This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
An Effective and Lightweight Full-Scale Target Detection Network for UAV Images Based on Deformable Convolutions and Multi-Scale Contextual Feature Optimization
by
Wanwan Yu
Wanwan Yu *
,
Junping Zhang
Junping Zhang
,
Dongyang Liu
Dongyang Liu ,
Yunqiao Xi
Yunqiao Xi and
Yinhu Wu
Yinhu Wu
School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2024, 16(16), 2944; https://doi.org/10.3390/rs16162944 (registering DOI)
Submission received: 21 June 2024
/
Revised: 7 August 2024
/
Accepted: 8 August 2024
/
Published: 11 August 2024
Abstract
Currently, target detection on unmanned aerial vehicle (UAV) images is a research hotspot. Due to the significant scale variability of targets and the interference of complex backgrounds, current target detection models face challenges when applied to UAV images. To address these issues, we designed an effective and lightweight full-scale target detection network, FSTD-Net. The design of FSTD-Net is based on three principal aspects. Firstly, to optimize the extracted target features at different scales while minimizing background noise and sparse feature representations, a multi-scale contextual information extraction module (MSCIEM) is developed. The multi-scale information extraction module (MSIEM) in MSCIEM can better capture multi-scale features, and the contextual information extraction module (CIEM) in MSCIEM is designed to capture long-range contextual information. Secondly, to better adapt to various target shapes at different scales in UAV images, we propose the feature extraction module fitting different shapes (FEMFDS), based on deformable convolutions. Finally, considering low-level features contain rich details, a low-level feature enhancement branch (LLFEB) is designed. The experiments demonstrate that, compared to the second-best model, the proposed FSTD-Net achieves improvements of 3.8%, 2.4%, and 2.0% in AP50, AP, and AP75 on the VisDrone2019, respectively. Additionally, FSTD-Net achieves enhancements of 3.4%, 1.7%, and 1% on the UAVDT dataset. Our proposed FSTD-Net has better detection performance compared to state-of-the-art detection models. The experimental results indicate the effectiveness of the FSTD-Net for target detection in UAV images.
Share and Cite
MDPI and ACS Style
Yu, W.; Zhang, J.; Liu, D.; Xi, Y.; Wu, Y.
An Effective and Lightweight Full-Scale Target Detection Network for UAV Images Based on Deformable Convolutions and Multi-Scale Contextual Feature Optimization. Remote Sens. 2024, 16, 2944.
https://doi.org/10.3390/rs16162944
AMA Style
Yu W, Zhang J, Liu D, Xi Y, Wu Y.
An Effective and Lightweight Full-Scale Target Detection Network for UAV Images Based on Deformable Convolutions and Multi-Scale Contextual Feature Optimization. Remote Sensing. 2024; 16(16):2944.
https://doi.org/10.3390/rs16162944
Chicago/Turabian Style
Yu, Wanwan, Junping Zhang, Dongyang Liu, Yunqiao Xi, and Yinhu Wu.
2024. "An Effective and Lightweight Full-Scale Target Detection Network for UAV Images Based on Deformable Convolutions and Multi-Scale Contextual Feature Optimization" Remote Sensing 16, no. 16: 2944.
https://doi.org/10.3390/rs16162944
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.