Visual MAV Tracker with Adaptive Search Region
Tracking a micro aerial vehicle (MAV) is challenging because of its small size and swift motion. A new model was developed by combining compact and adaptive search region (SR). The model can accurately and robustly track MAVs with a fast computation speed. A compact SR, which is slightly larger than...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/16/7741 |
_version_ | 1797524686566850560 |
---|---|
author | Wooryong Park Donghee Lee Junhak Yi Woochul Nam |
author_facet | Wooryong Park Donghee Lee Junhak Yi Woochul Nam |
author_sort | Wooryong Park |
collection | DOAJ |
description | Tracking a micro aerial vehicle (MAV) is challenging because of its small size and swift motion. A new model was developed by combining compact and adaptive search region (SR). The model can accurately and robustly track MAVs with a fast computation speed. A compact SR, which is slightly larger than a target MAV, is less likely to include a distracting background than a large SR; thus, it can accurately track the MAV. Moreover, the compact SR reduces the computation time because tracking can be conducted with a relatively shallow network. An optimal SR to MAV size ratio was obtained in this study. However, this optimal compact SR causes frequent tracking failures in the presence of the dynamic MAV motion. An adaptive SR is proposed to address this problem; it adaptively changes the location and size of the SR based on the size, location, and velocity of the MAV in the SR. The compact SR without adaptive strategy tracks the MAV with an accuracy of 0.613 and a robustness of 0.086, whereas the compact and adaptive SR has an accuracy of 0.811 and a robustness of 1.0. Moreover, online tracking is accomplished within approximately 400 frames per second, which is significantly faster than the real-time speed. |
first_indexed | 2024-03-10T09:01:12Z |
format | Article |
id | doaj.art-3fe39706bbb84cd7aee1704b8f424599 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T09:01:12Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-3fe39706bbb84cd7aee1704b8f4245992023-11-22T06:46:12ZengMDPI AGApplied Sciences2076-34172021-08-011116774110.3390/app11167741Visual MAV Tracker with Adaptive Search RegionWooryong Park0Donghee Lee1Junhak Yi2Woochul Nam3Department of Mechanical Engineering, Chung-Ang University, Seoul 06974, KoreaDepartment of Mechanical Engineering, Chung-Ang University, Seoul 06974, KoreaDepartment of Mechanical Engineering, Chung-Ang University, Seoul 06974, KoreaDepartment of Mechanical Engineering, Chung-Ang University, Seoul 06974, KoreaTracking a micro aerial vehicle (MAV) is challenging because of its small size and swift motion. A new model was developed by combining compact and adaptive search region (SR). The model can accurately and robustly track MAVs with a fast computation speed. A compact SR, which is slightly larger than a target MAV, is less likely to include a distracting background than a large SR; thus, it can accurately track the MAV. Moreover, the compact SR reduces the computation time because tracking can be conducted with a relatively shallow network. An optimal SR to MAV size ratio was obtained in this study. However, this optimal compact SR causes frequent tracking failures in the presence of the dynamic MAV motion. An adaptive SR is proposed to address this problem; it adaptively changes the location and size of the SR based on the size, location, and velocity of the MAV in the SR. The compact SR without adaptive strategy tracks the MAV with an accuracy of 0.613 and a robustness of 0.086, whereas the compact and adaptive SR has an accuracy of 0.811 and a robustness of 1.0. Moreover, online tracking is accomplished within approximately 400 frames per second, which is significantly faster than the real-time speed.https://www.mdpi.com/2076-3417/11/16/7741visual object trackerfully convolutional neural networkadaptive search regiontruncation preventionpath prediction |
spellingShingle | Wooryong Park Donghee Lee Junhak Yi Woochul Nam Visual MAV Tracker with Adaptive Search Region Applied Sciences visual object tracker fully convolutional neural network adaptive search region truncation prevention path prediction |
title | Visual MAV Tracker with Adaptive Search Region |
title_full | Visual MAV Tracker with Adaptive Search Region |
title_fullStr | Visual MAV Tracker with Adaptive Search Region |
title_full_unstemmed | Visual MAV Tracker with Adaptive Search Region |
title_short | Visual MAV Tracker with Adaptive Search Region |
title_sort | visual mav tracker with adaptive search region |
topic | visual object tracker fully convolutional neural network adaptive search region truncation prevention path prediction |
url | https://www.mdpi.com/2076-3417/11/16/7741 |
work_keys_str_mv | AT wooryongpark visualmavtrackerwithadaptivesearchregion AT dongheelee visualmavtrackerwithadaptivesearchregion AT junhakyi visualmavtrackerwithadaptivesearchregion AT woochulnam visualmavtrackerwithadaptivesearchregion |