Evaluation of Resource-Efficient Crater Detectors on Embedded Systems

TL;DR

This paper benchmarks and optimizes crater detection neural networks for embedded systems on spacecraft, enabling efficient real-time analysis on low-power hardware for Mars exploration missions.

Contribution

It provides a comprehensive performance analysis of YOLO networks on various embedded platforms and introduces optimized configurations for resource-constrained crater detection.

Findings

Identified optimal YOLO network-device pairings for embedded systems.

Demonstrated real-time crater detection feasibility on low-power hardware.

Provided open-source code for deployment and further research.

Abstract

Real-time analysis of Martian craters is crucial for mission-critical operations, including safe landings and geological exploration. This work leverages the latest breakthroughs for on-the-edge crater detection aboard spacecraft. We rigorously benchmark several YOLO networks using a Mars craters dataset, analyzing their performance on embedded systems with a focus on optimization for low-power devices. We optimize this process for a new wave of cost-effective, commercial-off-the-shelf-based smaller satellites. Implementations on diverse platforms, including Google Coral Edge TPU, AMD Versal SoC VCK190, Nvidia Jetson Nano and Jetson AGX Orin, undergo a detailed trade-off analysis. Our findings identify optimal network-device pairings, enhancing the feasibility of crater detection on resource-constrained hardware and setting a new precedent for efficient and resilient extraterrestrial imaging. Code at: https://github.com/billpsomas/mars_crater_detection.