Article
Engineering, Multidisciplinary
Jongbin Won, Jong-Woong Park, Changsu Shim, Man-Woo Park
Summary: Visual inspection is crucial for the maintenance of bridge structures, now enhanced by image-processing techniques that can localize damages. However, generating panoramic images from a series of bridge-surface images is challenging. This study introduces a method using Deepmatching for stitching bridge-surface images, with successful validation in lab-scale and field experiments.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
Summary: In this paper, an unsupervised deep image stitching framework was proposed to address the limitations of traditional feature-based image stitching technologies and learning-based methods. The framework consists of two stages aimed at coarse image alignment and image reconstruction. Extensive experiments demonstrate the superiority of the proposed method over other state-of-the-art solutions, with users preferring the image stitching quality even compared to supervised solutions.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Mathematics
Javier Perez Soler, Jose-Luis Guardiola, Alberto Perez Jimenez, Pau Garrigues Carbo, Nicolas Garcia Sastre, Juan-Carlos Perez-Cortes
Summary: The research proposes a camera-coherent point selection method for precise measurement of differences between a reconstructed object and a reference model. The algorithm reduces reconstruction errors by up to one fifth compared to traditional 3D reconstruction methods and assures the existence of any differences with the reference. This contributes significantly to advancements in the field of 3D object inspection.
Article
Engineering, Marine
Seonghun Hong, Jinwhan Kim
Summary: This paper presents a method for three-dimensional visual mapping of underwater ship hulls using monocular vision. The proposed method addresses the challenges of limited visibility and ineffective information in hull surface images by adopting a two-step approach of global registration and 3D reconstruction. Experimental results with image datasets obtained in real sea environments demonstrate the feasibility of the proposed method.
Article
Computer Science, Artificial Intelligence
Lang Nie, Chunyu Lin, Kang Liao, Yao Zhao
Summary: This paper proposes an image stitching learning framework that utilizes a multi-scale deep homography module and an edge-preserved deformation module to achieve accurate homography estimation and artifact elimination in image stitching.
Article
Engineering, Civil
Kai Cheng, Jiazeng Shan, Yuwen Liu
Summary: This study presents a feature-based image stitching method for panorama construction and visual inspection of building structures. The methodology framework is inspection-oriented with optimized inlier distribution. The reliability of the proposed feature-based stitching approach is parametrically studied with different setups of input images.
SMART STRUCTURES AND SYSTEMS
(2021)
Review
Chemistry, Analytical
Chris H. Bahnsen, Anders S. Johansen, Mark P. Philipsen, Jesper W. Henriksen, Kamal Nasrollahi, Thomas B. Moeslund
Summary: This study discusses the importance of automated inspection for sewer systems, introduces different 3D sensing technologies, and evaluates and compares the 3D reconstruction performance of sensors. The results show that the point cloud based on the ToF technology of the Pico Flexx is superior to other techniques.
Article
Computer Science, Information Systems
Xin Chen, Mei Yu, Yang Song
Summary: This study proposes an optimized seam-driven image stitching method considering depth, color, and texture information. By introducing depth information, the method can find the seam that adapts to the depth of the scene and effectively avoid passing through salient objects, resulting in high-quality stitching results.
Article
Computer Science, Artificial Intelligence
Izat Khamiyev, Dias Issa, Zahid Akhtar, M. Fatih Demirci
Summary: A traditional approach using RANSAC algorithm on SIFT correspondences for panoramic image generation is not robust enough for highly varying natural images, and deep learning approach has not been extensively explored. This paper proposes a deep learning model for panoramic image generation and achieves superior results compared to the state-of-the-art SIFT+RANSAC algorithm. A novel panoramic image generation dataset is also introduced.
Article
Construction & Building Technology
Hua-Fei Zhou, Zhao-Yi Li, Lin-Jun Lu, Yi-Qing Ni
Summary: The study introduces a method to establish a thermal-induced displacement function of the image plane for predicting and eliminating image drift in videogrammetric measurement. The displacement function is calibrated using stationary targets, allowing for the prediction of thermal-induced displacement in measurements. Satisfactory performance is achieved in both temperature-controlled and outdoor environments through verification tests.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Computer Science, Information Systems
Vasanth Subramanyam, Jayendra Kumar, Shiva Nand Singh
Summary: Surface inspection systems in the steel industry use multiple machine-vision cameras for real-time quality control. Existing approaches, including direct and deep-learning-based techniques, face limitations in terms of parallax and real-time application effectiveness. We propose a hybrid descriptor that effectively stitches low-textural images captured by multiple cameras using defect detection. Experimental results demonstrate that our hybrid descriptor outperforms existing feature descriptors in terms of matching accuracy and execution time, producing a seamlessly stitched output.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
Weilei Yu, Mayuko Nishio
Summary: This study proposed a multilevel bridge inspection framework based on computer vision technology and verified it using CNN models. By using different network models and datasets, the study achieved recognition and segmentation of bridge types and bridge components with high accuracy.
Article
Chemistry, Analytical
Povendhan Palanisamy, Rajesh Elara Mohan, Archana Semwal, Lee Ming Jun Melivin, Braulio Felix Gomez, Selvasundari Balakrishnan, Karthikeyan Elangovan, Balakrishnan Ramalingam, Dylan Ng Terntzer
Summary: This study introduces an AI-enabled robot-assisted framework for drain inspection and mapping, evaluated through deep learning and real-time trials. Results show that the robot's maneuverability was stable, with accurate mapping and localization in various drain types.
