Effective project monitoring has become crucial as the construction industry expands and the number of projects increases. Current monitoring methods, primarily relying on manual labor and traditional remote sensing techniques, face challenges such as insufficient image resolution and low processing speed. This study addresses these issues by applying deep convolutional neural networks to high-resolution remote sensing image recognition and developing an intelligent monitoring model based on YOLOv8 (CBGW-YOLOv8) for identifying various construction project stages. A dataset named “Construction Site,” containing different construction stages, was created using pre-processed remote sensing data from Jilin-1. An improved YOLOv8 architecture was adopted, with modifications to the network structure and loss function to enhance learning capability for construction features. The model's effectiveness in improving monitoring efficiency and accuracy was validated through actual deployment. Experimental results demonstrate that the CBGW-YOLOv8 model outperforms traditional methods and the original model in construction project detection, achieving a 2.9% increase in mAP_0.5 and a 2.6% increase in mAP_0.5:0.95, while exhibiting higher accuracy and faster processing speed.

Urban forests play a crucial role in sustaining habitable urban environments, and tree canopy height (TCH) is a key parameter for characterizing urban forest structure and ecological functions. However, accurate TCH retrieval using spaceborne lidar remains challenging in urban built-up areas because of the high spatial heterogeneity of urban land cover. This study proposes an urban-oriented method for ICESat-2 data processing and TCH extraction and evaluates it in Peoria, Illinois, USA. By integrating spectral constraints with photon spatial distribution patterns, the method further separates non-ground photons into vegetation photons and building photons. Individual tree crown polygons are then introduced as spatial constraints for TCH extraction, helping to overcome the limitations of regular grids in representing both the laser footprint scale and fine urban landscape detail. In addition, a non-exclusive photon-to-crown assignment strategy based on energy weighting allowed each photon to contribute to multiple crowns in proportion to the footprint energy intercepted by each crown. Among the 1391 crowns associated with vegetation photons, 286 met the thresholds for both total and high-weight photon counts and were retained for accuracy assessment. Validation against canopy heights derived from airborne laser scanning (ALS) reference data shows that the proposed method achieves an R² of 0.55 and an RMSE of 2.71 m. Further analysis indicates that retrieval accuracy is primarily controlled by beam strength: strong beams yield higher accuracy (R² ≈ 0.60), whereas daytime and nighttime observations differ only slightly. Overall, after targeted processing, ICESat-2 can provide a set of individual tree canopy height samples in urban built-up areas, which may support local calibration and serve as potential labels for subsequent regional canopy height mapping.