A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion

Remote sensing targets typically exhibit characteristics of gradual scale changes and diverse orientations. Most existing remote sensing detectors adapt to these differences by adding multi-level structures for feature fusion. However, this approach leads to incomplete coverage of the overall target...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Wang, Guanghu Xu, Donglin Jing
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766083628630016
author Qi Wang
Guanghu Xu
Donglin Jing
author_facet Qi Wang
Guanghu Xu
Donglin Jing
author_sort Qi Wang
collection DOAJ
description Remote sensing targets typically exhibit characteristics of gradual scale changes and diverse orientations. Most existing remote sensing detectors adapt to these differences by adding multi-level structures for feature fusion. However, this approach leads to incomplete coverage of the overall target by the extracted local features, resulting in the loss of critical directional information and an increase in computational complexity which affect the detector’s performance. To address this issue, this paper proposes a Rotation Target Detection Network based on Multi-kernel Interaction and Hierarchical Expansion (MIHE-Net) as a systematic solution. Specifically, we first refine scale modeling through the Multi-kernel Context Interaction (MCI) module and Hierarchical Expansion Attention (HEA) mechanism, achieving sufficient extraction of local features and global information for targets of different scales. Additionally, the Midpoint Offset Loss Function is employed to mitigate the impact of gradual scale changes on target direction perception, enabling precise regression for targets across various scales. We conducted comparative experiments on three commonly used remote sensing target datasets (DOTA, HRSC2016, and UCAS-AOD), with mean average precision (mAP) as the core evaluation metric. The mAP values of the method in this paper on the three datasets reached 81.72%, 92.43%, and 91.86% respectively, which were 0.65%, 1.93%, and 1.87% higher than those of the optimal method, significantly outperforming existing one-stage and two-stage detectors. Through multi-scale feature interaction and direction-aware optimization, MIHE-Net effectively addresses the challenges posed by scale gradation and direction diversity in remote sensing target detection, providing an efficient and feasible solution for high-precision remote sensing target detection.
format Article
id doaj-art-0c699c8da58f4a39917eb693aa7677ca
institution DOAJ
issn 2076-3417
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-0c699c8da58f4a39917eb693aa7677ca2025-08-20T03:04:42ZengMDPI AGApplied Sciences2076-34172025-08-011515872710.3390/app15158727A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical ExpansionQi Wang0Guanghu Xu1Donglin Jing2School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaRemote sensing targets typically exhibit characteristics of gradual scale changes and diverse orientations. Most existing remote sensing detectors adapt to these differences by adding multi-level structures for feature fusion. However, this approach leads to incomplete coverage of the overall target by the extracted local features, resulting in the loss of critical directional information and an increase in computational complexity which affect the detector’s performance. To address this issue, this paper proposes a Rotation Target Detection Network based on Multi-kernel Interaction and Hierarchical Expansion (MIHE-Net) as a systematic solution. Specifically, we first refine scale modeling through the Multi-kernel Context Interaction (MCI) module and Hierarchical Expansion Attention (HEA) mechanism, achieving sufficient extraction of local features and global information for targets of different scales. Additionally, the Midpoint Offset Loss Function is employed to mitigate the impact of gradual scale changes on target direction perception, enabling precise regression for targets across various scales. We conducted comparative experiments on three commonly used remote sensing target datasets (DOTA, HRSC2016, and UCAS-AOD), with mean average precision (mAP) as the core evaluation metric. The mAP values of the method in this paper on the three datasets reached 81.72%, 92.43%, and 91.86% respectively, which were 0.65%, 1.93%, and 1.87% higher than those of the optimal method, significantly outperforming existing one-stage and two-stage detectors. Through multi-scale feature interaction and direction-aware optimization, MIHE-Net effectively addresses the challenges posed by scale gradation and direction diversity in remote sensing target detection, providing an efficient and feasible solution for high-precision remote sensing target detection.https://www.mdpi.com/2076-3417/15/15/8727depthwise separable convolutionprogressive scale variationtargets with diverse orientations
spellingShingle Qi Wang
Guanghu Xu
Donglin Jing
A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
Applied Sciences
depthwise separable convolution
progressive scale variation
targets with diverse orientations
title A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
title_full A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
title_fullStr A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
title_full_unstemmed A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
title_short A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion
title_sort rotation target detection network based on multi kernel interaction and hierarchical expansion
topic depthwise separable convolution
progressive scale variation
targets with diverse orientations
url https://www.mdpi.com/2076-3417/15/15/8727
work_keys_str_mv AT qiwang arotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion
AT guanghuxu arotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion
AT donglinjing arotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion
AT qiwang rotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion
AT guanghuxu rotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion
AT donglinjing rotationtargetdetectionnetworkbasedonmultikernelinteractionandhierarchicalexpansion