arXiv subjects

Clinton Fookes

Publications and source records attributed to Clinton Fookes.

178 records · Page 10Linked to original sources

arXiv2018

Learning Free-Form Deformations for 3D Object Reconstruction

Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly from advances in computer vision by generalizing 2D convolutions to the 3D setting, they also have several considerable drawbacks. The computational complexity of voxel-encodings grows cubically with the resolution thus limiting such representations to low-resolution 3D reconstruction. In an attempt to solve this problem, point cloud representations have been proposed. Although point clouds are more efficient than voxel representations as they only cover surfaces rather than volumes, they do not encode detailed geometric information about relationships between points. In this paper we propose a method to learn free-form deformations (FFD) for the task of 3D reconstruction from a single image. By learning to deform points sampled from a high-quality mesh, our trained model can be used to produce arbitrarily dense point clouds or meshes with fine-grained geometry. We evaluate our proposed framework on both synthetic and real-world data and achieve state-of-the-art results on point-cloud and volumetric metrics. Additionally, we qualitatively demonstrate its applicability to label transferring for 3D semantic segmentation.

cs.CV↗

arXiv2018

Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking

Current multi-person localisation and tracking systems have an over reliance on the use of appearance models for target re-identification and almost no approaches employ a complete deep learning solution for both objectives. We present a novel, complete deep learning framework for multi-person localisation and tracking. In this context we first introduce a light weight sequential Generative Adversarial Network architecture for person localisation, which overcomes issues related to occlusions and noisy detections, typically found in a multi person environment. In the proposed tracking framework we build upon recent advances in pedestrian trajectory prediction approaches and propose a novel data association scheme based on predicted trajectories. This removes the need for computationally expensive person re-identification systems based on appearance features and generates human like trajectories with minimal fragmentation. The proposed method is evaluated on multiple public benchmarks including both static and dynamic cameras and is capable of generating outstanding performance, especially among other recently proposed deep neural network based approaches.

cs.CV↗

arXiv2018

Task Specific Visual Saliency Prediction with Memory Augmented Conditional Generative Adversarial Networks

Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these. To address this limitation, we propose a novel saliency estimation model which leverages the semantic modelling power of conditional generative adversarial networks together with memory architectures which capture the subject's behavioural patterns and task dependent factors. We make contributions aiming to bridge the gap between bottom-up feature learning capabilities in modern deep learning architectures and traditional top-down hand-crafted features based methods for task specific saliency modelling. The conditional nature of the proposed framework enables us to learn contextual semantics and relationships among different tasks together, instead of learning them separately for each task. Our studies not only shed light on a novel application area for generative adversarial networks, but also emphasise the importance of task specific saliency modelling and demonstrate the plausibility of fully capturing this context via an augmented memory architecture.

cs.CV↗

arXiv2018

Elastic LiDAR Fusion: Dense Map-Centric Continuous-Time SLAM

The concept of continuous-time trajectory representation has brought increased accuracy and efficiency to multi-modal sensor fusion in modern SLAM. However, regardless of these advantages, its offline property caused by the requirement of global batch optimization is critically hindering its relevance for real-time and life-long applications. In this paper, we present a dense map-centric SLAM method based on a continuous-time trajectory to cope with this problem. The proposed system locally functions in a similar fashion to conventional Continuous-Time SLAM (CT-SLAM). However, it removes the need for global trajectory optimization by introducing map deformation. The computational complexity of the proposed approach for loop closure does not depend on the operation time, but only on the size of the space it explored before the loop closure. It is therefore more suitable for long term operation compared to the conventional CT-SLAM. Furthermore, the proposed method reduces uncertainty in the reconstructed dense map by using probabilistic surface element (surfel) fusion. We demonstrate that the proposed method produces globally consistent maps without global batch trajectory optimization, and effectively reduces LiDAR noise by surfel fusion.

