Skip to main content

Research Repository

Advanced Search

Outputs (663)

Eliminating the Dreaded Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery (2018)
Presentation / Conference Contribution
Payen de La Garanderie, G., Atapour-Abarghouei, A., & Breckon, T. (2018). Eliminating the Dreaded Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery.

Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360... Read More about Eliminating the Dreaded Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery.

Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer (2018)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. (2018). Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer. In Proc. Computer Vision and Pattern Recognition (2800-2810). https://doi.org/10.1109/CVPR.2018.00296

Monocular depth estimation using learning-based approaches has become promising in recent years. However, most monocular depth estimators either need to rely on large quantities of ground truth depth data, which is extremely expensive and difficult t... Read More about Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer.

A user study on quantisation thresholds of triangle meshes (2017)
Presentation / Conference Contribution
Almutairi, A., Saarela, T., & Ivrissimtzis, I. (2017). A user study on quantisation thresholds of triangle meshes. In T. R. Wan, & F. Vidal (Eds.), Computer Graphics & Visual Computing (CGVC) 2017. Eurographics UK Chapter Proceedings, anchester Metropolitan University, United Kingdom, 14 – 15 September 2017. https://doi.org/10.2312/cgvc.20171283

We present the results of a user study on estimating a quantisation threshold above which the quantised triangle mesh is perceived as indistinguishable from its unquantised original. The design of the experiment and the analysis of the results focus... Read More about A user study on quantisation thresholds of triangle meshes.

Closed loop adaptive optics with a laser guide star for biological light microscopy (2012)
Presentation / Conference Contribution
Saunter, C. D., Bourgenot, C., Girkin, J. M., & Love, G. D. (2012). Closed loop adaptive optics with a laser guide star for biological light microscopy. In S. S. Oliver, T. G. Bifano, & J. Kubby (Eds.), . https://doi.org/10.1117/12.909927

We report on the development of a widefield microscope that achieves adaptive optics correction through the use of a wavefront sensor observing an artificial laser guide star induced within the sample. By generating this guide star at arbitrary posit... Read More about Closed loop adaptive optics with a laser guide star for biological light microscopy.

Realtime wavefront sensing in a SPIM microscope, and active aberration tracking (2015)
Presentation / Conference Contribution
Taylor, J. M., Saunter, C. D., Bourgenot, C., Girkin, J. M., & Love, G. D. (2015). Realtime wavefront sensing in a SPIM microscope, and active aberration tracking. In T. G. Bifano, J. Kubby, & S. Gigan (Eds.), . https://doi.org/10.1117/12.2080061

Adaptive optics (AO) can potentially allow high resolution imaging deep inside living tissue, mitigating against the loss of resolution due to aberrations caused by overlying tissue. Closed-loop AO correction is particularly attractive for moving tis... Read More about Realtime wavefront sensing in a SPIM microscope, and active aberration tracking.

DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation (2017)
Presentation / Conference Contribution
Atapour-Abarghouei, A., & Breckon, T. (2017). DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation. In Proc. British Machine Vision Conference (208.1-208.13). https://doi.org/10.5244/C.31.58

We address plausible hole filling in depth images in a computationally lightweight methodology that leverages recent advances in semantic scene segmentation. Firstly, we perform such segmentation over a co-registered color image, commonly available f... Read More about DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation.

An Optimised Deep Neural Network Approach for Forest Trail Navigation for UAV Operation within the Forest Canopy (2017)
Presentation / Conference Contribution
Maciel-Pearson, B., & Breckon, T. (2017). An Optimised Deep Neural Network Approach for Forest Trail Navigation for UAV Operation within the Forest Canopy. In Proc. Conf. on Robotics and Autonomous Systems - Robots that Work Among Us Workshop (1-3)

Autonomous flight within a forest canopy represents a key challenge for generalised scene understanding on-board a future Unmanned Aerial Vehicle (UAV) platform. Here we present an approach for automatic trail navigation within such an environment th... Read More about An Optimised Deep Neural Network Approach for Forest Trail Navigation for UAV Operation within the Forest Canopy.

An Exploration of Dropout with RNNs for Natural Language Inference (2018)
Presentation / Conference Contribution
Gajbhiye, A., Jaf, S., Al-Moubayed, N., McGough, A. S., & Bradley, S. (2018). An Exploration of Dropout with RNNs for Natural Language Inference. In V. Kurková, Y. Manolopoulos, B. Hammer, L. S. Iliadis, & I. G. Maglogiannis (Eds.), Artificial neural networks and machine learning - ICANN 2018 : 27th international Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, proceedings. Part III (157-167). https://doi.org/10.1007/978-3-030-01424-7_16

Dropout is a crucial regularization technique for the Recurrent Neural Network (RNN) models of Natural Language Inference (NLI). However, dropout has not been evaluated for the effectiveness at different layers and dropout rates in NLI models. In thi... Read More about An Exploration of Dropout with RNNs for Natural Language Inference.

Enhanced detection of movement onset in EEG through deep oversampling (2017)
Presentation / Conference Contribution
Al Moubayed, N., Hasan, B. A. S., & McGough, A. S. (2017). Enhanced detection of movement onset in EEG through deep oversampling. In 2017 International Joint Conference on Neural Networks (IJCNN 2017) : Anchorage, Alaska, USA, 14-19 May 2017 (71-78). https://doi.org/10.1109/ijcnn.2017.7965838

A deep learning approach for oversampling of electroencephalography (EEG) recorded during self-paced hand movement is investigated for the purpose of improving EEG classification in general and the detection of movement onset during online Brain-Comp... Read More about Enhanced detection of movement onset in EEG through deep oversampling.

