Seeing Beyond the Patch: Scale-Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery based on Reinforcement Learning

计算机科学 缩略图 分割 背景(考古学) 比例(比率) 人工智能 特征(语言学) 空间语境意识 图像分割 搜索引擎索引 计算机视觉 模式识别(心理学) 图像(数学) 地理 地图学 哲学 语言学 考古
作者
Yinhe Liu,Sunan Shi,Junjue Wang,Yanfei Zhong
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2309.15372
摘要

In remote sensing imagery analysis, patch-based methods have limitations in capturing information beyond the sliding window. This shortcoming poses a significant challenge in processing complex and variable geo-objects, which results in semantic inconsistency in segmentation results. To address this challenge, we propose a dynamic scale perception framework, named GeoAgent, which adaptively captures appropriate scale context information outside the image patch based on the different geo-objects. In GeoAgent, each image patch's states are represented by a global thumbnail and a location mask. The global thumbnail provides context beyond the patch, and the location mask guides the perceived spatial relationships. The scale-selection actions are performed through a Scale Control Agent (SCA). A feature indexing module is proposed to enhance the ability of the agent to distinguish the current image patch's location. The action switches the patch scale and context branch of a dual-branch segmentation network that extracts and fuses the features of multi-scale patches. The GeoAgent adjusts the network parameters to perform the appropriate scale-selection action based on the reward received for the selected scale. The experimental results, using two publicly available datasets and our newly constructed dataset WUSU, demonstrate that GeoAgent outperforms previous segmentation methods, particularly for large-scale mapping applications.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
1秒前
心灵完成签到 ,获得积分10
2秒前
小蘑菇应助高高采纳,获得10
2秒前
3秒前
湛一完成签到,获得积分10
3秒前
呆二龙发布了新的文献求助10
3秒前
lijia3完成签到,获得积分10
3秒前
bkagyin应助xiaolaohu采纳,获得10
4秒前
4秒前
华仔应助hahhh7采纳,获得10
4秒前
大王完成签到,获得积分20
5秒前
FashionBoy应助xiangoak采纳,获得10
5秒前
赘婿应助画个饼充饥采纳,获得10
6秒前
6秒前
7秒前
7秒前
量子星尘发布了新的文献求助10
8秒前
9秒前
栉风沐雨完成签到,获得积分10
9秒前
未道完成签到,获得积分10
9秒前
H..发布了新的文献求助10
9秒前
9秒前
斯文败类应助惜雨采纳,获得10
10秒前
11秒前
顺利秋灵发布了新的文献求助10
11秒前
11秒前
孙燕应助zhangfuchao采纳,获得10
11秒前
12秒前
sugarcane发布了新的文献求助10
12秒前
12秒前
12秒前
花花发布了新的文献求助10
13秒前
13秒前
13秒前
13秒前
大魔发布了新的文献求助10
13秒前
张鱼小源子完成签到,获得积分10
14秒前
未道发布了新的文献求助10
14秒前
Vapaus完成签到,获得积分10
14秒前
14秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988827
求助须知:如何正确求助?哪些是违规求助? 3531183
关于积分的说明 11252671
捐赠科研通 3269809
什么是DOI,文献DOI怎么找? 1804780
邀请新用户注册赠送积分活动 881885
科研通“疑难数据库(出版商)”最低求助积分说明 809021