Trees in urban spaces play important roles such as cooling heat islands, providing shade and biodiversity, and purifying the air. Monitoring tree structures such as tree trunk diameter, height, and woody dry weight is crucial for tree management. In this study, light detection and ranging (LiDAR) measurements were performed to monitor trees in urban spaces in lieu of manual measurement. Velodyne LiDAR and a mobile mapping system (MMS) were used for the tree measurement. Then, a method for automatic tree detection using machine learning and deep learning technique for 3D LiDAR point clouds was proposed. The proposed method can identify trees even when there are many non-tree objects in the environment. First, each object was segmented using 3D point cloud processing, and the segmented objects are projected onto 2D images. The projected images are then classified into tree or non-tree objects based on structural features using a support vector machine (SVM). In this step, a generative adversarial network (GAN) was utilized to augment the training images. Subsequently, 3D point clouds of the tree identification results are generated after the 2D-based classification. The classification accuracy of tree and non-tree 2D images after segmentation exceeds 95.0%, a significantly high degree of accuracy. Finally, tree structural information (e.g., woody dry weight) is calculated using a regression curve expression proposed in a prior study. This method enables an automatic monitoring of tree structures—for example, in urban forests, parks, and roads—using LiDAR.

Building information modeling (BIM) is one of the most promising advances in the architecture, engineering, and construction industry, which is generally embracing BIM/construction information modeling (CIM) by encouraging its association members and stakeholders to adopt these technologies. At the core of the BIM/CIM evolution is education. Accordingly, this research inquired into BIM education cases in the US, the UK, Australia, Hong Kong, and Singapore to comparatively analyze the BIM/CIM courses necessary to support industry development and plan a BIM/CIM curriculum. The process of BIM/CIM introduction in schools revealed that such an incorporation is more complex than simply adding new courses to an existing curriculum, as BIM/CIM has the potential to be an intrinsic part of an entire civil engineering program. This study developed a preliminary education framework that universities can use to collaborate with industry and IT companies in delivering BIM education. The program was developed by identifying the abilities required by industry for coordination with industry OJT. Moreover, two patterns of BIM/CIM education are proposed: cooperation in large metropolises and cooperation in local cities, for the equal development of construction industry.

Due to the rapid aging of bridges in Japan, there is a need for an advance and more reliable structural health monitoring techniques. This study conducted an unmanned aerial vehicle (UAV) semi-autopilot path flight controlled method by utilizing the DJI Software Development Kit (SDK) for inspection of Global Navigation Satelite System (GNSS)-denied parts of a bridge specifically in-between girders and other semi-closed and narrow areas. A mini-UAV’s path planning was pre-programmed under a known environment using waypoints and python programming language. A miniature low cost camera was attached as a payload and captured the images underneath the bridge deck aside from the captured images along the line of sight of the UAV. The UAV test flight was done in a pedestrian bridge located at Saitama University. The UAV successfully inspected underneath the bridge deck and some narrow parts in semi-autopilot mode. After that, corrosion, spalling, and crack damages were detected using two different vision based deep learning methods, YOLOv3 and Mask R-CNN. In addition, since the flight path plan was pre-programmed by measured commands, the location of the captured damages were easily located. To visualize the damage location, a 3D model underneath the decks was generated using structure from motion (SfM) and open sourced softwares. Due to the UAV’s small size and the ability to have a semi-autopilot controlled flight path, it eliminated the GNSS dependent problem in bridge damage inspection and been able to inspect narrow areas which were difficult to access. The combination of semi-autopilot inspection under gps-denied parts of bridge inspection, damage detection, and 3D model construction were the main focus of this research.

Digital transformation (DX) is defined as the process of integrating digital technology into all aspects of a business`s operations which accelerating the accomplishing of work via more efficiently by remote management and digitizing all process.

At construction site, by ensuring operational excellence and improved customer engagement through effectively managing risk, completing projects on time and on budget, improving workforce safety with the help of digital transformation (DX) is booming. AI techniques used to develop and find the factors influencing the mechanical properties of sustainable concrete1). In earthwork, some ICT construction related construction DX has been introduced. In this paper we focus on the crane which is one of the heavy machines used for movement of materials in structure construction. Cranes are used at construction site to transport materials and equipment. In developed European countries, it is widely used as three types of treasures along with trucks and backhoes. In Japan, on-site transportation at construction sites is often done manually, and cranes are often used when it is difficult to transport manually. For this reason, transportation of heavy materials and material fixing work are a physical burden on skilled workers.

This paper aims to achieve the goal of improving construction DX through comprising crane which is one of the heavy construction machines directly connected to the performance of skilled workers by clarifying the difference in operability and visibility between the hydraulic crane and stationary horizontal jib.

The Markov chain Monte Carlo (MCMC) method is applied to structural system identification under known seismic excitation in this study. In the method, unknown structural parameters are identified by sampling from a Bayesian posterior distribution. The unnormalized posterior probabilities of the parameters are calculated based on the state-space model using the Kalman filter (KF), from which the estimates of structural responses are also obtained. The performance of the method is first investigated numerically. When the model in the KF is the same as the true model, the identified parameters are precise and consistent. However, if model errors exist, the parameters are inconsistent under different excitations. For the system responses, the results present good accuracies. The method is further applied to a full-scale building experiment from the E-defense shaking table. Both 2D and 3D system models are considered. The estimated structural responses are shown to be accurate.

This research aims to compare the capabilities on pixel-level damage detection between semantic segmentation and instance segmentation, mainly in terms of speed and accuracy. Thus, the typical networks of these two segmentation methods, Fully Convolutional Network (FCN) and Mask R-CNN are trained and tested. In this research, 300 high resolution images of corrosions on steel bridges are collected and labeled to train and evaluate several FCN and Mask R-CNN models. To compare these two Deep Learning methods, the time of training and predicting processes are recorded and the predicted results are processed and calculated through different evaluation methods. Besides, one UAV-taken 4K image of severely corroded bridge is adopted to test the capability of the Deep Learning models under more complex environmental conditions.