Yan Huang
Research Subjects
Research Interests
Yan Huang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Dan Zheng
School of Electronic Engineering, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China
1 shared publication - Edore Akpokodje
Department of Computer Science, Aberystwyth University, Aberystwyth SY23 3DB, UK
1 shared publication - Jing Huang
School of Electronic Engineering, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China
1 shared publication - Meng Tang
Department of Computer Science, Aberystwyth University, Penglais, Aberystwyth SY23 3DB, UK
1 shared publication - Yilin Tong
School of Electronic Engineering, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China
1 shared publication - Yu Zhang
Hubei Institute of Measurement and Testing Technology, Wuhan 430223, China
1 shared publication
Latest Publications
- Open Access
BATFNet: Boundary-Aware Transformer Fusion Network for RGB-DSM Semantic Segmentation of Remote Sensing Images
Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes.
Open AccessBATFNet: Boundary-Aware Transformer Fusion Network for RGB-DSM Semantic Segmentation of Remote Sensing Images
Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes.