Image-Based Lunar Hazard Detection in Low Illumination Simulated Conditions via Vision Transformers
Open Access
Abstract
Hazard detection is fundamental for a safe lunar landing. State-of-the-art autonomous lunar hazard detection relies on 2D image-based and 3D Lidar systems. The lunar south pole is challenging for vision-based methods. The low sun inclination and the terrain rich in topographic features create large areas in shadow, hiding the terrain features. The proposed method utilizes a vision transformer (ViT) model, which is a deep learning architecture based on the transformer blocks used in natural language processing, to solve this problem. Our goal is to train the ViT model to extract terrain features information from low-light RGB images. The results show good performances, especially at high altitudes, beating the UNet, one of the most popular convolutional neural networks, in every scenario.Keywords
This publication has 28 references indexed in Scilit:
- A multilayer perceptron hazard detector for vision-based autonomous planetary landingAdvances In Space Research, 2016
- Guidance Summary and Assessment of the Chang’e-3 Powered Descent and LandingJournal of Spacecraft and Rockets, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Real-Time Hazard Detection and Avoidance Demonstration for a Planetary Lander2014
- Illumination conditions of the lunar polar regions using LOLA topographyIcarus, 2011
- Vision based Hazard detection and obstacle Avoidance for planetary landing2009
- Robust image corner detection through curvature scale spaceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- A Combined Corner and Edge Detector1988
- A Computational Approach to Edge Detection1987
- A Computational Approach to Edge DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986