Lester, D., & Zhu, P., & Narman, H. S., & Alzarrad, A. (2025, March), A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos  Paper presented at 2025 ASEE North Central Section  (NCS) Annual Conference, Marshall University, Huntington, West Virginia. 10.18260/1-2--54646

\bibitem{asee_peer_54646}
  Lester, D., \& Zhu, P., \& Narman, H. S., \& Alzarrad, A. (2025, March), \emph{A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos}
  Paper presented at 2025 ASEE North Central Section  (NCS) Annual Conference, Marshall University, Huntington, West Virginia.
  10.18260/1-2--54646

Dylan Lester, Pingping Zhu, Husnu Saner Narman, and Ammar Alzarrad.  "A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos".  2025 ASEE North Central Section  (NCS) Annual Conference, Marshall University, Huntington, West Virginia, 2025, March.  ASEE Conferences, 2025.  https://peer.asee.org/54646 Internet.  15 May, 2025

\bibitem{asee_peer_54646}
  Dylan Lester, Pingping Zhu, Husnu Saner Narman, and Ammar Alzarrad.
  "A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos".
  \emph{2025 ASEE North Central Section  (NCS) Annual Conference, Marshall University, Huntington, West Virginia, 2025, March}.
  ASEE Conferences, 2025.
  https://peer.asee.org/54646 Internet.  15 May, 2025

@INPROCEEDINGS{asee_peer_54646
author = "Dylan Lester, Pingping Zhu, Husnu Saner Narman, and Ammar Alzarrad"
title = "A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos"
booktitle = "2025 ASEE North Central Section  (NCS) Annual Conference"
year = "2025"
month = "March"
address = "Marshall University, Huntington, West Virginia"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/54646}
number = {10.18260/1-2--54646}
}

TY  - CPAPER
AB  - Manual labeling for large-scale image and video datasets is often time-intensive, error-prone, and costly, posing a significant barrier to efficient machine-learning workflows in fault detection from railroad videos. This study introduces a semi-automated labeling method that utilizes a pre-trained YOLO model to streamline the labeling process and enhance fault detection accuracy in railroad videos. By initiating the process with a small set of manually labeled data, our approach iteratively trains the YOLO model, using each cycle’s output to improve model accuracy and progressively reduce the need for human intervention.

To facilitate easy correction of model predictions, we developed a system to export YOLO’s detection data as an editable text file, enabling rapid adjustments when detections require refinement. This approach decreases labeling time from an average of 2–4 minutes per image to 30 seconds–2 minutes, effectively minimizing labor costs and labeling errors. Unlike costly AI-based labeling solutions on paid platforms, our method provides a cost-effective alternative for researchers and practitioners handling large datasets in fault detection and other detection-based machine learning applications.
AU  - Dylan Lester
AU  - Pingping Zhu
AU  - Husnu Saner Narman
AU  - Ammar Alzarrad
CY  - Marshall University, Huntington, West Virginia
DA  - 2025/03/28
PB  - ASEE Conferences
TI  - A YOLO-Based Semi-Automated Labeling Approach to Improve Fault Detection Efficiency in Railroad Videos
UR  - https://peer.asee.org/54646
DO  - 10.18260/1-2--54646
ER  -