亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Multi-Scale Feature Interaction Network for Remote Sensing Change Detection

计算机科学 合并(版本控制) 稳健性(进化) 特征提取 特征(语言学) 变更检测 编码(社会科学) 模式识别(心理学) 人工智能 解码方法 数据挖掘 算法 情报检索 数学 生物化学 化学 语言学 哲学 统计 基因
作者
Chong Zhang,Yonghong Zhang,Haifeng Lin
出处
期刊:Remote Sensing [Multidisciplinary Digital Publishing Institute]
卷期号:15 (11): 2880-2880 被引量:2
标识
DOI:10.3390/rs15112880
摘要

Change detection (CD) is an important remote sensing (RS) data analysis technology. Existing remote sensing change detection (RS-CD) technologies cannot fully consider situations where pixels between bitemporal images do not correspond well on a one-to-one basis due to factors such as seasonal changes and lighting conditions. Existing networks construct two identical feature extraction branches through convolution, which share weights. The two branches work independently and do not merge until the feature mapping is sent to the decoder head. This results in a lack of feature information interaction between the two images. So, directing attention to the change area is of research interest. In complex backgrounds, the loss of edge details is very important. Therefore, this paper proposes a new CD algorithm that extracts multi-scale feature information through the backbone network in the coding stage. According to the task characteristics of CD, two submodules (the Feature Interaction Module and Detail Feature Guidance Module) are designed to make the feature information between the bitemporal RS images fully interact. Thus, the edge details are restored to the greatest extent while fully paying attention to the change areas. Finally, in the decoding stage, the feature information of different levels is fully used for fusion and decoding operations. We build a new CD dataset to further verify and test the model’s performance. The generalization and robustness of the model are further verified by using two open datasets. However, due to the relatively simple construction of the model, it cannot handle the task of multi-classification CD well. Therefore, further research on multi-classification CD algorithms is recommended. Moreover, due to the high production cost of CD datasets and the difficulty in obtaining them in practical tasks, future research will look into semi-supervised or unsupervised related CD algorithms.

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
康子浩发布了新的文献求助10
3秒前
多情嫣然完成签到,获得积分10
7秒前
8秒前
ZaZa完成签到,获得积分10
8秒前
11秒前
summerer发布了新的文献求助10
17秒前
Lucas的应助被科研通管家采纳,获得10
18秒前
852的应助被科研通管家采纳,获得10
19秒前
共享精神的应助被科研通管家采纳,获得10
19秒前
殷宵箫发布了新的文献求助10
19秒前
英姑的应助被科研通管家采纳,获得10
19秒前
含蓄的芝麻完成签到,获得积分10
21秒前
ADAB0002完成签到,获得积分10
22秒前
果冻完成签到 ,获得积分10
23秒前
23秒前
vfdhjng完成签到,获得积分20
25秒前
25秒前
可爱的函函的应助被lx采纳,获得10
27秒前
28秒前
华仔的应助被怡宝采纳,获得10
29秒前
summerer发布了新的文献求助20
30秒前
31秒前
嘻嘻哈哈的应助被Gloria采纳,获得10
31秒前
费洛蒙漩涡完成签到,获得积分10
32秒前
孤独孤风完成签到,获得积分10
32秒前
苹果颖完成签到,获得积分10
33秒前
lx完成签到,获得积分10
34秒前
35秒前
35秒前
科研通AI6.4的应助被殷宵箫采纳,获得10
35秒前
36秒前
鱼鱼鱼完成签到,获得积分10
38秒前
lx发布了新的文献求助10
40秒前
40秒前
顺心尔冬完成签到,获得积分10
40秒前
41秒前
康子浩发布了新的文献求助10
41秒前
cong发布了新的文献求助10
43秒前
科研通AI6.2的应助被追寻芷采纳,获得10
45秒前
vfdhjng关注了科研通微信公众号
47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
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Hidden Empire of Finance: How Wall Street Profits from Our Cities and Fuels Global Inequality 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 8165846
求助须知:如何正确求助?哪些是违规求助? 9559318
关于积分的说明 21749858
捐赠科研通 7756681
什么是DOI,文献DOI怎么找? 3429083
关于科研通互助平台的介绍 2553354
邀请新用户注册赠送积分活动 2473622