Search

With the increasing availability of satellite monitoring data, the demand for storage and computational resources for updating the results of monitoring the surface subsidence in a mining area continues to rise. Sequential adjustment (SA) models are considered effective for rapidly updating time series interferometry synthetic aperture radar (TS-InSAR) measurements. However, the accuracy of surface subsidence values estimated through traditional sequential adjustment is highly sensitive to abnormal observations or prior information on anomalies. Moreover, the surface subsidence associated with mining exhibits nonlinear and large gradient characteristics, making general InSAR methods challenging for obtaining reliable monitoring results. In this study, we employ the phase unwrapping network (PUNet) to obtain unwrapped values of differential interferograms. To mitigate the impact of abnormal errors in the near real-time small baseline subset InSAR (SBAS-InSAR) sequential updating process in mining areas, a robust sequential adjustment method based on M-estimation is proposed to estimate the temporal deformation parameters by using the equivalent weight model. Using a coal backfilling mining face in Shanxi, China, as the study area and the Sentinel-1 SAR dataset, we comprehensively evaluate the performance of unwrapping methods and subsidence time series estimation techniques and evaluate the effect of filling mining on surface subsidence control. The results are validated using leveling measurements within the study area. The relative error of the proposed method is less than 5%, which can meet the requirements of monitoring the surface subsidence in mining areas. The method proposed in this study not only enhances computational efficiency but also addresses the issue of underestimation encountered by InSAR methods in mining area applications. Furthermore, it also mitigates unwrapping phase anomalies on the monitoring results. [ABSTRACT FROM AUTHOR]

• Proposed an automated deep learning-based framework for building facade parsing. • Provided an enhanced feature extraction algorithm utilizing BiFPN and SE module. • Dealt with the issue of occlusion and reflection based on the improved SOLOv2. • Achieved an accurate estimation of WWR with a mAP of 93% for window segmentation. • Discussed the effect of WWR granularity on energy simulation. Energy consumption simulation and renovation of existing buildings require accurate acquisition of building façade features which mostly relies on time-consuming manual calculations based on architectural drawings. In this article, we proposed an automated deep learning-based approach based on the SE module and BiFPN to achieve precise and efficient façade feature extraction. The approach eliminated the image distortion of building façades and then enabled accurate segmentation of windows and accessory structures even under the situation of occlusion and reflection. The improved SOLOv2 algorithm resulted in a high mean average precision of 93% for window segmentation, leading to a more precise window-to-wall ratio estimation with a mean absolute error of 2.9% than the experts' estimation and existing deep learning-based methods. Considering the accurate results of façade parsing, our method can be utilized for city-level building feature extraction, providing theoretical and practical references for urban building energy simulation, urban renewal, and building health examination. [ABSTRACT FROM AUTHOR]

The large-scale use of solar energy is an important means of achieving carbon neutrality. In cities, large stocks of building roofs are ideal for photovoltaic (PV) installations. However, the difficulty in acquiring urban building stock data limits the assessment of urban roof PV potential. Therefore, an instance segmentation model was used to extract all the roofs and their corresponding deep features from high-resolution open-source satellite maps. Subsequently, a multi-round semi-supervised clustering process was proposed to classify similar roofs. Finally, the total urban roof area was evaluated, involving pitched roof area correction. The PV available area ratios of all roofs were estimated by sampling each roof cluster to obtain the available roof area for PV installation. The corresponding urban PV potential capacity and energy generation were calculated. The proposed method was applied and validated in the Yangpu District of Shanghai, China. The results showed that the total building roof area of Yangpu District was 11.16 km2, and the roof PV available area ratio (R a s) varied between 0.4 and 0.92. The available roof area for PV installation was 7.46 km2. The PV installation area and capacity were 4.14 km2 and 913.74 MW, respectively. The annual PV energy production was 940.34 GW h. • Instance segmentation model was used for city-scale building roofs extraction. • A multi-rounds semi-supervised clustering process was proposed to classify roofs. • Potential roof PV capacity and energy production in Yangpu District were evaluated. [ABSTRACT FROM AUTHOR]

• Proposed a knowledge framework for 3D reconstruction in civil engineering. • Provided a technical framework of image-based 3D reconstruction with deep learning. • Summarized multi-scale state-of-the-practice of 3D reconstruction in civil engineering. • Pointed out eight research directions such as automated modeling, model fusion, etc. As a bridge between physical objects and as-built models, image-based 3D reconstruction performs a vital role by generating point cloud models, mesh models, textured models, and eventually BIMs from images. This study provides a quantitative and qualitative summary of image-based 3D reconstruction for civil engineering projects in the last decade. A bibliometric analysis of 286 journal papers suggested that 3D reconstruction is an interdisciplinary field that integrates photogrammetry, 3D point cloud analysis, semantic segmentation, and deep learning. Based on the analysis, we proposed a 3D reconstruction knowledge framework with three dimensions — essential elements, use phases, and reconstruction scales. The "essential elements" dimension is a technical framework of visual geometry and deep learning methods for 3D model generation. The "use phases" emphasize using 3D reconstruction techniques during the construction, operation, and maintenance phases, which are driven by the demands of visual inspection in various contexts. The "reconstruction scales" dimension synthesizes 3D reconstruction applications from the component level to the city scale with highlights of their opportunities and challenges. This 3D reconstruction knowledge framework sheds light on eight future research directions: automated modeling, model fusion, performance optimization, data fusion, enhanced virtual experience, real-time modeling, standardized reference, and in-depth deep learning research. This review can help scholars understand the present status and highlight research trends of image-based 3D reconstruction in civil engineering associated with the integration of deep learning methods. [ABSTRACT FROM AUTHOR]

Traditional construction progress tracking relies on labor-intensive activities with time lags, potential man-made errors, and inefficient progress management, which demands for an innovative and automated progress tracking approach. This paper describes a deep learning method that utilizes image segmentation to automatically evaluate the wall construction progress of an entire floor with the progress results streamlined to BIM. The approach was applied to a case study in China for assessing plastering construction activities with high segmentation accuracy (mean average precision = 96.8%). Further improvement of Mask Region-Based Convolutional Neural Networks (Mask R-CNN) and evaluation of its superiority over other models have also been discussed. This study provides both theoretical and practical references for unmanned supervision of progress tracking and intelligent schedule management. • Described an evaluation framework to recognize wall progress of an entire floor. • Proposed an image segmentation method to calculate wall construction area. • Improved Mask R-CNN algorithm to increase segmentation accuracy. • Discussed the influence of image light on segmentation accuracy. • Applied the framework to a case study with mean Average Precision of 96.8%. [ABSTRACT FROM AUTHOR]