Andrew Markham

Andrew Markham
University of Oxford | OX · Department of Computer Science

PhD in Electrical Engineering

About

182
Publications
40,839
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,457
Citations
Introduction
I am a University Lecturer in Software Engineering in the Department of Computer Science, University of Oxford. My research revolves around using novel sensing techniques, low power processing and wireless communication to address challenging applications like animal tracking, underground communication and indoor localization. OrCID ID: 0000-0001-5716-3941
Additional affiliations
March 2012 - present
University of Oxford
Position
  • Undertracker: wildlife sensing in challenging environments
Description
  • This is a cross-disciplinary project to track and map the behaviours of animals using low power, custom designed, sensor modules. using a world-first underground positioning system in 3-D.
August 2008 - February 2012
University of Oxford
Position
  • WildSensing
Description
  • High impact project to monitor badger activity using RFID and other sensors
Education
January 2005 - December 2008
University of Cape Town
Field of study
  • Electrical Engineering
January 2000 - December 2004
University of Cape Town
Field of study
  • Electrical Engineering

Publications

Publications (182)
Preprint
Full-text available
Ultra-Wide-Band (UWB) ranging sensors have been widely adopted for robotic navigation thanks to their extremely high bandwidth and hence high resolution. However, off-the-shelf devices may output ranges with significant errors in cluttered, severe non-line-of-sight (NLOS) environments. Recently, neural networks have been actively studied to improve...
Preprint
Full-text available
Self-supervised deep learning methods for joint depth and ego-motion estimation can yield accurate trajectories without needing ground-truth training data. However, as they typically use photometric losses, their performance can degrade significantly when the assumptions these losses make (e.g. temporal illumination consistency, a static scene, and...
Article
Extracting distinctive, robust, and general 3D local features is essential to downstream tasks such as point cloud registration. However, existing methods either rely on noise-sensitive handcrafted features, or depend on rotation-variant neural architectures. It remains challenging to learn robust and general local feature descriptors for surface m...
Article
Deep convolutional neural networks have been leveraged to achieve huge improvements in video understanding and human activity recognition performance in the past decade. However, most existing methods focus on activities that have similar time scales, leaving the task of action recognition on multiscale human behaviors less explored. In this study,...
Preprint
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields or signed distance fields which can only model closed 3D surfaces, our approach is not restricted to any type of topology. Being different from the existing unsigned dist...
Preprint
Full-text available
Sampling is a key operation in point-cloud task and acts to increase computational efficiency and tractability by discarding redundant points. Universal sampling algorithms (e.g., Farthest Point Sampling) work without modification across different tasks, models, and datasets, but by their very nature are agnostic about the downstream task/model. As...
Preprint
Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification since the unstructured points make it hard or even impossible to efficiently and effectively trace point-wise correspondences. To capture 3D motions without explicitly tr...
Article
In the last decade, numerous supervised deep learning approaches have been proposed for visual inertial odometry (VIO) and depth map estimation, which require large amounts of labelled data. To overcome the data limitation, self-supervised learning has emerged as a promising alternative that exploits constraints such as geometric and photometric co...
Article
Full-text available
With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to facilitate research in 3D computer vision. However, existing datasets either cover relatively small areas or have limited semantic annotations. Fine-grained understanding o...
Preprint
With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to facilitate research in 3D computer vision. However, existing datasets either cover relatively small areas or have limited semantic annotations. Fine-grained understanding o...
Article
Full-text available
Direction finding and positioning systems based on RF signals are significantly impacted by multipath propagation, particularly in indoor environments. Existing algorithms (e.g MUSIC) perform poorly in resolving Angle of Arrival (AoA) in the presence of multipath or when operating in a weak signal regime. We note that digitally sampled RF frontends...
Article
Context: Synchronised acoustic recorders can be used as a non-invasive tool to detect and localise sounds of interest, including vocal wildlife and anthropogenic sounds. Due to the high cost of commercial synchronised recorders, acoustic localisation has typically been restricted to small or well funded surveys. Recently, low-cost acoustic recorder...
Preprint
Ubiquitous positioning for pedestrian in adverse environment has served a long standing challenge. Despite dramatic progress made by Deep Learning, multi-sensor deep odometry systems yet pose a high computational cost and suffer from cumulative drifting errors over time. Thanks to the increasing computational power of edge devices, we propose a nov...
Preprint
Full-text available
Camera localization is a fundamental and crucial problem for many robotic applications. In recent years, using deep-learning for camera-based localization has become a popular research direction. However, they lack robustness to large domain shifts, which can be caused by seasonal or illumination changes between training and testing data sets. Data...
