Search Results for author: Toby P. Breckon

Found 60 papers, 25 papers with code

U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation

no code implementations10 Nov 2023 Jiaxu Liu, Zhengdi Yu, Toby P. Breckon, Hubert P. H. Shum

To achieve this, U3DS$^3$ leverages a generalized unsupervised segmentation method for both object and background across both indoor and outdoor static 3D point clouds with no requirement for model pre-training, by leveraging only the inherent information of the point cloud to achieve full 3D scene segmentation.

Point Cloud Segmentation Representation Learning +2

On Pixel-level Performance Assessment in Anomaly Detection

no code implementations25 Oct 2023 Mehdi Rafiei, Toby P. Breckon, Alexandros Iosifidis

Anomaly detection methods have demonstrated remarkable success across various applications.

Anomaly Detection

Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers

1 code implementation ICCV 2023 Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon, Hubert P. H. Shum, Chris G. Willcocks

Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment.

Racial Bias within Face Recognition: A Survey

no code implementations1 May 2023 Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon

Facial recognition is one of the most academically studied and industrially developed areas within computer vision where we readily find associated applications deployed globally.

Face Recognition Face Verification

Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation

1 code implementation CVPR 2023 Li Li, Hubert P. H. Shum, Toby P. Breckon

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving.

 Ranked #1 on 3D Semantic Segmentation on ScribbleKITTI (mIoU-1% metric)

3D Semantic Segmentation Autonomous Driving +3

ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction

1 code implementation CVPR 2023 Zhengdi Yu, Shaoli Huang, Chen Fang, Toby P. Breckon, Jue Wang

Our method significantly outperforms the best interacting-hand approaches on the InterHand2. 6M dataset while yielding comparable performance with the state-of-the-art single-hand methods on the FreiHand dataset.

3D Interacting Hand Pose Estimation 3D Reconstruction +1

1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results

no code implementations24 Nov 2022 Benjamin Kiefer, Matej Kristan, Janez Perš, Lojze Žust, Fabio Poiesi, Fabio Augusto de Alcantara Andrade, Alexandre Bernardino, Matthew Dawkins, Jenni Raitoharju, Yitong Quan, Adem Atmaca, Timon Höfer, Qiming Zhang, Yufei Xu, Jing Zhang, DaCheng Tao, Lars Sommer, Raphael Spraul, Hangyue Zhao, Hongpu Zhang, Yanyun Zhao, Jan Lukas Augustin, Eui-ik Jeon, Impyeong Lee, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Sagar Verma, Siddharth Gupta, Shishir Muralidhara, Niharika Hegde, Daitao Xing, Nikolaos Evangeliou, Anthony Tzes, Vojtěch Bartl, Jakub Špaňhel, Adam Herout, Neelanjan Bhowmik, Toby P. Breckon, Shivanand Kundargi, Tejas Anvekar, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudengudi, Arpita Vats, Yang song, Delong Liu, Yonglin Li, Shuman Li, Chenhao Tan, Long Lan, Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi, Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang, Pyong-Kun Kim, Kwangju Kim, Kyoungoh Lee, Shuai Jiang, Haiwen Li, Zheng Ziqiang, Tuan-Anh Vu, Hai Nguyen-Truong, Sai-Kit Yeung, Zhuang Jia, Sophia Yang, Chih-Chung Hsu, Xiu-Yu Hou, Yu-An Jhang, Simon Yang, Mau-Tsuen Yang

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.

Object object-detection +2

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields

1 code implementation CVPR 2023 Brian K. S. Isaac-Medina, Chris G. Willcocks, Toby P. Breckon

In this paper, we explore the use of an exact approach for calculating the IPE by using a pyramid-based integral formulation instead of an approximated conical-based one.

Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagery

no code implementations29 Oct 2022 Neelanjan Bhowmik, Toby P. Breckon

X-ray baggage security screening is in widespread use and crucial to maintaining transport security for threat/anomaly detection tasks.

Anomaly Detection Segmentation

On Fine-Tuned Deep Features for Unsupervised Domain Adaptation

no code implementations25 Oct 2022 Qian Wang, Toby P. Breckon

Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular domain adaptation task.

Unsupervised Domain Adaptation

Does lossy image compression affect racial bias within face recognition?

no code implementations16 Aug 2022 Seyma Yucer, Matt Poyser, Noura Al Moubayed, Toby P. Breckon

Yes - This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject.

Face Recognition Image Compression

Evaluating Gaussian Grasp Maps for Generative Grasping Models

no code implementations1 Jun 2022 William Prew, Toby P. Breckon, Magnus Bordewich, Ulrik Beierholm

We propose a continuous Gaussian representation of annotated grasps to generate ground truth training data which achieves a higher success rate on a simulated robotic grasping benchmark.

Object Robotic Grasping +1

Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery

no code implementations16 May 2022 Neelanjan Bhowmik, Jack W. Barker, Yona Falinie A. Gaus, Toby P. Breckon

When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0. 823 with Cascade R-CNN across the FLIR dataset, outperforming prior work.

Image Compression object-detection +1

DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications

1 code implementation International Conference on 3D Vision (3DV) 2021 Li Li, Khalid N. Ismail, Hubert P. H. Shum, Toby P. Breckon

Leveraging DurLAR, with a resolution exceeding that of prior benchmarks, we consider the task of monocular depth estimation and use this increased avail- ability of higher resolution, yet sparse ground truth scene depth information to propose a novel joint supervised/self- supervised loss formulation.

Autonomous Driving Monocular Depth Estimation

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes

3 code implementations24 Nov 2021 Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki, Toby P. Breckon, Chris G. Willcocks

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements.

Image Generation

Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation

no code implementations25 Oct 2021 Qian Wang, Fanlin Meng, Toby P. Breckon

The common subspace learning algorithm OSLPP simultaneously aligns the labelled source data and pseudo-labelled target data from known classes and pushes the rejected target data away from the known classes.

Domain Adaptation Image Classification +1

Measuring Hidden Bias within Face Recognition via Racial Phenotypes

1 code implementation19 Oct 2021 Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon

We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject.

Attribute Face Identification +2

Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery

no code implementations10 Oct 2021 Thomas W. Webb, Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon

The recent advancement in deep Convolutional Neural Network (CNN) has brought insight into the automation of X-ray security screening for aviation security and beyond.

Data Augmentation Data Compression +3

On the impact of using X-ray energy response imagery for object detection via Convolutional Neural Networks

no code implementations27 Aug 2021 Neelanjan Bhowmik, Yona Falinie A. Gaus, Toby P. Breckon

Automatic detection of prohibited items within complex and cluttered X-ray security imagery is essential to maintaining transport security, where prior work on automatic prohibited item detection focus primarily on pseudo-colour (rgb}) X-ray imagery.

Object object-detection +1

PANDA : Perceptually Aware Neural Detection of Anomalies

no code implementations28 Apr 2021 Jack W. Barker, Toby P. Breckon

Semi-supervised methods of anomaly detection have seen substantial advancement in recent years.

Anomaly Detection Defect Detection

UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-identification in Video Imagery

1 code implementation13 Apr 2021 Daniel Organisciak, Matthew Poyser, Aishah Alsehaim, Shanfeng Hu, Brian K. S. Isaac-Medina, Toby P. Breckon, Hubert P. H. Shum

As unmanned aerial vehicles (UAVs) become more accessible with a growing range of applications, the potential risk of UAV disruption increases.

Vehicle Re-Identification

UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models

no code implementations12 Apr 2021 Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain.

Denoising Image-to-Image Translation +1

Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery

no code implementations21 Dec 2020 Qian Wang, Toby P. Breckon

Specifically, we formulate it as a 3D semantic segmentation problem to identify material types for all voxels based on which contraband materials can be detected.

