Multi-Ship Tracking by Robust Similarity metric
This work solves the problem of accurate ship tracking for maritime situational awareness and autonomous navigation systems, representing an incremental improvement by adapting existing methods to a specific domain challenge.
The paper tackles the problem of multi-ship tracking by addressing the poor performance of existing multi-object tracking algorithms on ship datasets due to low frame rates and image shake, which cause minimal Intersection of Union (IoU) and identity switches. It introduces a tracking version of IoU (TIoU) that incorporates convex shapes and shape similarity, achieving consistent improvements when integrated into frameworks like DeepSort and ByteTrack.
Multi-ship tracking (MST) as a core technology has been proven to be applied to situational awareness at sea and the development of a navigational system for autonomous ships. Despite impressive tracking outcomes achieved by multi-object tracking (MOT) algorithms for pedestrian and vehicle datasets, these models and techniques exhibit poor performance when applied to ship datasets. Intersection of Union (IoU) is the most popular metric for computing similarity used in object tracking. The low frame rates and severe image shake caused by wave turbulence in ship datasets often result in minimal, or even zero, Intersection of Union (IoU) between the predicted and detected bounding boxes. This issue contributes to frequent identity switches of tracked objects, undermining the tracking performance. In this paper, we address the weaknesses of IoU by incorporating the smallest convex shapes that enclose both the predicted and detected bounding boxes. The calculation of the tracking version of IoU (TIoU) metric considers not only the size of the overlapping area between the detection bounding box and the prediction box, but also the similarity of their shapes. Through the integration of the TIoU into state-of-the-art object tracking frameworks, such as DeepSort and ByteTrack, we consistently achieve improvements in the tracking performance of these frameworks.