Intelligence, Informatics and Infrastructure
Online ISSN : 2758-5816
Volume 4, Issue 2
Displaying 1-9 of 9 articles from this issue
  • Samantha Louise N. JARDER, Osamu MARUYAMA
    2023 Volume 4 Issue 2 Pages 1-6
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    As hazards and damages become more complex as population and progress evolve, strategies for minimizing or eliminating the impacts are not universal for all scenarios. Here in this paper, it proposes how to utilize a decision tree to determine a priority-scenario-based restoration strategy for a seismic damaged pipeline network. Using the available information of a city and the parameters for the pipeline system, the damage rate and losses after a seismic event can be obtained using available models. DTs were produced at different priority scenarios, namely: vulnerability, damage, and cost. Results show different areas affected by different priority scenarios. There were areas that are repeatedly highlighted in different priority scenarios. A priority-based strategy can be produced depending on whichever factor decisionmakers, consultants, or clients decide.

  • Yoshihiro NITTA, Hiraku INAMURA, Ji DANG, Xin WANG
    2023 Volume 4 Issue 2 Pages 7-14
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML
    J-STAGE Data

    In this research, the proposed method for automatic detection of cracks in interior wall surfaces using an unmanned ground vehicle (UGV) is presented. The method consists of three main steps: (1) acquiring interior wall surface images using an autonomous UGV, (2) generating orthoimages to capture an overall view of the inspection area, and (3) detecting crack locations using the YOLO-v7 model. For creating the orthoimages used by Structure from Motion (SfM), an indoor navigation algorithm combining AR markers and LiDAR data is proposed. The algorithm detects AR markers using OpenCV and uses LiDAR to measure the distance and angle between the UGV and the wall. The UGV is guided to maintain a constant distance and align parallel to the wall. Experimental verification is conducted on mortar-finished interior wall surfaces in a building, demonstrating the effectiveness of the proposed method. The UGV captures images while in motion, creating orthoimages and detecting cracks using YOLO-v7. The results show that orthoimages allow for the detection of significant cracks, but direct utilization of UGV-captured images is necessary to detect all cracks. The proposed method offers a convenient way to acquire wall surface images and enables automatic crack detection using orthoimages and YOLO-v7. The navigation algorithm facilitates UGV traversal at a constant distance from the wall. Overall, the research presented the potential of using UGVs for automatic crack detection from images of indoor building environments.

  • Manish Man SHAKYA, Kotaro SASAI, Kiyoyuki KAITO
    2023 Volume 4 Issue 2 Pages 15-26
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    Road asset management (RAM) is a systematic process of maintaining, upgrading, and operating physical assets such as roads and bridges in a cost-effective way. The Department of Roads (DOR) is the responsible agency established for the RAM of Strategic Road Network (SRN) in Nepal. Maintenance planning and implementation activities are done by DOR to preserve and maximize the service periods of road assets. The DOR faces the challenge to maintain over 95 percent SRN in fair to good condition. The determination of the rates of deterioration of the road pavements is important for planning the appropriate maintenance approach. However, the pavement condition deterioration curve for SRN in Nepal is not available to forecast future deterioration. Based on the annual road condition survey data, an empirical method developed in the early 2000s is still being used to prepare the integrated annual road maintenance plan. The deterioration process and deterioration rates depend on the pavement’s characteristics, use, and environmental factors. The Markov deterioration hazard model can be applied to estimate and forecast the deterioration process of the pavement. In the model, the deterioration process is described by transition probabilities. The deterioration states are categorized into several ranks based on inspection results and their deterioration rates are estimated by the hazard models. The application of the Markov deterioration hazard model for describing the pavement conditions of SRNs in Nepal using the Surface Distress Index (SDI) and International Roughness Index (IRI) data set from 2014 to 2023 is presented in this paper. For periodic maintenance of road sections in Nepal, only SDI is considered as the prime indicator. In this paper, IRI is discussed as an alternative parameter for making maintenance decisions and prioritizing road sections for periodic maintenance.

  • Katrina MONTES, Jiaming LIU, Ji DANG, Pang-jo CHUN
    2023 Volume 4 Issue 2 Pages 27-34
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    Periodical bridge inspection is essential to monitor the deterioration and maintenance progress. However, traditional inspection method requires a lot of works, expensive equipments, and time costly, and its difficult to implement periodically specially in developing countries. Therefore, this study proposed a Structure-from-Segmented-Motion (SfSM) method to enhance the bridge vision based inspection process. This method can localize and visualize the damage location in the bridge by utilizing various technologies such as UAV for data gathering, deep learning methods for damage segmentation, and Mixed Reality (MR) for digital transformation (DX). Firstly, optimal flight path for a single span I-girder bridge using UAV was proposed. This helps to fasten the visual bridge inspection, reduce workforce, and inspect some difficult to access parts without the use of expensive equipments. Then, the trained Deeplabv3+ was used to segment the corrosion damages of the images gathered. Finally, the 3D bridge model with and without the segmented corrosion were reconstructred using SfM and SfSM to visualize the location of damage in the whole bridge and viewed in a mixed reality (MR) platform. The proposed method will help the engineers to evaluate the bridge condition remotely which will save time and makes it safer.

  • Shijun PAN, Keisuke YOSHIDA, Satoshi NISHIYAMA
    2023 Volume 4 Issue 2 Pages 35-49
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    In recent years, unmanned aerial vehicles (UAVs) have been increased in civil engineering and infrastructure maintenance due to their potential to detect cracks in asphalt pavement, especially in riparian areas. Vegetation growth in riparian areas can create benefits for the infrastructures, e.g. embankment consolidation, but can also cause cracks and potholes to form. Local authorities should proactively manage vegetation growth in the riparian asphalt pavement to avoid these adverse effects. The monitoring before the maintenance operation also needs lots of time, and the efficient approach to understanding the work amount in the large-scale area is considered. UAVs assisted with computer vision algorithms, such as the You Only Look Once version 7 (YOLOv7) object detection model, have shown great potential in detecting and segmenting riparian road asphalt pavement cracks. This approach cannot just locate the cracks and also segment the cracks in the instances with pixel (px)-based sizes. This study provides three models derived from the divided dataset, one custom dataset with several bounding box sizes (i.e., 20-, 30-, 100-px), and two public datasets using asphalt pavement surface damage type and instances to annotate the crack. Based on the above results, the resulting inference was taken to compare with the True Label in mesh and had around 90% accuracy (i.e., Recall and F1).

  • Shijun PAN, Keisuke YOSHIDA, Takashi KOJIMA
    2023 Volume 4 Issue 2 Pages 50-59
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    Waste pollution detection has emerged as one of the crucial environmental concerns in recent years, and the accuracy of this practical application has been significantly improving with advancements in deep learning (DL) algorithms. To efficiently detect and quantify waste over large areas, the use of unmanned aerial vehicles (UAVs) has become essential. However, UAV flights and real-world image collection pose challenges that demand expertise, significant time, and financial investments. These challenges are particularly prominent in specialized applications such as waste detection, which rely on large amounts of data. Notably, the availability of adequate and accurately labeled data is vital for the performance of object detection models. Therefore, the identification and acquisition of suitable training data are critical objectives of this study. While ensuring data quality, AI-Generated Content (AIGC), specifically derived from Stable Diffusion, is emerging as a promising data source for DL-based object detection models. This research employed the Stable Diffusion to generate images by utilizing the prompts generated from specified images. Subsequently, the public dataset-based existing trained model automatically labeled the AIGC, which were then assigned corresponding labels in a uniform ratio for training, validation, and testing purposes. To assess the performance differences between the generated dataset and the dataset collected from real-world scenarios, several benchmark datasets were used for accuracy evaluation in this work. The results revealed that the AIGC exhibited superior accuracy in identifying high Ground Sample Distance (GSD) targets in simple backgrounds compared to the realistic collected dataset (F1 score-based). The results demonstrate the potential of AIGC in providing data for object detection models.

  • Sheng LIAN, Fumiya MATSUSHITA
    2023 Volume 4 Issue 2 Pages 60-65
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    Despite recent advancements in autonomous construction using robotics technology (RT), challenges persist in terms of limited user accessibility, interoperability across different robot platforms, and the absence of effective communication mechanisms for intuitive human-robot interaction (HRI). This study addresses these challenges by leveraging web technologies and visual programming to develop a master system that combines intuitive robot control program prototyping and interaction. The web interface utilizes JavaScript libraries such as roslibjs, ros2djs, and ros3djs to enable intuitive robot control and visualization of camera views and sensor data. It acts as a remote hub for centralized control and management of robot fleets from a unified internet-based location, enhancing coordination and operational efficiency. Furthermore, the rapid prototyping process utilizes Matlab Simulink for algorithm development and code generation, with performance simulation and assessment in Unity. Validated control nodes are then transferred to real machines via cloud services, enabling accelerated development of efficient and robust robotic systems.

  • Osama ABBAS, Ji DANG
    2023 Volume 4 Issue 2 Pages 66-74
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML
    J-STAGE Data

    Automatic structural evaluation is crucial, particularly in post-disaster scenarios. While significant progress has been made in Image Captioning, its potential as a tool for structural damage assessment has not been thoroughly explored. Image captioning offers the ability to generate descriptive captions that aid in further analysis, and decision-making processes. This study focuses on developing an image captioning model designed for structural damage images and compares four popular convolutional neural networks (CNNs), namely VGG16, ResNet50, InceptionV3, and EfficientNet. Interestingly, all evaluated models performed very well in generating captions for structural damage images. However, InceptionV3 showcased a slight edge over the other models. This highlights its excellent caption generation ability for structural damage evaluation. Furthermore, while variations in training times were observed among the CNN models, it is noteworthy that during practical applications, the differences in processing times for caption generation were found to be negligible. The findings of this study underscore the effectiveness of different CNN models for image captioning in the context of structural damage evaluation. Moreover, it emphasizes the potential of image captioning as a valuable tool in automated structural evaluation. The study also calls for further research to enhance the accuracy, efficiency, and interpretability of automatic structural evaluation using image captioning approaches.

  • Jonpaul Nnamdi OPARA, Ryo MORIWAKI, Pang-Jo CHUN
    2023 Volume 4 Issue 2 Pages 75-86
    Published: 2023
    Released on J-STAGE: November 14, 2023
    JOURNAL FREE ACCESS FULL-TEXT HTML

    Japan is known for its landslide susceptibility due to its steep topography, high seismic activity, and heavy rainfall patterns. These landslides have resulted in significant loss of life and infrastructure damage. To effectively manage landslide risks, accurate mapping of landslide-prone areas is essential. This research focuses on enhancing landslide mapping in Japan using an automated system based on the Segformer model, which combines Transformers and MLP decoders for semantic segmentation. A dataset of aerial images from various regions in Japan was used to train and evaluate the model. The Segformer model achieved a Mean Accuracy of 0.85, a Mean IoU of 0.80, loss value of 0.13 with a recall and precision value of 0.92, respectively, demonstrating its effectiveness in identifying regions prone to landslides. By leveraging advanced algorithms and data analysis techniques, the automated system improves the efficiency and accuracy of landslide mapping efforts. The research findings significantly impact proactive disaster management and mitigation strategies in Japan.

feedback
Top