Fiachra Collins

Fiachra Collins

Auto-generated profile, based on publicly available information

Fiachra Collins

Valeo Vision Systems, Tuam, Ireland

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 February 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
AMAnam Manzoor
Anam Manzoor
RMReenu Mohandas
Reenu Mohandas
ASAnthony G. Scanlan
Anthony G. Scanlan
EGEoin Martino Grua
Eoin Martino Grua
FCFiachra Collins
Fiachra Collins
CECiaran Eising
Ciaran Eising
The automotive industry has made significant strides in enhancing road safety and enabling automated driving features through advanced computer vision techniques. This is particularly true for short-range vehicle automation, where non-linear fisheye cameras are commonly used. However, these cameras are challenged by optical distortions, known as fisheye geometric distortions, which lead to object deformation within the image and significant pixel distortion, particularly at the image periphery. Based on the observation that fisheye and spherical images exhibit at least superficially similar geometric characteristics, we investigate the applicability of spherical models—including Spherical Convolutional Neural Networks (CNNs) and Spherical Vision Transformers (ViTs)—to fisheye images, even though fisheye images are not truly spherical. We perform our comparison using fisheye datasets—Woodscape, SynWoodscape, and SynCityscapes in autonomous driving scenarios, with a specific focus on the ability of spherical methods (Spherical CNNs and ViTs) to manage fisheye distortions and compared them against traditional non-spherical methods. Our findings indicate that spherical methods effectively address fisheye distortions without needing extra data augmentations. This results in better mean Intersection over Union (mIoU) scores, pixel accuracy, and better surround-view perception than other modern approaches for fisheye semantic segmentation. However, we also find that spherical methods have a greater tendency to overfit smaller datasets compared with non-spherical models. These advancements highlight how non-linear camera images can take advantage of spherical approximations through spherical models in autonomous driving.

8 July 2025 in IEEE Sensors Journal
Verified
Journal Article
Open access
EDEthan Delaney
Ethan Delaney
TBTim Brophy
Tim Brophy
EWEnda Ward
Enda Ward
FCFiachra Collins
Fiachra Collins
EJEdward Jones
Edward Jones
MGMartin Glavin
Martin Glavin
Event-based vision sensors have a higher temporal resolution, a wider dynamic range, and a lower latency than conventional frame-based cameras. For these reasons, event-based sensors are being considered for advanced driver assistance systems applications. If these sensors are to be used for automotive sensing and perception, their performance under adverse conditions, such as rain and fog, must be characterized to ensure reliable performance. This study presents a suite of tests using an event-based sensor under controlled conditions across a range of rainfall rates, ambient light levels, fog visibility levels and distances from the targets. To evaluate the performance of these sensors, the average event rate (number of events per second) was compared with rainfall rates and visibility. The results indicated that the diameter of the raindrops had a larger effect on the number of events than the rainfall rate. Furthermore, the investigation revealed that, by carefully configuring the camera settings, it is possible to mitigate the effects of rain on the sensor output.

3 April 2026 in IEEE Open Journal of Intelligent Transportation Systems
Verified
Journal Article
Open access
JLJiarong Li
Jiarong Li
ISImad Ali Shah
Imad Ali Shah
DGDiarmaid Geever
Diarmaid Geever
FCFiachra Collins
Fiachra Collins
EWEnda Ward
Enda Ward
BDBrian Deegan
Brian Deegan
Protecting Vulnerable Road Users (VRU) remains a key challenge in automotive perception, particularly when RGB imagery exhibits metameric ambiguity under challenging illumination. Hyperspectral Imaging (HSI) can provide material-dependent cues beyond RGB, including in the Near-Infrared (NIR), but its high dimensionality limits deployment in automotive systems. This paper proposes a compact band-selection pipeline that combines joint mutual information maximization with a patch-based contrast signal-to-noise ratio criterion to select a practical 3-band HSI subset for VRU perception. On the Hyperspectral City V2 dataset, the proposed pipeline selects a VIS-NIR triplet at 521 nm, 753 nm, and 903 nm. We evaluate VRU-Road separability under higher-illumination scenes and an objectively defined low-illumination subset using per-scene distributions, and bootstrap confidence intervals. Results are reported in both a metric-ready representation (for direct comparison with co-registered RGB) and a sensor-native representation. Downstream utility is further evaluated by semantic segmentation using U-Net, DeepLabV3+, and PSPNet over three random seeds. The selected triplet improves VRU-Road separability on key criteria, remains robust under low illumination, and yields competitive downstream performance among the evaluated HSI-derived inputs. Overall, the proposed approach reduces spectral dimensionality from 128 bands to 3 (97.7% reduction) and supports compact multispectral sensing as a practical complement to RGB for robust VRU perception.

