# Robust Tracker: Integrating CPM-YOLO and BOTSORT for Cross-Modal Vessel Tracking

## TL;DR

This paper introduces a robust vessel tracking method combining CPM-YOLO and BOTSORT for accurate and efficient maritime tracking in complex environments.

## Contribution

The novel integration of CPM-YOLO and BOTSORT improves detection and tracking accuracy while maintaining real-time performance.

## Key findings

- The method improves Precision, Recall, mAP@0.5, and mAP@0.5:0.95 by 4.0%, 5.0%, 5.1%, and 5.4% on the NIR dataset.
- It outperforms state-of-the-art approaches on the VIS dataset in detection accuracy and robustness.
- The framework achieves 188 FPS on the NIR dataset and 187 FPS on the VIS dataset, maintaining real-time performance.

## Abstract

This paper presents a high-accuracy and robust multi-object tracking method for maritime vessel detection and tracking in complex marine environments, characterized by dense targets, large-scale variations, and frequent occlusions. The proposed approach adopts an enhanced YOLOv8-based detector with lightweight feature enhancement and attention mechanisms to improve its capability in detecting small-scale vessels and complex scenes. Furthermore, a tracking framework combining BOTSORT with an OSNet-based re-identification (ReID) model is employed to achieve stable and reliable vessel association. Experimental results on the Near-Infrared On-Shore (NIR) dataset demonstrate that the proposed method improves Precision, Recall, mAP@0.5, and mAP@0.5:0.95 by approximately 4.0%, 5.0%, 5.1%, and 5.4%, respectively, compared with the baseline YOLOv8, while reducing parameter count and model size by 11.6% and 6.5%. On the Visible On-Shore (VIS) dataset, the proposed method outperforms state-of-the-art approaches in detection accuracy and robustness, further validating its effectiveness and cross-modal generalization capability. In multi-object tracking tasks, the proposed CPM-YOLO and BOTSORT framework demonstrates clear advantages in trajectory continuity, occlusion handling, and identity preservation compared with mainstream tracking algorithms. On the NIR dataset, the proposed method achieves a competitive inference speed of 188 FPS, while running at 187 FPS on the VIS dataset, demonstrating that the accuracy improvements are achieved without sacrificing real-time performance. Overall, the proposed method achieves a favorable balance between detection accuracy, tracking robustness, and model efficiency, making it well-suited for practical maritime applications.