DCP-Net: Learning Detail–Context Perception via Spatial-Frequency Guidance for Tiny Object Detection in Remote Sensing Images

遥感 计算机科学 计算机视觉 目标检测 人工智能 对象(语法) 感知 遥感应用 基于对象 地球遥感 反射率 像素 特征提取 视觉对象识别的认知神经科学 图像处理 雷达成像
作者
Yupei Wang,Yaxin Jia,Xiaogang Yu,W Liu,Liang Chen
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:64: 5630614-5630614 被引量:3
标识
DOI:10.1109/tgrs.2026.3705062
摘要

Tiny object detection (TOD) in remote sensing images has long been challenging due to the low resolution of tiny objects and complex backgrounds. However, existing adaptive receptive field methods mainly focus on object and contextual information, making them susceptible to interference from complex backgrounds. This interference exacerbates the imbalance in sample assignment and hinders accurate adaptation of receptive fields to object scales, resulting in insufficient representation of fine-grained object details. In addition, most loss functions are prone to gradient instability in scenarios involving small objects. To address the aforementioned problems, this article proposes a detail–context perception network (DCP-Net), which learns detail–context perception under spatial-frequency guidance. To enhance the representation of details of tiny objects, the network is the first to leverage spatial frequency to distinguish the structural features of objects and background. By introducing a spatial-frequency guided dual-dilated convolution (SpatialFGDDConv), it effectively enhances local object details and global semantic associations while suppressing interference from complex backgrounds. Based on this convolutional unit, we further design a cross-layer fine-grained fusion module to recover lost object details at a lower computational cost. Furthermore, we introduce a Gaussian classification-regression loss to address the issues of imbalanced sample allocation and unstable gradient, while applying a decoupled probabilistic metric strategy and a multiscale enhanced decoupled head (ME-Decoupled Head) to improve localization accuracy. Extensive experimental results demonstrate the effectiveness of the proposed method. Specifically, DCP-Net achieves an average precision (AP) of 27.5% on the AI-TODv2 dataset and an AP50 of 78.0% on the DOTA-v1.0 dataset. The code will be found at:https://github.com/yangyvni/DCP-Net
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
朝夕完成签到,获得积分10
刚刚
淙淙完成签到,获得积分10
1秒前
风雨完成签到,获得积分10
1秒前
赵涵完成签到,获得积分20
1秒前
1秒前
hi发布了新的文献求助10
2秒前
2秒前
水煮电吹风的应助被星驰采纳,获得10
2秒前
3秒前
文献冲浪er完成签到,获得积分10
3秒前
朝夕发布了新的文献求助10
3秒前
科研通AI6.4的应助被wj采纳,获得10
3秒前
科研通AI65的应助被林中鹿采纳,获得10
3秒前
dhakuwshuk发布了新的文献求助30
4秒前
4秒前
4秒前
5秒前
zz完成签到,获得积分10
6秒前
RZ关闭了RZ的文献求助
6秒前
打游客嘴巴子完成签到,获得积分10
7秒前
ari发布了新的文献求助10
8秒前
隐形友蕊完成签到,获得积分10
8秒前
无极微光的应助被Peng采纳,获得20
8秒前
xuexi发布了新的文献求助20
8秒前
积极北上完成签到,获得积分10
9秒前
9秒前
a502410600完成签到,获得积分10
9秒前
11秒前
迷路的如波完成签到 ,获得积分20
11秒前
卡卡完成签到,获得积分10
11秒前
李健的应助被wg采纳,获得10
12秒前
田様的应助被开心德地采纳,获得50
13秒前
cdercder的应助被123采纳,获得10
13秒前
高大颜演完成签到,获得积分20
13秒前
15秒前
高挑的远山完成签到,获得积分10
15秒前
15秒前
林中鹿完成签到,获得积分10
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188785
求助须知:如何正确求助?哪些是违规求助? 9576421
关于积分的说明 21847553
捐赠科研通 7786814
什么是DOI,文献DOI怎么找? 3435417
关于科研通互助平台的介绍 2559647
邀请新用户注册赠送积分活动 2482366