Article
Chemistry, Analytical
Jannis Holtkotter, Rita Amaral, Rute Almeida, Cristina Jacome, Ricardo Cardoso, Ana Pereira, Mariana Pereira, Ki H. Chon, Joao Almeida Fonseca
Summary: Long-term adherence to medication is crucial for managing chronic diseases, but current objective tools for tracking adherence are lacking or inconvenient. To address this issue, a pill intake detection tool was developed using digital image processing. The tool showed promising results in detecting the presence of round pills.
Article
Computer Science, Information Systems
Chiranjibi Sitaula, Tej Bahadur Shahi, Faezeh Marzbanrad, Jagannath Aryal
Summary: With the rise of deep learning algorithms, scene image representation methods have improved significantly in accuracy for classification. However, the complexity of scene images leads to intra-class dissimilarity and inter-class similarity problems, limiting the overall performance. This paper reviews existing methods and compares their performance qualitatively and quantitatively, while also speculating on future research directions. This survey provides in-depth insights and applications of recent scene image representation methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Yulu Luke Chen, Mohammad R. Jahanshahi, Preetham Manjunatha, WeiPhang Gan, Mohamed Abdelbarr, Sami F. Masri, Burcin Becerik-Gerber, John P. Caffrey
IEEE SENSORS JOURNAL
(2016)
Article
Instruments & Instrumentation
Mohamed Abdelbarr, Yulu Luke Chen, Mohammad R. Jahanshahi, Sami F. Masri, Wei-Men Shen, Uvais A. Qidwai
SMART MATERIALS AND STRUCTURES
(2017)
Article
Construction & Building Technology
Yulu Luke Chen, Mohamed Abdelbarr, Mohammad R. Jahanshahi, Sami F. Masri
STRUCTURAL CONTROL & HEALTH MONITORING
(2017)
Article
Automation & Control Systems
Fu-Chen Chen, Mohammad R. Jahanshahi
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2018)
Review
Engineering, Multidisciplinary
Rih-Teng Wu, Mohammad Reza Jahanshahi
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2020)
Article
Construction & Building Technology
Muhammad Ali Akbar, Uvais Qidwai, Mohammad R. Jahanshahi
STRUCTURAL CONTROL & HEALTH MONITORING
(2019)
Article
Chemistry, Analytical
Ahmadreza Mahmoudzadeh, Amir Golroo, Mohammad R. Jahanshahi, Sayna Firoozi Yeganeh
Article
Computer Science, Interdisciplinary Applications
Srinath Shiv Kumar, Mingzhu Wang, Dulcy M. Abraham, Mohammad R. Jahanshahi, Tom Iseley, Jack C. P. Cheng
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2020)
Article
Construction & Building Technology
Tarutal Ghosh Mondal, Mohammad R. Jahanshahi, Rih-Teng Wu, Zheng Yi Wu
STRUCTURAL CONTROL & HEALTH MONITORING
(2020)
Article
Engineering, Electrical & Electronic
Fu-Chen Chen, Mohammad R. Jahanshahi
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2020)
Article
Computer Science, Artificial Intelligence
Fu-Chen Chen, Mohammad R. Jahanshahi
MACHINE VISION AND APPLICATIONS
(2020)
Article
Engineering, Mechanical
Rih-Teng Wu, Mehdi Jokar, Mohammad R. Jahanshahi, Fabio Semperlotti
Summary: This study proposes a novel approach based on deep auto-encoder to solve the inverse problem of designing assemblies of acoustic scattering elements, achieving more efficient solution methodologies. The proposed network is validated numerically through three design scenarios, demonstrating its feasibility and performance.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Interdisciplinary Applications
Fu-Chen Chen, Abhishek Subedi, Mohammad R. Jahanshahi, David R. Johnson, Edward J. Delp
Summary: Floods are a common and devastating natural disaster that cause significant economic losses and human casualties worldwide. This study proposes a laborless and financially feasible framework that utilizes deep learning and Google Street View images to collect building attribute data and estimate various attributes, such as foundation height, type, building type, and number of stories. The framework achieves accurate results and can predict attributes for a large number of buildings in a short amount of time.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Tarutal Ghosh Mondal, Mohammad R. Jahanshahi, Zheng Yi Wu
Summary: Recent advancements in computer vision and deep learning have expanded the possibilities for autonomous condition assessment of civil infrastructure based on vision. However, the existing literature shows that most vision-based inspection techniques only rely on color information, leading to a loss of distance and scale information. This study addresses the knowledge gap by incorporating depth fusion into a semantic segmentation model. The study explores different encoding techniques for depth data and investigates fusion strategies for RGB and depth data. Overall, feature-level fusion is found to be the most effective, improving deep learning-based damage segmentation algorithms by up to 25% without increasing computation time. A novel volumetric damage quantification approach is also introduced. This study is expected to advance infrastructure resilience and maintenance.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2023)
Review
Robotics
Mohammad R. Jahanshahi, Wei-Men Shen, Tarutal Ghosh Mondal, Mohamed Abdelbarr, Sami F. Masri, Uvais A. Qidwai
INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS
(2017)