Chia Ming Toh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chia Ming Toh has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Masakazu Komatsuzaki
College of Agriculture, Ibaraki University, 3-21-1 Ami, Ibaraki 300-0393, Japan
1 shared publication - Nengcheng Chen
National Engineering Research Center for Geographic Information System, China University of Geosciences, Wuhan 430078, China
1 shared publication - Tiyan Shen
School of Government, Peking University, Beijing 100871, China
1 shared publication - Tsuyoshi Okayama
College of Agriculture, Ibaraki University, Ibaraki 300-0393, Japan
1 shared publication - Wenyi Lu
China University of Geosciences, Wuhan 430074, China
1 shared publication - Xiang Zhang
National Engineering Research Center of Geographic Information System, School of Geography and Information Engineering, China University of Geosciences, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 12 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (22) , 3888
STC-PFTF-Net: Structure-Guided Prior Fusion for Cover-Crop Canopy Delineation in Residue-Rich UAV Imagery
Delineating early cover-crop vegetation in unmanned aerial vehicle (UAV) imagery requires preserving slender leaves amid cast shadows, desiccated residue, and heterogeneous soil. Weak foliage contrast and leaf-like background edges make appearance and geometry jointly important. We propose the Shadow, Topology, and Chromatic-aware Prior Feature Topology Fusion Network (STC-PFTF-Net), which integrates structure-guided reconstruction with complementary appearance representations. A coherence-guided tangent–normal decomposition preserves tangential sampling displacement and attenuates displacement across local structures. Chromatic–photometric encoding, directional wavelet filtering, and local connectivity refinement support this reconstruction throughout the feature hierarchy. On the 32 validation tiles of the Residue-rich Cover-Crop UAV Dataset, drawn from an area spatially separated from training, STC-PFTF-Net achieves 77.71% foreground intersection over union (IoU), 50.88% Boundary IoU, 83.84% centerline Dice (clDice), and 87.35% F1. At a common decision threshold, the complete model also exceeds the comparison architectures in all four measures. Spatial analyses associate its higher boundary recall with vegetation–background transitions and identify low-greenness foliage as a distinct source of omission. These findings show the value of combining appearance information with explicit reconstruction geometry for fine-scale canopy delineation. With 2.12 million parameters, the model offers a compact representation for UAV-derived vegetation mapping and subsequent canopy-cover assessment.
- 12 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (22) , 3888
Open AccessSTC-PFTF-Net: Structure-Guided Prior Fusion for Cover-Crop Canopy Delineation in Residue-Rich UAV Imagery
Delineating early cover-crop vegetation in unmanned aerial vehicle (UAV) imagery requires preserving slender leaves amid cast shadows, desiccated residue, and heterogeneous soil. Weak foliage contrast and leaf-like background edges make appearance and geometry jointly important. We propose the Shadow, Topology, and Chromatic-aware Prior Feature Topology Fusion Network (STC-PFTF-Net), which integrates structure-guided reconstruction with complementary appearance representations. A coherence-guided tangent–normal decomposition preserves tangential sampling displacement and attenuates displacement across local structures. Chromatic–photometric encoding, directional wavelet filtering, and local connectivity refinement support this reconstruction throughout the feature hierarchy. On the 32 validation tiles of the Residue-rich Cover-Crop UAV Dataset, drawn from an area spatially separated from training, STC-PFTF-Net achieves 77.71% foreground intersection over union (IoU), 50.88% Boundary IoU, 83.84% centerline Dice (clDice), and 87.35% F1. At a common decision threshold, the complete model also exceeds the comparison architectures in all four measures. Spatial analyses associate its higher boundary recall with vegetation–background transitions and identify low-greenness foliage as a distinct source of omission. These findings show the value of combining appearance information with explicit reconstruction geometry for fine-scale canopy delineation. With 2.12 million parameters, the model offers a compact representation for UAV-derived vegetation mapping and subsequent canopy-cover assessment.