arXiv subjects

Ondrej Hlinka

Publications and source records attributed to Ondrej Hlinka.

9 recordsLinked to original sources

arXiv2026

The Rapid ASKAP Continuum Survey VII: Spectra and Polarisation In Cutouts of Extragalactic Sources (SPICE-RACS) Second Data Release -- Unveiling the Magnetised Sky

We present the second data release (DR2) of Spectra and Polarisation in Cutouts of Extragalactic sources from RACS (SPICE-RACS). SPICE-RACS DR2 is derived from the third low-band epoch of the Rapid ASKAP Continuum Survey (RACS-low3) and covers the entire sky from the South celestial pole up to a declination of $+49^\circ$; approximately 87.5% of the celestial sphere. We produce 'cutout' spectral cubes in Stokes $I$, $Q$, $U$ around 4 million radio sources and extract spectra towards 5 million radio components. Across our observed band of 799.5--1087.5 MHz we find an $rms$ noise of $\sim200μ\mathrm{Jy/PSF}$, an angular resolution of $\sim15''$, and residual wide-field instrumental polarisation on the order of 0.1%. After de-duplication, our polarisation catalogue contains the detection of $2.5\times10^5$ ($3.4\times10^5$) Faraday rotation measures (RM) for components with a linearly polarised signal above $8σ$ ($6σ$). This places SPICE-RACS DR2 as the largest single RM catalogue ever produced by nearly an order of magnitude; the number of RMs in our catalogue alone is $\sim5$ times larger than every previous RM catalogue combined. Our resulting RM grid has an areal density of $6.7^{+1.8}_{-1.7}\mathrm{deg}^{-2}$, providing an effective 'resolution' of $\sim23'$, and reveals striking features across the sky. The broad-band RMs have a median uncertainty of $\sim2\ \mathrm{rad\ m}^{-2}$, and include complexity metrics and information from the time domain. The breadth and quality of the SPICE-RACS DR2 dataset will enable a new generation of RM science. Further, SPICE-RACS will provide an ideal reference for forthcoming deep polarisation surveys such as the ASKAP POSSUM survey. All of our data products are publicly available on the CSIRO Data Access Portal (DAP) and the CSIRO ASKAP Science Data Archive (CASDA).

astro-ph.GA↗

arXiv2026

Perspective-aware fusion of incomplete depth maps and surface normals for accurate 3D reconstruction

We address the problem of reconstructing 3D surfaces from depth and surface normal maps acquired by a sensor system based on a single perspective camera. Depth and normal maps can be obtained through techniques such as structured-light scanning and photometric stereo, respectively. We propose a perspective-aware log-depth fusion approach that extends existing orthographic gradient-based depth-normals fusion methods by explicitly accounting for perspective projection, leading to metrically accurate 3D reconstructions. Additionally, the method handles missing depth measurements by leveraging available surface normal information to inpaint gaps. Experiments on the DiLiGenT-MV data set demonstrate the effectiveness of our approach and highlight the importance of perspective-aware depth-normals fusion.

cs.CV↗

arXiv2025

Tackling fluffy clouds: robust field boundary delineation across global agricultural landscapes with Sentinel-1 and Sentinel-2 Time Series

Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing methodologies often face significant challenges, particularly in their reliance on extensive manual efforts for cloud-free data curation and limited adaptability to diverse global conditions. In this paper, we introduce PTAViT3D, a deep learning architecture specifically designed for processing three-dimensional time series of satellite imagery from either Sentinel-1 (S1) or Sentinel-2 (S2). Additionally, we present PTAViT3D-CA, an extension of the PTAViT3D model incorporating cross-attention mechanisms to fuse S1 and S2 datasets, enhancing robustness in cloud-contaminated scenarios. The proposed methods leverage spatio-temporal correlations through a memory-efficient 3D Vision Transformer architecture, facilitating accurate boundary delineation directly from raw, cloud-contaminated imagery. We comprehensively validate our models through extensive testing on various datasets, including Australia's ePaddocks - CSIRO's national agricultural field boundary product - alongside public benchmarks Fields-of-the-World, PASTIS, and AI4SmallFarms. Our results consistently demonstrate state-of-the-art performance, highlighting excellent global transferability and robustness. Crucially, our approach significantly simplifies data preparation workflows by reliably processing cloud-affected imagery, thereby offering strong adaptability across diverse agricultural environments. Our code and models are publicly available at https://github.com/feevos/tfcl.

