Technology Category
Computer Vision: Motion & TrackingIntelligent Robots: State EstimationPlanning, Routing, and Scheduling: Activity and Plan Recognition
Visual Trajectory Prediction of Vessels for Inland Navigation
🤖 AI Summary
To address challenges in video-based vessel tracking in complex inland waterway environments—including false detections, trajectory jitter, and low long-term prediction accuracy—this paper proposes a detection–filtering–interpolation collaborative framework. Robust detection is achieved using YOLO-series models; Kalman filtering is empirically validated to outperform mainstream multi-object trackers (e.g., BoT-SORT) in trajectory smoothing for inland waterways. B-spline interpolation is introduced to compensate for missed detections and occlusions. A customized inland waterway dataset is constructed to train domain-adapted models. Experiments demonstrate significant improvements in trajectory prediction accuracy across diverse inland scenarios, reducing mean absolute error (MAE) by 23.6%. The framework enhances the timeliness of collision warnings and the reliability of maritime situational awareness, thereby providing critical technical support for autonomous navigation and remote operation of unmanned surface vessels.
Technology Category
Application Category
📝 Abstract
The future of inland navigation increasingly relies on autonomous systems and remote operations, emphasizing the need for accurate vessel trajectory prediction. This study addresses the challenges of video-based vessel tracking and prediction by integrating advanced object detection methods, Kalman filters, and spline-based interpolation. However, existing detection systems often misclassify objects in inland waterways due to complex surroundings. A comparative evaluation of tracking algorithms, including BoT-SORT, Deep OC-SORT, and ByeTrack, highlights the robustness of the Kalman filter in providing smoothed trajectories. Experimental results from diverse scenarios demonstrate improved accuracy in predicting vessel movements, which is essential for collision avoidance and situational awareness. The findings underline the necessity of customized datasets and models for inland navigation. Future work will expand the datasets and incorporate vessel classification to refine predictions, supporting both autonomous systems and human operators in complex environments.
Problem
Research questions and friction points this paper is trying to address.
Accurate vessel trajectory prediction for inland navigation
Challenges in video-based vessel tracking and object misclassification
Improving collision avoidance and situational awareness in complex environments
Innovation
Methods, ideas, or system contributions that make the work stand out.
Integrates object detection and Kalman filters
Uses spline-based interpolation for trajectories
Compares tracking algorithms for robustness
🔎 Similar Papers
No similar papers found.
