Paper Info
Title
AI-Enabled Object Detection in UAVs: Challenges, Design Choices, and Research Directions
Abstract
Unmanned aerial vehicles (UAVs) are emerging as a powerful tool for various industrial and smart city applications. UAVs coupled with various sensors can perform many cognitive tasks such as object detection, surveillance, traffic management, and urban planning. Deep learning has emerged as a popular technique to speed up the processing of high-dimensional data like images and videos, which has led to several applications in surveillance and autonomous driving. However, the area of aerial object detection has been understudied. This work proposes a deep learning approach for detection of objects in aerial scenes captured by UAVs. Our work first categorizes the current methods for aerial object detection using deep learning techniques and discusses how the task is different from general object detection scenarios. We delineate the specific challenges involved and experimentally demonstrate the key design decisions that significantly affect the accuracy and robustness of models. We further propose an optimized architecture that utilizes these optimal design choices along with the recent Res-NeSt backbone to achieve superior performance in aerial object detection. Lastly, we propose several research directions to inspire further advancement in aerial object detection.
Year
DOI
Venue
2021
10.1109/MNET.011.2000643
IEEE Network
Keywords
DocType
Volume
aerial object detection,deep learning techniques,general object detection scenarios,AI-enabled object detection,UAVs,unmanned aerial vehicles,industrial city applications,smart city applications
Journal
35
Issue
ISSN
Citations 
4
0890-8044
0
PageRank 
References 
Authors
0.34
2
7
Name
Order
Citations
PageRank
Ayush Kumar Jain1288.45
Rohit Ramaprasad200.68
Pratik Narang300.34
Murari Mandal400.34
Vinay Chamola517424.09
Fei Yu65116335.58
Mohsen Guizan700.34