Yan Zhao

Yan Zhao

Auto-generated profile, based on publicly available information

Yan Zhao

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
8 October 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
XWXinsheng Wang
Xinsheng Wang
DPDong PI
Dong PI
Mi WangMi Wang
Mi Wang
YZYan Zhao
Yan Zhao
XCXu Cheng
Xu Cheng
JZJianping Zhao
Jianping Zhao
Reconstructing 3D spatial information from satellite images remains a pivotal challenge in photogrammetry. While traditional methods rely on stereo image pairs, recent advances in monocular height estimation (MHE) have demonstrated the promising feasibility of recovering 3D information without stereo observation conditions. At present, the mainstream deep learning-based MHE models typically learn the mapping between the image-derived deep features and height distribution from extensive RGB-height image pairs. However, the scarcity of satellite MHE datasets severely restricts the application of MHE models in real-world scenarios. In addition, existing MHE datasets predominantly rely on pairs of approximate orthophotography images, which can not be guaranteed in practical satellite imagery acquisitions, undoubtedly leading to the inability of the existing MHE models to learn elevation perception information from varying observation geometries. On the other hand, collecting multi-angle imagery data through cross-orbit or multi-temporal satellite observation introduces significant costs and temporal latency for producing such multi-angle datasets. To this end, this paper constructs the Multi-Angle Monocular Height Estimation Dataset (MAMHESet) to verify the performance of the MHE models when processing multi-angle images. The proposed dataset is constructed using multi-angle images acquired from the Luojia3-01 optical video satellite in gazing mode and the corresponding aerial LiDAR point clouds. We develop a novel dataset generation pipeline, which effectively mitigates dataset construction challenges caused by the inherent heterogeneous point cloud quality differences. To the best of our knowledge, this is the first MHE dataset derived from optical video satellite imagery with multiple observation angles. The extensive training and accuracy evaluations on several mainstream MHE models have demonstrated the practicality of this dataset, which further expands the application potential of the monocular satellite imagery in 3D reconstruction tasks.

9 March 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
DPDong PI
Dong PI
YZYan Zhao
Yan Zhao
Mi WangMi Wang
Mi Wang
DLDeren Li
Deren Li
BYBo Yang
Bo Yang
XLXin Li
Xin Li
Due to the discrepancies of geometric and radiometric factors, automatic image matching often fails to generate tie points, leading to positioning inconsistences in satellite image blocks. To address this issue, we proposed a novel observation anomaly detection method based on uncertainty propagation and clustering analysis. The method propagates the geometric precision of a reference image throughout the image block under the intersection and elevation constraints. A feature space is then constructed based on the statistics of the geometric accuracies and the DBSCAN clustering algorithm is applied to distinguish anomalous images from normal ones. Experiments using 149 multispectral and 298 panchromatic GF-7 images demonstrated that the method achieved 100% detection accuracy under the optimal image-space compensation model and the optimal feature space. While some moderate observation anomalies were missed with a single reference image, incorporating multiple well-distributed reference images enabled accurate detection. Further analysis revealed significant discrepancies in positioning accuracies between anomalous and normal images after block adjustment, with mean differences up to 4.77 m and 5.40 m in line and sample directions, respectively. By adding approximately 1300 tie points to anomalous images, spatial connectivity was restored, reducing RMS errors by over 91% and aligning their precision with that of normal images.