Nikola Lopac
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nikola Lopac has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Jonatan Lerga
Department of Computer Engineering, Faculty of Engineering, University of Rijeka, 51000 Rijeka, Croatia
7 shared publications Jonatan Lerga
6 shared publications- Irena Jurdana
Sveučilište u Rijeci, Pomorski fakultet, Rijeka, Hrvatska
5 shared publications Irena Jurdana
University of Rijeka,Faculty of Maritime Studies,Rijeka,Croatia,51000
4 shared publicationsKarlo Severinski
3 shared publications- Nobukazu Wakabayashi
Graduate School of Maritime Sciences, Kobe University, Kobe 658-0022, Japan
3 shared publications
Latest Publications
- 19 August 2026
- Published by Springer Nature in Journal of Marine Science and Technology
- p. 1-33
Forecasting maritime vessel trajectories: a comprehensive review of data-driven approaches
- 19 August 2026
- Published by Springer Nature in Journal of Marine Science and Technology
- p. 1-33
Forecasting maritime vessel trajectories: a comprehensive review of data-driven approaches
- Open Access
- 3 August 2026
- Published by MDPI AG in Technologies
- Vol. 14 (8) , 482
YOLO-Driven Vessel Detection and Multi-Object Tracking in Fixed-Camera Marina Environments
Vessel detection and multi-object tracking (MOT) in marinas remain challenging because of occlusions, small targets, cluttered backgrounds, and changing illumination. This paper presents a controlled, feasibility-focused comparative evaluation of YOLO-driven vessel detection and tracking in a fixed-camera marina environment, comparing YOLOv11 with the more attention-oriented YOLOv12 detector family. A dataset of 3546 annotated images was collected using a static ground-level camera at a marina in the northern Adriatic, Croatia. YOLOv11s, YOLOv11m, YOLOv12s, and YOLOv12m were fine-tuned using transfer learning, evaluated across five random seeds, and integrated into a common tracking-by-detection pipeline with Kalman filter (KF) and extended Kalman filter (EKF) motion models. Detection was assessed using COCO-style mAP metrics, while tracking was evaluated using MOT and HOTA-based metrics. YOLOv11m achieved the highest mean test-set mAP@50–95 (0.7458 ± 0.0027) and significantly outperformed YOLOv11s and YOLOv12s. Although YOLOv12m did not achieve the highest frame-level mAP, it obtained the highest mean AssA and IDF1 when averaged across the two motion models. KF achieved higher mean HOTA, DetA, AssA, MOTA, and IDF1 than EKF, whereas EKF achieved only marginally higher MOTP; the KF advantage was statistically significant for IDF1. Overall, the results show that frame-level detection accuracy does not necessarily determine downstream tracking performance, thereby supporting the joint evaluation of detector and motion-model choices.
- 3 August 2026
- Published by MDPI AG in Technologies
- Vol. 14 (8) , 482
Open AccessYOLO-Driven Vessel Detection and Multi-Object Tracking in Fixed-Camera Marina Environments
Vessel detection and multi-object tracking (MOT) in marinas remain challenging because of occlusions, small targets, cluttered backgrounds, and changing illumination. This paper presents a controlled, feasibility-focused comparative evaluation of YOLO-driven vessel detection and tracking in a fixed-camera marina environment, comparing YOLOv11 with the more attention-oriented YOLOv12 detector family. A dataset of 3546 annotated images was collected using a static ground-level camera at a marina in the northern Adriatic, Croatia. YOLOv11s, YOLOv11m, YOLOv12s, and YOLOv12m were fine-tuned using transfer learning, evaluated across five random seeds, and integrated into a common tracking-by-detection pipeline with Kalman filter (KF) and extended Kalman filter (EKF) motion models. Detection was assessed using COCO-style mAP metrics, while tracking was evaluated using MOT and HOTA-based metrics. YOLOv11m achieved the highest mean test-set mAP@50–95 (0.7458 ± 0.0027) and significantly outperformed YOLOv11s and YOLOv12s. Although YOLOv12m did not achieve the highest frame-level mAP, it obtained the highest mean AssA and IDF1 when averaged across the two motion models. KF achieved higher mean HOTA, DetA, AssA, MOTA, and IDF1 than EKF, whereas EKF achieved only marginally higher MOTP; the KF advantage was statistically significant for IDF1. Overall, the results show that frame-level detection accuracy does not necessarily determine downstream tracking performance, thereby supporting the joint evaluation of detector and motion-model choices.
