Akila Pemasiri

Zi Huang, Akila Pemasiri, Simon Denman et al.

Radio signal recognition is a crucial task in both civilian and military applications, as accurate and timely identification of unknown signals is an essential part of spectrum management and electronic warfare. The majority of research in this field has focused on applying deep learning for modulation classification, leaving the task of signal characterisation as an understudied area. This paper addresses this gap by presenting an approach for tackling radar signal classification and characterisation as a multi-task learning (MTL) problem. We propose the IQ Signal Transformer (IQST) among several reference architectures that allow for simultaneous optimisation of multiple regression and classification tasks. We demonstrate the performance of our proposed MTL model on a synthetic radar dataset, while also providing a first-of-its-kind benchmark for radar signal characterisation.

Huy Nguyen, Kien Nguyen, Akila Pemasiri et al.

We introduce AG-VPReID, a new large-scale dataset for aerial-ground video-based person re-identification (ReID) that comprises 6,632 subjects, 32,321 tracklets and over 9.6 million frames captured by drones (altitudes ranging from 15-120m), CCTV, and wearable cameras. This dataset offers a real-world benchmark for evaluating the robustness to significant viewpoint changes, scale variations, and resolution differences in cross-platform aerial-ground settings. In addition, to address these challenges, we propose AG-VPReID-Net, an end-to-end framework composed of three complementary streams: (1) an Adapted Temporal-Spatial Stream addressing motion pattern inconsistencies and facilitating temporal feature learning, (2) a Normalized Appearance Stream leveraging physics-informed techniques to tackle resolution and appearance changes, and (3) a Multi-Scale Attention Stream handling scale variations across drone altitudes. We integrate visual-semantic cues from all streams to form a robust, viewpoint-invariant whole-body representation. Extensive experiments demonstrate that AG-VPReID-Net outperforms state-of-the-art approaches on both our new dataset and existing video-based ReID benchmarks, showcasing its effectiveness and generalizability. Nevertheless, the performance gap observed on AG-VPReID across all methods underscores the dataset's challenging nature. The dataset, code and trained models are available at https://github.com/agvpreid25/AG-VPReID-Net.

Huy Nguyen, Kien Nguyen, Akila Pemasiri et al.

Person re-identification (Re-ID) across visible and infrared modalities is crucial for 24-hour surveillance systems, but existing datasets primarily focus on ground-level perspectives. While ground-based IR systems offer nighttime capabilities, they suffer from occlusions, limited coverage, and vulnerability to obstructions--problems that aerial perspectives uniquely solve. To address these limitations, we introduce AG-VPReID.VIR, the first aerial-ground cross-modality video-based person Re-ID dataset. This dataset captures 1,837 identities across 4,861 tracklets (124,855 frames) using both UAV-mounted and fixed CCTV cameras in RGB and infrared modalities. AG-VPReID.VIR presents unique challenges including cross-viewpoint variations, modality discrepancies, and temporal dynamics. Additionally, we propose TCC-VPReID, a novel three-stream architecture designed to address the joint challenges of cross-platform and cross-modality person Re-ID. Our approach bridges the domain gaps between aerial-ground perspectives and RGB-IR modalities, through style-robust feature learning, memory-based cross-view adaptation, and intermediary-guided temporal modeling. Experiments show that AG-VPReID.VIR presents distinctive challenges compared to existing datasets, with our TCC-VPReID framework achieving significant performance gains across multiple evaluation protocols. Dataset and code are available at https://github.com/agvpreid25/AG-VPReID.VIR.

Akila Pemasiri, Ethan Goan, Glen Lichtwark et al.

This paper presents a biomechanically interpretable framework for gait analysis using 3D human reconstruction from video data. Unlike conventional keypoint based approaches, the proposed method extracts biomechanically meaningful markers analogous to motion capture systems and integrates them within OpenSim for joint kinematic estimation. To evaluate performance, both spatiotemporal and kinematic gait parameters were analysed against reference marker-based data. Results indicate strong agreement with marker-based measurements, with considerable improvements when compared with pose-estimation methods alone. The proposed framework offers a scalable, markerless, and interpretable approach for accurate gait assessment, supporting broader clinical and real world deployment of vision based biomechanics

Zi Huang, Akila Pemasiri, Simon Denman et al.

Radio signal recognition is a crucial function in electronic warfare. Precise identification and localisation of radar pulse activities are required by electronic warfare systems to produce effective countermeasures. Despite the importance of these tasks, deep learning-based radar pulse activity recognition methods have remained largely underexplored. While deep learning for radar modulation recognition has been explored previously, classification tasks are generally limited to short and non-interleaved IQ signals, limiting their applicability to military applications. To address this gap, we introduce an end-to-end multi-stage learning approach to detect and localise pulse activities of interleaved radar signals across an extended time horizon. We propose a simple, yet highly effective multi-stage architecture for incrementally predicting fine-grained segmentation masks that localise radar pulse activities across multiple channels. We demonstrate the performance of our approach against several reference models on a novel radar dataset, while also providing a first-of-its-kind benchmark for radar pulse activity segmentation.

