Philip Birch
YOU?
Author Swipe
View article: Assisting annotators of wearable activity recognition datasets through automated sensor-based suggestions
Assisting annotators of wearable activity recognition datasets through automated sensor-based suggestions Open
Wearable Activity Recognition consists of recognizing actions of people from on-body sensor data using machine learning. Developing suitable machine learning models typically requires substantial amounts of annotated training data. Manuall…
View article: Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation
Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation Open
The scarcity of high-quality labeled data in sensor-based Human Activity Recognition (HAR) hinders model performance and limits generalization across real-world scenarios. Data augmentation is a key strategy to mitigate this issue by enhan…
View article: WIMUSim: simulating realistic variabilities in wearable IMUs for human activity recognition
WIMUSim: simulating realistic variabilities in wearable IMUs for human activity recognition Open
Introduction Physics simulation has emerged as a promising approach to generate virtual Inertial Measurement Unit (IMU) data, offering a solution to reduce the extensive cost and effort of real-world data collection. However, the fidelity …
View article: AI-driven UAV system for autonomous vehicle tracking and license plate recognition
AI-driven UAV system for autonomous vehicle tracking and license plate recognition Open
The integration of Artificial Intelligence (AI) with image processing and autonomous flight capabilities in Unmanned Aerial Vehicles (UAVs) represents a significant advancement in modern surveillance and tracking systems. This research exp…
View article: ETTrack: enhanced temporal motion predictor for multi-object tracking
ETTrack: enhanced temporal motion predictor for multi-object tracking Open
Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, traditional tracking-by-detection (TBD) methods, relying on the Kalman Filter, often work well in linear m…
View article: ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking
ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking Open
Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…
View article: Aerial Surveillance Leveraging Delaunay Triangulation and Multiple-UAV Imaging Systems
Aerial Surveillance Leveraging Delaunay Triangulation and Multiple-UAV Imaging Systems Open
In aerial surveillance systems, achieving optimal object detection precision is of paramount importance for effective monitoring and reconnaissance. This article presents a novel approach to enhance object detection accuracy through the in…
View article: RETRACTED: Airplane Detection via Deep Learning based on VGGs and SVMs
RETRACTED: Airplane Detection via Deep Learning based on VGGs and SVMs Open
The authors have requested that this preprint be removed from Research Square.
View article: OBSERVATIONS OF THE SUPERNOVA SN2023IXF
OBSERVATIONS OF THE SUPERNOVA SN2023IXF Open
Residing in a spiral arm of the Pinwheel Galaxy (M101), Supernova SN2023ixf was distinguished as one of the most intrinsically luminous objects visible in the 2023 summer night sky. Its astronomical significance is further highlighted by i…
View article: G-DMD: A Gated Recurrent Unit-Based Digital Elevation Model for Crop Height Measurement from Multispectral Drone Images
G-DMD: A Gated Recurrent Unit-Based Digital Elevation Model for Crop Height Measurement from Multispectral Drone Images Open
Crop height is a vital indicator of growth conditions. Traditional drone image-based crop height measurement methods primarily rely on calculating the difference between the Digital Elevation Model (DEM) and the Digital Terrain Model (DTM)…
View article: Ubiquitous Unmanned Aerial Vehicles (UAVs): A Comprehensive Review
Ubiquitous Unmanned Aerial Vehicles (UAVs): A Comprehensive Review Open
Unmanned aerial vehicles (UAVs) or drones have found applications in various fields including military operations, construction, parcel delivery, mapping, medical, search and rescue missions, exploration of hidden areas, monitoring power l…
View article: Hierarchical Feature Recovery for Robust Human Activity Recognition in Body Sensor Networks
Hierarchical Feature Recovery for Robust Human Activity Recognition in Body Sensor Networks Open
With the advances in Body Sensor Networks (BSNs) and textile-integrated sensing, more sensor data becomes available from which human activities are recognised. However, some sensors may become unavailable unexpectedly in practice. Previous…
View article: Design considerations for optical deep learning networks
Design considerations for optical deep learning networks Open
Performing deep learning in the optical domain is attractive due to the very low electrical power requirements when compared to running networks on a GPU. Since a single positive lens can perform a Fourier transform, correlation operations…
View article: Transportation mode recognition fusing wearable motion, sound and vision sensors
Transportation mode recognition fusing wearable motion, sound and vision sensors Open
