Article
Construction & Building Technology
Siyeon Kim, Seok Hwan Hong, Hyodong Kim, Meesung Lee, Sungjoo Hwang
Summary: A small object detection (SOD) system based on the YOLOv5 algorithm was developed for real-time and accurate detection of small objects in various sizes, improving site monitoring and safety management.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Geography, Physical
K. R. Akshatha, A. K. Karunakar, B. Satish Shenoy, K. Phani Pavan, Chinmay V. Dhareshwar, Dennis George Johnson
Summary: Intelligent UAV video analysis has gained attention for its potential in computer vision applications. In order to address the challenge of small object detection, a Manipal-UAV person detection dataset was created, consisting of images captured from UAVs in varying conditions. The dataset provides a benchmark for evaluating state-of-the-art object detection algorithms on small person objects in aerial view scenarios. The dataset is publicly available for researchers to advance UAV and small object detection research.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Interdisciplinary Applications
Jin Gang Lee, Jeongbin Hwang, Seokho Chi, JoonOh Seo
Summary: This paper presents a systematic method to create synthetic training image datasets for computer vision-based construction object detection. The use of synthetic images allows for easy customization and improved accuracy in training deep learning algorithms. The results show that training with synthetic images outperforms training with real site images.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Shi Zhou, Zijun Yang, Miaomiao Zhu, He L. Li, Seiichi Serikawa, Mitsunori Mizumachi, Lifeng Zhang
Summary: This paper proposes an automatic dataset creation method for object detection tasks. It extracts objects from source images and combines them as synthetic images, which are annotated automatically and used directly for training. The proposed method shows strong adaptation and generalization ability. Experimental results demonstrate that the trained neural networks using this method achieve high accuracy in object detection tasks in a vending supermarket.
Article
Computer Science, Artificial Intelligence
Roman Solovyev, Weimin Wang, Tatiana Gabruseva
Summary: This study introduces a novel method, weighted boxes fusion, for combining predictions from different object detection models, significantly improving the quality of the ensemble predicted rectangles. The method achieved top results in various datasets and challenges, with the 3D version of boxes fusion being successfully applied in winning teams of specific competitions.
IMAGE AND VISION COMPUTING
(2021)
Article
Computer Science, Theory & Methods
N. U. Haq, M. M. Fraz, T. S. Hashmi, M. Shahzad
Summary: Automatic detection of weapons is critical for enhancing security, but it is a challenging task due to the variety and occlusion of weapons. In this study, a CNN architecture for Orientation Aware Weapons Detection is proposed, which achieves improved performance compared to existing object detection algorithms. A new dataset with annotated bounding boxes is also provided for further research in this area.
Article
Computer Science, Artificial Intelligence
Zhe Chen, Jing Zhang, Dacheng Tao
Summary: In this study, a Recursive Context Routing (ReCoR) mechanism is proposed for more effective context modeling in object detection. By progressively modeling more contexts through a recursive structure, a more comprehensive method to utilize complicated contexts and contextual relationships is provided, with validated effectiveness on both the MS COCO and PASCAL VOC datasets.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Construction & Building Technology
Xuzhong Yan, Hong Zhang, Yefei Wu, Chen Lin, Shengwei Liu
Summary: This paper introduces a new image dataset aimed at advancing state-of-the-art instance segmentation in the field of construction management. The dataset contains 50,000 images with ten object categories belonging to construction workers, machines, and materials.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Computer Science, Information Systems
Aanchal Sharma, Rahul Gautam, Jaspal Singh
Summary: The WHO declared COVID-19 a pandemic and recommended wearing masks. An autonomous face mask monitoring system using deep learning is necessary due to the difficulty of manual monitoring. The development of a novel dataset is crucial for accurate face mask detection, and models like YOLOv5 have achieved high accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Review
Engineering, Industrial
Hafiz Mughees Ahmad, Afshin Rahimi
Summary: This paper presents a comprehensive survey of deep learning-based object detection methods for industrial applications. It discusses their applications in industrial settings and presents challenges and future trends in the field.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Zhe Liu, Kai Han, Kaifeng Xue, Yuqing Song, Lu Liu, Yangyang Tang, Yan Zhu
Summary: In this study, a comprehensive improvement on the original YOLOv3 for lesion detection in medical CT images is proposed, achieving enhanced accuracy and speed-accuracy trade-off compared to state-of-the-art methods. The proposed model shows promising results in detecting lesions with high precision and efficiency.