cs.CV↗

arXiv2023

SSG2: A new modelling paradigm for semantic segmentation

State-of-the-art models in semantic segmentation primarily operate on single, static images, generating corresponding segmentation masks. This one-shot approach leaves little room for error correction, as the models lack the capability to integrate multiple observations for enhanced accuracy. Inspired by work on semantic change detection, we address this limitation by introducing a methodology that leverages a sequence of observables generated for each static input image. By adding this "temporal" dimension, we exploit strong signal correlations between successive observations in the sequence to reduce error rates. Our framework, dubbed SSG2 (Semantic Segmentation Generation 2), employs a dual-encoder, single-decoder base network augmented with a sequence model. The base model learns to predict the set intersection, union, and difference of labels from dual-input images. Given a fixed target input image and a set of support images, the sequence model builds the predicted mask of the target by synthesizing the partial views from each sequence step and filtering out noise. We evaluate SSG2 across three diverse datasets: UrbanMonitor, featuring orthoimage tiles from Darwin, Australia with five spectral bands and 0.2m spatial resolution; ISPRS Potsdam, which includes true orthophoto images with multiple spectral bands and a 5cm ground sampling distance; and ISIC2018, a medical dataset focused on skin lesion segmentation, particularly melanoma. The SSG2 model demonstrates rapid convergence within the first few tens of epochs and significantly outperforms UNet-like baseline models with the same number of gradient updates. However, the addition of the temporal dimension results in an increased memory footprint. While this could be a limitation, it is offset by the advent of higher-memory GPUs and coding optimizations.

cs.CV↗

arXiv2015

Distributed Localization and Tracking of Mobile Networks Including Noncooperative Objects - Extended Version

We propose a Bayesian method for distributed sequential localization of mobile networks composed of both cooperative agents and noncooperative objects. Our method provides a consistent combination of cooperative self-localization (CS) and distributed tracking (DT). Multiple mobile agents and objects are localized and tracked using measurements between agents and objects and between agents. For a distributed operation and low complexity, we combine particle-based belief propagation with a consensus or gossip scheme. High localization accuracy is achieved through a probabilistic information transfer between the CS and DT parts of the underlying factor graph. Simulation results demonstrate significant improvements in both agent self-localization and object localization performance compared to separate CS and DT, and very good scaling properties with respect to the numbers of agents and objects.

cs.IT↗

arXiv2013

Sigma Point Belief Propagation

The sigma point (SP) filter, also known as unscented Kalman filter, is an attractive alternative to the extended Kalman filter and the particle filter. Here, we extend the SP filter to nonsequential Bayesian inference corresponding to loopy factor graphs. We propose sigma point belief propagation (SPBP) as a low-complexity approximation of the belief propagation (BP) message passing scheme. SPBP achieves approximate marginalizations of posterior distributions corresponding to (generally) loopy factor graphs. It is well suited for decentralized inference because of its low communication requirements. For a decentralized, dynamic sensor localization problem, we demonstrate that SPBP can outperform nonparametric (particle-based) BP while requiring significantly less computations and communications.

cs.AI↗

arXiv2012

Simultaneous Distributed Sensor Self-Localization and Target Tracking Using Belief Propagation and Likelihood Consensus

We introduce the framework of cooperative simultaneous localization and tracking (CoSLAT), which provides a consistent combination of cooperative self-localization (CSL) and distributed target tracking (DTT) in sensor networks without a fusion center. CoSLAT extends simultaneous localization and tracking (SLAT) in that it uses also intersensor measurements. Starting from a factor graph formulation of the CoSLAT problem, we develop a particle-based, distributed message passing algorithm for CoSLAT that combines nonparametric belief propagation with the likelihood consensus scheme. The proposed CoSLAT algorithm improves on state-of-the-art CSL and DTT algorithms by exchanging probabilistic information between CSL and DTT. Simulation results demonstrate substantial improvements in both self-localization and tracking performance.

cs.NI↗

arXiv2012

Likelihood Consensus and Its Application to Distributed Particle Filtering

We consider distributed state estimation in a wireless sensor network without a fusion center. Each sensor performs a global estimation task---based on the past and current measurements of all sensors---using only local processing and local communications with its neighbors. In this estimation task, the joint (all-sensors) likelihood function (JLF) plays a central role as it epitomizes the measurements of all sensors. We propose a distributed method for computing, at each sensor, an approximation of the JLF by means of consensus algorithms. This "likelihood consensus" method is applicable if the local likelihood functions of the various sensors (viewed as conditional probability density functions of the local measurements) belong to the exponential family of distributions. We then use the likelihood consensus method to implement a distributed particle filter and a distributed Gaussian particle filter. Each sensor runs a local particle filter, or a local Gaussian particle filter, that computes a global state estimate. The weight update in each local (Gaussian) particle filter employs the JLF, which is obtained through the likelihood consensus scheme. For the distributed Gaussian particle filter, the number of particles can be significantly reduced by means of an additional consensus scheme. Simulation results are presented to assess the performance of the proposed distributed particle filters for a multiple target tracking problem.

stat.AP↗

arXiv2011

Likelihood Consensus-Based Distributed Particle Filtering with Distributed Proposal Density Adaptation

We present a consensus-based distributed particle filter (PF) for wireless sensor networks. Each sensor runs a local PF to compute a global state estimate that takes into account the measurements of all sensors. The local PFs use the joint (all-sensors) likelihood function, which is calculated in a distributed way by a novel generalization of the likelihood consensus scheme. A performance improvement (or a reduction of the required number of particles) is achieved by a novel distributed, consensus-based method for adapting the proposal densities of the local PFs. The performance of the proposed distributed PF is demonstrated for a target tracking problem.

stat.AP↗