineage-specific markers were characterised by FACS, ICC and Q-PCR revealing MSCs maintained their multilineage potential, including neural lineages throughout expansion. Co-expression of multiple lineage markers along with continued CD45 expression in MSCs did not affect completion of osteogenic and adipogenic specification or the formation of neurospheres. Improved standardised isolation and characterisation of MSCs may facilitate the identification of biomarkers to improve therapeutic efficacy to ensure increased reproducibility and routine production of MSCs for therapeutic applications including neural repair.

Extended Conversation Pieces

'Extended Conversation Pieces' brings together conversations about art, and conversation as art. The exhibition features collaborative works by six Brisbane-based artists, Catherine or Kate (Catherine Sagin and Kate Woodcroft), Scott Ferguson (Erika Scott and Brooke Ferguson) and Courtney Coombs and Caitlin Franzmann. These artists engage with ideas of contemporary feminism through processes of dialogue and exchange; exploring subjectivity, humour and intimacy in performance and installation works. 'Extended Conversation Pieces' showcases the distinctive approach to contemporary practice at Boxcopy, an artist run initiative focused on supporting and commissioning new experimental works by Australian artists, and engaging with collaborative processes and practices. This project was commissioned by the Melbourne Art Foundation and presented at the MAF Project Rooms, Melbourne Art Fair, Melbourne in 2014.

Tetragonal bismuth bilayer: A stable and robust quantum spin hall insulator

Topological insulators (TIs) exhibit novel physics with great promise for new devices, but considerable challenges remain to identify TIs with high structural stability and large nontrivial band gap suitable for practical applications. Here we predict by first-principles calculations a two-dimensional (2D) TI, also known as a quantum spin Hall (QSH) insulator, in a tetragonal bismuth bilayer (TB-Bi) structure that is dynamically and thermally stable based on phonon calculations and finite-temperature molecular dynamics simulations. Density functional theory and tight-binding calculations reveal a band inversion among the Bi-p orbits driven by the strong intrinsic spin-orbit coupling, producing a large nontrivial band gap, which can be effectively tuned by moderate strains. The helical gapless edge states exhibit a linear dispersion with a high Fermi velocity comparable to that of graphene, and the QSHphase remains robust on a NaCl substrate. These remarkable properties place TB-Bi among the most promising 2D TIs for high-speed spintronic devices, and the present results provide insights into the intriguing QSH phenomenon in this new Bi structure and offer guidance for its implementation in potential applications.

Robust superhydrophobicity of hierarchical ZnO hollow microspheres fabricated by two-step self-assembly

Superhydrophobic and superhydrophilic surfaces have been extensively investigated due to their importance for industrial applications. It has been reported, however, that superhydrophobic surfaces are very sensitive to heat, ultraviolet (UV) light, and electric potential, which interfere with their long-term durability. In this study, we introduce a novel approach to achieve robust superhydrophobic thin films by designing architecture-defined complex nanostructures. A family of ZnO hollow microspheres with controlled constituent architectures in the morphologies of 1D nanowire networks, 2D nanosheet stacks, and 3D mesoporous nanoball blocks, respectively, was synthesized via a two-step self-assembly approach, where the oligomers or the constituent nanostructures with specially designed structures are first formed from surfactant templates, and then further assembled into complex morphologies by the addition of a second co-surfactant. The thin films composed of two-step synthesized ZnO hollow microspheres with different architectures presented superhydrophobicities with contact angles of 150°-155°, superior to the contact angle of 103° for one-step synthesized ZnO hollow microspheres with smooth and solid surfaces. Moreover, the robust superhydrophobicity was further improved by perfluorinated silane surface modification. The perfluorinated silane treated ZnO hollow microsphere thin films maintained excellent hydrophobicity even after 75 h of UV irradiation. The realization of environmentally durable superhydrophobic surfaces provides a promising solution for their long-term service under UV or strong solar light irradiations.

Mixed pixel analysis for flood mapping using extended support vector machine

This paper addresses the challenges of flood mapping using multispectral images. Quantitative flood mapping is critical for flood damage assessment and management. Remote sensing images obtained from various satellite or airborne sensors provide valuable data for this application, from which the information on the extent of flood can be extracted. However the great challenge involved in the data interpretation is to achieve more reliable flood extent mapping including both the fully inundated areas and the 'wet' areas where trees and houses are partly covered by water. This is a typical combined pure pixel and mixed pixel problem. In this paper, an extended Support Vector Machines method for spectral unmixing developed recently has been applied to generate an integrated map showing both pure pixels (fully inundated areas) and mixed pixels (trees and houses partly covered by water). The outputs were compared with the conventional mean based linear spectral mixture model, and better performance was demonstrated with a subset of Landsat ETM+ data recorded at the Daly River Basin, NT, Australia, on 3rd March, 2008, after a flood event.

Spectral unmixing with estimated adaptive endmember index using Extended Support Vector Machine

The most difficult operation in the flood inundation mapping using optical flood images is to separate fully inundated areas from the ‘wet’ areas where trees and houses are partly covered by water. This can be referred as a typical problem the presence of mixed pixels in the images. A number of automatic information extraction image classification algorithms have been developed over the years for flood mapping using optical remote sensing images. Most classification algorithms generally, help in selecting a pixel in a particular class label with the greatest likelihood. However, these hard classification methods often fail to generate a reliable flood inundation mapping because the presence of mixed pixels in the images. To solve the mixed pixel problem advanced image processing techniques are adopted and Linear Spectral unmixing method is one of the most popular soft classification technique used for mixed pixel analysis. The good performance of linear spectral unmixing depends on two important issues, those are, the method of selecting endmembers and the method to model the endmembers for unmixing. This paper presents an improvement in the adaptive selection of endmember subset for each pixel in spectral unmixing method for reliable flood mapping. Using a fixed set of endmembers for spectral unmixing all pixels in an entire image might cause over estimation of the endmember spectra residing in a mixed pixel and hence cause reducing the performance level of spectral unmixing. Compared to this, application of estimated adaptive subset of endmembers for each pixel can decrease the residual error in unmixing results and provide a reliable output. In this current paper, it has also been proved that this proposed method can improve the accuracy of conventional linear unmixing methods and also easy to apply. Three different linear spectral unmixing methods were applied to test the improvement in unmixing results. Experiments were conducted in three different sets of Landsat-5 TM images of three different flood events in Australia to examine the method on different flooding conditions and achieved satisfactory outcomes in flood mapping.