TY - GEN
T1 - A Sequential Approach for On-board Rock Detection from Lunar Images
AU - Bosowski, Piotr
AU - Sadel, Jakub
AU - Cwiek, Marcin
AU - Strzalka, Tomasz
AU - Wiejak, Marek
AU - Benecki, Pawel
AU - Kawulok, Michal
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Rock segmentation in lunar images is a crucial computer vision task for visual navigation of planetary rovers. Even though numerous approaches have been already proposed to address this task, many solutions are underpinned with computationally-intensive deep learning models, which makes them unsuitable for on-board processing. In the study reported here, we address this important problem and we propose a sequential pipeline, which combines a U-Net-based network for rock segmentation with a YOLO model for final object detection. We demonstrate that putting two lightweight models together improves the detection performance, making it close to that obtained with full-sized architectures. Even though this is an initial study, the obtained results indicate that this direction is promising and it is worthy of further investigation.
AB - Rock segmentation in lunar images is a crucial computer vision task for visual navigation of planetary rovers. Even though numerous approaches have been already proposed to address this task, many solutions are underpinned with computationally-intensive deep learning models, which makes them unsuitable for on-board processing. In the study reported here, we address this important problem and we propose a sequential pipeline, which combines a U-Net-based network for rock segmentation with a YOLO model for final object detection. We demonstrate that putting two lightweight models together improves the detection performance, making it close to that obtained with full-sized architectures. Even though this is an initial study, the obtained results indicate that this direction is promising and it is worthy of further investigation.
UR - https://www.scopus.com/pages/publications/85178353361
U2 - 10.1109/IGARSS52108.2023.10282642
DO - 10.1109/IGARSS52108.2023.10282642
M3 - Conference contribution
AN - SCOPUS:85178353361
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 4195
EP - 4197
BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Y2 - 16 July 2023 through 21 July 2023
ER -