Treffer: 聚合全局重构语义的航空遥感多目标分割模型.

To address the challenges of multiple target scales, insufficient semantic information, and blurred feature boundaries in aerial remote sensing images, a segmentation model that aggregates global information and reconstructs semantic representations after feature classification is proposed. Swin-Transformer is employed as the encoder to capture contextual information and extract deep features. A designed deep shallow semantic reconstruction module and a channel residual reconstruction module classify and reconstruct these features based on their information contens. Subsequently, a regional upsampling and downsampling connection strategy is introduced to fuse the reconstructed features with the encoder features into a comprehensive feature aggregation block for final output. This approach enables the fine-grained reconstruction of multi-target features and the generation of accurate segmentation maps, thereby enhancing segmentation precision and achieving high-quality pixel-wise regression. Experimental results show that the model achieves mean intersection over union (mIoU) scores of 87.2% and 82.9%, and overall accuracy (OA) scores of 91.4% and 91.2% on the ISPRS Vaihingen and ISPRS Potsdam datasets, respectively. [ABSTRACT FROM AUTHOR]

为了解决航空遥感图像存在目标尺度多且语义信息不足和特征边界不清晰等问题, 设计了一种聚合全局信 息再对特征分类后重构语义的分割模型。将 Swin-Transformer 作为编码结构, 利用其对上下文信息的理解来提取特 征, 再通过设计的深浅语义重构模块和通道残差重构模块将提取到的特征按信息量进行分类后重构, 最后通过设计 的区域上采样及下采样连接, 将重构后的特征与编码器提取的特征融合成全面的特征聚合块后进行输出。对多目 标下重构目标特征做到精细化并生成对应的分割图, 以此提高分割精度, 实现了高质量的逐像素回归。在 ISPRS Vaihingen 和 ISPRS Potsdam 两个数据集上的平均交并比 (mean intersection over union, mIoU) 分数达到了 87.2%和 82.9%, 整体精准度 (overall accuracy, OA) 分数达到了 91.4%和 91.2%。 [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)