Article
Automation & Control Systems
Mingwei Cao, Liping Zheng, Wei Jia, Huimin Lu, Xiaoping Liu
Summary: This article focuses on modeling 3-D scenes from image data obtained from the IoT, proposing an accurate 3-D reconstruction method for dealing with various repetitive structures. Experimental results show that the proposed method outperforms state-of-the-art methods on benchmark datasets.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Yves M. Galvao, Leticia Portela, Janderson Ferreira, Pablo Barros, Oberta Andrade De Araujo Fagundes, Bruno J. T. Fernandes
Summary: The research aims to detect and identify fall events using an anomaly identification framework without explicit labeling. The framework's performance is validated through experiments on different datasets, including cross-dataset evaluation.
Article
Engineering, Electrical & Electronic
Yuxuan Chen, Ben Wang, Qiongwei Li, Yujun Zhong, Yi Jin, Changan Zhu
Summary: This article proposes a FOV-enlarged single-camera 3-D shape reconstruction system by using a saccade mirror to generate virtual cameras and reconstruct objects with multiview images. The system achieves a larger FOV without sacrificing image resolution, simplifies the calibration process, and demonstrates robustness in real-life experiments.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Rui Fan, Umar Ozgunalp, Yuan Wang, Ming Liu, Ioannis Pitas
Summary: A novel pothole detection algorithm based on road disparity map estimation and segmentation is proposed in this article, featuring the incorporation of stereo rig roll angle into shifting distance calculation and the utilization of semiglobal matching for efficient estimation of road disparities. The algorithm further transforms the disparity map to better distinguish damaged road areas and utilizes linear iterative clustering to group transformed disparities for pothole detection, achieving state-of-the-art accuracy and efficiency in experimental results.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Electrical & Electronic
Chalavadi Vishnu, Rajeshreddy Datla, Debaditya Roy, Sobhan Babu, C. Krishna Mohan
Summary: The proposed approach efficiently models spatio-temporal features using fall motion vector, achieving better performance in fall detection in various scenarios compared to existing methods.
IEEE SENSORS JOURNAL
(2021)
Review
Engineering, Electrical & Electronic
Mengyin Fu, Hao Liang, Chunhui Zhu, Zhipeng Dong, Rundong Sun, Yufeng Yue, Yi Yang
Summary: Image stitching is a technique to generate a wide view and high-resolution image by stitching multiple overlapping images together. It can be achieved through feature-based or deep learning methods. This article provides a systematic literature review of image stitching techniques applied on the plane and 3-D models.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Ji Li, Jingtian Guan, Xiaobo Chen, Xinyi Le, Juntong Xi
Summary: This article proposes an exposure map fusion method for precise 3-D reconstruction of high dynamic range surfaces, which addresses the issues caused by using image intensity for reconstruction. The method improves reconstruction accuracy by using exposure maps and enhances the signal-to-noise ratio through fusing multiple exposure maps.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Hirofumi Morioka, Toshie Misu, Taichi Suginoshita, Hideki Mitsumine
Summary: This study conducted 3D reconstruction experiments using multiple fixed cameras. To improve the image quality, the optimal number and placement of cameras were determined and 3D reconstruction was performed using visual hull and stereo matching. Additionally, the addition of a surface light field and the use of a deep neural network for video translation further enhanced the reconstruction quality.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Geochemistry & Geophysics
Yeping Peng, Mingbin Yang, Genping Zhao, Guangzhong Cao
Summary: The SFM method based on binocular vision can reconstruct plant morphology in 3D for plant growth monitoring. The method shows accurate measurement results for plant height, canopy size, and trunk diameter. This approach demonstrates promising potential for online growth monitoring of agricultural plants.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Peng Chi, Zhenmin Wang, Haipeng Liao, Ting Li, Jinhua Zhan, Xiangmiao Wu, Jiyu Tian, Qin Zhang
Summary: In recent years, 3-D reconstruction has been widely used in various fields, including robot pose estimation, mine exploration, and building of digital twins. While visual-based reconstruction methods have good real-time performance and high frequency, they are slightly inadequate in scenes that require high accuracy with no obvious demand for update frequency. To address this issue, a new visual-based pose estimation and 3-D reconstruction method based on image feature extraction and point cloud recognition was proposed in this research, which improves the accuracy of visual-based pose estimation methods. The method was tested in different scenarios and showed significant improvement in reconstruction accuracy while maintaining low-latency performance.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Mojing Li, Changku Sun, Luhua Fu, Peng Wang