Zi Huang, Simon Denman, Akila Pemasiri et al.

Radar signal recognition (RSR) plays a pivotal role in electronic warfare (EW), as accurately classifying radar signals is critical for informing decision-making. Recent advances in deep learning have shown significant potential in improving RSR in domains with ample annotated data. However, these methods fall short in EW scenarios where annotated radio frequency (RF) data are scarce or impractical to obtain. To address these challenges, we introduce a self-supervised learning (SSL) method which utilises masked signal modelling and RF domain adaption to perform few-shot RSR and enhance performance in environments with limited RF samples and annotations. We propose a two-step approach, first pre-training masked autoencoders (MAE) on baseband in-phase and quadrature (I/Q) signals from diverse RF domains, and then transferring the learned representations to the radar domain, where annotated data are scarce. Empirical results show that our lightweight self-supervised ResNet1D model with domain adaptation achieves up to a 17.5% improvement in 1-shot classification accuracy when pre-trained on in-domain signals (i.e., radar signals) and up to a 16.31% improvement when pre-trained on out-of-domain signals (i.e., comm signals), compared to its baseline without using SSL. We also present reference results for several MAE designs and pre-training strategies, establishing a new benchmark for few-shot radar signal classification.

Thisun Dayarathna, Thamidu Muthukumarana, Yasiru Rathnayaka et al.

Recently, in-bed human pose estimation has attracted the interest of researchers due to its relevance to a wide range of healthcare applications. Compared to the general problem of human pose estimation, in-bed pose estimation has several inherent challenges, the most prominent being frequent and severe occlusions caused by bedding. In this paper we explore the effective use of images from multiple non-visual and privacy-preserving modalities such as depth, long-wave infrared (LWIR) and pressure maps for the task of in-bed pose estimation in two settings. First, we explore the effective fusion of information from different imaging modalities for better pose estimation. Secondly, we propose a framework that can estimate in-bed pose estimation when visible images are unavailable, and demonstrate the applicability of fusion methods to scenarios where only LWIR images are available. We analyze and demonstrate the effect of fusing features from multiple modalities. For this purpose, we consider four different techniques: 1) Addition, 2) Concatenation, 3) Fusion via learned modal weights, and 4) End-to-end fully trainable approach; with a state-of-the-art pose estimation model. We also evaluate the effect of reconstructing a data-rich modality (i.e., visible modality) from a privacy-preserving modality with data scarcity (i.e., long-wavelength infrared) for in-bed human pose estimation. For reconstruction, we use a conditional generative adversarial network. We conduct ablative studies across different design decisions of our framework. This includes selecting features with different levels of granularity, using different fusion techniques, and varying model parameters. Through extensive evaluations, we demonstrate that our method produces on par or better results compared to the state-of-the-art.

Akila Pemasiri, Kien Nguyen Thanh, Sridha Sridharan et al.

This work addresses hand mesh recovery from a single RGB image. In contrast to most of the existing approaches where the parametric hand models are employed as the prior, we show that the hand mesh can be learned directly from the input image. We propose a new type of GAN called Im2Mesh GAN to learn the mesh through end-to-end adversarial training. By interpreting the mesh as a graph, our model is able to capture the topological relationship among the mesh vertices. We also introduce a 3D surface descriptor into the GAN architecture to further capture the 3D features associated. We experiment two approaches where one can reap the benefits of coupled groundtruth data availability of images and the corresponding meshes, while the other combats the more challenging problem of mesh estimations without the corresponding groundtruth. Through extensive evaluations we demonstrate that the proposed method outperforms the state-of-the-art.

Akila Pemasiri, Kien Nguyen, Sridha Sridhara et al.

Establishing semantic correspondence across images when the objects in the images have undergone complex deformations remains a challenging task in the field of computer vision. In this paper, we propose a hierarchical method to tackle this problem by first semantically targeting the foreground objects to localize the search space and then looking deeply into multiple levels of the feature representation to search for point-level correspondence. In contrast to existing approaches, which typically penalize large discrepancies, our approach allows for significant displacements, with the aim to accommodate large deformations of the objects in scene. Localizing the search space by semantically matching object-level correspondence, our method robustly handles large deformations of objects. Representing the target region by concatenated hypercolumn features which take into account the hierarchical levels of the surrounding context, helps to clear the ambiguity to further improve the accuracy. By conducting multiple experiments across scenes with non-rigid objects, we validate the proposed approach, and show that it outperforms the state of the art methods for semantic correspondence establishment.

Akila Pemasiri, Kien Nguyen, Sridha Sridharan et al.

Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch matching. We propose a new paradigm which encodes image patch details by encoding the patch and subsequently using this sparse representation as input to a neural network to compare the patches. As sparse coding is based on a generative model of natural image patches, it can represent the patch in terms of the fundamental visual components from which it has been composed of, leading to similar sparse codes for patches which are built from similar components. Once the sparse coded features are extracted, we employ a fully-connected neural network, which captures the non-linear relationships between features, for comparison. We have evaluated our approach using the Liberty and Notredame subsets of the popular UBC patch dataset and set a new benchmark outperforming all state-of-the-art patch matching techniques for these datasets.