- 11 June 2026
- Published by Elsevier in Ocean Engineering
- Vol. 362
Machine learning for ship-motion-based sea-state estimation
- 11 June 2026
- Published by Elsevier in Ocean Engineering
- Vol. 362
Machine learning for ship-motion-based sea-state estimation
- Open Access
- 19 May 2025
- Published by University of Rijeka, Faculty of Maritime Studies in Pomorstvo
- Vol. 39 (1) , 141-149
Design of a Conceptual Underwater Wireless Communication System Integrating Electromagnetic and Optical Technologies
Underwater wireless communication is pivotal for advancing maritime technology, supporting applications such as underwater exploration, autonomous underwater vehicles (AUVs), diver communication, search-and-rescue operations, and military systems. Traditional acoustic communication systems, while effective over long distances, are constrained by low bandwidth and high latency, limiting their suitability for data-intensive operations. Electromagnetic (EM) and optical communication technologies offer promising alternatives, providing higher data rates, greater bandwidth, and lower latency, but face challenges such as signal attenuation, scattering, and environmental interference. To address these challenges, this paper explores the potential of an integrated wireless communication and navigation system combining EM and optical technologies. Initial experimental measurements of EM wave propagation in freshwater provided valuable insights into signal attenuation and frequency-dependent performance, demonstrating the feasibility of overcoming attenuation in such environments. Building on these observations, this paper proposes a conceptual system comprising three interconnected segments: a space segment utilizing the Galileo High Accuracy Service (HAS) for precise GNSS signals, a waterline segment processing and transmitting GNSS-like signals, and an underwater segment facilitating navigationand communication for divers and AUVs. Preliminary findings highlight the potential of combining EM and optical technologies for reliable, near real-time underwater wireless communication. Future work will focus on extending functionality, validating the system in saltwater environments, and refining the design for practical deployment.
- 19 May 2025
- Published by University of Rijeka, Faculty of Maritime Studies in Pomorstvo
- Vol. 39 (1) , 141-149
Open AccessDesign of a Conceptual Underwater Wireless Communication System Integrating Electromagnetic and Optical Technologies
Underwater wireless communication is pivotal for advancing maritime technology, supporting applications such as underwater exploration, autonomous underwater vehicles (AUVs), diver communication, search-and-rescue operations, and military systems. Traditional acoustic communication systems, while effective over long distances, are constrained by low bandwidth and high latency, limiting their suitability for data-intensive operations. Electromagnetic (EM) and optical communication technologies offer promising alternatives, providing higher data rates, greater bandwidth, and lower latency, but face challenges such as signal attenuation, scattering, and environmental interference. To address these challenges, this paper explores the potential of an integrated wireless communication and navigation system combining EM and optical technologies. Initial experimental measurements of EM wave propagation in freshwater provided valuable insights into signal attenuation and frequency-dependent performance, demonstrating the feasibility of overcoming attenuation in such environments. Building on these observations, this paper proposes a conceptual system comprising three interconnected segments: a space segment utilizing the Galileo High Accuracy Service (HAS) for precise GNSS signals, a waterline segment processing and transmitting GNSS-like signals, and an underwater segment facilitating navigationand communication for divers and AUVs. Preliminary findings highlight the potential of combining EM and optical technologies for reliable, near real-time underwater wireless communication. Future work will focus on extending functionality, validating the system in saltwater environments, and refining the design for practical deployment.
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1760-1765
Advancements and Challenges in Underwater Wireless Optical Communication in the Marine Environment
Underwater wireless communication represents an important field for various applications such as oceanographic data collection, environmental monitoring, and the operation of autonomous underwater vehicles. The transmission of information through the marine environment can be done by acoustic, radio frequency (RF), and optical signals, with each technique having advantages and limitations. This paper focuses primarily on optical communication, which is based on the transmission of light in the visible spectrum through water. This type of communication offers significant advantages over acoustic and RF methods, primarily in terms of high data rates and lower latency, which are essential for real-time applications. However, optical communication also faces unique challenges, including light absorption and scattering, which can significantly degrade signal quality and limit the effective range of communication. This paper covers the theoretical foundations of optical communication and explains its principles, methods, and the technological advances that have been made in the field. It also discusses the current limitations and challenges of optical communication, such as light attenuation under various undersea conditions and the difficulties in aligning and maintaining stable communication links. Despite these challenges, optical communication remains a promising avenue for high-speed communication in marine environments, with ongoing research focusing on enhancing its robustness and range.
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1760-1765
Advancements and Challenges in Underwater Wireless Optical Communication in the Marine Environment
Underwater wireless communication represents an important field for various applications such as oceanographic data collection, environmental monitoring, and the operation of autonomous underwater vehicles. The transmission of information through the marine environment can be done by acoustic, radio frequency (RF), and optical signals, with each technique having advantages and limitations. This paper focuses primarily on optical communication, which is based on the transmission of light in the visible spectrum through water. This type of communication offers significant advantages over acoustic and RF methods, primarily in terms of high data rates and lower latency, which are essential for real-time applications. However, optical communication also faces unique challenges, including light absorption and scattering, which can significantly degrade signal quality and limit the effective range of communication. This paper covers the theoretical foundations of optical communication and explains its principles, methods, and the technological advances that have been made in the field. It also discusses the current limitations and challenges of optical communication, such as light attenuation under various undersea conditions and the difficulties in aligning and maintaining stable communication links. Despite these challenges, optical communication remains a promising avenue for high-speed communication in marine environments, with ongoing research focusing on enhancing its robustness and range.