发表机构
Interlake High School（因特莱克高中）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NEO-Bench 是一个包含 8,376 张图像的多源基准，用于评估天文条纹检测的跨源泛化能力，通过留一源出协议发现现有方法泛化性能不稳定，揭示了该领域的开放挑战。
AI 中文摘要
近地天体（NEOs）在长时间曝光的 astronomical 图像中可能呈现为暗淡的条纹。在不同天文台之间检测这些条纹，需要方法在面对图像质量、方向、天空背景和噪声差异时保持可靠性。然而，现有检测器通常仅使用单一来源的数据进行评估，这为跨源泛化提供的证据有限。我们提出了 NEO-Bench，一个包含来自五个天文图像数据集的 8,376 张图像的多源基准。这些来源包括哈勃太空望远镜、Stellina 智能望远镜、阿联酋流星监测网络、使用 Celestron C14 和 Fastar 的 TETRA1 望远镜，以及 Roboflow 小行星数据集。我们将数据转换为统一的 YOLO 格式，审计了部分标签样本，并定义了源内和留一源出评估协议。我们评估了四种方法：Hough、Radon、Gaussian PSF 和 YOLO26L。留一源出的 F1 分数在 20 个图像级方法-源组合中有 14 个下降，在 20 个 IoU@0.50 定位组合中有 13 个下降。在分类为中等或困难的数据集中，F1 分数在 12 个图像级组合中有 11 个下降，在 12 个定位组合中有 9 个下降。这些结果表明，跨源性能仍然不一致，跨天文成像源的可靠泛化仍是一个开放挑战。该基准、代码和数据公开可用。
英文摘要
Near-Earth Objects (NEOs) can appear as faint streaks in long-exposure astronomical images. Detecting these streaks across diverse observatories requires methods that remain reliable despite differences in image quality, orientation, sky background, and noise. However, existing detectors are commonly evaluated using data from only one source, providing limited evidence of cross-source generalization. We introduce NEO-Bench, a multi-source benchmark containing 8,376 images from five astronomical-image datasets. The sources include the Hubble Space Telescope, a Stellina smart telescope, the United Arab Emirates Meteor Monitoring Network, a TETRA1 telescope using a Celestron C14 with Fastar, and the Roboflow Asteroid dataset. We converted the data to a common YOLO format, audited a sample of labels, and defined within-source and leave-one-source-out evaluation protocols. We evaluated four approaches: Hough, Radon, Gaussian PSF, and YOLO26L. Leave-one-source-out F1 decreased in 14 of 20 image-level method-source pairs and 13 of 20 IoU@0.50 localization pairs. Across the datasets categorized as medium or hard, F1 decreased in 11 of 12 image-level pairs and 9 of 12 localization pairs. These results show that cross-source performance remains inconsistent and that reliable generalization across astronomical imaging sources remains an open challenge. The benchmark, code, and data are publicly available.
CommentsThe code and data used in NEO-BENCH are publicly available on GitHub at https://github.com/he-jiayou/NEOBench and on Hugging Face at https://huggingface.co/datasets/jiayou-he/NEO-Bench