Preprint
Direction finding and positioning systems based on RF signals are significantly impacted by multipath propagation, particularly in indoor environments. Existing algorithms (e.g MUSIC) perform poorly in resolving Angle of Arrival (AoA) in the presence of multipath or when operating in a weak signal regime. We note that digitally sampled RF frontends...
Article
Simultaneous localization and mapping (SLAM) system typically employs vision-based sensors to observe the surrounding environment. However, the performance of such systems highly depends on the ambient illumination conditions. In scenarios with adverse visibility or in the presence of airborne particulates (e.g., smoke, dust, etc.), alternative mod...
Article
Full-text available
In this paper, we present a novel end-to-end learning-based LiDAR sensor relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input. Compared to visual sensor-based relocalization, LiDAR sensors can provide rich and robust geometric information about a scene. However, point clouds of LiDAR...
Preprint
mmWave FMCW radar has attracted huge amount of research interest for human-centered applications in recent years, such as human gesture/activity recognition. Most existing pipelines are built upon conventional Discrete Fourier Transform (DFT) pre-processing and deep neural network classifier hybrid methods, with a majority of previous works focusin...
Article
Dynamical models estimate and predict the temporal evolution of physical systems. State-space models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations, e.g., the Kalman filter. Howev...
Preprint
Full-text available
We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight n...
Article
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight...
Preprint
Full-text available
We study the problem of labelling effort for semantic segmentation of large-scale 3D point clouds. Existing works usually rely on densely annotated point-level semantic labels to provide supervision for network training. However, in real-world scenarios that contain billions of points, it is impractical and extremely costly to manually annotate eve...
Article
Long-distance vocalization is a characteristic of African lion, Panthera leo, behaviour and is important for maintaining territorial boundaries as well as locating distant group members. Vocal signalling is, however, a flexible behaviour that involves varying costs and benefits depending on environmental, social and spatial factors. Motivated by pr...
Preprint
Relocalization is a fundamental task in the field of robotics and computer vision. There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images. However, learning-based methods have not yet been applied to the radar sensory data. In this work, we investigate how to exploit deep learning to pr...
Article
Localisation is an important part of many applications. Our motivating scenarios are short-term construction work and emergency rescue. These scenarios also require rapid setup and robustness to environmental conditions additional to localisation accuracy. These requirements preclude the use of many traditional high-performance methods, e.g. vision...
Preprint
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed, the derivation of a shared descriptor and joint keypoint detector that directly matches pixels and points remai...
Article
The key to offering personalised services in smart spaces is knowing where a particular person is with a high degree of accuracy. Visual tracking is one such solution, but concerns arise around the potential leakage of raw video information and many people are not comfortable accepting cameras in their homes or workplaces. We propose a human tracki...
Preprint
Full-text available
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neither general nor representative. In this paper, we introduce a new, yet con...
Preprint
Accurate motion capture of aerial robots in 3-D is a key enabler for autonomous operation in indoor environments such as warehouses or factories, as well as driving forward research in these areas. The most commonly used solutions at present are optical motion capture (e.g. VICON) and Ultrawideband (UWB), but these are costly and cumbersome to depl...
Preprint
Full-text available
Positional estimation is of great importance in the public safety sector. Emergency responders such as fire fighters, medical rescue teams, and the police will all benefit from a resilient positioning system to deliver safe and effective emergency services. Unfortunately, satellite navigation (e.g., GPS) offers limited coverage in indoor environmen...
Article
Previous research has shown that African lions (Panthera leo) have the ability to discriminate between conspecific vocalisations, but little is known about how individual identity is conveyed in the spectral structure of roars. Using acoustic – accelerometer biologgers that allow vocalisations to be reliably associated with individual identity, we...
Article
Robust indoor ego-motion estimation has attracted significant interest in the last decades due to the fastgrowing demand for location-based services in indoor environments. Among various solutions, frequency-modulated continuous-wave (FMCW) radar sensors in millimeter-wave (MMWave) spectrum are gaining more prominence due to their intrinsic advanta...
Preprint
Full-text available
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are either in relative small spatial scales or have limited semantic annotations due to the expensive cost of data...
Preprint
Full-text available