3D Semantic Segmentation Computed Tomography (CT) +2

Competitive Simplicity for Multi-Task Learning for Real-Time Foggy Scene Understanding via Domain Adaptation

no code implementations9 Dec 2020 Naif Alshammari, Samet Akcay, Toby P. Breckon

For optimal performance in semantic segmentation, our model generates depth to be used as complementary source information with RGB in the segmentation network.

Domain Adaptation Monocular Depth Estimation +4

Multi-Model Learning for Real-Time Automotive Semantic Foggy Scene Understanding via Domain Adaptation

no code implementations9 Dec 2020 Naif Alshammari, Samet Akcay, Toby P. Breckon

Using this architectural formulation with dense skip connections, our model achieves comparable performance to contemporary approaches at a fraction of the overall model complexity.

Domain Adaptation Scene Segmentation +1

Data Augmentation with norm-VAE for Unsupervised Domain Adaptation

1 code implementation1 Dec 2020 Qian Wang, Fanlin Meng, Toby P. Breckon

As a result, our proposed methods (i. e. naive-SPL and norm-VAE-SPL) can achieve new state-of-the-art performance with the average accuracy of 93. 4% and 90. 4% on Office-Caltech and ImageCLEF-DA datasets, and comparable performance on Digits, Office31 and Office-Home datasets with the average accuracy of 97. 2%, 87. 6% and 67. 9% respectively.

Data Augmentation Image Classification +1

Not 3D Re-ID: a Simple Single Stream 2D Convolution for Robust Video Re-identification

no code implementations14 Aug 2020 Toby P. Breckon, Aishah Alsehaim

Video-based person re-identification has received increasing attention recently, as it plays an important role within surveillance video analysis.

Transfer Learning Video-Based Person Re-Identification

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders

no code implementations3 Aug 2020 Qian Wang, Toby P. Breckon

In this paper, we formulate this particular domain adaptation problem within a generalized zero-shot learning framework by treating the labelled source domain samples as semantic representations for zero-shot learning.

Domain Adaptation Generalized Zero-Shot Learning

Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery

no code implementations3 Aug 2020 Qian Wang, Neelanjan Bhowmik, Toby P. Breckon

X-ray Computed Tomography (CT) based 3D imaging is widely used in airports for aviation security screening whilst prior work on automatic prohibited item detection focus primarily on 2D X-ray imagery.

3D Object Detection Computed Tomography (CT) +3

On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures

no code implementations28 Jul 2020 Matt Poyser, Amir Atapour-Abarghouei, Toby P. Breckon

Recent advances in generalized image understanding have seen a surge in the use of deep convolutional neural networks (CNN) across a broad range of image-based detection, classification and prediction tasks.

Action Recognition Image Compression +7

Leveraging Synthetic Subject Invariant EEG Signals for Zero Calibration BCI

1 code implementation16 Jul 2020 Nik Khadijah Nik Aznan, Amir Atapour-Abarghouei, Stephen Bonner, Jason D. Connolly, Toby P. Breckon

Our approach, entitled the Subject Invariant SSVEP Generative Adversarial Network (SIS-GAN), produces synthetic EEG data from multiple SSVEP classes using a single network.

Signal Processing Image and Video Processing

Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery

no code implementations5 May 2020 Hiroshi Sasaki, Chris G. Willcocks, Toby P. Breckon

However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches.

Classification Data Augmentation +4

Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation

1 code implementation26 Apr 2020 Qian Wang, Toby P. Breckon

Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from the source and target domains are of different modalities (e. g., texts and images) or feature dimensions (e. g., features extracted with different methods).

Domain Adaptation Transfer Learning

Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation

no code implementations19 Apr 2020 Seyma Yucer, Samet Akçay, Noura Al-Moubayed, Toby P. Breckon

Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society.

Data Augmentation Face Recognition

On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery

no code implementations27 Mar 2020 Qian Wang, Neelanjan Bhowmik, Toby P. Breckon

As the first attempt to use 3D CNN for volumetric 3D CT baggage security screening, we first evaluate different CNN architectures on the classification of isolated prohibited item volumes and compare against traditional methods which use hand-crafted features.

