MarsNet: Automated Rock Segmentation With Transformers for Tianwen-1 Mission

• Published in: IEEE geoscience and remote sensing letters Vol. 20; pp. 1 - 5
• Main Authors: Lv, Weikun, Wei, Linhui, Zheng, Dian, Liu, Yu, Wang, Yumei
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Barriers; Convolution; Datasets; Decoding; Exploration; Feature extraction; Hybrid dilated convolution (HDC); Image processing; Image segmentation; Mars; Mars exploration; Mars rovers; Mars surface; Navigation; Neural networks; Path planning; Rock; rock segmentation; Rocks; Semantic segmentation; Source code; Transformers; TWMARS dataset; Zhurong Rover
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2022.3227338

The Mars exploration mission of China named Tianwen-1 is being carried out as scheduled. The Navigation and Terrain Cameras (NaTeCam) equipped on the Zhurong Rover play an essential role in obstacle recognition. The main obstacles on the Martian surface are rocks of different sizes, which influence the path planning of Zhurong Rover in scientific exploration. Most existing semantic segmentation methods are based on the U-Net architecture with ResNet or other backbones, and features extracted by these methods lack long-range dependencies. To fully exploit the context information, we propose the MarsNet framework for the Mars image, which combines transformers with the convolutional neural network (CNN) as the backbone, and hybrid dilated convolution (HDC) is also employed to the decoder path to help detect the huge rocks. Besides, since there are few open-source datasets for rock segmentation for Mars, we establish a segmentation dataset from the Martian surface image, named TWMARS, captured by NaTeCam. Extensive experiments are conducted on the TWMARS dataset, and the experimental results demonstrate that MarsNet achieves accurate rock segmentation and outperforms state-of-the-art methods. The source code is available at https://github.com/BUPT-ANT-1007/MarsNet .