Abstract Drones are nowadays considered as a valuable solution to monitor urban traffic. Object detectors face numerous challenges when dealing with high-resolution aerial images captured by drones, due to variations in altitude, viewing angle, and weather conditions. To address these challenges, we present an object detector called Butterfly detector that is tailored to detect objects in aerial images. It is an anchor-free method that leverages field-based representations. We introduce Butterfly fields, a type of composite field that describes the spatial information of output features as well as the scale of the detected objects. We employ a voting mechanism between related Butterfly vectors pointing to the object center. We highlight the benefits of our method for urban traffic monitoring by (i) evaluating the recall/precision rate of our detector on two publicly available drone datasets (UAVDT and VisDrone2019), and (ii) measuring the error rate for flow estimations on our newly released EPFL roundabout dataset. We outperform the performance of previous methods while remaining real-time.
Highlights Introduce a novel anchor-free object detector called Butterfly Detector. Leverage composite fields to deal with the challenges of detection from aerial images. Improve aerial object detection performance especially in high altitude scenarios.
Traffic perception from aerial images using butterfly fields
2023-05-17
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Automatic traffic data collection using aerial video images
Kraftfahrwesen | 1989
|Automatic traffic data collection using aerial video images
Tema Archiv | 1989
|BASE | 2015
|Entity Perception Using Remotely Piloted Aerial Vehicle
Springer Verlag | 2024
|