Article
Computer Science, Information Systems
Ping Juei Liu
Summary: A novel image enhancement framework is proposed to enhance the visibility of the image's content. The framework utilizes a new dehazing algorithm to achieve double-side enhancement in contrast and brightness. Experimental results demonstrate that the new dehazing algorithm outperforms others and is more compatible with the proposed framework. The proposed framework surpasses single dehazing algorithms or combinations in contrast and brightness enhancements.
Article
Engineering, Electrical & Electronic
Biswarup Ganguly, Anwesa Bhattacharya, Ananya Srivastava, Debangshu Dey, Sugata Munshi
Summary: This article presents an efficient single image dehazing method by cascading two models, which generates better performance than the state-of-the-art methods in terms of quality and quantity.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Fayaz Ali Dharejo, Yuanchun Zhou, Farah Deeba, Munsif Ali Jatoi, Yi Du, Xuezhi Wang
Summary: This research introduces a new image enhancement approach for image dehazing based on dark channel prior and piecewise linear transformation, as well as contrast limited adaptive histogram equalisation. Experimental results demonstrate that the proposed method significantly improves the visibility of dark remote-sensing images and hazy natural images.
IET IMAGE PROCESSING
(2021)
Article
Meteorology & Atmospheric Sciences
Zefeng Zhang, Hengnan Guo, Hanqing Kang, Jing Wang, Junlin An, Xingna Yu, Jingjing Lv, Bin Zhu
Summary: This study analyzes the relationship between visibility, extinction coefficient, and atmospheric compositions, and proposes using the harmonic average of visibility data as the average visibility, which is recommended for studies on climate change, atmospheric radiation, air pollution, and environmental health.
ATMOSPHERIC MEASUREMENT TECHNIQUES
(2022)
Article
Engineering, Civil
C. H. Lyu, B. P. Gilbert, H. Guan, I. D. Underhill, S. Gunalan, H. Karampour
Summary: This paper presents experimental tests on progressive collapse of mass timber buildings under an edge column removal scenario, investigating the load redistribution mechanisms, structural responses, and failure modes with two types of beam-to-column connectors. The results show efficient load transfer to nearby columns and the superior capacity of Cross Laminated Timber (CLT) panels, with a proposed novel connector demonstrating increased capacity and ductility compared to commonly used connectors. A simplified theoretical model underestimated the test capacity by 53%.
ENGINEERING STRUCTURES
(2021)
Article
Optics
Sergey K. Ivanov, Yaroslav V. Kartashov, Lluis Torner
Summary: We introduce a new type of thresholdless three-dimensional soliton states in higher-order topological insulators based on a Su-Schrieffer-Heeger array of coupled waveguides. These structures have a topological gap with corner states in their linear spectrum. We find that a focusing Kerr nonlinearity allows stable three-dimensional solitons to exist, which inherit topological protection from the linear corner states and can survive in the presence of disorder. The spatial localization and temporal widths of these solitons depend on the array dimerization and they reduce instabilities caused by higher-order effects.
Review
Chemistry, Analytical
Dat Ngo, Seungmin Lee, Tri Minh Ngo, Gi-Dong Lee, Bongsoon Kang
Summary: This paper provides a systematic review and meta-analysis of visibility restoration algorithms for poor weather conditions, proposing a general framework and discussing related challenges and future developments.
Article
Meteorology & Atmospheric Sciences
Rui Lyu, Yanyu Wang, Yarong Peng, Wei Gao, Hequn Yang, Xinyao Tan, Qianshan He, Tiantao Cheng, Renjian Zhang
Summary: This study investigated the long-term trend of low-visibility events in China, particularly focusing on the transition from haze days to fog days around 2004. The analysis showed that the dominant factor influencing this transition was relative humidity variation, rather than aerosol change in the low atmosphere. The results provide insights into the factors affecting the occurrence of fog and haze in China over the past few decades.
ATMOSPHERIC RESEARCH
(2021)
Article
Engineering, Chemical
Tao Wei, Shuo Yang, Xuanbing Yang, Lianze Wang
Summary: This study reported a new capture technology for haze particles based on the particle sink effect. The technology can effectively reduce particulate matter concentrations within a radius of 30 m in about one hour, unaffected by environmental factors. The cooperation of different operation modes of the haze removal device was found to enhance the removal of haze particles, and the influences of wind direction and wind speed on the haze removal effect were revealed.
Article
Geosciences, Multidisciplinary
Atefeh Jebah, Mohammad Zare, Mohammad Reza Ekhtesasi, Reza Jafari
Summary: Significant dust storms have been occurring in the Central part of Iran, particularly in the hyper-arid and arid zones of Yazd province, with increased frequency and intensity in recent years. A study conducted in the region utilized weather codes to monitor wind erosion and dust storm frequency, introducing new indices for evaluating air pollution in terms of different dust events. The findings suggest a significant increase in wind erosion and air pollution, highlighting the need for effective solutions to address these environmental challenges.
Article
Meteorology & Atmospheric Sciences
Yingchuan Yang, Baozhu Ge, Xueshun Chen, Wenyi Yang, Zhongjie Wang, Huansheng Chen, Danhui Xu, Junhua Wang, Qixin Tan, Zifa Wang
Summary: This study investigates the relationship between atmospheric visibility and PM2.5 concentrations, relative humidity, and total column water vapor in Beijing. It identifies the key factors affecting visibility changes, with water vapor content playing a significant role in the evolution of visibility. The study also introduces a novel method to distinguish between haze and fog, providing insights into the forecasting and early warning of low visibility events.
ATMOSPHERIC RESEARCH
(2021)
Article
Engineering, Electrical & Electronic
Alina Majeed Chaudhry, M. Mohsin Riaz, Abdul Ghafoor
Summary: This work proposes a simple and unique framework for visibility enhancement using image decomposition, adaptive boundary constraint, and quadtree-based dehazing, detail enhancement, and fusion. The proposed methodology is evaluated and compared with state-of-the-art techniques, demonstrating its effectiveness.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Engineering, Multidisciplinary
Zhixiang Chen, Binna Ou
Summary: The algorithm proposes a visibility detection method based on a single fog image, determining visibility range and calculating normalized differences between residual energy ratios of different wavelengths to improve accuracy. It effectively reflects fog image visibility and is suitable for evaluating the effectiveness of defogging algorithms and color restoration degree.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jun Liu, Ryan Wen Liu, Jianing Sun, Tieyong Zeng
Summary: In this article, a new real-time scene recovery framework is proposed to restore degraded images under different weather/imaging conditions. The method introduces a rank-one matrix to characterize the degradation phenomenon and achieves real-time recovery. Experimental results demonstrate that the proposed method outperforms several state-of-the-art imaging methods in terms of efficiency and robustness.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Environmental Sciences
Umer Ali, Mohd Faisal, Dilip Ganguly, Mayank Kumar, Vikram Singh
Summary: This study examined the characteristics of aerosol liquid water content (ALWC) in PM2.5 in Delhi using real-time measurements and thermodynamic modeling. The results showed that ALWC increased by 60% in the winter of 2020-2021 compared to the previous year, with an exponential relationship with relative humidity (RH) and significant increase when RH > 80%. Ammonium sulphate and ammonium nitrate were the main contributors to ALWC, with their relative contributions varying under different RH conditions. Increased ALWC due to high PM2.5 and RH resulted in a significant reduction in visibility.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Computer Science, Information Systems
Shih-Chia Huang, Ming-Kai Jiau, Yu-Ping Liu
IEEE SYSTEMS JOURNAL
(2019)
Article
Automation & Control Systems
Jing-Jie Lin, Shih-Chia Huang, Ming-Kai Jiau
IEEE TRANSACTIONS ON CYBERNETICS
(2019)
Article
Engineering, Civil
Shih-Chia Huang, Jing-Jie Lin, Ming-Kai Jiau
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Article
Engineering, Electrical & Electronic
Yan-Tsung Peng, Zhihui Lu, Fan-Chieh Cheng, Yalun Zheng, Shih-Chia Huang
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2020)
Editorial Material
Business
Patrick C. K. Hung, Haluk Demirkan, Shih-Chia Huang
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2021)
Article
Engineering, Electrical & Electronic
Da-Wei Jaw, Shih-Chia Huang, Sy-Yen Kuo
Summary: This paper introduces a network architecture for single-image snow-removal using a pyramidal hierarchical design and generative adversarial networks to improve image quality and computational performance. By probing features at different scales, the performance is further enhanced.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Chemistry, Analytical
Shih-Chia Huang, Quoc-Viet Hoang, Trung-Hieu Le, Yan-Tsung Peng, Ching-Chun Huang, Cheng Zhang, Benjamin C. M. Fung, Kai-Han Cheng, Sha-Wo Huang
Summary: Researchers propose a novel method for image denoising, utilizing techniques such as deep image prior, image fusion, and progressive refinement to address the challenge of image noise removal. Their method demonstrates efficiency, superiority, and robustness in qualitative and quantitative evaluations.
Article
Computer Science, Artificial Intelligence
Jwen Fai Low, Benjamin C. M. Fung, Farkhund Iqbal, Shih-Chia Huang
Summary: The study demonstrates that applying transformers neural network architecture to distinguish between satirical news and fake news yields better results compared to traditional machine-learning methods. Further improvements in model performance can be achieved through the use of non-standard tokenization schemes and different pre-training strategies.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Shih-Chia Huang, Quoc-Viet Hoang, Trung-Hieu Le
Summary: In this article, a novel selective features absorption network (SFA-Net) is proposed to improve the performance of object detection under different weather conditions. The SFA-Net utilizes three subnetworks to achieve this objective. Additionally, a large-scale rainy image dataset called srRain is introduced for training and testing purposes. Experimental results demonstrate that the SFA-Net outperforms state-of-the-art object detectors and the combination of image deraining and object detection models.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Civil
Shih-Chia Huang, Da-Wei Jaw, Quoc-Viet Hoang, Trung-Hieu Le
Summary: In recent years, many lightweight detection models have been developed, but they often lack studies on their performance under rainy conditions. To address this issue, we propose a new and effective approach called 3FL-Net to improve the performance of lightweight object detectors in the presence of rain. Our approach incorporates four subnetworks to learn diverse features and achieve accuracy improvement. Experimental results demonstrate that our 3FL-Net significantly outperforms combination models between rain removal and object detection methods on different rain datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Da-Wei Jaw, Shih-Chia Huang, I-Chuan Lin, Cheng Zhang, Ching-Chun Huang, Sy-Yen Kuo
Summary: Advanced object detection techniques have been widely studied and successfully applied in real-world applications. However, they face challenges in nighttime image detection, especially in low-luminance conditions. In this study, a lightweight framework using generative adversarial networks (GANs) is proposed for multidomain object detection, which includes feature domain transformation and a training policy to achieve luminance-invariant feature extraction. The proposed method outperforms existing algorithms with a 9.95% improvement in average precision, without incurring additional computational costs.
IEEE SENSORS JOURNAL
(2023)
Article
Automation & Control Systems
Da-Wei Jaw, Shih-Chia Huang, Zhi-Hui Lu, Benjamin C. M. Fung, Sy-Yen Kuo
Summary: This article introduces an innovative unsupervised feature domain knowledge distillation (KD) framework for extracting valuable features from low-luminance images. By combining generative adversarial networks and unsupervised knowledge distillation, as well as a region-based multiscale discriminator, this method outperforms other approaches in both low-luminance and sufficient-luminance domains.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Shih-Chia Huang, Da-Wei Jaw, Bo-Hao Chen, Sy-Yen Kuo
Summary: This paper introduces a single image enhancement algorithm based on the human visual system, which can assess and enhance image illumination based on Luminance Perception procedure, with experimental results showing superior performance compared to other algorithms.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Computer Science, Information Systems
Shih-Chia Huang, Da-Wei Jaw, Wenli Li, Zhihui Lu, Sy-Yen Kuo, Benjamin C. M. Fung, Bo-Hao Chen, Thanisa Numnonda
Summary: In this study, a novel haze removal method targeting images with disproportionate haze distribution is proposed, demonstrating higher efficacy compared to other state-of-the-art methods in restoring test images captured in real-world environments.
Article
Computer Science, Hardware & Architecture
Trung-Hieu Le, Po-Hsiung Lin, Shih-Chia Huang
IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY
(2020)
