导航

Acta Aeronautica et Astronautica Sinica

    Next Articles

Research advances on deep learning-based small object detection in UAV aerial images

  

  • Received:2024-06-20 Revised:2024-09-10 Online:2024-09-20 Published:2024-09-20
  • Contact: Yi-Quan WU

Abstract: Small object detection in UAV (Unmanned Aerial Vehicle) aerial images based on deep learning has a wide range of applications in military intelligence reconnaissance, battlefield surveillance and assessment, military object cap-ture and verification, intelligent traffic management, infrastructure inspection and maintenance, disaster prevention and control, search and rescue, crop management and analysis, ecological protection and monitoring and other fields, and has become a current research hotspot in recent years. However, no review on this topic has been found, so a comprehensive and in-depth investigation is conducted on small object detection in UAV aerial images based on deep learning in the past five years. First of all, the definition and challenges of small object detection in UAV aerial images are introduced. Secondly, focus on discriminative feature learning, super-resolution technology, real-time lightweight detection, and other improvement ideas to summarize the drone aerial image small object detection methods in detail. Then systematically summarize the small object detection datasets of UAV aerial images, and analyze the performance of different algorithms based on the VisDrone Challenge. Finally, comprehensively present the specific applications of small object detection in UAV aerial images in the military and civilian fields, discuss its potential future development directions, and point out some concerns about UAV aerial photography. It is expected that this review would inspire relevant researchers to further promote the development of small object detection in UAV aerial images based on deep learning.

Key words: small object detection, unmanned aerial vehicle, aerial images, deep learning, performance evaluation, small object detection applications

CLC Number: