arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.07528astro-ph.EPastro-ph.IMcs.LGeess.IV
收藏

基于高分辨率卫星图像的行星表面巨石自动表征

Automatic characterization of boulders on planetary surfaces from high-resolution satellite images

Stanford University(斯坦福大学);University of Oslo(奥斯陆大学);California State Polytechnic University Pomona(加州州立理工大学波莫纳分校);Arizona State University(亚利桑那州立大学);Medvedev Consulting(梅德韦杰夫咨询公司);Technion(以色列理工学院);Sun Yat-Sen University(中山大学);Volcanic Basin Energy Research(火山盆地能源研究机构);A.P. Karpinsky Russian Geological Research Institute(A.P. 卡尔平斯基俄罗斯地质研究所)

Nils C. Prieur, Brian Amaro, Emiliano Gonzalez, Hannah Kerner, Sergei Medvedev, Lior Rubanenko, Stephanie C. Werner, Zhiyong Xiao8, Dmitry Zastrozhnov, Mathieu G. A. Lapôtre

AI总结:

本文提出基于 Mask R-CNN 的 BoulderNet,利用地球、月球和火星高分辨率卫星图像自动检测并勾勒巨石,检测与形态表征性能优于现有方法,为行星表面巨石场表征提供开源工具。

摘要:

巨石由多种地质过程形成,其大小、形状和方向可能有助于我们更好地理解这些过程。此外,它们还代表着航天器着陆需要加以表征的潜在危险。然而,在广阔区域内逐一绘制巨石图极为费力,这往往限制了巨石被表征的范围以及所获巨石形态计量数据的统计稳健性。为了实现巨石表征的自动化,我们使用实例分割神经网络 Mask R-CNN 在高分辨率卫星图像中检测并勾勒巨石轮廓。我们的神经网络 BoulderNet 基于来自地球、月球和火星的超过 750 个图像切片中的超过 33,000 块巨石的数据集训练而成。BoulderNet 不仅能正确检测图像中的大多数巨石,还能以高保真度识别巨石轮廓,当仅将交并比大于 50% 的检测视为有效时,相对于测试数据集中人工数字化的巨石,其平均精确率和召回率分别达到 72% 和 64%。这些数值与人工制图员所获得的结果相近。在地球上,从预测结果中提取的等效巨石直径、纵横比和方向与地面实测值进行了基准比较,其结果分别落在真值的 15%、0.20 和 20 度以内。与现有方法相比,BoulderNet 实现了更优的巨石检测和表征性能,为表征行星表面整个巨石场提供了一个多功能的开源工具。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