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 2407.09372cs.CVcs.RO
收藏

钢筋混凝土结构的分割数据集

Segmentation Dataset for Reinforced Concrete Construction

DTU - Technical University of Denmark(丹麦技术大学)

Patrick Schmidt, Lazaros Nalpantidis

AI总结:

本文构建了包含14,805张图像的钢筋混凝土缺陷分割数据集,评估YOLOv8L-seg等模型性能,发现数据量是影响深度学习模型表现的关键因素。

摘要:

本文提供了一个包含14,805张RGB图像的数据集,带有分割标签,用于钢筋混凝土缺陷的自主机器人检测。建立了YOLOv8L-seg、DeepLabV3和U-Net分割模型的基线。通过统计方法解决了标注不一致问题,并分析了其对模型性能的影响。使用错误识别工具检查了模型的错误模式。论文表明YOLOv8L-seg表现最佳,验证mIOU得分高达0.59。标签不一致对模型性能的影响可以忽略不计,而增加数据量可提升性能。假阴性被识别为主要失败模式。结果强调了数据可用性对深度学习模型性能的重要性。公开数据的缺乏被认为是导致假阴性的重要因素。为此,本文倡导建筑社区增加开源方法。

英文摘要:

This paper provides a dataset of 14,805 RGB images with segmentation labels for autonomous robotic inspection of reinforced concrete defects. Baselines for the YOLOv8L-seg, DeepLabV3, and U-Net segmentation models are established. Labelling inconsistencies are addressed statistically, and their influence on model performance is analyzed. An error identification tool is employed to examine the error modes of the models. The paper demonstrates that YOLOv8L-seg performs best, achieving a validation mIOU score of up to 0.59. Label inconsistencies were found to have a negligible effect on model performance, while the inclusion of more data improved the performance. False negatives were identified as the primary failure mode. The results highlight the importance of data availability for the performance of deep learning-based models. The lack of publicly available data is identified as a significant contributor to false negatives. To address this, the paper advocates for an increased open-source approach within the construction community.

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。

↑