Research Article
Tracking and Classification of Aerial Objects
@INPROCEEDINGS{10.1007/978-3-030-38822-5_18, author={Marcia Baptista and Luis Fernandes and Paulo Chaves}, title={Tracking and Classification of Aerial Objects}, proceedings={Intelligent Transport Systems. From Research and Development to the Market Uptake. Third EAI International Conference, INTSYS 2019, Braga, Portugal, December 4--6, 2019}, proceedings_a={INTSYS}, year={2020}, month={1}, keywords={Object tracking Deep learning Residual networks}, doi={10.1007/978-3-030-38822-5_18} }- Marcia Baptista
Luis Fernandes
Paulo Chaves
Year: 2020
Tracking and Classification of Aerial Objects
INTSYS
Springer
DOI: 10.1007/978-3-030-38822-5_18
Abstract
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.
