Vehicle detection in UAV traffic videos using GAN online augmentation: a transfer learning approach

YingJie Du; YuWei Yi; He Guo; XiangJie Tian

doi:10.1117/12.2660020

3 February 2023 Vehicle detection in UAV traffic videos using GAN online augmentation: a transfer learning approach

YingJie Du, YuWei Yi, He Guo, XiangJie Tian

Proceedings Volume 12511, Third International Conference on Computer Vision and Data Mining (ICCVDM 2022); 1251132 (2023) https://doi.org/10.1117/12.2660020
Event: Third International Conference on Computer Vision and Data Mining (ICCVDM 2022), 2022, Hulun Buir, China

Abstract

Low resolution object detection could be challenging. In this paper, we proposed a GAN-based real-time data augmentation algorithm for the transfer learning task of UAV vehicle detection from ImageNet, with improvements including using FocalLoss to replace the cross-entropy loss commonly used in the industry, as well as redesigning the target detection Head combination to improve the model’s detection accuracy by 4% over original YOLOv5 model. We make it feasible for deployments on UAV-carried ARM systems.

Citation Download Citation

YingJie Du, YuWei Yi, He Guo, and XiangJie Tian "Vehicle detection in UAV traffic videos using GAN online augmentation: a transfer learning approach", Proc. SPIE 12511, Third International Conference on Computer Vision and Data Mining (ICCVDM 2022), 1251132 (3 February 2023); https://doi.org/10.1117/12.2660020

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available