A comprehensive survey on the applications of machine learning techniques on maritime surveillance to detect abnormal maritime vessel behaviors

Automated surveillance systems are becoming a critical requirement in maritime domain, due to the continuous expansion of maritime security threats. Although several automated systems have been developed, detection of maritime threats is becoming more challenging due to the constantly changing tactics adopted by seafarers to evade detection. Machine learning algorithms are a popular choice when detecting maritime threats based on the abnormalities of vessels. This paper categorizes the security threats according to three processing levels: abnormal activities, behaviors, and intents, and presents available machine learning techniques to detect these threats, including several deep learning techniques which is the current trend in detecting abnormalities. Supervised learning and unsupervised learning techniques used in the literature are discussed in this paper, where the advantages and disadvantages of each approach in the context of maritime surveillance are discussed in detail. Supervised learning was used predominantly for detecting relatively simple abnormal behaviors and intents such as movement abnormalities. Such learning methods yielded higher accuracy values in comparison to unsupervised learning methods, which achieved 80–95% accuracy. Supervised learning methods perform between 93 and 99% accuracy, where the highest accuracy is achieved by SVM (support vector machine) and 91% accuracy by CNN (convolutional neural network) as the best among deep learning methods. Furthermore, this analysis reveals that supervised deep learning methods such as CNN and long short-term memory (LSTM) will be the future trends in developing high-accurate maritime surveillance systems with the ability to detect more maritime threats.