Runway vs. Taxiway: Challenges in Automated Line Identification and Notation Approaches

TL;DR

The paper investigates automated labeling of runway versus taxiway markings and identifies the limitations of the ALINA framework when applied to runways due to environmental context and visual interferences. To address this, it introduces AssistNet, a CNN-based classifier that distinguishes runway from taxiway images and guides subsequent labeling, coupled with refined color thresholds and a reduced ROI. On the AssistTaxi dataset, AssistNet achieves a validation accuracy of approximately 99.5% after dataset expansion and ROI-focused preprocessing, demonstrating robustness against variations such as occlusion and motion blur. This work lays groundwork for more reliable automated runway labeling, with future directions including dynamic ROI, contextual horizon cues, and sensor fusion to further enhance performance in diverse aviation environments.

Abstract

The increasing complexity of autonomous systems has amplified the need for accurate and reliable labeling of runway and taxiway markings to ensure operational safety. Precise detection and labeling of these markings are critical for tasks such as navigation, landing assistance, and ground control automation. Existing labeling algorithms, like the Automated Line Identification and Notation Algorithm (ALINA), have demonstrated success in identifying taxiway markings but encounter significant challenges when applied to runway markings. This limitation arises due to notable differences in line characteristics, environmental context, and interference from elements such as shadows, tire marks, and varying surface conditions. To address these challenges, we modified ALINA by adjusting color thresholds and refining region of interest (ROI) selection to better suit runway-specific contexts. While these modifications yielded limited improvements, the algorithm still struggled with consistent runway identification, often mislabeling elements such as the horizon or non-relevant background features. This highlighted the need for a more robust solution capable of adapting to diverse visual interferences. In this paper, we propose integrating a classification step using a Convolutional Neural Network (CNN) named AssistNet. By incorporating this classification step, the detection pipeline becomes more resilient to environmental variations and misclassifications. This work not only identifies the challenges but also outlines solutions, paving the way for improved automated labeling techniques essential for autonomous aviation systems.

Figures (5)

• Figure 1: Results of ALINA’s Line Labeling on Runway Instances with Adjusted Color Thresholding.
• Figure 2: Proposed Labeling Framework with Initial Classification Step
• Figure 3: Instances from the AssistTaxi Dataset ganeriwala2023assisttaxi
• Figure 4: Training and Validation Results over 20 epochs
• Figure 5: Classification Results