Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vellas, Simon, Psomas, Bill, Karadima, Kalliopi, Danopoulos, Dimitrios, Paterakis, Alexandros, Lentaris, George, Soudris, Dimitrios, Karantzalos, Konstantinos
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.16953
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917676363808768
author Vellas, Simon
Psomas, Bill
Karadima, Kalliopi
Danopoulos, Dimitrios
Paterakis, Alexandros
Lentaris, George
Soudris, Dimitrios
Karantzalos, Konstantinos
author_facet Vellas, Simon
Psomas, Bill
Karadima, Kalliopi
Danopoulos, Dimitrios
Paterakis, Alexandros
Lentaris, George
Soudris, Dimitrios
Karantzalos, Konstantinos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluation of Resource-Efficient Crater Detectors on Embedded Systems
Vellas, Simon
Psomas, Bill
Karadima, Kalliopi
Danopoulos, Dimitrios
Paterakis, Alexandros
Lentaris, George
Soudris, Dimitrios
Karantzalos, Konstantinos
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Performance
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.
title Evaluation of Resource-Efficient Crater Detectors on Embedded Systems
topic Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Performance
url https://arxiv.org/abs/2405.16953