cs.RO↗

arXiv2018

Deep Classification of Epileptic Signals

Electrophysiological observation plays a major role in epilepsy evaluation. However, human interpretation of brain signals is subjective and prone to misdiagnosis. Automating this process, especially seizure detection relying on scalp-based Electroencephalography (EEG) and intracranial EEG, has been the focus of research over recent decades. Nevertheless, its numerous challenges have inhibited a definitive solution. Inspired by recent advances in deep learning, we propose a new classification approach for EEG time series based on Recurrent Neural Networks (RNNs) via the use of Long-Short Term Memory (LSTM) networks. The proposed deep network effectively learns and models discriminative temporal patterns from EEG sequential data. Especially, the features are automatically discovered from the raw EEG data without any pre-processing step, eliminating humans from laborious feature design task. We also show that, in the epilepsy scenario, simple architectures can achieve competitive performance. Using simple architectures significantly benefits in the practical scenario considering their low computation complexity and reduced requirement for large training datasets. Using a public dataset, a multi-fold cross-validation scheme exhibited an average validation accuracy of 95.54\% and an average AUC of 0.9582 of the ROC curve among all sets defined in the experiment. This work reinforces the benefits of deep learning to be further attended in clinical applications and neuroscientific research.

cs.LG↗

arXiv2017

Image2Mesh: A Learning Framework for Single Image 3D Reconstruction

One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks. Recent works have relied on volumetric or point cloud representations, but such approaches suffer from a number of issues such as computational complexity, unordered data, and lack of finer geometry. This paper demonstrates that a mesh representation (i.e. vertices and faces to form polygonal surfaces) is able to capture fine-grained geometry for 3D reconstruction tasks. A mesh however is also unstructured data similar to point clouds. We address this problem by proposing a learning framework to infer the parameters of a compact mesh representation rather than learning from the mesh itself. This compact representation encodes a mesh using free-form deformation and a sparse linear combination of models allowing us to reconstruct 3D meshes from single images. In contrast to prior work, we do not rely on silhouettes and landmarks to perform 3D reconstruction. We evaluate our method on synthetic and real-world datasets with very promising results. Our framework efficiently reconstructs 3D objects in a low-dimensional way while preserving its important geometrical aspects.

cs.CV↗

arXiv2017

Probabilistic Surfel Fusion for Dense LiDAR Mapping

With the recent development of high-end LiDARs, more and more systems are able to continuously map the environment while moving and producing spatially redundant information. However, none of the previous approaches were able to effectively exploit this redundancy in a dense LiDAR mapping problem. In this paper, we present a new approach for dense LiDAR mapping using probabilistic surfel fusion. The proposed system is capable of reconstructing a high-quality dense surface element (surfel) map from spatially redundant multiple views. This is achieved by a proposed probabilistic surfel fusion along with a geometry considered data association. The proposed surfel data association method considers surface resolution as well as high measurement uncertainty along its beam direction which enables the mapping system to be able to control surface resolution without introducing spatial digitization. The proposed fusion method successfully suppresses the map noise level by considering measurement noise caused by laser beam incident angle and depth distance in a Bayesian filtering framework. Experimental results with simulated and real data for the dense surfel mapping prove the ability of the proposed method to accurately find the canonical form of the environment without further post-processing.

cs.RO↗

arXiv2017

Compact Model Representation for 3D Reconstruction

3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image. It is well known however that only one image cannot provide enough information for such a reconstruction. A prior knowledge that has been entertained are 3D CAD models due to its online ubiquity. A fundamental question is how to compactly represent millions of CAD models while allowing generalization to new unseen objects with fine-scaled geometry. We introduce an approach to compactly represent a 3D mesh. Our method first selects a 3D model from a graph structure by using a novel free-form deformation FFD 3D-2D registration, and then the selected 3D model is refined to best fit the image silhouette. We perform a comprehensive quantitative and qualitative analysis that demonstrates impressive dense and realistic 3D reconstruction from single images.

