Vessel Re-identification and Activity Detection in Thermal Domain for Maritime Surveillance

TL;DR

This paper presents a thermal vision-based maritime surveillance system that re-identifies vessels and detects suspicious activities, introducing a novel viewpoint-independent algorithm and a new thermal dataset for benchmarking.

Contribution

It introduces a novel viewpoint-independent vessel re-identification algorithm and the first publicly available thermal maritime surveillance dataset, advancing thermal vision applications.

Findings

Vessel re-identification achieves 81.8% Top1 accuracy.

Suspicious activity detection reaches 72.4% frame mAP.

First benchmark dataset for thermal maritime surveillance.

Abstract

Maritime surveillance is vital to mitigate illegal activities such as drug smuggling, illegal fishing, and human trafficking. Vision-based maritime surveillance is challenging mainly due to visibility issues at night, which results in failures in re-identifying vessels and detecting suspicious activities. In this paper, we introduce a thermal, vision-based approach for maritime surveillance with object tracking, vessel re-identification, and suspicious activity detection capabilities. For vessel re-identification, we propose a novel viewpoint-independent algorithm which compares features of the sides of the vessel separately (separate side-spaces) leveraging shape information in the absence of color features. We propose techniques to adapt tracking and activity detection algorithms for the thermal domain and train them using a thermal dataset we created. This dataset will be the first publicly available benchmark dataset for thermal maritime surveillance. Our system is capable of re-identifying vessels with an 81.8% Top1 score and identifying suspicious activities with a 72.4\% frame mAP score; a new benchmark for each task in the thermal domain.