To generate indoor as-built building information models (AB BIMs) automatically and economically is a great technological challenge. Many approaches have been developed to address this problem in recent years, but it is far from being settled, particularly for the point cloud segmentation and the extraction of the relationship among different elements due to the complicated indoor environment. This is even more difficult for the low-quality point cloud generated by low-cost scanning equipment. This paper proposes an automatic as-built BIMs generation framework that transforms the noisy 3D point cloud produced by a low-cost RGB-D sensor (about 708 USD for data collection equipment, 379 USD for the Structure sensor and 329 USD for iPad) to the as-built BIMs, without any manual intervention. The experiment results show that the proposed method has competitive robustness and accuracy, compared to the high-quality Terrestrial Lidar System (TLS), with the element extraction accuracy of 100%, mean dimension reconstruction accuracy of 98.6% and mean area reconstruction accuracy of 93.6%. Also, the proposed framework makes the BIM generation workflows more efficient in both data collection and data processing. In the experiments, the time consumption of data collection for a typical room, with an area of 45–67 ${\mathrm{m}}^2$ , is reduced to 4–6 min with an RGB-D sensor from 50–60 min with TLS. The processing time to generate BIM models is about half minutes automatically, from around 10 min with a conventional semi-manual method.

The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its performance can be degraded in urban environments because of signal reflections or blockages. To address these GNSS outages, pedestrian dead reckoning (PDR) is commonly used due to its significant improvements in both the stability and continuity of positioning, which are dependent on three key factors: continuous absolute position, heading and step information. Signals of opportunity are commonly used in positioning, whereas the installation of Bluetooth low energy (BLE) sensors on lampposts can provide an opportunity for positioning and heading estimation in urban canyons. In this article, a system integrating the GNSS, PDR, and BLE techniques is implemented in smartphones to provide a real-time positioning solution for pedestrians, which includes a new position correction method based on BLE heading, a reliable heading estimation integrating BLE and inertial sensors, an unconstrained step detection method with high accuracy, and an extended Kalman filter (EKF) to integrate multiple sensors and techniques. In several field experiments, with improvements in availability and robustness, the heading accuracy of the proposed fusion approach could reach approximately 3 degrees; the positioning accuracy achieved between 2.7 m and 4.2 m, compared with a 30 m error from the GNSS alone. Simultaneously, this system could achieve a high positioning accuracy of 2.4 m with unconstrained smartphones in a mixed environment. The proposed system has been demonstrated to perform well in urban canyons.

As an essential part of point cloud processing, autonomous classification is conventionally used in various multifaceted scenes and non-regular point distributions. State-of-the-art point cloud classification methods mostly process raw point clouds, using a single point as the basic unit and calculating point cloud features by searching local neighbors via the k-neighborhood method. Such methods tend to be computationally inefficient and have difficulty obtaining accurate feature descriptions due to inappropriate neighborhood selection. In this paper, we propose a robust and effective point cloud classification approach that integrates point cloud supervoxels and their locally convex connected patches into a random forest classifier, which effectively improves the point cloud feature calculation accuracy and reduces the computational cost. Considering the different types of point cloud feature descriptions, we divide features into three categories (point-based, eigen-based, and grid-based) and accordingly design three distinct feature calculation strategies to improve feature reliability. Two International Society of Photogrammetry and Remote Sensing benchmark tests show that the proposed method achieves state-of-the-art performance, with average F1-scores of 89.16 and 83.58, respectively. The successful classification of point clouds with great variation in elevation also demonstrates the reliability of the proposed method in challenging scenes.

This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combines smart phone internal MEMS sensors, GNSS and beacon observations together. Heading estimation is generally a key issue of the PDR algorithm. We design an orientation fusion algorithm to improve smart phone heading using MEMS measurements. Static and kinematic tests are performed, superiority of the improved heading algorithm is verified. We also present different heading processing solutions for comparison and analysis. Heading bias increases with time due to error accumulation and model inaccuracy. Thus, we develop a related heading calibration method based on beacons. This method can help correct smart phone headings continuously to decrease cumulative error. In addition to PDR, we also use GNSS and beacon measurements to integrate a fusion location. In the fusion procedure, we design related algorithms to adjust or limit the use of these different type observations to constrain large jumps in our Kalman filter model, thereby making the solution stable. Navigation experiments are performed in the streets of Mong Kok and Wanchai, which are typically the most crowded areas of Hong Kong, with narrow streets and many pedestrians, vehicles and tall buildings. The first experiment uses the strategy PDR + GNSS + beacon, in east–west orientation street, in which 10 m positioning error is improved from $30\%$ (smart phone internal GNSS) to $80\%$ and in south–north orientation street, in which 15 m positioning error is improved from $20\%$ (smart phone internal GNSS) to $80\%$ . The second experiment performs two long-distance tests without any beacons, in which the fusion scheme also has significant improvement, that is, 10 m positioning error is improved from $38\%$ to $60\%$ .

Three-dimensional (3D) reconstruction using RGB-D camera with simultaneous color image and depth information is attractive as it can significantly reduce the cost of equipment and time for data collection. Point feature is commonly used for aligning two RGB-D frames. Due to lacking reliable point features, RGB-D simultaneous localization and mapping (SLAM) is easy to fail in low textured scenes. To overcome the problem, this paper proposes a robust RGB-D SLAM system fusing both points and lines, because lines can provide robust geometry constraints when points are insufficient. To comprehensively fuse line constraints, we combine 2D and 3D line reprojection error with point reprojection error in a novel cost function. To solve the cost function and filter out wrong feature matches, we build a robust pose solver using the Gauss–Newton method and Chi-Square test. To correct the drift of camera poses, we maintain a sliding-window framework to update the keyframe poses and related features. We evaluate the proposed system on both public datasets and real-world experiments. It is demonstrated that it is comparable to or better than state-of-the-art methods in consideration with both accuracy and robustness.