Ship Contour: A Novel Ship Instance Segmentation Method Using Deep Snake and Attention Mechanism

Ship instance segmentation technologies enable the identification of ship targets and their contours, serving as an auxiliary tool for monitoring, tracking, and providing critical support for maritime and port safety management. However, due to the different shapes and sizes of ships, as well as the complexity and fluctuation of lighting and weather, existing ship instance segmentation approaches frequently struggle to accomplish correct contour segmentation. To address this issue, this paper introduces Ship Contour, a real-time segmentation method for ship instances based on contours that detects ship targets using an improved CenterNet algorithm. This method utilizes DLA-60 (deep layer aggregation) as the core network to ensure detection accuracy and speed, and it integrates an efficient channel attention (ECA) mechanism to boost feature extraction capability. Furthermore, a Mish activation function replaces ReLU to better adapt deep network learning. These improvements to CenterNet enhance model robustness and effectively reduce missed and false detection. In response to the issue of low accuracy in extracting ship target edge contours using the original deep snake end-to-end method, a scale- and translation-invariant normalization scheme is employed to enhance contour quality. To validate the effectiveness of the proposed method, this research builds a dedicated dataset with up to 2300 images. Experiments demonstrate that this method achieves competitive performance, with an accuracy rate of AP0.5:0.95 reaching 63.6% and a recall rate of AR0.5:0.95 reaching 67.4%.