Chen Su

Chen Su

Auto-generated profile, based on publicly available information

Chen Su

Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 May 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
QMQingyan Meng
Qingyan Meng
MZMaofan Zhao
Maofan Zhao
LZLinlin Zhang
Linlin Zhang
WSWenxu Shi
Wenxu Shi
CSChen Su
Chen Su
LBLorenzo Bruzzone
Lorenzo Bruzzone
Remote sensing (RS) scene classification has attracted extensive attention due to its large number of applications. Recently, convolutional neural network (CNN) methods have shown impressive ability of feature learning in the RS scene classification. However, the performance is still limited by large-scale variance and complex background. To address these problems, we present a multilayer feature fusion network with spatial attention and gated mechanism (MLF2Net_SAGM) for RS scene classification. First, the backbone is employed to extract multilayer convolutional features. Then, a residual spatial attention module (RSAM) is proposed to enhance discriminative regions of the multilayer feature maps, and the key areas can be harvested. Finally, the multilayer spatial calibration features are fused to form the final feature map, and a gated fusion module (GFM) is designed to eliminate feature redundancy and mutual exclusion (FRME). To verify the effectiveness of the proposed method, we conduct comparative experiments based on three widely used RS image scene classification benchmarks. The results show that the direct fusion of multilayer features via element-wise addition leads to FRME, whereas our method fuses multilayer features more effectively and improves the performance of scene classification.

4 April 2024 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
JWJiahao Wu
Jiahao Wu
QMQingyan Meng
Qingyan Meng
LGLiang Gao
Liang Gao
LZLinlin Zhang
Linlin Zhang
MZMaofan Zhao
Maofan Zhao
CSChen Su
Chen Su

21 July 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WSWenxu Shi
Wenxu Shi
QMQingyan Meng
Qingyan Meng
LZLinlin Zhang
Linlin Zhang
MZMaofan Zhao
Maofan Zhao
CSChen Su
Chen Su
PAPeter Atkinson
Peter Atkinson
Extracting 3D building information from monocular satellite sensor imagery remains a formidable challenge in the field of remote sensing. Multitask frameworks based on deep learning, which particularly for simultaneously predicting 2D building outlines and their respective heights using ortho-rectified satellite imagery, have shown promise in addressing this challenge. Height estimation is notably complex due to the absence of explicit height indicators, limited interaction between semantic-height features, and inadequate representation of building relationships. Moreover, the availability of data sources is a limiting factor for broader application. To overcome these issues, this study introduces an innovative instance-level multitask learning model (named BDH-Net) that leverages off-nadir perspectives and roof-to-footprint offset vectors to enhance modeling. This model comprises four key components: a pixel-wise feature extraction image encoder-decoder, a query transformer decoder, a multitask decoder, and a height decoder that employs intra-instance and inter-instance attention for precise building height estimation. Additionally, we pioneer the use of Google Earth imagery to construct an off-nadir satellite dataset with roof-to-footprint offset vectors specifically designed for building instance segmentation and height prediction, known as the BDH dataset. Comprehensive experiments demonstrate that the proposed BDH-Net significantly improves the accuracy of monocular 3D building data extraction by integrating roof-to-footprint offset vectors and leveraging context specific to each building instance. With the extensive coverage and regular updates of Google Earth imagery, BDH-Net holds substantial potential for wide-ranging and long-term applications. The source code of the proposed BDH-Net and the BDH dataset are publicly available at https://github.com/wishx98/BDHNet.

29 April 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
CSChen Su
Chen Su
QMQingyan Meng
Qingyan Meng
LZLinlin Zhang
Linlin Zhang
FZFuqing Zhang
Fuqing Zhang
HWHantian Wu
Hantian Wu
SHSorin Herban
Sorin Herban
Accurate delineation of Local Climate Zones (LCZs) is essential for comprehending urban thermal environments and supporting sustainable urban planning. Traditional LCZ mapping approaches often rely on single-modality data or perform only shallow-level fusion, which limits their capacity to represent intricate urban semantics. To address this limitation, we introduce CMHFuse, a new Cross-Modal Hierarchical Fusion framework for LCZ classification utilizing multi-modal remote sensing data. CMHFuse independently extracts hierarchical features from multiple modalities (e.g., Sentinel-2 imagery, land use/land cover, and building height) using modality-specific encoders, where a Channel-Spatial Attention (CSA) module is integrated to emphasize semantically important features. A Cross-Attention module enables the primary modality to selectively integrate complementary information from auxiliary modalities. It is embedded into a Transformer-based architecture to form a hierarchical cross-modal fusion pipeline. Furthermore, a specific-to-fused feature enhancement strategy adaptively combines enhanced and primary modality features at the feature level to improve classification robustness. Comprehensive evaluations on datasets collected from four cities confirm that CMHFuse outperforms current approaches. Additional ablation analysis highlights the individual importance of each modality and verifies the robustness of the proposed fusion strategy.