Year: 2021
Type: preprint
Abstract: The Mars Perseverance rover applies computer vision for navigation and hazard avoidance. The challenge to do onboard object recognition highlights the need for low-power, customized training, often including low-contrast backgrounds. We investigate deep learning methods for the classification and detection of Martian rocks. We report greater than 97% accuracy for binary classifications (rock vs. rover). We fine-tune a detector to render geo-located bounding boxes while counting rocks. For these models to run on microcontrollers, we shrink and quantize the neural networks' weights and demonstrate a low-power rock hunter with faster frame rates (1 frame per second) but lower accuracy (37%).
Source: arXiv (Cornell University)
Authors: Noever, David, Noever, Samantha E. Miller
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3154340422