Home // SENSORDEVICES 2021, The Twelfth International Conference on Sensor Device Technologies and Applications // View article

Tracking Suspicious Entities Using UAVs in Critical Urban Areas: A R-CNN Approach

Authors:
Mathias Afonso Guedes de Menezes
Paulo Fernando Ferreira Rosa
Erick Menezes Moreira

Keywords: object detection, object tracking, r-cnn, surveillance.

Abstract:
This paper proposes a tracking application that integrates object detection with a Region-based Convolutional Neural Network as the object detector and the Discriminative Correlation Filter with Channel and Spatial Reliability as the tracking algorithm for the tracking method. Our approach has the objective and motivation of assisting the operational actions of the security forces in Rio de Janeiro, especially the Military Police, in deflagrated regions. The results of the generated model showed an average accuracy of 86% for the object detector and an average of 74% for the object tracker when applied to the video sequences of our dataset.

Pages: 19 to 24

Copyright: Copyright (c) IARIA, 2021

Publication date: November 14, 2021

Published in: conference

ISSN: 2308-3514

ISBN: 978-1-61208-918-8

Location: Athens, Greece

Dates: from November 14, 2021 to November 18, 2021