MULTIMEDIA SYSTEMS
(2022)
Article
Agricultural Engineering
Ruzhun Zhao, Yuchang Zhu, Yuanhong Li
Summary: This paper explores the simultaneous detection of grape clusters and their picking points in the task of automatic grape harvesting. It proposes a lightweight end-to-end model called YOLO-GP, which utilizes a ghost bottleneck to reduce model parameters and predicts picking points using grape cluster bounding boxes. The experiments demonstrate that YOLO-GP achieves a mean Average Precision of 93.27% for grape cluster detection and a distance error of less than 40 pixels for picking point detection, showing comparable performance to baseline models.
BIOSYSTEMS ENGINEERING
(2022)
Article
Forestry
Paulo A. S. Mendes, Antonio Paulo Coimbra, Anibal T. de Almeida
Summary: Forest fires have become a significant threat globally, and countries like the USA and Portugal have experienced recurrent fires. To minimize the impact of forest fires, one preventive measure is to use autonomous unmanned ground vehicles with AI technology to detect and classify forest vegetation and reduce the amount of combustible fuel. This innovative study compares two deep learning methodologies, YOLOv5 and YOLOR, for the detection and classification of forest vegetation.
Article
Computer Science, Information Systems
Yueyan Zhu, Hai Huang, Huayan Yu, Aoran Chen, Guanliang Zhao
Summary: This paper proposes an anchor-free pedestrian detector called CAPNet to address the challenges in pedestrian detection. It introduces a feature extraction module, a global feature mining and aggregation network, and an attribute-guided multiple receptive field module to enhance the detection performance. Experimental results show that the context and attribute perception greatly improves the detection, and CAPNet achieves new state-of-the-art performance on Caltech and CityPersons datasets.
Article
Plant Sciences
Rong Tang, Yujie Lei, Beisiqi Luo, Junbo Zhang, Jiong Mu
Summary: This paper proposes an efficient plum fruit detection model based on an improved YOLOv7 algorithm. The model can quickly and accurately detect plum fruits in complex orchard environments. By capturing high-resolution images of plum fruits growing in natural conditions and forming a dataset through manual screening, data enhancement, and annotation, the YOLOv7-plum algorithm achieved an average precision (AP) value of 94.91%, a 2.03% improvement compared to the YOLOv7 model. The experimental results demonstrate the better performance of the proposed method in detecting plum fruits in complex backgrounds, which contributes to the development of intelligent cultivation in the plum industry.
Article
Construction & Building Technology
Lang-Tao Wu, Jia-Rui Lin, Shuo Leng, Jiu-Lin Li, Zhen-Zhong Hu
Summary: This paper proposes a rule-based approach for MEP information extraction and verifies its feasibility and efficiency through experiments.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Construction & Building Technology
Zhe Zheng, Wenjie Liao, Jiarui Lin, Yucheng Zhou, Chi Zhang, Xinzheng Lu
Summary: The investigation of collapse accidents is crucial for preventing future incidents and improving structural resilience. However, conventional methods face challenges in dealing with complex collapse accidents. The proposed digital twin-based investigation method offers an effective solution by integrating real-world data into virtual models, allowing for efficient analysis and revealing potential collapse mechanisms.
ADVANCES IN CIVIL ENGINEERING
(2022)
Article
Construction & Building Technology
Can Jiang, Xin Li, Jia-Rui Lin, Ming Liu, Zhiliang Ma
Summary: Poor management of construction work, resource, and cash flows can lead to time and cost overruns, bankruptcy, and project failure due to their complexity and dynamics. This paper proposes a model and method to adaptively control resource flows and optimize the work and cash flows of construction projects. A mathematical model based on a partially observable Markov decision process is established to capture the complex interactions and uncertainties. A Deep Reinforcement Learning (DRL) based method is introduced for continuous adaptive optimal control, and a simulator based on discrete event simulation assists the training process. Experiments show that our method outperforms traditional methods and a hybrid approach combining DRL and empirical method achieves the best result.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Chemistry, Multidisciplinary
Dongyang An, Hui Deng, Cheng Shen, Yiwen Xu, Lina Zhong, Yichuan Deng
Summary: Construction courses often lack teaching of practical knowledge due to safety and cost concerns, but VR can improve this by facilitating interactions between teachers and students. This study evaluated the effect of VR in construction teaching and found that it enhances students' enthusiasm and satisfaction, especially in practical knowledge. Students also believe a combination of traditional and VR teaching is more helpful. These findings strengthen the advantages of VR in delivering practical knowledge in construction teaching.
APPLIED SCIENCES-BASEL
(2023)
Review
Construction & Building Technology
Jing-Ke Yan, Zhe Zheng, Yu-Cheng Zhou, Jia-Rui Lin, Yi-Chuan Deng, Xin-Zheng Lu
Summary: Intelligent construction is a new approach to transform the AEC industry through the integration of advanced information technologies. This study provides a comparative review of relevant literature and discusses the differences between developing and developed countries in the field of intelligent construction. Four future research directions are suggested.
Article
Construction & Building Technology
Cheng Yang, Jia-Rui Lin, Ke-Xiao Yan, Yi-Chuan Deng, Zhen-Zhong Hu, Cheng Liu
Summary: This paper proposes a data-driven approach to quantitatively evaluate the performance of construction supervisors by integrating analytic hierarchy process (AHP) and activity tracking.
Editorial Material
Construction & Building Technology
Hongling Guo, Jia-Rui Lin, Yantao Yu
Article
Construction & Building Technology
Can Jiang, Xiong Liang, Yu-cheng Zhou, Yong Tian, Shengli Xu, Jia-Rui Lin, Zhiliang Ma, Shiji Yang, Hao Zhou
Summary: In Chinese building codes, it is necessary for residential buildings to receive a minimum amount of direct sunlight on a specified winter day. This requirement is essential for obtaining a building permit during the conceptual design phase, and official software is commonly used to assess sunlight performance. The paper proposes a real-time shading time interval prediction method based on multilayer perceptron, which reduces computation time significantly with high accuracy. A residential neighborhood layout planning plug-in for Rhino 7/Grasshopper is also developed based on the proposed model. The study demonstrates the potential of using deep learning techniques for accelerating sunlight hour simulations in the conceptual design phase.
BUILDING AND ENVIRONMENT
(2023)
Article
Virology
Mingqian Xu, Jiarui Lin, Shuaibing Yang, Jiahu Yao, Meiyang Chen, Jinfu Feng, Liang Zhang, Li Zhou, Junjie Zhang, Qingsong Qin
Summary: The Epstein-Barr virus (EBV) encoded miRNA miR-BART11-3p promotes cell proliferation, migration, and invasion in gastric cancer (GC) by targeting DUSP6 and dysregulating the MAPK pathway. Restoring DUSP6 expression reverses the tumor-promoting effects of miR-BART11-3p, and blocking ERK phosphorylation inhibits the effects of miR-BART11-3p-expressing cells. These findings provide new insights into tumorigenesis in EBV-associated gastric cancer (EBVaGC) and potential therapeutic strategies.
JOURNAL OF VIROLOGY
(2023)
Article
Engineering, Mechanical
Yide Zheng, Yi Zhang, Jiarui Lin
Summary: Two algorithms based on survival signatures are proposed to analyze the reliability of complex systems with independently distributed components. The results demonstrate that these algorithms can effectively reduce the computation time and are applied to analyze a real practical problem.
PROBABILISTIC ENGINEERING MECHANICS
(2023)
Article
Construction & Building Technology
Yide Zheng, Yi Zhang, Jiarui Lin
Summary: Building Information Modelling (BIM) technology is widely used in the building industry, but the current BIM-based infrastructure time effect analysis mainly focuses on cost and schedule analyses, neglecting the impact on system safety. This paper developed a BIM-reliability integrated technology for time-varying and system analysis of structural safety, which was demonstrated using two different case studies.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Automation & Control Systems
Zhe Zheng, Yu-Cheng Zhou, Ke-Yin Chen, Xin-Zheng Lu, Zhong-Tian She, Jia-Rui Lin
Summary: This research aims to propose a novel approach to automatically evaluate and enhance the machine interpretability of single clauses and building codes. By introducing classification categories and developing a text classification model, the machine interpretability of building codes is improved, and a quantitative evaluation method is proposed. Experimental results show that the proposed method outperforms existing methods, and it is suggested that there is still room for improvement in the interpretability of building codes.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Proceedings Paper
Construction & Building Technology
Jingke Yan, Zhe Zheng, Yucheng Zhou, Jiarui Lin, Yichuan Deng
Summary: With the development of information technologies and the transformation and upgrading of the AEC industry, intelligent construction is gaining increasing attention. Integrating with construction industrialization, intelligent construction has become an important way to achieve high-quality development of the AEC industry. Through a bibliometric analysis of related research, this study found that English articles transitioned from theoretical methods to engineering practice, while Chinese articles showed a rapid development in recent years with close interactions with engineering practice.
CARBON PEAK AND NEUTRALITY STRATEGIES OF THE CONSTRUCTION INDUSTRY (ICCREM 2022)
(2022)
Article
Construction & Building Technology
Jia Liang, Qipeng Zhang, Xingyu Gu
Summary: A lightweight PCSNet-based segmentation model is developed to address the issues of insufficient performance in feature extraction and boundary loss information. The introduction of generalized Dice loss improves prediction performance, and the visualization of class activation mapping enhances model interpretability.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Gilsu Jeong, Minhyuk Jung, Seongeun Park, Moonseo Park, Changbum Ryan Ahn
Summary: This study introduces a contextual audio-visual approach to recognize multi-equipment activities in tunnel construction sites, improving monitoring effectiveness. Tested against real-world operation data, the model achieved remarkable results, emphasizing the potential of contextual multimodal models in enhancing operational efficiency in complex construction sites.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Jin Wang, Zhigao Zeng, Pradip Kumar Sharma, Osama Alfarraj, Amr Tolba, Jianming Zhang, Lei Wang
Summary: This study presents a dual-path network for pavement crack segmentation, combining Convolutional Neural Network (CNN) and transformer. A lightweight CNN encoder is used for local feature extraction, while a novel transformer encoder integrates high-low frequency attention mechanism and efficient feedforward network for global feature extraction. Additionally, a complementary fusion module is introduced to aggregate intermediate features extracted from both encoders. Evaluation on three datasets confirms the superior performance of the proposed network.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Pierre Gilibert, Romain Mesnil, Olivier Baverel
Summary: This paper introduces a flexible method for crafting 2D assemblies adaptable to various geometric assumptions in the realm of sustainable construction. By utilizing digital fabrication technologies and optimization approaches, precise control over demountable buildings can be achieved, improving mechanical performance and sustainability.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Jorge Loy-Benitez, Myung Kyu Song, Yo-Hyun Choi, Je-Kyum Lee, Sean Seungwon Lee
Summary: This paper discusses the advancement of tunnel boring machines (TBM) through the application of artificial intelligence. It highlights the significance of AI-based management subsystems for automatic TBM operations and presents recent contributions in this field. The paper evaluates modeling, monitoring, and control subsystems and suggests research paths for integrating existing management subsystems into TBM automation.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Alireza Shamshiri, Kyeong Rok Ryu, June Young Park
