Share Email Print

Proceedings Paper

Improving unmanned aerial vehicle-based object detection via adversarial training: a (almost) free lunch to enjoy (Conference Presentation)

Paper Abstract

Object detection from images captured by Unmanned Aerial Vehicles (UAVs) are widely used for surveillance, precision agricultural, package delivery, aerial photography, among others. Very recently, a benchmark on object detection using UAVs collected images called VisDrone2018 has been released. However, large performance drop is observed when current state-of-the-art object detection approaches developed primarily for ground-to-ground images are directly applied on the VisDrone2018 dataset. For example, the best detection model on the VisDrone2018 has only achieved detection accuracy of 0.31 mAP, significantly lower than that of ground-based object detection. This performance drop is mainly caused by several challenges, such as 1) varying flying altitudes from 1000 feet to 10 feet, 2) different weather conditions like foggy, rainy and low-light 3) a wide range of camera viewing angles. To overcome these challenges, in this paper we propose to leverage a novel approach of adversarial training that aims to learn domain invariant features with respect to varying altitudes, viewing angles, weather conditions, and object scales. The adversarial training draws on “free” meta-data that comes with the UAV datasets providing information about the data themselves, such as heights, scene visibility, viewing angles, etc. We demonstrate the effectiveness of our proposed algorithm on the recently proposed UAVDT dataset, and also show it to generalize well when applied to a different VisDrone2018 dataset. We will also show robustness of the proposed approach to variations in altitude, viewing angle, weather, and object scale.

Paper Details

Date Published: 14 May 2019
Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 110061B (14 May 2019); doi: 10.1117/12.2518835
Show Author Affiliations
Zhenyu Wu, Texas A&M Univ. (United States)
Karthik Suresh, Texas A&M Univ. (United States)
Zhangyang Wang, Texas A&M Univ. (United States)
Priya Narayanan, U.S. Army Research Lab. (United States)
Heesung Kwon, U.S. Army Research Lab. (United States)

Published in SPIE Proceedings Vol. 11006:
Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications
Tien Pham, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?