Conference paper Open Access

Tracking and Classification of Aerial Objects

Baptista, Marcia; Fernandes, Luis; Chaves, Paulo

Unauthorized drone flying can prompt disruptions in critical facilities such as airports or railways. To prevent these situations, we propose a surveillance system that can sense malicious and/or illicit aerial targets. The idea is to track moving aerial objects using a static camera and when a tracked object is considered suspicious, the camera zooms in to take a snapshot of the target. This snapshot is then classified as an aircraft, drone, bird or cloud. In this work, we propose the classical technique of two-frame background subtraction to detect moving objects. We use the discrete Kalman filter to predict the location of each object and the Jonker-Volgenant algorithm to match objects between consecutive image frames. A deep residual network, trained with transfer learning, is used for image classification. The residual net ResNet-50 developed for the ILSVRC competition was retrained for this purpose. The performance of the system was evaluated with positive results in real-world conditions. The system was able to track multiple aerial objects with acceptable accuracy and the classification system also exhibited high performance.

Files (532.5 kB)
Name Size
532.5 kB Download
All versions This version
Views 8787
Downloads 144144
Data volume 76.7 MB76.7 MB
Unique views 7676
Unique downloads 136136


Cite as