用手机拍照3秒估出工业电缆盘长度，误差低于5%。
CableDex: Cable Length Estimation on Industrial Reels Using a Handheld Device
- 通过图像分割+姿态估计+体积计算，从单张照片估算电缆长度。
- 在75个电缆盘上测试，平均绝对百分比误差仅4.90%。
- 适合工厂、仓库等需要快速测量电缆的场景使用。
CableDex 是一个计算机视觉系统，旨在解决工业电缆盘上电缆长度依赖人工测量导致耗时且不准确的问题。该系统基于手机拍摄的一张照片，结合相机标定、实例分割、姿态估计与体积计算，实现对五种不同卷轴类型和多种电缆尺寸的长度估计。系统采用在1,000张手动标注图像上训练的实例分割模型，达到99.5%的mAP50，单图推理时间仅为5.66毫秒。在覆盖五种卷轴类型的75个电缆盘上进行评估，系统实现4.90%的平均绝对百分比误差（MAPE），优于工业界普遍接受的10%误差容忍度。演示展示了从扫描卷轴标签、拍照到分割与长度估算的完整端到端流程，集成于移动端应用中。
原文摘要 · Abstract (English)
CableDex is a computer vision system that addresses the time-consuming and inaccurate manual measurement of cable length on industrial reels from a single photograph captured with a mobile phone. The system combines camera calibration, instance segmentation, pose estimation, and volumetric calculation to estimate the cable length across five different reel types and various cable sizes. This system is based on an instance segmentation model trained on 1,000 manually annotated images, achieving 99.5\% mAP50 with an inference time of 5.66 ms per image. Evaluated on 75 reels across five reel types, the system achieves a MAPE of 4.90\%, within the 10\% error tolerance commonly accepted in industrial cable-reel measurement. The demonstration presents the end-to-end pipeline, from reel label scanning and image capture to segmentation and length estimation, through the mobile application.
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。