Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications
The ever-burgeoning growth of autonomous unmanned aerial vehicles (UAVs) has demonstrated a promising platform for utilization in real-world applications. In particular, a UAV equipped with a vision system could be leveraged for surveillance applications. This paper proposes a learning-based UAV sys...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/23/7888 |
_version_ | 1797507207999258624 |
---|---|
author | Li-Yu Lo Chi Hao Yiu Yu Tang An-Shik Yang Boyang Li Chih-Yung Wen |
author_facet | Li-Yu Lo Chi Hao Yiu Yu Tang An-Shik Yang Boyang Li Chih-Yung Wen |
author_sort | Li-Yu Lo |
collection | DOAJ |
description | The ever-burgeoning growth of autonomous unmanned aerial vehicles (UAVs) has demonstrated a promising platform for utilization in real-world applications. In particular, a UAV equipped with a vision system could be leveraged for surveillance applications. This paper proposes a learning-based UAV system for achieving autonomous surveillance, in which the UAV can be of assistance in autonomously detecting, tracking, and following a target object without human intervention. Specifically, we adopted the YOLOv4-Tiny algorithm for semantic object detection and then consolidated it with a 3D object pose estimation method and Kalman filter to enhance the perception performance. In addition, UAV path planning for a surveillance maneuver is integrated to complete the fully autonomous system. The perception module is assessed on a quadrotor UAV, while the whole system is validated through flight experiments. The experiment results verified the robustness, effectiveness, and reliability of the autonomous object tracking UAV system in performing surveillance tasks. The source code is released to the research community for future reference. |
first_indexed | 2024-03-10T04:45:16Z |
format | Article |
id | doaj.art-3a5272b174ae4a5c94346f6774646ea6 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T04:45:16Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-3a5272b174ae4a5c94346f6774646ea62023-11-23T03:01:04ZengMDPI AGSensors1424-82202021-11-012123788810.3390/s21237888Dynamic Object Tracking on Autonomous UAV System for Surveillance ApplicationsLi-Yu Lo0Chi Hao Yiu1Yu Tang2An-Shik Yang3Boyang Li4Chih-Yung Wen5Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ChinaDepartment of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ChinaDepartment of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ChinaDepartment of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, Taipei 10608, TaiwanDepartment of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ChinaDepartment of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ChinaThe ever-burgeoning growth of autonomous unmanned aerial vehicles (UAVs) has demonstrated a promising platform for utilization in real-world applications. In particular, a UAV equipped with a vision system could be leveraged for surveillance applications. This paper proposes a learning-based UAV system for achieving autonomous surveillance, in which the UAV can be of assistance in autonomously detecting, tracking, and following a target object without human intervention. Specifically, we adopted the YOLOv4-Tiny algorithm for semantic object detection and then consolidated it with a 3D object pose estimation method and Kalman filter to enhance the perception performance. In addition, UAV path planning for a surveillance maneuver is integrated to complete the fully autonomous system. The perception module is assessed on a quadrotor UAV, while the whole system is validated through flight experiments. The experiment results verified the robustness, effectiveness, and reliability of the autonomous object tracking UAV system in performing surveillance tasks. The source code is released to the research community for future reference.https://www.mdpi.com/1424-8220/21/23/7888UAVobject detectionobject trackingdeep learningKalman Filterautonomous surveillance |
spellingShingle | Li-Yu Lo Chi Hao Yiu Yu Tang An-Shik Yang Boyang Li Chih-Yung Wen Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications Sensors UAV object detection object tracking deep learning Kalman Filter autonomous surveillance |
title | Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications |
title_full | Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications |
title_fullStr | Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications |
title_full_unstemmed | Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications |
title_short | Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications |
title_sort | dynamic object tracking on autonomous uav system for surveillance applications |
topic | UAV object detection object tracking deep learning Kalman Filter autonomous surveillance |
url | https://www.mdpi.com/1424-8220/21/23/7888 |
work_keys_str_mv | AT liyulo dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications AT chihaoyiu dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications AT yutang dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications AT anshikyang dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications AT boyangli dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications AT chihyungwen dynamicobjecttrackingonautonomousuavsystemforsurveillanceapplications |