Boundary Enhancement-Driven Accurate Semantic Segmentation Networks for Unmanned Surface Vessels in Complex Marine Environments
Liye Zhang, Xiaoyu Sun, Zhongzheng Li, Dong Kong, Jigang Liu, Peizhou Ni
Abstract
Semantic segmentation of complex marine environments based on images is crucial for the autonomous navigation of unmanned surface vessels (USVs). However, existing semantic segmentation methods mainly categorize images into three coarse categories: sea surface, obstacles, and sky, with limited attention to the boundaries between significant elements. Moreover, the dynamic changes in marine environments often affect these methods, resulting in shortcomings such as blurry boundary segmentation. To address these issues, this article proposes a boundary enhancement-driven semantic segmentation network tailored for complex marine environments, focusing primarily on the accuracy of interclass boundaries. Specifically, 1) a boundary extraction module is proposed to extract multiscale boundary features from the backbone network, which are fused via continuous boundary attention streams (BASs) and supervised with boundary loss. 2) A boundary enhancing module (BEM) is introduced, wherein the connection between channel features is strengthened using the astous convolutional pyramid module and channel attention (CA) module, enhancing the perception of contextual boundary information and improving the accuracy of category boundaries in the segmentation results. Comprehensive comparative experiments were conducted on the MaSTr1325 dataset and MID dataset, and the proposed method was evaluated on the MODD2 dataset using the MODS evaluation method. Results demonstrate that our approach, BEMSNet, achieves clearer and more accurate boundary segmentation compared to other networks.