MarsSeg: Mars Surface Semantic Segmentation With Multilevel Extractor and Connector

Abstract

The segmentation and interpretation of the Martian surface play a pivotal role in Mars exploration, providing essential data for the trajectory planning and obstacle avoidance of rovers. However, the complex topography, self-similar surface features, and the lack of extensive annotated data pose significant challenges to the high-precision semantic segmentation of the Martian surface. To address these challenges, we propose a novel encoder–decoder-based Mars segmentation network, termed MarsSeg. To facilitate a high-level semantic understanding across the multilevel feature maps, we introduce a feature enhancement module, which incorporates a multiscale feature pyramid (MFP) and strip attention pyramid pooling module (SAPPM). The MFP is specifically designed for shallow feature enhancement, thereby enabling the expression of local details and small objects. Conversely, the SAPPM is employed for deep feature enhancement, facilitating the extraction of high-level semantic category-related information. To effectively fuse features from different levels, we propose a feature fusion module, which contains Mars polarized self-attention (Mars-PSA) and pixel attention head (PA-Head). Mars-PSA enables the fusion of multilevel information while directing the model’s attention to salient features. The PA-Head focuses on detailed information at the pixel level. Experimental results derived from the Mars-Seg and AI4Mars datasets prove that the proposed MarsSeg outperforms other state-of-the-art methods in segmentation performance, validating the efficacy of each proposed component.