融合嫁接注意力和细节感知的遥感影像超像素分割
Segmentation of Remote Sensing by Fusing Grafting-Type Attention and Detail Perception
张艺杰 1谢新林 1樊静 1段泽云1
作者信息
- 1. 太原科技大学电子信息工程学院,山西 太原 030024;先进控制与装备智能化山西省重点实验室,山西 太原 030024
- 折叠
摘要
高分辨率遥感影像含有丰富的细节和光谱信息,在土地利用、建筑检测、地物覆盖分类等对地检测场景具有重要应用.针对纹理区域划分错误、小目标丢失等问题,提出一种融合嫁接注意力和细节感知的超像素分割算法.首先,构建边缘引导的空间细节模块,弱化不同层级合并时的差异,弥补采样过程中的空间细节信息丢失.其次,设计嫁接型注意力机制,增强局部区域特征,提高小目标边缘的提取能力.最后,提出纹理感知损失,通过自适应调整特征图的纹理权重,提升纹理区域的表达.在遥感影像数据集上的实验结果表明,对比当前主流超像素分割算法,所提算法在欠分割误差和边界召回性能指标上分别达到了0.15%和0.87%,能够提高模型对纹理和小目标区域的分割性能.
Abstract
High resolution remote sensing images contain rich details and spectral information.Consequently,they have important applications in land use,building detection,land cover classification,and other ground detection scenarios.This study proposed a superpixel segmentation algorithm that combined grafting attention and detail perception to address the issues of incorrect segmentation of texture regions and loss of small targets.First,an edge-guided spatial detail module was constructed to weaken the differences in merging different levels and compensate for the loss of spatial detail information during the sampling process.Second,a grafting attention mechanism was designed to enhance local region features and consequently improve the ability to extract edges of small targets.Finally,the concept of texture aware loss was proposed for enhancing the expression of texture regions through adaptive adjustments to the texture weights of feature maps.Compared to existing mainstream superpixel segmentation algorithms,the experimental results using the proposed algorithm on remote sensing image datasets yield segmentation error and boundary recall performance indicators of 0.15%and 0.87%,respectively.This indicates an improvement in the segmentation performance of the model for texture and small target areas.
关键词
超像素分割/高分辨率遥感影像/神经网络/注意力机制Key words
superpixel segmentation/high-resolution remote sensing image/neural network/attention mechanism引用本文复制引用
出版年
2024
NETL
NSTL
万方数据