用深度学习自动识别电线杆和警示牌，精度超90%。
Advancing Utility Pole and Sign Detection Through Deep Learning
- 基于DETR改进模型，结合图像分割与角度估计
- 电线杆检测准确率90.43%，警示牌88.26%，角度误差仅1.01度
- 自建4570张街景数据集，公开可用作基准
电力电线杆是支撑配电系统与公共设施的关键基础设施，定期巡检对电网安全至关重要。本文提出一种深度学习框架，利用地面视角图像实现木质电线杆的自动检测、分割及倾斜角度估计，并对附着的电气警示牌进行分类。模型在包含4,570张标注图像的自建数据集上训练，该数据集源自Google Street View，涵盖真实场景中特征不明显的木质电线杆。模型基于检测变压器（DETR）改进并训练，优于传统检测器（RetinaNet、Faster R-CNN、YOLOv3-Tiny），在电线杆检测上达到90.43%的平均精度，在警示牌检测上达88.26%。通过增加分割头生成实例掩码，进而估算电线杆倾斜角度，测试集中1,367根电线杆的倾斜估计准确，平均绝对误差为1.01度。此外，本研究构建的定制数据集也公开发布，可作为未来研究的基准。
原文摘要 · Abstract (English)
Utility poles are an essential part of the infrastructure used to support power distribution systems and other critical public services. Their regular inspection is crucial to ensure the stability and safety of the electrical grid. A deep learning framework is presented for the automated detection, segmentation and lean angle estimation of wooden utility poles, and classification of attached electrical warning signs, using ground-level imagery. The system is trained on a custom dataset of 4,570 annotated images extracted from Google Street View, featuring challenging real-world scenes with visually ambiguous wooden poles lacking distinctive features. The proposed model is based on the Detection Transformer (DETR), suitably modified and trained on the custom dataset. The model outperforms standard object detectors (RetinaNet, Faster R-CNN, YOLOv3-Tiny), achieving a mean average precision of 90.43% for pole detection and 88.26% for sign detection. Extending this model with a segmentation head enables per-instance mask generation, which is then used to estimate pole lean angle. The model accurately estimates lean for 1,367 out of 1,433 test-set poles, with a mean absolute error of 1.01 degrees. Moreover, the custom dataset created in this work is also made publicly available to be used as a benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。