A Robust Deep Affinity Network for Multiple Ship Tracking

Wen Zhang

doi:10.1109/TIM.2021.3077679

Return

A Robust Deep Affinity Network for Multiple Ship Tracking

2021-01-01

PRE

DOI：10.1109/TIM.2021.3077679

Original

Original request for help

Save

Abstract

En 中文

Multiple ship tracking (MST) is an important task in marine surveillance and ship situational awareness systems. Considerable work has been conducted on multiple object tracking in recent years, but it has focused primarily on pedestrians and automobiles, leaving a gap in studies on MST due to the particularities of complex marine scenes, such as ship scale variations, the long-tailed distribution of ships, and long-term occlusions caused by ship movements. In this article, we present a robust deep affinity network (RoDAN) for MST. To overcome the above difficulties in MST, we start with the basic deep affinity network (DAN) and improve it in three aspects: scale, region, and motion. For the scale dimension, we integrate an atrous spatial pyramid pooling (ASPP) module to improve the modeling ability for multiscale ships. For the region dimension, we propose the joint global region modeling (JGRM) module, which further strengthens the modeling ability of DAN and exploit it to overcome the long- tailed distribution property of ships. For the motion dimension, we propose the motion-matching optimization (MMO) module to fine-tune the tracking results and make our tracker more robust, less reliant on the front-end detector, and ameliorate long-term occlusions. The experimental results demonstrate that our MST method outperforms the state-of-the-art methods. In particular, it reduces the number of ID switches (IDSs) and trajectory fragmentations (FMs), achieving holistically preferable performance. Meanwhile, our method achieves a comparable speed.

Keywords:

Complex marine scenes

joint global region modeling (JGRM) module

marine surveillance

motion-matching optimization (MMO) module

multiple ship tracking (MST)

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.