Research/ SPACE AI & AUTONOMY
Evaluation of Resource-Efficient Crater Detectors on Embedded Systems
Simon Vellas, Bill Psomas, Kalliopi Karadima, Dimitrios Danopoulos, Alexandros Paterakis, George Lentaris, Dimitrios Soudris, Konstantinos Karantzalos
Perception & State EstimationarXiv: cs.CV · Learning-based MethodsOpenAlex topic: Advanced Neural Network Applications · Design, Mechanisms & HardwareOpenAlex keyword: edge computing
arXivcs.CV · cs.DC · cs.PFOpenAlexAdvanced Neural Network Applications · IoT and Edge/Fog Computing · Embedded Systems and FPGA Design
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.
Comments: Accepted at 2024 IEEE International Geoscience and Remote Sensing Symposium