Over the last decade, a 3D reconstruction technique has been developed to present the latest as-is information for various objects and build the city information models. Meanwhile, deep learning based approaches are employed to add semantic information to the models. Studies have proved that the accuracy of the model could be improved by combining multiple data channels (e.g., XYZ, Intensity, D, and RGB). Nevertheless, the redundant data channels in large-scale datasets may cause high computation cost and time during data processing. Few researchers have addressed the question of which combination of channels is optimal in terms of overall accuracy (OA) and mean intersection over union (mIoU). Therefore, a framework is proposed to explore an efficient data fusion approach for semantic segmentation by selecting an optimal combination of data channels. In the framework, a total of 13 channel combinations are investigated to pre-process data and the encoder-to-decoder structure is utilized for network permutations. A case study is carried out to investigate the efficiency of the proposed approach by adopting a city-level benchmark dataset and applying nine networks. It is found that the combination of IRGB channels provide the best OA performance, while IRGBD channels provide the best mIoU performance.

Floor vibration induced by human activities has become an important concern to both designers and developers, especially for modern structures designed with larger spans and lower weights. However, there is currently no systematic approach in codes of practices to assessing floor vibration, and the load models induced by human walking are usually oversimplified by ignoring overlapping between successive footfalls. This paper addresses those shortcomings by conducting a series of finite element simulations of three slabs with different thicknesses subjected to dynamic loads induced by human walking activities. A total of six load models ranging from the most realistic to the most simplified were used for the simulations. The simulation results show that the overlapping time between successive footfalls has a significant impact on human-induced vibration for floors with thicknesses of 100-200 mm. The results also indicate that the critical walking frequency should be shifted to a higher value than the resonant frequency, to allow for the humaninduced load increasing with walking frequency.

Recent years have witnessed an increasing use of 3D models in general and 3D geometric models specifically of built environment for various applications, owing to the advancement of mapping techniques for accurate 3D information. Depending on the application scenarios, there exist various types of approaches to automate the construction of 3D building geometry. However, in those studies, less attention has been paid to watertight geometries derived from point cloud data, which are of use to the management and the simulations of building energy. To this end, an efficient reconstruction approach was introduced in this study and involves the following key steps. The point cloud data are first voxelised for the ray-casting analysis to obtain the 3D indoor space. By projecting it onto a horizontal plane, an image representing the indoor area is obtained and is used for the room segmentation. The 2D boundary of each room candidate is extracted using new grammar rules and is extruded using the room height to generate 3D models of individual room candidates. The room connection analyses are applied to the individual models obtained to determine the locations of doors and the topological relations between adjacent room candidates for forming an integrated and watertight geometric model. The approach proposed was tested using the point cloud data representing six building sites of distinct spatial confirmations of rooms, corridors and openings. The experimental results showed that accurate watertight building geometries were successfully created. The average differences between the point cloud data and the geometric models obtained were found to range from 12 to 21 mm. The maximum computation time taken was less than 5 min for the point cloud of approximately 469 million data points, more efficient than the typical reconstruction methods in the literature.

No abstract