EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects
This work addresses monitoring needs for security, wildlife conservation, and environmental studies, but it is incremental as it applies existing point-based methods to a new event-based dataset.
The paper tackles the problem of detecting and recognizing flying objects like birds, insects, and drones in real-world scenarios, where traditional RGB-based methods face challenges such as motion blur and scale variations, by introducing EV-Flying, an event-based dataset with spatio-temporal annotations, and employs a point-based approach for classification.
Monitoring aerial objects is crucial for security, wildlife conservation, and environmental studies. Traditional RGB-based approaches struggle with challenges such as scale variations, motion blur, and high-speed object movements, especially for small flying entities like insects and drones. In this work, we explore the potential of event-based vision for detecting and recognizing flying objects, in particular animals that may not follow short and long-term predictable patters. Event cameras offer high temporal resolution, low latency, and robustness to motion blur, making them well-suited for this task. We introduce EV-Flying, an event-based dataset of flying objects, comprising manually annotated birds, insects and drones with spatio-temporal bounding boxes and track identities. To effectively process the asynchronous event streams, we employ a point-based approach leveraging lightweight architectures inspired by PointNet. Our study investigates the classification of flying objects using point cloud-based event representations. The proposed dataset and methodology pave the way for more efficient and reliable aerial object recognition in real-world scenarios.