Real-Time Fusion of Visual and Chart Data for Enhanced Maritime Vision
This addresses the need for more reliable maritime navigation systems by providing enhanced vision capabilities for operators, though it appears incremental as it builds on existing detection and fusion methods.
The paper tackles the problem of enhancing marine vision by fusing real-time visual data with nautical chart information, achieving significant improvements in object localization and association accuracy in dynamic maritime environments.
This paper presents a novel approach to enhancing marine vision by fusing real-time visual data with chart information. Our system overlays nautical chart data onto live video feeds by accurately matching detected navigational aids, such as buoys, with their corresponding representations in chart data. To achieve robust association, we introduce a transformer-based end-to-end neural network that predicts bounding boxes and confidence scores for buoy queries, enabling the direct matching of image-domain detections with world-space chart markers. The proposed method is compared against baseline approaches, including a ray-casting model that estimates buoy positions via camera projection and a YOLOv7-based network extended with a distance estimation module. Experimental results on a dataset of real-world maritime scenes demonstrate that our approach significantly improves object localization and association accuracy in dynamic and challenging environments.