Automatic characterization of boulders on planetary surfaces from high-resolution satellite images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916091686551552 |
|---|---|
| author | Prieur, Nils C. Amaro, Brian Gonzalez, Emiliano Kerner, Hannah Medvedev, Sergei Rubanenko, Lior Werner, Stephanie C. Xiao8, Zhiyong Zastrozhnov, Dmitry Lapôtre, Mathieu G. A. |
| author_facet | Prieur, Nils C. Amaro, Brian Gonzalez, Emiliano Kerner, Hannah Medvedev, Sergei Rubanenko, Lior Werner, Stephanie C. Xiao8, Zhiyong Zastrozhnov, Dmitry Lapôtre, Mathieu G. A. |
| contents | Boulders form from a variety of geological processes, which their size, shape, and orientation may help us better understand. Furthermore, they represent potential hazards to spacecraft landing that need to be characterized. However, mapping individual boulders across vast areas is extremely labor-intensive, often limiting the extent over which they are characterized and the statistical robustness of obtained boulder morphometrics. To automate boulder characterization, we use an instance segmentation neural network, Mask R-CNN, to detect and outline boulders in high-resolution satellite images. Our neural network, BoulderNet, was trained from a dataset of > 33,000 boulders in > 750 image tiles from Earth, the Moon, and Mars. BoulderNet not only correctly detects the majority of boulders in images, but it identifies the outline of boulders with high fidelity, achieving average precision and recall values of 72% and 64% relative to manually digitized boulders from the test dataset, when only detections with intersection-over-union ratios > 50% are considered valid. These values are similar to those obtained by human mappers. On Earth, equivalent boulder diameters, aspect ratios, and orientations extracted from predictions were benchmarked against ground measurements and yield values within 15%, 0.20, and 20 degrees of their ground-truth values, respectively. BoulderNet achieves better boulder detection and characterization performance relative to existing methods, providing a versatile open-source tool to characterize entire boulder fields on planetary surfaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07528 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic characterization of boulders on planetary surfaces from high-resolution satellite images Prieur, Nils C. Amaro, Brian Gonzalez, Emiliano Kerner, Hannah Medvedev, Sergei Rubanenko, Lior Werner, Stephanie C. Xiao8, Zhiyong Zastrozhnov, Dmitry Lapôtre, Mathieu G. A. Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics Machine Learning Image and Video Processing Boulders form from a variety of geological processes, which their size, shape, and orientation may help us better understand. Furthermore, they represent potential hazards to spacecraft landing that need to be characterized. However, mapping individual boulders across vast areas is extremely labor-intensive, often limiting the extent over which they are characterized and the statistical robustness of obtained boulder morphometrics. To automate boulder characterization, we use an instance segmentation neural network, Mask R-CNN, to detect and outline boulders in high-resolution satellite images. Our neural network, BoulderNet, was trained from a dataset of > 33,000 boulders in > 750 image tiles from Earth, the Moon, and Mars. BoulderNet not only correctly detects the majority of boulders in images, but it identifies the outline of boulders with high fidelity, achieving average precision and recall values of 72% and 64% relative to manually digitized boulders from the test dataset, when only detections with intersection-over-union ratios > 50% are considered valid. These values are similar to those obtained by human mappers. On Earth, equivalent boulder diameters, aspect ratios, and orientations extracted from predictions were benchmarked against ground measurements and yield values within 15%, 0.20, and 20 degrees of their ground-truth values, respectively. BoulderNet achieves better boulder detection and characterization performance relative to existing methods, providing a versatile open-source tool to characterize entire boulder fields on planetary surfaces. |
| title | Automatic characterization of boulders on planetary surfaces from high-resolution satellite images |
| topic | Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2401.07528 |