TartanAviation: Image, Speech, and ADS-B Trajectory Datasets for Terminal Airspace Operations

TL;DR

TartanAviation, an open-source multi-modal dataset focused on terminal-area airspace operations, is introduced, believing it has many potential use cases and would be particularly vital in allowing AI and machine learning technologies to be integrated into air traffic control systems and advance the adoption of autonomous aircraft in the airspace.

Abstract

We introduce TartanAviation, an open-source multi-modal dataset focused on terminal-area airspace operations. TartanAviation provides a holistic view of the airport environment by concurrently collecting image, speech, and ADS-B trajectory data using setups installed inside airport boundaries. The datasets were collected at both towered and non-towered airfields across multiple months to capture diversity in aircraft operations, seasons, aircraft types, and weather conditions. In total, TartanAviation provides 3.1M images, 3374 hours of Air Traffic Control speech data, and 661 days of ADS-B trajectory data. The data was filtered, processed, and validated to create a curated dataset. In addition to the dataset, we also open-source the code-base used to collect and pre-process the dataset, further enhancing accessibility and usability. We believe this dataset has many potential use cases and would be particularly vital in allowing AI and machine learning technologies to be integrated into air traffic control systems and advance the adoption of autonomous aircraft in the airspace.

Figures (6)

• Figure 1: Our custom data collection setup installed at the Allegheny County Airport with its approximate location within the airport premises with respect to the runway geometry. The setup recorded images, audio, and aircraft trajectory data.
• Figure 2: Our custom setup hardware with the camera and ADS-B antenna mounts (left). We also showcase the data collection pipeline with the associated sensor suite and automatic logic that triggers camera and speech recordings (right).
• Figure 3: Qualitative samples from the TartanAviation Image dataset showcasing the diversity of the collected images in different lighting conditions, seasons, cloud covers, and aircraft types.
• Figure 4: Log-normed trajectory histograms from ADS-B aircraft position reports.
• Figure 5: Quantitative diversity from the TartanAviation Image dataset showcasing the distribution of the collected images with respect to aircraft groups, cloud heights, and cloud cover.