Time filter

Source Type

Birmingham, United Kingdom

Edwards D.J.,Innovation and Enterprise | Holt G.D.,Birmingham City Business School | Holt G.D.,University of Central Lancashire
Journal of Construction Engineering and Management | Year: 2014

Wheel detachment from plant trailers used on public highways represents a significant health and safety hazard and major financial risk, especially for construction and utility companies that rely on these type of trailers to transport machinery such as miniexcavators or road rollers. This study uncovers the antecedents of plant trailer wheel detachment and suggests pragmatic guidance for mitigating this risk. A case study using elements of action research studies the problem in the field through direct observation and stakeholder interviews. Analysis of resulting qualitative data conceptualizes antecedents on which guidance is formulated. Risks are found to result from a combination of physical failure underpinned by inadequate human interventions and poor risk management. The primary contributions of the study are that it describes entirely novel research on trailer wheel detachment, produces new safety guidance for businesses and practitioners that operate plant trailers, and resultantly contributes to lowering the risks identified. © 2014 American Society of Civil Engineers. Source

Nguyen T.V.,Innovation and Enterprise
Proceedings of the National Conference on Artificial Intelligence | Year: 2015

Salient object detection has gradually become a popular topic in robotics and computer vision research. This paper presents a real-time system that detects salient object by integrating objectness, foreground and compactness measures. Our algorithm consists of four basic steps. First, our method generates the objectness map via object proposals. Based on the objectness map, we estimate the background margin and compute the corresponding foreground map which prefers the foreground objects. From the objectness map and the foreground map, the compactness map is formed to favor the compact objects. We then integrate those cues to form a pixel-accurate saliency map which covers the salient objects and consistently separates fore- and background. © Copyright 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Source

Nguyen T.V.,Innovation and Enterprise | Feng J.,University of California at Berkeley | Yan S.,National University of Singapore
Journal of Computer Science and Technology | Year: 2014

Human weight estimation is useful in a variety of potential applications, e.g., targeted advertisement, entertainment scenarios and forensic science. However, estimating weight only from color cues is particularly challenging since these cues are quite sensitive to lighting and imaging conditions. In this article, we propose a novel weight estimator based on a single RGB-D image, which utilizes the visual color cues and depth information. Our main contributions are three-fold. First, we construct the W8-RGBD dataset including RGB-D images of different people with ground truth weight. Second, the novel sideview shape feature and the feature fusion model are proposed to facilitate weight estimation. Additionally, we consider gender as another important factor for human weight estimation. Third, we conduct comprehensive experiments using various regression models and feature fusion models on the new weight dataset, and encouraging results are obtained based on the proposed features and models. © 2014, Springer Science+Business Media New York. Source

Wei F.,Nanyang Technological University | Wei F.,Innovation and Enterprise | Gasparyan H.,University of Liverpool | Keenan P.J.,University of Birmingham | And 7 more authors.
Journal of Materials Chemistry A | Year: 2015

Electrolytes with oxide ion conductivities higher than 10-2 S cm-1 at moderate temperatures (∼500-900 °C) offer the possibility for solid oxide fuel cells to operate with less maintenance. This study of [A1+xB1-x]2[Ga]2[Ga2O7+x/2]2 (0 ≤ x ≤ 0.5) (A = La, Nd; B = Ca, Sr) layered-melilite found that in large single crystals intralayer oxide ion conduction is dominant. This anisotropic behavior arises by relaxation about the interstitial oxygen through changes in the interlayer A and Ga coordination, and at 850 °C conductivities are ∼0.008 S cm-1 along the c direction and ∼0.036 S cm-1 perpendicular to the c axis. It is found that the ionic conductivity can be optimized by increasing the number of interstitial oxygen and reducing the size of interlayer cations. © The Royal Society of Chemistry 2015. Source

Nguyen T.V.,Innovation and Enterprise | Song Z.,Visenze Pte. Ltd. | Yan S.,National University of Singapore
IEEE Transactions on Circuits and Systems for Video Technology | Year: 2015

Human action recognition is valuable for numerous practical applications, e.g., gaming, video surveillance, and video search. In this paper we hypothesize that the classification of actions can be boosted by designing a smart feature pooling strategy under the prevalently used bag-of-words-based representation. Founded on automatic video saliency analysis, we propose the spatial-temporal attention-aware pooling scheme for feature pooling. First, the video saliencies are predicted using the video saliency model, and the localized spatial-temporal features are pooled at different saliency levels and video-saliency-guided channels are formed. Saliency-aware matching kernels are thus derived as the similarity measurement of these channels. Intuitively, the proposed kernels calculate the similarities of the video foreground (salient areas) or background (nonsalient areas) at different levels. Finally, the kernels are fed into popular support vector machines for action classification. Extensive experiments on three popular data sets for action classification validate the effectiveness of our proposed method, which outperforms the state-of-the-art methods, namely 95.3% on UCF Sports (better by 4.0%), 87.9% on YouTube data set (better by 2.5%), and achieves comparable results on Hollywood2 dataset. © 1991-2012 IEEE. Source

Discover hidden collaborations