Beyond Land: A Review of Benchmarking Datasets, Algorithms, and Metrics for Visual-Based Ship Tracking

Abstract

Object tracking has gained much interest in the last few years, especially in the context of multiple object tracking. Many datasets used for tracking provide video sequences of people and objects in very different contexts. Although it has been attracting much attention, no dataset or tracking algorithm has been applied to coastal surveillance and ship tracking. Besides image/video-based tracking technologies, other technologies, such as radar and automatic identification systems (AISs), are also used for this task, especially in maritime applications. In the AIS case, commonly known issues, such as information omission, remain to be dealt with. As for radars, the most important issue is the impossibility of identifying the ship type/class and correlating it with AIS information. However, image/video-based solutions can be combined with these technologies to mitigate or even solve these issues. This work aims to review the most recent datasets and state-of-the-art tracking algorithms (also known as trackers) for single or multiple objects tracking for objects in general and its possibilities for maritime scenarios. The goal is to gain insights for developing novel datasets; benchmarking metrics; and mainly, novel ship tracking algorithms.

Object Tracking Using Computer Vision: A Review

“…Recent reviews have looked into detection-based multiple-object tracking [24], data association methods [25], long-term visual tracking [26], and methods used in ship tracking [27]. Dai et al [24] introduced a taxonomy of multiple-object tracking and provided a detailed summary of the results of algorithms on popular datasets.…”

“…Liu et al [26] reviewed long-term tracking algorithms while describing existing benchmarks and evaluation protocols. Rocha et al [27] reviewed datasets and state-of-the-art algorithms for single and multiple-object tracking with the view of applying them to ship tracking. Furthermore, they provided insights into developing novel datasets, benchmarking metrics, and novel ship-tracking algorithms.…”

Performance Evaluation of Edge Computing Object Detection Models for Maritime Surveillance on Raspberry Pi

“…Leveraging cameras in these locations presents an opportunity to develop intelligent applications employing Computer Vision (CV) techniques. Cameras offer a cost-effective alternative for low-energy applications, particularly when coupled with efficient, fast, and robust detection techniques using embedded systems with CV capabilities [2,3].…”