Aiming at the problems of easy switching of tracking ID （identity） and low accuracy caused by complex scenes, including platform shaking and small object due to long distance during autonomous collection of surface floating debris by cleaning vessels, a multi-object tracking (MOT) method based on improved YOLOv5-Byte was proposed.

First, the Byte data association model was integrated with the YOLOv5 detector to construct the MOT algorithm. Secondly, aiming at the problem that CIoU (complete intersection over union） in YOLOv5 is sensitive to small objects, the normalized Wasserstein distance metric is proposed for the boundary box Gaussian modeling. Then, the balance factor is introduced to adjust the contribution of CIoU and normalized Wasserstein distance measures to the loss function to adjust the sensitivity of the detector to small objects. Finally, IoU (intersection over union）is introduced into the adjustable hyper-parameter in the form of a power exponent in the Byte data association model to reduce the risk of small objects being discarded due to low confidence.

The experimental results on the surface floating debris dataset showed that the tracking assessment metrics IDF1 (identification F1 score) and MOTA (multiple object tracking accuracy) increased by 11.5% and 8.7%, respectively, while the number of IDs (identity switches) decreased by 7 compared to the algorithm before improvement.

The proposed algorithm achieves accurate tracking of multiple small objects on the water surface, providing a reference for the autonomous debris collection technology of intelligent floating cleaning vessels.