• Journals

Integrated Optical-SAR Texture Analysis for Neural Network-Based Emergency Landslide Surveying and Mapping

Optical remote sensing imagery provides critical spectral information for mapping landslide inventories but is frequently hindered by cloud cover and adverse weather. In contrast, Synthetic Aperture Radar (SAR) penetrates clouds and is highly sensitive to surface backscatter changes, offering complementary insights for detecting landslide disturbances. This study presents an integrated approach combining optical and SAR data to enable rapid and reliable landslide detection under challenging conditions. The proposed framework applies object-based image analysis (OBIA) to segment terrain into meaningful units and derives NDVI_(diff) and NDSI indices from pre- and post-event imagery, together with six GLCM-based texture features, to characterize surface disturbances. Four classification scenarios, including optical-only, SAR-only, cloud-obstructed optical, and fusion-based models, were systematically compared. Results demonstrate that the fusion approach consistently yields more spatially coherent and complete landslide inventories, while SAR-based mapping alone successfully delineates most large-scale landslides under heavy cloud cover. These findings confirm the operational effectiveness of the proposed optical-SAR framework for rapid, event-driven landslide mapping and disaster risk assessment.

• Journals

陸海交界處大地起伏建模精度探討：以臺灣東部為例

本研究以臺灣東部花蓮清水斷崖沿岸為研究區，探討數值地形模型（DEM）、數值海底地形模型（DBM）空間解析度與海岸線定位精度對陸海交界處重力法大地起伏建模之影響。研究採用GSHHG與人工數化海岸線，結合不同解析度DEM-DBM，於去除－回復架構下，以剩餘地形模型及最小二乘配置法建立大地起伏模型，並以GNSS／水準觀測資料進行精度檢核。結果顯示，GSHHG海岸線於斷崖海岸與實際海岸線存在明顯差異，易造成海岸附近地形遮罩與改正誤差；人工數化海岸線可提升陸海邊界一致性與模型穩定性。解析度比較顯示，3"×3"DEM-DBM之整體精度優於9"×9"與1"×1"。研究結果指出，精確海岸線與適當地形解析度為提升陸海交界區大地起伏建模品質之關鍵。

• Journals

使用深度學習進行快速無參考標的無人機影像品質評估

隨著無人飛行載具（UAV）應用於基礎設施監測，影像品質穩定性成為影響深度學習與攝影測量精度的關鍵。然而UAV影像常受環境干擾影響，現行品質篩選多仰賴人工檢視，且傳統結構相似度指標（SSIM）需參考影像並受限於空間對齊，難以實務應用。為此，本研究提出一套基於Swin-Unet的快速無參考影像品質評估方法。首先設計改良型CLIP-SSIM結合Swin-Transformer，建立高精度影像品質圖（RMSE=0.0193），再以該品質圖作為標註資料訓練Swin-Unet模型，使單張影像推論時間降至0.3秒，並維持良好準確度（RMSE=0.04）。結果顯示，本方法可有效取代人工檢視流程，滿足高頻UAV影像應用需求。

• Journals

應用深度資訊於混凝土橋梁結構物影像拼接之研究

影像拼接可擴展視野、消除盲區，但場景深度差異容易導致視差與重影。為此，本研究整合單影像深度估計與語義分割模型，建立橋梁立面影像拼接流程，重建完整結構外觀圖作為損壞分析和管理底圖。透過遷移學習建置橋側影像數據集，沿用預訓練參數訓練RGB-D語義分割模型，mIoU達86.44%、mAcc 91.24%、召回率92.11%、F1-score 91.56%，展現穩定性與泛化能力，並藉其成果間接驗證深度估計模型準確性。針對影像傾斜導致的幾何錯位，利用深度圖重建點雲校正。拼接精度比較顯示，結合分割模型與校正影像之平均SSIM為0.6807高於傳統方法0.5081，證實本研究方法在精度與視覺一致性上的優勢。