Home > Articles > All Issues > 2024 > Volume 12, No. 4, 2024 >
JOIG 2024 Vol.12(4):345-361
doi: 10.18178/joig.12.4.345-361

A Fast Horizon Detector and a New Annotated Dataset for Maritime Video Processing

Yassir Zardoua 1,*, Mohammed Boulaala 2, Mhamed El Mrabet 2, and Abdelali Astito1
1. Smart Systems and Emerging Technologies, Faculty of Science and Technologies of Tangier (FSTT), Abdelmalek Essaadi University, Tetouan, Morocco
2. Industrial Systems Engineering and Energy Conversion Team, Faculty of Science and Technologies of Tangier (FSTT), Abdelmalek Essaadi University, Tetouan, Morocco
Email: yassirzardoua@gmail.com (Y.Z.); m.boulaala@gmail.com (M.B.); m.elmrabet@gmail.com (M.E.M.); abdelali_astito@yahoo.com (A.A.)
*Corresponding author

Manuscript received January 26, 2024; revised April 12, 2024; accepted May 13, 2024; published October 18, 2024

Abstract—Accurate and fast sea horizon detection is vital for tasks in autonomous navigation and maritime security, such as video stabilization, target region reduction, precise tracking, and obstacle avoidance. This paper introduces a novel sea horizon detector from RGB videos, focusing on rapid and effective sea noise suppression while preserving weak horizon edges. Line fitting methods are subsequently employed on filtered edges for horizon detection. We address the filtering problem by extracting line segments with a very low edge threshold, ensuring the detection of line segments even in low-contrast horizon conditions. We show that horizon line segments have simple and relevant properties in RGB images, which we exploit to suppress noisy segments. Then we use the surviving segments to construct a filtered edge map and infer the horizon from the filtered edges. We propose a careful incorporation of temporal in- formation for horizon inference and experimentally show its effectiveness. We address the computational constraint by providing a vectorized implementation for efficient CPU execution, and leveraging image downsizing with minimal loss of accuracy on the original size. Moreover, we contribute a public horizon line dataset to enrich existing data resources. After extensive tests, we report the following major findings: 1) thanks to its filter, our algorithm accurately detects horizon lines with low or weak edge response, 2) the vectorized filter takes no more than 1.71% of the overall computations, while most of the computations are taken by the Line Segment Detection (LSD) algorithm we integrated into our pipeline, 3) our strategy of incorporating the temporal information avoids outlier detections, mitigates the effect of strong noisy lines, and exhibits high robustness when using incorrect detections as a temporal reference. Our algorithm’s performance is rigorously evaluated against state-of-the-art methods, and its core components are validated through ablation experiments.

Keywords—horizon line, sea-sky line, real-time execution, vectorized computations, maritime video processing, annotated dataset, maritime target tracking

Cite: Yassir Zardoua, Mohammed Boulaala, Mhamed El Mrabet, and Abdelali Astito, "A Fast Horizon Detector and a New Annotated Dataset for Maritime Video Processing," Journal of Image and Graphics, Vol. 12, No. 4, pp. 345-361, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.