cs.CV↗

arXiv2017

Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes

In this paper the problem of complex event detection in the continuous domain (i.e. events with unknown starting and ending locations) is addressed. Existing event detection methods are limited to features that are extracted from the local spatial or spatio-temporal patches from the videos. However, this makes the model vulnerable to the events with similar concepts e.g. "Open drawer" and "Open cupboard". In this work, in order to address the aforementioned limitations we present a novel model based on the combination of semantic and temporal features extracted from video frames. We train a max-margin classifier on top of the extracted features in an adaptive framework that is able to detect the events with unknown starting and ending locations. Our model is based on the Bidirectional Region Neural Network and large margin Structural Output SVM. The generality of our model allows it to be simply applied to different labeled and unlabeled datasets. We finally test our algorithm on three challenging datasets, "UCF 101-Action Recognition", "MPII Cooking Activities" and "Hollywood", and we report state-of-the-art performance.

cs.CV↗

arXiv2017

Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition

In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards learning salient spatial features via a convolutional neural network (CNN) and then map their temporal relationship with the aid of Long-Short-Term-Memory (LSTM) networks. Our contribution in this paper is a deep fusion framework that more effectively exploits spatial features from CNNs with temporal features from LSTM models. We also extensively evaluate their strengths and weaknesses. We find that by combining both the sets of features, the fully connected features effectively act as an attention mechanism to direct the LSTM to interesting parts of the convolutional feature sequence. The significance of our fusion method is its simplicity and effectiveness compared to other state-of-the-art methods. The evaluation results demonstrate that this hierarchical multi stream fusion method has higher performance compared to single stream mapping methods allowing it to achieve high accuracy outperforming current state-of-the-art methods in three widely used databases: UCF11, UCFSports, jHMDB.

cs.CV↗

arXiv2017

Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection

As humans we possess an intuitive ability for navigation which we master through years of practice; however existing approaches to model this trait for diverse tasks including monitoring pedestrian flow and detecting abnormal events have been limited by using a variety of hand-crafted features. Recent research in the area of deep-learning has demonstrated the power of learning features directly from the data; and related research in recurrent neural networks has shown exemplary results in sequence-to-sequence problems such as neural machine translation and neural image caption generation. Motivated by these approaches, we propose a novel method to predict the future motion of a pedestrian given a short history of their, and their neighbours, past behaviour. The novelty of the proposed method is the combined attention model which utilises both "soft attention" as well as "hard-wired" attention in order to map the trajectory information from the local neighbourhood to the future positions of the pedestrian of interest. We illustrate how a simple approximation of attention weights (i.e hard-wired) can be merged together with soft attention weights in order to make our model applicable for challenging real world scenarios with hundreds of neighbours. The navigational capability of the proposed method is tested on two challenging publicly available surveillance databases where our model outperforms the current-state-of-the-art methods. Additionally, we illustrate how the proposed architecture can be directly applied for the task of abnormal event detection without handcrafting the features.

cs.CV↗

arXiv2016

Automatic Event Detection for Signal-based Surveillance

Signal-based Surveillance systems such as Closed Circuits Televisions (CCTV) have been widely installed in public places. Those systems are normally used to find the events with security interest, and play a significant role in public safety. Though such systems are still heavily reliant on human labour to monitor the captured information, there have been a number of automatic techniques proposed to analysing the data. This article provides an overview of automatic surveillance event detection techniques . Despite it's popularity in research, it is still too challenging a problem to be realised in a real world deployment. The challenges come from not only the detection techniques such as signal processing and machine learning, but also the experimental design with factors such as data collection, evaluation protocols, and ground-truth annotation. Finally, this article propose that multi-disciplinary research is the path towards a solution to this problem.

cs.CV↗

arXiv2016

Improving Short Utterance PLDA Speaker Verification using SUV Modelling and Utterance Partitioning Approach

This paper analyses the short utterance probabilistic linear discriminant analysis (PLDA) speaker verification with utterance partitioning and short utterance variance (SUV) modelling approaches. Experimental studies have found that instead of using single long-utterance as enrolment data, if long enrolled utterance is partitioned into multiple short utterances and average of short utterance i-vectors is used as enrolled data, that improves the Gaussian PLDA (GPLDA) speaker verification. This is because short utterance i-vectors have speaker, session and utterance variations, and utterance-partitioning approach compensates the utterance variation. Subsequently, SUV-PLDA is also studied with utterance partitioning approach, and utterance partitioning-based SUV-GPLDA system shows relative improvement of 9% and 16% in EER for NIST 2008 and NIST 2010 truncated 10sec-10sec evaluation condition as utterance partitioning approach compensates the utterance variation and SUV modelling approach compensates the mismatch between full-length development data and short-length evaluation data.

cs.SD↗

arXiv2016

Domain adaptation based Speaker Recognition on Short Utterances

This paper explores how the in- and out-domain probabilistic linear discriminant analysis (PLDA) speaker verification behave when enrolment and verification lengths are reduced. Experiment studies have found that when full-length utterance is used for evaluation, in-domain PLDA approach shows more than 28% improvement in EER and DCF values over out-domain PLDA approach and when short utterances are used for evaluation, the performance gain of in-domain speaker verification reduces at an increasing rate. Novel modified inter dataset variability (IDV) compensation is used to compensate the mismatch between in- and out-domain data and IDV-compensated out-domain PLDA shows respectively 26% and 14% improvement over out-domain PLDA speaker verification when SWB and NIST data are respectively used for S normalization. When the evaluation utterance length is reduced, the performance gain by IDV also reduces as short utterance evaluation data i-vectors have more variations due to phonetic variations when compared to the dataset mismatch between in- and out-domain data.

cs.SD↗

arXiv2016

DNN based Speaker Recognition on Short Utterances

This paper investigates the effects of limited speech data in the context of speaker verification using deep neural network (DNN) approach. Being able to reduce the length of required speech data is important to the development of speaker verification system in real world applications. The experimental studies have found that DNN-senone-based Gaussian probabilistic linear discriminant analysis (GPLDA) system respectively achieves above 50% and 18% improvements in EER values over GMM-UBM GPLDA system on NIST 2010 coreext-coreext and truncated 15sec-15sec evaluation conditions. Further when GPLDA model is trained on short-length utterances (30sec) rather than full-length utterances (2min), DNN-senone GPLDA system achieves above 7% improvement in EER values on truncated 15sec-15sec condition. This is because short length development i-vectors have speaker, session and phonetic variation and GPLDA is able to robustly model those variations. For several real world applications, longer utterances (2min) can be used for enrollment and shorter utterances (15sec) are required for verification, and in those conditions, DNN-senone GPLDA system achieves above 26% improvement in EER values over GMM-UBM GPLDA systems.

cs.SD↗

arXiv2015

Learning Temporal Alignment Uncertainty for Efficient Event Detection

In this paper we tackle the problem of efficient video event detection. We argue that linear detection functions should be preferred in this regard due to their scalability and efficiency during estimation and evaluation. A popular approach in this regard is to represent a sequence using a bag of words (BOW) representation due to its: (i) fixed dimensionality irrespective of the sequence length, and (ii) its ability to compactly model the statistics in the sequence. A drawback to the BOW representation, however, is the intrinsic destruction of the temporal ordering information. In this paper we propose a new representation that leverages the uncertainty in relative temporal alignments between pairs of sequences while not destroying temporal ordering. Our representation, like BOW, is of a fixed dimensionality making it easily integrated with a linear detection function. Extensive experiments on CK+, 6DMG, and UvA-NEMO databases show significant performance improvements across both isolated and continuous event detection tasks.

cs.CV↗