NU-AIR -- A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles
This provides a specialized dataset for neuromorphic vision research in aerial applications, addressing a domain-specific need but is incremental as it builds on existing dataset efforts.
The authors introduced NU-AIR, an open-source aerial neuromorphic dataset with 70.75 minutes of event footage for detecting and localizing pedestrians and vehicles in urban settings, validated by training 10 DNNs and 3 SNNs to ensure data quality.
This paper presents an open-source aerial neuromorphic dataset that captures pedestrians and vehicles moving in an urban environment. The dataset, titled NU-AIR, features 70.75 minutes of event footage acquired with a 640 x 480 resolution neuromorphic sensor mounted on a quadrotor operating in an urban environment. Crowds of pedestrians, different types of vehicles, and street scenes featuring busy urban environments are captured at different elevations and illumination conditions. Manual bounding box annotations of vehicles and pedestrians contained in the recordings are provided at a frequency of 30 Hz, yielding 93,204 labels in total. Evaluation of the dataset's fidelity is performed through comprehensive ablation study for three Spiking Neural Networks (SNNs) and training ten Deep Neural Networks (DNNs) to validate the quality and reliability of both the dataset and corresponding annotations. All data and Python code to voxelize the data and subsequently train SNNs/DNNs has been open-sourced.