Summary: In stereo phase-shifting profilometry (PSP), the performance of stereo matching algorithm directly affects the final reconstruction result. This paper introduces deep learning for correspondence retrieval, utilizing the power of deep image prior (DIP) in untrained image restoration. By exploiting the inner relevance and invariance across stereo image pairs, this approach achieves accurate pixel correspondences without assuming system geometry, resulting in consistent reconstruction.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Yangyang Liu, Shuo Chang, Zhiqing Wei, Kezhong Zhang, Zhiyong Feng
Summary: This paper focuses on fusing millimeter-wave radar data with monocular images at the feature level to enhance 3-D detection capability.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Geochemistry & Geophysics
Pinhe Wang, Limin Shi, Bao Chen, Zhanyi Hu, Jianzhong Qiao, Qiulei Dong
Summary: In this study, a hierarchical reconstruction framework based on multiple optical satellite images is proposed to recover the 3-D scene structure. With only four ground control points (GCPs), the proposed framework achieves fully automated reconstruction and outperforms several state-of-the-art methods in most cases.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Review
Engineering, Electrical & Electronic
Mehdi Maboudi, MohammadReza Homaei, Soohwan Song, Shirin Malihi, Mohammad Saadatseresht, Markus Gerke
Summary: Unmanned aerial vehicles (UAVs) are popular platforms for data capturing due to their high maneuverability, autonomous data acquisition capability, and ability to reach difficult vantage points. This article explores a wide range of algorithmic approaches for viewpoints and path planning in 3-D reconstruction using UAV-captured data. With over 200 references, it covers different aspects of the topic and focuses on single-UAV outdoor 3-D reconstruction. The article discusses evaluation strategies, highlights innovations and limitations, and provides a critical analysis of existing challenges and future research perspectives.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Pablo Vera, Octavio Icasio-Hernandez, Joaquin Salas
Summary: This article assesses the relevance of accurately measuring the center of radial distortion (CoD) for reliable 3-D reconstructions from multiple views. The study found that using the image center (CI) as a replacement for CoD significantly increases reconstruction error, especially at the corners of the image, in high distortion lenses.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Information Systems
Pierre Plantard, Hubert P. H. Shum, Franck Multon
MULTIMEDIA TOOLS AND APPLICATIONS
(2017)
Article
Neurosciences
E. Auvinet, F. Multon, V. Manning, J. Meunier, J. P. Cobb
Article
Engineering, Biomedical
He Liu, Edouard Auvinet, Joshua Giles, Ferdinando Rodriguez y Baena
ANNALS OF BIOMEDICAL ENGINEERING
(2018)
Article
Orthopedics
C. Riviere, F. Iranpour, S. Harris, E. Auvinet, A. Aframian, S. Parratte, J. Cobb
ORTHOPAEDICS & TRAUMATOLOGY-SURGERY & RESEARCH
(2018)
Article
Orthopedics
Charles Riviere, Fatima Dhaif, Hemina Shah, Adam Ali, Edouard Auvinet, Arash Aframian, Justin Cobb, Stephen Howell, Simon Harris
ORTHOPAEDICS & TRAUMATOLOGY-SURGERY & RESEARCH
(2018)
Article
Computer Science, Artificial Intelligence
Said Yacine Boulahia, Eric Anquetil, Franck Multon, Richard Kulpa
COMPUTER VISION AND IMAGE UNDERSTANDING
(2018)
Article
Orthopedics
Kartik Logishetty, Luke Western, Ruairidh Morgan, Farhad Iranpour, Justin P. Cobb, Edouard Auvinet
CLINICAL ORTHOPAEDICS AND RELATED RESEARCH
(2019)
Article
Multidisciplinary Sciences
Huixiang Wang, Kapil Sugand, Simon Newman, Gareth Jones, Justin Cobb, Edouard Auvinet
Article
Orthopedics
Cedric Maillot, Edouard Auvinet, Ciara Harman, Justin Cobb, Charles Riviere
ORTHOPAEDICS & TRAUMATOLOGY-SURGERY & RESEARCH
(2020)
Review
Orthopedics
H. Vermue, J. Lambrechts, T. Tampere, N. Arnout, E. Auvinet, J. Victor
BONE & JOINT JOURNAL
(2020)
Article
Computer Science, Software Engineering
Jean Basset, Stefanie Wuhrer, Edmond Boyer, Franck Multon
COMPUTERS & GRAPHICS-UK
(2020)
Article
Computer Science, Software Engineering
Xiaofang Wang, Stephanie Prevost, Adnane Boukhayma, Eric Desjardin, Celine Loscos, Benoit Morisset, Franck Multon
Summary: This paper addresses the problem of capturing the shape and pose of a human character using a single depth sensor. The authors propose a hybrid approach that combines the advantages of model fitting and deep learning. Extensive experiments demonstrate that this hybrid approach improves pose and shape estimation compared to using either method separately.
COMPUTERS & GRAPHICS-UK
(2023)
Article
Computer Science, Software Engineering
Mohamed Younes, Ewa Kijak, Richard Kulpa, Simon Malinowski, Franck Multon
Summary: This paper proposes a Multi-Agent Generative Adversarial Imitation Learning based approach for simulating interactions and motions of multiple physics-based characters. The approach trains the system using two datasets, one with motions of a single actor and another with interactions between multiple actors. The method allows each character to imitate the interactive skills associated with each actor, while preserving their intrinsic style.
PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES
(2023)
Article
Neurosciences
Sam W. Hughes, Hongyan Zhao, Edouard J. Auvinet, Paul H. Strutton
Article
Engineering, Industrial
Pierre Plantard, Hubert P. H. Shum, Anne-Sophie Le Pierres, Franck Multon
APPLIED ERGONOMICS
(2017)