17 March 2026 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
MUMuhammad Usama
Muhammad Usama
ISImad Ali Shah
Imad Ali Shah
Roshan GeorgeRoshan George
Roshan George
EWEnda Ward
Enda Ward
FCFiachra Collins
Fiachra Collins
EJEdward Jones
Edward Jones
Object Detection significantly benefits from combining complementary spectral modalities; however, its performance suffers greatly from misregistration between sensor streams due to spatial misalignments, viewpoint differences between sensors, and inconsistent annotations, a common feature of multi-modal datasets used in object detection system development. In this work, we address the critical challenge of modality misregistration. We propose a comprehensive alignment framework based on object-aware local homography estimation, anchored on Long-Wave Infrared Radiation (LWIR) annotations, to generate a spatially aligned training dataset for improved model development. For our experiments, we utilise the Multispectral Object Detection (MOD) dataset, which includes RGB, Short-Wave Infrared Radiation (SWIR), Mid-Wave Infrared Radiation (MWIR), and Long-Wave Infrared Radiation (LWIR) imagery. The proposed alignment pipeline ensures a consistent field of view, resolution normalization, and accurate cross-modality annotation projection. To quantify the impact of alignment, we benchmark four state-of-the-art fusion architectures (DEYOLO, TarDAL, CMTFusion, and U2Fusion) on both the original and the aligned versions of the MOD dataset. Experimental results demonstrate significant improvements of 10 to 30 percentage points in mAP@0.5 after training on the aligned MOD data, with enhanced localization accuracy and reduced false detections. We further verified the generalizability of the proposed alignment framework on a different dataset (FLIR ADAS), observing 3.54 percentage points improvement in mAP@0.5 after training on the aligned RGB-LWIR image pairs. U2Fusion emerged as the architecture most tolerant to misregistration in initial experiments, and this architecture is used to conduct a further sensitivity analysis to evaluate model robustness against real-world misalignments, in a controlled way. The results of this sensitivity analysis could be useful for designers of practical systems, where small misalignment errors between image modalities commonly occur.

5 November 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
NTNikos Theodoridis
Nikos Theodoridis
TBTim Brophy
Tim Brophy
RMReenu Mohandas
Reenu Mohandas
GSGanesh Sistu
Ganesh Sistu
FCFiachra Collins
Fiachra Collins
CECiaran Eising
Ciaran Eising
Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on tasks that require both visual and textual understanding. Their strong generalisation abilities make them a promising component for automated driving systems, which must handle unexpected corner cases. However, to be trusted in such safety-critical applications, a model must first possess a reliable perception system. Since critical objects and agents in traffic scenes are often at a distance, we require systems that are not “shortsighted,” i.e., systems with strong perception capabilities at both close (up to 20 meters) and long (30+ meters) range. With this in mind, we introduce Distance-Annotated Traffic Perception Question Answering (DTPQA), the first Visual Question Answering (VQA) benchmark focused solely on perception-based questions in traffic scenes, enriched with distance annotations. By excluding questions that require reasoning, we ensure that model performance reflects perception capabilities alone. Since automated driving hardware has limited processing power and cannot support large VLMs, our study centers on smaller VLMs. We evaluate several state-of-the-art (SOTA) small VLMs on DTPQA and show that, despite the simplicity of the questions, these models significantly underperform compared to humans (∼60% average accuracy for the best-performing small VLM versus ∼85% human performance). However, the human sample size was relatively small, which imposes statistical limitations. We also identify specific perception tasks, such as distinguishing left from right, that remain particularly challenging. We hope our findings will encourage further research into improving the perception capabilities of small VLMs in traffic scenarios, making them more suitable for automated driving applications.

4 December 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
DJDaniel Jakab
Daniel Jakab
JVJoel Herrera Vázquez
Joel Herrera Vázquez
JBJulian Barthel
Julian Barthel
JHJan Honsbrok
Jan Honsbrok
BDBrian Deegan
Brian Deegan
ABAlexander Braun
Alexander Braun
Automotive datasets are typically captured using a small number of cameras, with each camera fixed at a single focus setting. In practice, however, camera modules exhibit unit-to-unit variability in their effective focus due to manufacturing tolerances. Since perception models are usually trained on images captured at one nominal focus position, real-world deviations in focus can introduce a domain mismatch that degrades perception performance. We demonstrate this effect by simulating two different optical systems on synthetic and real images with fields of view of $100^\circ$ and $150^\circ$. For all simulations, we utilise the Python-based ray-tracing library KrakenOS, an open-source optical simulation tool. By assigning each optical system to a suitable dataset, we degrade the held-out test data of four public automotive datasets: KITTI, Virtual KITTI 2.0, Woodscape, and Parallel Domain Woodscape. We evaluate the impact of applying optical defocus on 2D Object Detection models with the popular OpenMMLab toolkit for MMDetection and the YOLOv11 architecture. For each optical system, we simulate 9 defocus settings on the test data, representative of the production tolerance range for camera defocus. The results show that object detection performance degrades as the magnitude of defocus increases. Align DETR, despite having the second fewest parameters, establishes the strongest baseline and remains robust under modest defocus ($|\Delta z|\leq 20\,\mu \mathrm{m}$) across all datasets. However, at extreme defocus ($\pm 100 \,\mu \mathrm{m}$), YOLOv11x surpasses Align DETR by 1.5%–12.2% mAP$_{50:95}$ across all datasets. Finally, we show that defocus-augmented training of Align DETR, recovers the performance drop caused by the defocus in the held-out test data.