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.
Water quality monitoring of medium-sized inland water is important for water environment protection given the large number of small-to-medium size water bodies in China. A case study was conducted on Yuandang Lake in the Yangtze Delta region, with a surface area of 13 km2. This study proposed utilising a multispectral uncrewed aerial vehicle (UAV) to collect large-scale data and retrieve multiple water quality parameters using machine learning algorithms. An alternate processing method is proposed to process large and repetitive lake surface images for mapping the water quality data to the image. Machine learning regression methods (Random Forest, Gradient Boosting, Backpropagation Neural Network, and Convolutional Neural Network) were used to construct separate water quality inversion models for ten water parameters. The results showed that several water quality parameters (CODMn, temperature, pH, DO, and NC) can be retrieved with reasonable accuracy (R2 = 0.77, 0.75, 0.73, 0.67, and 0.64, respectively), although others (NH3-N, BGA, TP, Turbidity, and Chl-a) have a determination coefficient (R2) less than 0.6. This work demonstrated the tremendous potential of employing multispectral data in conjunction with machine learning algorithms to retrieve multiple water quality parameters for monitoring medium-sized bodies of water.
1 September 2021 in Journal of Construction Engineering and Management
The terrestrial laser scanner (TLS) is an effective tool to generate geometric models of existing buildings and other structures. TLS has shown great potential in the architecture, engineering, and construction (AEC) industry. High standards for accuracy and density of point clouds are essential for producing accurate models. Some requirements have been developed for evaluating the deliverability of collected point clouds. However, practical guidelines for collecting qualified data may not always be available in every scenario. Consequently, either over-dense point clouds are collected to cover as large a range as possible, a conservative approach that results in wasted time in data collection and processing, or sparse point clouds are collected to reduce data collection time, which results in missing data. The present work proposes a methodology to calculate the effective scan range based on rigorous mathematical reasoning with straightforward equations considering all the neighboring points on the target plane. Using the proposed workflow, appropriate angular resolution can be quickly estimated to balance the scanning range and the collected data size in site surveying. Two case studies were carried out to investigate the feasibility of the proposed methodology. The results show that the point clouds within the suggested effective scanning range are highly consistent with expectations, which indicates that the proposed methodology is feasible and reliable.
The emergence of a photogrammetry-based 3D reconstruction technique enables rapid 3D modeling at a low cost and uncovers many applications in documenting the geometric dimensions of the environment. Although the theoretical accuracy of photogrammetry-based reconstruction has been studied intensively in the literature, the problem remains in evaluating the accuracy of the generated point cloud in practice. Typically, checking the coordinates of ground control points (GCPs) using a total station is considered a promising approach; however, the GCPs have clear and identifiable features and consistent normal vectors or less roughness, which cannot be considered as a typical sample for an accuracy evaluation of the point cloud. Meanwhile, the cloud-to-cloud (C2C) and cloud-to-mesh (C2M) comparison methods usually consider either the closest point or the neighboring points within a fixed searching radius as the “ground truth”, which may not reflect the actual accuracy; therefore, the present paper proposes an adaptive cloud-to-cloud (AC2C) comparison method to search the potential “ground truth” in the theoretical error space. The theoretical error space of each point is estimated according to the position of the corresponding visible cameras and their distances to a target point. A case study is carried out to investigate the feasibility of the proposed AC2C comparison method. The results presented basically the same error distribution range from 0 to 20 mm with the C2C and C2M methods, but with a higher mean value and a much smaller standard deviation. Compared to the existing methods, the proposed method provides new thinking in evaluating the accuracy of SfM-MVS by including the theoretical error constraints.