Summary: This paper reviews the application of text mining and natural language processing in the construction field, highlighting the need for automation and minimizing manual tasks. The study identifies potential research opportunities in strengthening overlooked construction aspects, coupling diverse data formats, and leveraging pre-trained language models and reinforcement learning.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Zhengyi Chen, Hao Wang, Keyu Chen, Changhao Song, Xiao Zhang, Boyu Wang, Jack C. P. Cheng
Summary: This study proposes an improved coverage path planning system that leverages building information modeling and robotic configurations to optimize coverage performance in indoor environments. Experimental validation shows the effectiveness and applicability of the system. Future research will focus on further enhancing coverage ratio and optimizing computation time.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Yonglin Fu, Junjie Chen, Weisheng Lu
Summary: This study presents a review of human-robot collaboration (HRC) in modular construction manufacturing (MCM), focusing on tasks, human roles, and interaction levels. The review found that HRC solutions are applicable to various MCM tasks, with a primary focus on timber component production. It also revealed the diverse collaborative roles humans can play and the varying levels of interaction with robots.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Qiong Liu, Shengbo Cheng, Chang Sun, Kailun Chen, Wengui Li, Vivian W. Y. Tam
Summary: This paper presents an approach to enhance the path-following capability of concrete printing by integrating steel cables into the printed mortar strips, and validates the feasibility and effectiveness of this approach through experiments.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Honghu Chu, Lu Deng, Huaqing Yuan, Lizhi Long, Jingjing Guo
Summary: The study proposes a method called Cascade CATransUNet for high-resolution crack image segmentation. This method combines the coordinate attention mechanism and self-cascaded design to accurately segment cracks. Through a customized feature extraction architecture and an optimized boundary loss function, the proposed method achieves impressive segmentation performance on HR images and demonstrates its practicality in UAV crack detection tasks.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Daniel Lamas, Andres Justo, Mario Soilan, Belen Riveiro
Summary: This paper introduces a new method for creating synthetic point clouds of truss bridges and demonstrates the effectiveness of a deep learning approach for semantic and instance segmentation of these point clouds. The proposed methodology has significant implications for the development of automated inspection and monitoring systems for truss bridges.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Kahyun Jeon, Ghang Lee, Seongmin Yang, Yonghan Kim, Seungah Suh
Summary: This study proposes two enhanced unsupervised text classification methods for domain-specific non-English text. The results of the tests show that these methods achieve excellent performance on Korean building defect complaints, outperforming state-of-the-art zero-shot and few-shot text classification methods, with minimal data preparation effort and computing resources.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Yoonhwa Jung, Julia Hockenmaier, Mani Golparvar-Fard
Summary: This study introduces a transformer-based natural language processing model, UNIfORMATBRIDGE, that automatically labels activities in a project schedule with Uniformat classification. Experimental results show that the model performs well in matching unstructured schedule data to Uniformat classifications. Additionally, the study highlights the importance of this method in developing new techniques.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
De-Graft Joe Opoku, Srinath Perera, Robert Osei-Kyei, Maria Rashidi, Keivan Bamdad, Tosin Famakinwa
Summary: This paper introduces a digital twin technology combining Building Information Modelling and the Internet of Things for the construction industry, aiming to optimize building conditions. The technology is implemented in a university library, successfully achieving real-time data capture and visual representation of internal conditions.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Zaolin Pan, Yantao Yu
Summary: The construction industry faces safety and workforce shortages globally, and worker-robot collaboration is seen as a solution. However, robots face challenges in recognizing worker intentions in construction. This study tackles these challenges by proposing a fusion method and investigating the best granularity for recognizing worker intentions. The results show that the proposed method can recognize multi-granular worker intentions effectively, contributing to seamless worker-robot collaboration in construction.
AUTOMATION IN CONSTRUCTION
(2024)