Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms

Marcus Märtens, Kevin Farries, John Culton, Tat-Jun Chin

TL;DR

SLT provides a solid foundation to analyse the limits of RGB-cameras and potential advantages or synergies in utilizing neuromorphic visions with the goal of enabling and improving lunar specific applications like rover navigation, landing in cratered environments or similar.

Abstract

Synthetic Lunar Terrain (SLT) is an open dataset collected from an analogue test site for lunar missions, featuring synthetic craters in a high-contrast lighting setup. It includes several side-by-side captures from event-based and conventional RGB cameras, supplemented with a high-resolution 3D laser scan for depth estimation. The event-stream recorded from the neuromorphic vision sensor of the event-based camera is of particular interest as this emerging technology provides several unique advantages, such as high data rates, low energy consumption and resilience towards scenes of high dynamic range. SLT provides a solid foundation to analyse the limits of RGB-cameras and potential advantages or synergies in utilizing neuromorphic visions with the goal of enabling and improving lunar specific applications like rover navigation, landing in cratered environments or similar.

Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms

TL;DR

SLT provides a solid foundation to analyse the limits of RGB-cameras and potential advantages or synergies in utilizing neuromorphic visions with the goal of enabling and improving lunar specific applications like rover navigation, landing in cratered environments or similar.

Abstract

Synthetic Lunar Terrain (SLT) is an open dataset collected from an analogue test site for lunar missions, featuring synthetic craters in a high-contrast lighting setup. It includes several side-by-side captures from event-based and conventional RGB cameras, supplemented with a high-resolution 3D laser scan for depth estimation. The event-stream recorded from the neuromorphic vision sensor of the event-based camera is of particular interest as this emerging technology provides several unique advantages, such as high data rates, low energy consumption and resilience towards scenes of high dynamic range. SLT provides a solid foundation to analyse the limits of RGB-cameras and potential advantages or synergies in utilizing neuromorphic visions with the goal of enabling and improving lunar specific applications like rover navigation, landing in cratered environments or similar.
Paper Structure (5 sections, 5 figures, 1 table)

This paper contains 5 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Data Collection
  3. Data Post-processing
  4. Analysis, Observations and Limitations
  5. Conclusions and Future Directions

Figures (5)

  • Figure 1: Comparison of one example from POLAR Hansen2023polar (left) with RGB-modality of SLT Martens2024synthetic (right).
  • Figure 2: Lunar Terrain at Exterres Lab, experimental setup.
  • Figure 3: Example of anti-clockwise recording sweep over the terrain from position A4. All positions from which the jib-arm was moved are shown.
  • Figure 4: Map of manually identified crater-like structures within global coordinate system, top-down view.
  • Figure 5: Example of terminator in RGB-image left (A4_ACW_frame296.tif) and event-stream (A4_ACW.raw) right.