We present the first work that investigates the potential of improving the performance of transportation mode recognition through fusing multimodal data from wearable sensors: motion, sound and vision. We first train three independent deep…
View article: Benchmarking deep classifiers on mobile devices for vision-based transportation recognition
Benchmarking deep classifiers on mobile devices for vision-based transportation recognition Open
Vision-based human activity recognition can provide rich contextual information but has traditionally been computationally prohibitive. We present a characterisation of five convolutional neural networks (DenseNet169, MobileNet, ResNet50, …
View article: Enhanced target recognition employing spatial correlation filters and affine scale invariant feature transform
Enhanced target recognition employing spatial correlation filters and affine scale invariant feature transform Open
A spatial domain optimal trade-off Maximum Average Correlation Height (SPOT-MACH) filter has been shown to have advantages over frequency domain implementations of the Optimal Trade-Off Maximum Average Correlation Height (OR-MACH) filter a…
View article: No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain
No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain Open
Considering the relatively poor robustness of quality scores for different types of distortion and the lack of mechanism for determining distortion types, a no-reference image quality assessment (NR-IQA) method based on the AdaBoost BP Neu…
View article: Real-time unmanned aerial vehicle tracking of fast moving small target on ground
Real-time unmanned aerial vehicle tracking of fast moving small target on ground Open
To solve the problems of occlusion and fast motion of small targets in unmanned aerial vehicle target tracking, an adaptive algorithm that fuses the improved color histogram tracking response and the correlation filter tracking response ba…
View article: A simplification of the Shor quantum factorization algorithm employing a quantum Hadamard transform
A simplification of the Shor quantum factorization algorithm employing a quantum Hadamard transform Open
The Shor quantum factorization algorithm allows the factorization or large integers in logarithmic squared time whereas classical algorithms require an exponential time increase with the bit length of the number to be factored. The hardwar…
View article: Obstacle detection system based on colour segmentation using monocular vision for an unmanned ground vehicle
Obstacle detection system based on colour segmentation using monocular vision for an unmanned ground vehicle Open
An obstacle detection algorithm is introduced for aiding the navigation of unmanned ground vehicles (UGV). Coloured obstacles are placed randomly in an indoor environment. The coloured obstacles are detected, analysed and processed using a…
View article: High power lasers - systems and weapons
High power lasers - systems and weapons Open
The presentation covers some history on lasers, then goes on to describe the the USA Airborne Laser Testbed and its Chemical Oxygen Iodine Laser (COIL). The significance of laser modes for beam propagation is explained. Fibre lasers and th…
View article: Classical and Quantum Optical Computing
Classical and Quantum Optical Computing Open
The quantum Fourier transform (QFT);Similarities and differences of coherent optical FFT to the QFT. Grover’s search algorithm implemented with a coherent optical correlator. Quantum algorithms requiring bit entanglement -Shor’s algorithm …
View article: Gyrotron power beams for defence applications
Gyrotron power beams for defence applications Open
Gyrotrons are capable of producing Megawatt power radiation at millimeter and sub-millimeter wavelengths , they are very efficient, circa 60% and can be made to chirp over wide frequency ranges. Gryratrons offer a very effective means of d…
View article: A low cost high resolution scanning aperture fluorescent microscope
A low cost high resolution scanning aperture fluorescent microscope Open
Fluorescent microscopy is one of the most widely used tools in the life-sciences. The ability to tag molecules of interest and then localise their positions within two or even three dimensions provides a great deal of information about the…
View article: A wide field time resolved fluorescent lifetime imaging microscope
A wide field time resolved fluorescent lifetime imaging microscope Open
Fluorescence lifetime imaging microscopy (FLIM) is a tool that has become of important use to many biologists and medical researchers. It allows for the imaging of fluorescent markers within cells and as well their decay lifetime informati…
View article: A capacitive division imaging readout detector for light‐sheet FLIM
A capacitive division imaging readout detector for light‐sheet FLIM Open
Measuring the spatial position and lifetime distribution of the fluorophores enables users to discern vital information about the chemical environment within a biological system. It however, remains challenging since the photon count is us…