Deep learning based localization and mapping has recently attracted great attentions. Instead of crating hand-designed algorithms via exploiting physical models or geometry theory, deep learning based solutions provide an alternative to solve the problem in a data-driven way. Benefited from the ever-increasing amount of data and computational power...
Preprint
Robust and accurate trajectory estimation of mobile agents such as people and robots is a key requirement for providing spatial awareness to emerging capabilities such as augmented reality or autonomous interaction. Although currently dominated by vision based techniques e.g., visual-inertial odometry, these suffer from challenges with scene illumi...
Article
Calibration of the zero-velocity detection threshold is an essential prerequisite for zero-velocity-aided inertial navigation. However, the literature is lacking a self-contained calibration method, suitable for large-scale use in unprepared environments without map information or pre-deployed infrastructure. In this paper, the calibration of the z...
Article
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions t...
Article
Due to the sparse rewards and high degree of environmental variation, reinforcement learning approaches, such as deep deterministic policy gradient (DDPG), are plagued by issues of high variance when applied in complex real-world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an a...
Preprint
Recent learning-based research has achieved impressive results in the field of single-shot camera relocalization. However, how best to fuse multiple modalities, for example, image and depth, and how to deal with degraded or missing input are less well studied. In particular, we note that previous approaches towards deep fusion do not perform signif...
Preprint
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map. Compared to RGB image-based relocalization, LiDAR frames can provide rich and robust geometric information about a scene. However,...
Article
Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered by the...
Article
Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots. Exploiting inertial data for accurate and reliable pedestrian navigation supports is a key component for emerging Internet-of-Things applications and services. Recently, there has been a growing interest in applying...
Preprint
Full-text available
Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots. Exploiting inertial data for accurate and reliable pedestrian navigation supports is a key component for emerging Internet-of-Things applications and services. Recently, there has been a growing interest in applying...
Article
Full-text available
We study the problem of recovering an underlying 3D shape from a set of images. Existing learning based approaches usually resort to recurrent neural nets, e.g., GRU, or intuitive pooling operations, e.g., max/mean poolings, to fuse multiple deep features encoded from input images. However, GRU based approaches are unable to consistently estimate 3...
Preprint
Full-text available
Autonomous vehicles and mobile robotic systems are typically equipped with multiple sensors to provide redundancy. By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system states, e.g. locations and orientations. Although deep learning approaches for multimodal odometry est...
Preprint
Full-text available
Demand for smartwatches has taken off in recent years with new models which can run independently from smartphones and provide more useful features, becoming first-class mobile platforms. One can access online banking or even make payments on a smartwatch without a paired phone. This makes smartwatches more attractive and vulnerable to malicious at...
Preprint
Full-text available
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight...
Preprint
In the last decade, numerous supervised deep learning approaches requiring large amounts of labeled data have been proposed for visual-inertial odometry (VIO) and depth map estimation. To overcome the data limitation, self-supervised learning has emerged as a promising alternative, exploiting constraints such as geometric and photometric consistenc...
Article
Acoustic localisation technology has been widely tested and applied for passive acoustic monitoring and ecological research, however, hardware costs of commercially available devices limit scalability. Furthermore, few studies have explored its use with low-density arrays. We present a low-cost, custom-designed hardware and software system termed ‘...
Preprint
Full-text available
Single-chip Millimetre wave (mmWave) radar is emerging as an affordable, low-power range sensor in automotive and mobile applications. It can operate well in low visibility conditions, such as in the presence of smoke and debris, fitting the payloads of resource-constrained robotic platforms. Due to the nature of the sensor, however, distance measu...
Preprint
Full-text available
Calibration of the zero-velocity detection threshold is an essential prerequisite for zero-velocity-aided inertial navigation. However, the literature is lacking a self-contained calibration method, suitable for large-scale use in unprepared environments without map information or pre-deployed infrastructure. In this paper, the calibration of the z...
Preprint
Odometry is of key importance for localization in the absence of a map. There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images. These learning-based approaches have led to more accurate and robust VO systems. Howe...
Article
Magneto-inductive navigation is an inexpensive and easily deployable solution to many of today’s navigation problems. By utilizing very low frequency magnetic fields, magneto-inductive technology circumvents the problems with attenuation and multipath that often plague competing modalities. Using triaxial transmitter and receiver coils, it is possi...
Preprint
Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal imaging cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered...