Article
Computer Science, Artificial Intelligence
Yuguang Shi, Yu Guo, Zhenqiang Mi, Xinjie Li
Summary: In this study, a 3D object detection method called Stereo CenterNet (SC) is proposed, which utilizes geometric information from stereo imagery. SC predicts the key points and utilizes 2D and 3D information to restore the object's bounding box in 3D space. Experimental results show that SC achieves the best trade-off between speed and accuracy.
Article
Computer Science, Interdisciplinary Applications
Euijeong Song, Seokjung Kim, Seok Chung, Minho Chang
Summary: This paper presents a novel deep-learning-based photometric stereo method that uses superresolution images to enhance original image information. By optimizing the input-output of the network, better results were achieved compared to existing methods.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2021)
Article
Optics
S. A. N. A. O. HUANG, Y. I. N. G. J. I. E. SHI, M. I. N. G. LI, J. I. N. G. W. E. I. QIAN, K. E. XU
Summary: This study analyzes the convergence of a near-field point light source in water using a light propagation model. The photometric stereo formula is determined based on accurate estimation of illuminance entering the camera. An underwater photometric stereo system is designed to validate the proposed method's feasibility. Experimental results demonstrate improved accuracy in normal calculation, enabling accurate 3D reconstruction for underwater surface microdefect detection.
Article
Optics
Ritz Ann Aguilar, Nathaniel Hermosa, Maricor Soriano
Summary: In this study, three-dimensional computational ghost imaging was achieved using multiple photoresistors as single-pixel detectors with the semi-calibrated lighting approach. The depth map and surface normals of the scene were retrieved accurately by performing imaging in the spatial frequency domain and applying semi-calibrated photometric stereo (SCPS) to the obtained spectra.
Article
Chemistry, Analytical
Xiaogang Jia, Wei Chen, Zhengfa Liang, Xin Luo, Mingfei Wu, Chen Li, Yulin He, Yusong Tan, Libo Huang
Summary: Stereo matching is an important research field in computer vision. By integrating fast 2D stereo methods with accurate 3D networks, this study improves performance and reduces computational time effectively. The method strikes a balance between speed and accuracy, achieving significant improvement in accuracy while being faster than other existing stereo networks.
Article
Computer Science, Artificial Intelligence
Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Xiaojun Tong, Wenxiu Sun
Summary: This paper proposes a new deep learning framework to infer the 3D shape of an object from a pair of stereo images, achieving better performance than state-of-the-art methods. Additionally, a large-scale synthetic benchmarking dataset named StereoShapeNet is introduced to evaluate the reconstruction algorithms.
Article
Engineering, Multidisciplinary
Qinghua Wang, Shuo Wang, Bo Li, Ke Zhu, Tonghai Wu
Summary: This study proposes an optimized photometric stereo approach to improve the reconstruction of worn surfaces. By constructing a multi-branch network and embedding prior knowledge, the influence of image noise on the reconstruction results is effectively suppressed. Compared with Laser Scanning Confocal Microscopy, this method can achieve over 88% similarity in worn surface roughness.
Article
Astronomy & Astrophysics
Rok Nezic, Stefano Bagnulo, Geraint H. Jones, Matthew M. Knight, Galin Borisov
Summary: This study investigated the photometric and polarimetric observations of a sungrazing Kreutz comet C/2010 E6 using Twin STEREO spacecraft. The comet disintegrated during its perihelion passage, and the observations showed various changes, such as the broadening and increase of intensity peak, the drop to zero polarization at high phase angles, and the emergence of negative polarization at low phase angles. The analysis suggested that the steep slope of increasing polarization with increasing cometocentric distance may be attributed to sublimation of refractory organic matrix and the processing of dust grains. The proximity to the Sun also caused changes in polarization signatures, indicating the fragmentation of the nucleus and the exposure of fresh silicate particles followed by gradual sublimation.
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
(2022)
Article
Chemistry, Analytical
Xiaobo Chen, Jinkai Zhang, Juntong Xi
Summary: This paper presents a novel 3D metrology method using a camera with rotating anamorphic lenses. The method reconstructs the 3D data of the measured object from two anamorphic images captured before and after the rotation of the lens. The main advantage of this method is the simplicity of point matching, making it suitable for compact sensors for fast 3D measurements.
Article
Engineering, Multidisciplinary
Ru Yang, Yaoke Wang, Shuheng Liao, Ping Guo
Summary: This paper presents a new deep learning method, DPPS, for recovering surface normal and height maps under varying illumination conditions. The method combines physics-based and data-driven approaches to handle reflective metal surfaces with unknown surface roughness. Experimental results show that DPPS outperforms commercial 3D scanners in accuracy and provides guidance for the application of deep learning in manufacturing.
Article
Chemistry, Analytical
Ali Karami, Fabio Menna, Fabio Remondino
Summary: This paper presents a method for generating an accurate 3D reconstruction of non-collaborative surfaces by combining photogrammetry and photometric stereo, enhancing the reliability and precision of the reconstruction through the fusion of geometric information and high-resolution details.
Article
Engineering, Electrical & Electronic
Huiyu Liu, Yunhui Yan, Kechen Song, Han Yu
Summary: In this article, a self-attention photometric stereo network (SPS-Net) is proposed to exploit information in all three dimensions without violating natural characters. The SPS-Net achieved higher performance than state-of-the-art algorithms in photometric stereo tasks with dense lightings and also outperformed benchmarks in sparse and light-information-robust photometric stereo tasks.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Chemistry, Analytical
Huaizhou Li, Shuaijun Wang, Zhenpeng Bai, Hong Wang, Sen Li, Shupei Wen
Summary: Thermal infrared imaging is less affected by lighting conditions and smoke compared to visible light imaging. However, the lower resolution and lack of rich texture details in thermal infrared images make them unsuitable for stereo matching and 3D reconstruction. To address this issue, we propose an advanced stereo matching algorithm that enhances the quality of infrared stereo imaging. The algorithm includes preprocessing, camera calibration, and disparity map generation using the SGBM algorithm, resulting in improved stereo matching accuracy and practical value for thermal infrared imaging.
Article
Computer Science, Artificial Intelligence
Zhong Xiang, Huaxiong Wu, Ding Zhou
Summary: This study investigates accurate industry online scene text recognition techniques for metallic debossed characters (MDCs) by proposing a multi-scale image fusion algorithm and utilizing a U-shaped network for text localization. The methods enhance the contrast and accuracy of MDC recognition for long texts.
IET IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Xin Tian, Rui Liu, Zhongyuan Wang, Jiayi Ma
Summary: A novel 3D reconstruction method combining polarization imaging and binocular stereo vision has been proposed, which aims to improve accuracy by correcting azimuth angle errors and utilizing low-rank matrix factorization constraints. Experimental results demonstrate the efficiency of the method and its wide application prospects in 3D reconstruction.
INFORMATION FUSION
(2022)
Article
Construction & Building Technology
Gary A. Atkinson, Wenhao Zhang, Mark F. Hansen, Mathew L. Holloway, Ashley A. Napier
AUTOMATION IN CONSTRUCTION
(2020)
Article
Multidisciplinary Sciences
Gary A. Atkinson, Lyndon N. Smith, Melvyn L. Smith, Christopher K. Reynolds, David J. Humphries, Jon M. Moorby, David K. Leemans, Alison H. Kingston-Smith
SCIENTIFIC REPORTS
(2020)
Review
Computer Science, Interdisciplinary Applications
Melvyn L. Smith, Lyndon N. Smith, Mark F. Hansen
Summary: In recent years, rapid developments in machine learning and faster GPU computing hardware have led to a significant growth in machine vision applications, benefiting industries such as manufacturing, security, and medicine. Additionally, machine vision has opened up new areas such as agriculture and construction. Looking ahead, machine vision will continue to face challenges and opportunities for further development.
COMPUTERS IN INDUSTRY
(2021)
Article
Agronomy
Mark F. Hansen, Emma M. Baxter, Kenneth M. D. Rutherford, Agnieszka Futro, Melvyn L. Smith, Lyndon N. Smith
Summary: This research demonstrates that the impact of increased stress on animal welfare can be identified through frontal images of animals, paving the way for developing an automated system to improve animal welfare in precision livestock farming.
Article
Computer Science, Information Systems
Gary A. Atkinson, Sean O'Hara Nash, Lyndon N. Smith
Summary: This paper evaluates the precision of polarisation imaging technology for the inspection of carbon fibre composite components, showing sub-degree accuracy can be obtained in ideal conditions. The precision varies depending on illumination, lens choice and material type, with limited application for non-planar regions in three-dimensional component inspection.
Article
Veterinary Sciences
Mark F. Hansen, Alphonsus Oparaeke, Ryan Gallagher, Amir Karimi, Fahim Tariq, Melvyn L. Smith
Summary: This article presents the application of machine vision in the livestock industry, specifically in the field of insect farming. State of the art object detection and classification techniques were used to accurately count and measure the size of insects, as well as classify their gender. The low-cost Insecto IoT device was introduced for environmental condition monitoring and high resolution image capture.
FRONTIERS IN VETERINARY SCIENCE
(2022)
Article
Engineering, Aerospace
L. Fletcher, R. Clarke, T. Richardson, M. Hansen
Summary: This paper investigates the application of reinforcement learning to the problem of controlling a custom sweep-wing aircraft's perched landing manoeuvre. It builds upon previous work by introducing enhancements and modifications to improve performance and reduce error. The study finds that hyperparameter optimization has the most significant impact on increasing reward performance.
AERONAUTICAL JOURNAL
(2022)
Article
Chemistry, Multidisciplinary
Cid Ramon Gonzalez-Gonzalez, Mark Hansen, Alexandros Ch Stratakos
Summary: This study presents a practical method for identifying foodborne pathogenic bacteria using a Raman handheld device. The method is simple, low-cost, and achieves high accuracy in identifying monocultures in a shorter time.
APPLIED SCIENCES-BASEL
(2022)
Proceedings Paper
Computer Science, Information Systems
Wenhao Zhang, Melvyn L. Smith
Summary: This paper investigates a passive eye center localization approach using convolutional neural networks, achieving high accuracy. The method performed well in experiments and was validated on a high-resolution dataset.
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS, ICCSA 2022, PT I
(2022)
Proceedings Paper
Computer Science, Software Engineering
Lyndon N. Smith, Max P. Langhof, Mark F. Hansen, Melvyn L. Smith
Summary: Palmprints are a reliable biometric with high user acceptance, and 3D palmprint systems avoid spoofing by photos and can be captured in a contactless manner for hygiene and convenience. A novel approach using high-resolution non-contact photometric stereo is able to bridge the gap between low and high-resolution palmprint recognition, allowing for accurate and user-friendly palmprint identification.
APPLICATIONS OF DIGITAL IMAGE PROCESSING XLIV
(2021)
Proceedings Paper
Optics
Lyndon N. Smith, Arlo Byrne, Mark F. Hansen, Wenhao Zhang, Melvyn L. Smith
APPLICATIONS OF MACHINE LEARNING
(2019)
Article
Computer Science, Interdisciplinary Applications
Francesco Pistolesi, Michele Baldassini, Beatrice Lazzerini
Summary: More than one in four workers worldwide suffer from back pain, resulting in the loss of 264 million work days annually. In the U.S., it costs $50 billion in healthcare expenses each year, rising up to $100 billion when accounting for decreased productivity and lost wages. The impending Industry 5.0 revolution emphasizes worker well-being and their rights, such as privacy, autonomy, and human dignity. This paper proposes a privacy-preserving artificial intelligence system that monitors the posture of assembly line workers. The system accurately assesses upper-body and lower-body postures while respecting privacy, enabling the detection of harmful posture habits and reducing the likelihood of musculoskeletal disorders.
COMPUTERS IN INDUSTRY
(2024)
Article
Computer Science, Interdisciplinary Applications
Xavier Boucher, Camilo Murillo Coba, Damien Lamy
Summary: This paper explores the new business strategies of digital servitization and smart PSS delivery, and develops conceptual prototypes of smart PSS value offers for early stages of the design process. It presents the development and experimentation of a modelling language and toolkit, and applies it to the design of a smart PSS in the field of heating appliances.
COMPUTERS IN INDUSTRY
(2024)
Article
Computer Science, Interdisciplinary Applications
Dieudonne Tchuente, Jerry Lonlac, Bernard Kamsu-Foguem
Summary: Artificial Intelligence (AI) is becoming increasingly important in various sectors of society. However, the black box nature of most AI techniques such as Machine Learning (ML) hinders their practical application. This has led to the emergence of Explainable artificial intelligence (XAI), which aims to provide AI-based decision-making processes and outcomes that are easily understood, interpreted, and justified by humans. While there has been a significant amount of research on XAI, there is currently a lack of studies on its practical applications. To address this research gap, this article proposes a comprehensive review of the business applications of XAI and a six-step framework to improve its implementation and adoption by practitioners.
COMPUTERS IN INDUSTRY
(2024)
Article
Computer Science, Interdisciplinary Applications
Francois-Alexandre Tremblay, Audrey Durand, Michael Morin, Philippe Marier, Jonathan Gaudreault
Summary: Continuous high-frequency wood drying, integrated with a traditional wood finishing line, improves the value of lumber by correcting moisture content piece by piece. Using reinforcement learning for continuous drying operation policies outperforms current industry methods and remains robust to sudden disturbances.
COMPUTERS IN INDUSTRY
(2024)
Article
Computer Science, Interdisciplinary Applications
Luyao Xia, Jianfeng Lu, Yuqian Lu, Wentao Gao, Yuhang Fan, Yuhao Xu, Hao Zhang
Summary: Efficient assembly sequence planning is crucial for enhancing production efficiency, ensuring product quality, and meeting market demands. This study proposes a dynamic graph learning algorithm called assembly-oriented graph attention sequence (A-GASeq), which optimizes the assembly graph structure to guide the search for optimal assembly sequences. The algorithm demonstrates superiority and broad utility in real-world scenarios.
COMPUTERS IN INDUSTRY
(2024)
Article
Computer Science, Interdisciplinary Applications
Mutahar Safdar, Padma Polash Paul, Guy Lamouche, Gentry Wood, Max Zimmermann, Florian Hannesen, Christophe Bescond, Priti Wanjara, Yaoyao Fiona Zhao
Summary: Metal-based additive manufacturing can achieve fully dense metallic components, and the application of machine learning in this field has been growing rapidly. However, there is a lack of framework to manage these machine learning models and guidance on the fundamental requirements for a cross-disciplinary platform to support process-based machine learning models in industrial metal AM.
COMPUTERS IN INDUSTRY
(2024)