Evaluation of Resource-Efficient Crater Detectors on Embedded Systems

Simon Vellas, Bill Psomas, Kalliopi Karadima, Dimitrios Danopoulos, Alexandros Paterakis +3 more
5/27/2024
cs.CVcs.DCcs.PF

Official code: billpsomas/mars_crater_detection (15 stars, Apache-2.0, last commit 2024-08-27).

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.

View on arXivView PDF

Code Implementations(1)

billpsomas/mars_crater_detectionOfficial100%
Apache-2.0

Official PyTorch implementation for IGARSS 2024 paper: "Evaluation of Resource-Efficient Crater Detectors on Embedded Systems"

150C++, ShellDec 12, 20232 years agoApache-2.0
computer-visioncrater-detectiondeep-learningearth-observationmars+6 more

Similar Papers

Camera-Pose Robust Crater Detection from Chang'e 5

80% match2024

AQ-PCDSys: An Adaptive Quantized Planetary Crater Detection System for Autonomous Space Exploration

80% match2025

Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks

79% match2025

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

79% match2024

Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

79% match2026

ARTPS: Depth-Enhanced Hybrid Anomaly Detection and Learnable Curiosity Score for Autonomous Rover Target Prioritization

79% match2025

Cite this paper

@article{vellas2024evaluation,
  title  = {Evaluation of Resource-Efficient Crater Detectors on Embedded Systems},
  author = {Simon Vellas and Bill Psomas and Kalliopi Karadima and Dimitrios Danopoulos and Alexandros Paterakis and George Lentaris and Dimitrios Soudris and Konstantinos Karantzalos},
  year   = {2024},
  eprint = {2405.16953},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.16953v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.16953.svg)](https://codeofpaper.com/paper/2405.16953)

Discussion