3D Object Detection Computed Tomography (CT) +3

A Reference Architecture for Plausible Threat Image Projection (TIP) Within 3D X-ray Computed Tomography Volumes

1 code implementation15 Jan 2020 Qian Wang, Najla Megherbi, Toby P. Breckon

Threat Image Projection (TIP) is a technique used in X-ray security baggage screening systems that superimposes a threat object signature onto a benign X-ray baggage image in a plausible and realistic manner.

Computed Tomography (CT)

Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environments

no code implementations11 Dec 2019 Bruna G. Maciel-Pearson, Letizia Marchegiani, Samet Akcay, Amir Atapour-Abarghouei, James Garforth, Toby P. Breckon

With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge.

Navigate reinforcement-learning +1

Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection

no code implementations20 Nov 2019 Ganesh Samarth C. A., Neelanjan Bhowmik, Toby P. Breckon

In this work we explore different Convolutional Neural Network (CNN) architectures and their variants for non-temporal binary fire detection and localization in video or still imagery.

Fire Detection

Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss

1 code implementation18 Nov 2019 Qian Wang, Toby P. Breckon

Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants.

Crowd Counting Image Classification

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

1 code implementation18 Nov 2019 Qian Wang, Toby P. Breckon

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains.

Clustering Structured Prediction +1

Multi-Task Learning for Automotive Foggy Scene Understanding via Domain Adaptation to an Illumination-Invariant Representation

no code implementations17 Sep 2019 Naif Alshammari, Samet Akçay, Toby P. Breckon

Joint scene understanding and segmentation for automotive applications is a challenging problem in two key aspects:- (1) classifying every pixel in the entire scene and (2) performing this task under unstable weather and illumination changes (e. g. foggy weather), which results in poor outdoor scene visibility.

Domain Adaptation Multi-Task Learning +1

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

no code implementations15 Aug 2019 Amir Atapour-Abarghouei, Toby P. Breckon

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation.

Autonomous Driving Depth Completion +3

TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text

1 code implementation28 Apr 2019 Fady Medhat, Mahnaz Mohammadi, Sardar Jaf, Chris G. Willcocks, Toby P. Breckon, Peter Matthews, Andrew Stephen McGough, Georgios Theodoropoulos, Boguslaw Obara

In this work, we present a generic process flow for text recognition in scanned documents containing mixed handwritten and machine-printed text without the need to classify text in advance.

Evaluation of a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery

no code implementations10 Apr 2019 Yona Falinie A. Gaus, Neelanjan Bhowmik, Samet Akçay, Paolo M. Guillen-Garcia, Jack W. Barker, Toby P. Breckon

Subsequently, leveraging a range of established CNN object and fine-grained category classification approaches we formulate within object anomaly detection as a two-class problem (anomalous or benign).

Anomaly Detection General Classification +3

Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition

1 code implementation25 Mar 2019 Qian Wang, Penghui Bu, Toby P. Breckon

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain.

domain classification Generalized Zero-Shot Learning +1

Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection

2 code implementations25 Jan 2019 Samet Akçay, Amir Atapour-Abarghouei, Toby P. Breckon

By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain and hence detect abnormality based on deviation from this model.

Scene Understanding Unsupervised Anomaly Detection

A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks

1 code implementation20 Nov 2018 Qian Wang, Ning Jia, Toby P. Breckon

Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks.

Classification Data Augmentation +3

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

9 code implementations17 May 2018 Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal).

Generative Adversarial Network Semi-supervised Anomaly Detection +1

Depth Not Needed - An Evaluation of RGB-D Feature Encodings for Off-Road Scene Understanding by Convolutional Neural Network

no code implementations4 Jan 2018 Christopher J. Holder, Toby P. Breckon, Xiong Wei

Scene understanding for autonomous vehicles is a challenging computer vision task, with recent advances in convolutional neural networks (CNNs) achieving results that notably surpass prior traditional feature driven approaches.

Autonomous Vehicles road scene understanding +3

Cannot find the paper you are looking for? You can Submit a new open access paper.