On the Classification of SSVEP-Based Dry-EEG Signals via Convolutional Neural Networks (2018)
Presentation / Conference Contribution
Aznan, N., Bonner, S., Connolly, J., Al Moubayed, N., & Breckon, T. (2018). On the Classification of SSVEP-Based Dry-EEG Signals via Convolutional Neural Networks. In Proceedings of the 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC2018): Miyazaki, Japan, 7-10 October 2018 (3726-3731). https://doi.org/10.1109/smc.2018.00631

Electroencephalography (EEG) is a common signal acquisition approach employed for Brain-Computer Interface (BCI) research. Nevertheless, the majority of EEG acquisition devices rely on the cumbersome application of conductive gel (so-called wet-EEG)... Read More about On the Classification of SSVEP-Based Dry-EEG Signals via Convolutional Neural Networks.

Order-randomized Laplacian mesh smoothing (2017)
Presentation / Conference Contribution
Yang, Y., Rushmeier, H., & Ivrissimtzis, I. (2017). Order-randomized Laplacian mesh smoothing. In M. S. Floater, T. Lyche, M. Mazure, K. Mørken, & L. L. Schumaker (Eds.), Mathematical methods for curves and surfaces : 9th International Conference, MMCS 2016, Tønsberg, Norway, June 23 - June 28, 2016. Revised selected papers (312-323). https://doi.org/10.1007/978-3-319-67885-6_17

In this paper we compare three variants of the graph Laplacian smoothing. The first is the standard synchronous implementation, corresponding to multiplication by the graph Laplacian matrix. The second is a voter process inspired asynchronous impleme... Read More about Order-randomized Laplacian mesh smoothing.

Using Machine Learning in Trace-driven Energy-Aware Simulations of High-Throughput Computing Systems (2017)
Presentation / Conference Contribution
McGough, A. S., Al Moubayed, N., & M, F. (2017). Using Machine Learning in Trace-driven Energy-Aware Simulations of High-Throughput Computing Systems. In Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering Companion (ICPE '17 Companion), April 22 - 26, 2017, L’Aquila, Italy (55-60). https://doi.org/10.1145/3053600.3053612

When performing a trace-driven simulation of a High Throughput Computing system we are limited to the knowledge which should be available to the system at the current point within the simulation. However, the trace-log contains information we would n... Read More about Using Machine Learning in Trace-driven Energy-Aware Simulations of High-Throughput Computing Systems.

Gaze Prediction using Machine Learning for Dynamic Stereo Manipulation in Games (2016)
Presentation / Conference Contribution
Koulieris, G., Drettakis, G., Cunningham, D., & Mania, K. (2016). Gaze Prediction using Machine Learning for Dynamic Stereo Manipulation in Games. In T. Höllerer, V. Interrante, A. Lécuyer, & E. Suma (Eds.), 2016 IEEE Virtual Reality Conference (VR) : Greenville, South Carolina, USA, 19-23 March 2016. Proceedings (113-120). https://doi.org/10.1109/vr.2016.7504694

Comfortable, high-quality 3D stereo viewing is becoming a requirement for interactive applications today. Previous research shows that manipulating disparity can alleviate some of the discomfort caused by 3D stereo, but it is best to do this locally,... Read More about Gaze Prediction using Machine Learning for Dynamic Stereo Manipulation in Games.

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection (2018)
Presentation / Conference Contribution
Dunnings, A., & Breckon, T. (2018). Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection. In Proc. Int. Conf. on Image Processing (1558-1562). https://doi.org/10.1109/ICIP.2018.8451657

In this work we investigate the automatic detection of fire pixel regions in video (or still) imagery within real-time bounds without reliance on temporal scene information. As an extension to prior work in the field, we consider the performance of e... Read More about Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection.

Adaptive optics for wide-field microscopy (2011)
Presentation / Conference Contribution
Bourgenot, C., Saunter, C., Girkin, J., & Love, G. (2011). Adaptive optics for wide-field microscopy. . https://doi.org/10.1117/12.873857

We report on recent developments in the use of adaptive optics (AO) in wide-field microscopy to remove both system and sample induced aberrations. We describe progress on using both a full AO system and image optimization techniques (wavefront sensor... Read More about Adaptive optics for wide-field microscopy.

Design, manufacture, and evaluation of prototype telescope windows for use in low-vision aids (2017)
Presentation / Conference Contribution
Young, L., Robertson, D., Love, G., Girkin, J., Cowie, E., Bourgenot, C., & Courtial, J. (2017). Design, manufacture, and evaluation of prototype telescope windows for use in low-vision aids. In A. J. Davis, C. F. Hahlweg, & J. R. Mulley (Eds.), Novel optical systems design and optimization XX. https://doi.org/10.1117/12.2272992

Pixellated Optics, a class of optical devices which preserve phase front continuity only over small sub areas of the device, allow for a range of uses that would not otherwise be possible. One potential use is as Low Vision Aids (LVAs), where they ar... Read More about Design, manufacture, and evaluation of prototype telescope windows for use in low-vision aids.

A Survey of Pattern Recognition Applications in Cancer Diagnosis (2009)
Presentation / Conference Contribution
Atapour-Abarghouei, A., Ghanizadeh, A., Sinaie, S., & Shamsuddin, S. M. (2009). A Survey of Pattern Recognition Applications in Cancer Diagnosis. . https://doi.org/10.1109/socpar.2009.93

In this paper, some of the image processing and pattern recognition methods that have been used on medical images for cancer diagnosis are reviewed. Previous studies on Artificial Neural Networks, Genetic Programming, and Wavelet Analysis are describ... Read More about A Survey of Pattern Recognition Applications in Cancer Diagnosis.