FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection

UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially dis...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-09, Vol.22 (18), p.6993
Main Authors: Xu, Wenyu, Zhang, Chaofan, Wang, Qi, Dai, Pangda
Format: Article
Language:English
Subjects:
aerial images
Computational linguistics
Datasets
Deep learning
Design
Electric transformers
Feature maps
Flying-machines
foreground enhancement attention
Image enhancement
improved bidirectional feature pyramid network
Language processing
Natural language interfaces
Neural networks
object detection
Semantics
transformer-based
Unmanned aerial vehicles
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially distributed in a very dense manner, these methods have limited performance for UAV-based object detection. In this paper, we propose a novel transformer-based object detection model to improve the accuracy of object detection in UAV images. To detect dense objects competently, an advanced foreground enhancement attention Swin Transformer (FEA-Swin) framework is designed by integrating context information into the original backbone of a Swin Transformer. Moreover, to avoid the loss of information of small objects, an improved weighted bidirectional feature pyramid network (BiFPN) is presented by designing the skip connection operation. The proposed method aggregates feature maps from four stages and keeps abundant information of small objects. Specifically, to balance the detection accuracy and efficiency, we introduce an efficient neck of the BiFPN network by removing a redundant network layer. Experimental results on both public datasets and a self-made dataset demonstrate the performance of our method compared to the state-of-the-art methods in terms of detection accuracy.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22186993