🤖 AI Summary
To address low accuracy and poor real-time performance in horizon line detection from RGB videos under low-contrast, high-noise sea conditions, this paper proposes a lightweight and robust horizon detection method. Methodologically: (i) a weak-edge-preserving vectorized filtering mechanism is designed to suppress sea-surface noise while enhancing faint edges; (ii) geometric priors of horizon segments are introduced for the first time to guide noise suppression; (iii) a temporal consistency fusion strategy is constructed to improve robustness; and (iv) efficient CPU-side vectorization and adaptive image scaling are implemented. Contributions include: releasing the first publicly available horizon-line annotated dataset; achieving real-time performance while retaining 98.3% of original accuracy, with only 1.71% computational overhead from filtering; and reducing outlier rate by 42% over state-of-the-art methods under strong interference and weak-edge scenarios.
📝 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.