Coastal surveillance video helps officials to obtain on-site visual information on maritime traffic situations, which benefits building up the maritime transportation detection infrastructure. The previous ship detection methods focused on detecting distant small ships in maritime videos, with less attention paid to the task of ship detection from coastal surveillance video. To address this challenge, a novel framework is proposed to detect ships from coastal maritime images in three typical traffic situations in three consecutive steps. First the Canny detector is introduced to determine the potential ship edges in each maritime frame. Then, the self-adaptive Gaussian descriptor is employed to accurately rule out noisy edges. Finally, the morphology operator is developed to link the detected separated edges to connected ship contours. The model's performance is tested under three typical maritime traffic situations. The experimental results show that the proposed ship detector achieved satisfactory performance (in terms of precision, accuracy and time cost) compared with other state-of-the-art algorithms. The findings of the study offer the potential of providing real-time visual traffic information to maritime regulators, which is crucial for the development of intelligent maritime transportation.

Most previous research has handled the task of ship type recognition by exploring hand-craft ship features, which may fail to distinguish ships with similar visual appearances. This situation motivates us to propose a novel deep learning based ship type recognition framework which we have named coarse-to-fine cascaded convolution neural network (CFCCNN). First, the proposed CFCCNN framework formats the input training ship images and data, and provides trainable input data for the hidden layers of the CFCCNN. Second, the coarse and fine steps are run in a nesting manner to explore discriminative features for different ship types. More specifically, the coarse step is trained in a similar manner to the traditional convolution neural network, while the fine step introduces regularisation mechanisms to extract more intrinsic ship features, and fine tunes parameter settings to obtain better recognition performance. Finally, we evaluate the performance of the CFCCNN model for recognising the most common types of merchant ship (oil tanker, container, LNG tanker, chemical carrier, general cargo, bulk carrier, etc.). The experimental results show that the proposed framework obtains better recognition performance than the conventional methods of ship type recognition.

Conventional visual ship tracking methods employ single and shallow features for the ship tracking task, which may fail when a ship presents a different appearance and shape in maritime surveillance videos. To overcome this difficulty, we propose to employ a multi-view learning algorithm to extract a highly coupled and robust ship descriptor from multiple distinct ship feature sets. First, we explore multiple distinct ship feature sets consisting of a Laplacian-of-Gaussian (LoG) descriptor, a Local Binary Patterns (LBP) descriptor, a Gabor filter, a Histogram of Oriented Gradients (HOG) descriptor and a Canny descriptor, which present geometry structure, texture and contour information, and more. Then, we propose a framework for integrating a multi-view learning algorithm and a sparse representation method to track ships efficiently and effectively. Finally, our framework is evaluated in four typical maritime surveillance scenarios. The experimental results show that the proposed framework outperforms the conventional and typical ship tracking methods.