Article
Computer Science, Information Systems
Karen Panetta, Landry Kezebou, Victor Oludare, Sos Agaian, Zehua Xia
Summary: This paper introduces a large scale HDR image benchmark dataset LVZ-HDR for evaluating TMO performance, presents a deep learning-based TMO-Net method and comparative analysis of 19 state-of-the-art TMOs on the new dataset, demonstrating qualitative and quantitative improvement over current TMOs.
Article
Neurosciences
Tianshu Song, Leida Li, Hancheng Zhu, Jiansheng Qian
Summary: Current image quality assessment metrics mainly focus on distortion aspects, neglecting the importance of intelligibility for robust quality estimation. This study proposes a new framework for integrating intelligibility to build a highly generalizable image quality model, achieving better performance than state-of-the-art metrics. Feature selection strategy is devised to avoid negative transfer during the fusion process.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Chemistry, Analytical
Demetris Marnerides, Thomas Bashford-Rogers, Kurt Debattista
Summary: Inverse Tone Mapping (ITM) methods aim to reconstruct HDR information from LDR images, with challenges in recovering missing information from under-exposed areas. Work based on Generative Adversarial Networks (GANs) shows potential and can improve the quality of inverse tone mapping results.
Article
Computer Science, Hardware & Architecture
Tian Yuan, Chen Li, Lihua Tian, Guo Li
Summary: Recent years have seen significant progress in image quality assessment, especially in the field of no-reference (NR)-IQA with the development of deep learning. The proposed framework in this study utilizes a range mapping method to enhance the accuracy and generalization of NR-IQA models by mapping existing full-reference (FR)-IQA datasets to NR-IQA datasets. Experimental results using the largest available datasets have confirmed the effectiveness of this approach.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Jiachen Yang, Yanshuang Zhou, Yang Zhao, Jiabao Wen
Summary: This paper proposes a quality assessment method for tone-mapped images based on generating multi-exposure sequences. By using a generative adversarial network to generate sequences with different exposure levels and utilizing a convolutional neural network to extract features and learn mapping relationships, the proposed method achieves quality assessment of tone-mapped images.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2022)
Article
Computer Science, Information Systems
Naima Aamir, Junaid Mir, Imran Fareed Nizami, Furqan Shaukat, Muhammad Majid
Summary: This paper presents the first BVQA model for HDR content, which is inspired by spatio-temporal natural scene statistics model. By developing a comprehensive subjective HDR video quality dataset and extracting HDR relevant features, the proposed HDR-BVQM is shown to correlate with human judgment of quality.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Xiyu Chen, Tao Jia, Jiangjian Xiao, Jiayan Zhuang
Summary: High dynamic range (HDR) image acquisition technology is important for recording real-scene information, but most display devices do not support HDR images. Tone mapping operators are used to compress the dynamic range and enable visualization of HDR images. However, traditional methods have limitations and deep learning has shown better results. This study proposes a lightweight network that estimates tone curve parameters for HDR images, and introduces a self-supervised loss term for quality assessment. Experimental results demonstrate that the proposed method achieves better results with low computational cost.
COMPUTERS & GRAPHICS-UK
(2023)
Article
Computer Science, Theory & Methods
M. P. Pavan Kumar, B. Poornima, H. S. Nagendraswamy, C. Manjunath, B. E. Rangaswamy
Summary: The paper introduces a framework combining HDR and image abstraction to enhance prominent image features and convey shapes from blatant range images by preserving tonal and structural features while suppressing unnecessary details.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Mingxing Jiang, Liquan Shen, Min Hu, Ping An, Fuji Ren
Summary: This paper proposes a Blind Quality Evaluator of Tone-Mapped HDR and Multi-Exposure Fused Images (BQE-TM/MEFI) for electronic displays and consumer electronics, utilizing segment models and multiple quality-perception features to measure local artifacts and generate a quality score.
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
(2021)
Article
Engineering, Electrical & Electronic
Manoj Purohit, Manvendra Singh, Ajay Kumar, Brajesh Kumar Kaushik
Summary: This study investigates the feasibility of using high dynamic range (HDR) techniques with image sensors for enhancing range performance, and analyzes the HDR requirements while optimizing available HDR techniques for real-time scenarios.
IEEE SENSORS JOURNAL
(2021)
Proceedings Paper
Computer Science, Hardware & Architecture
Junbin Zhang, Yixiao Wang, Hamidreza Tohidypour, Mahsa T. Pourazad, Panos Nasiopoulos
Summary: High dynamic range (HDR) has become the preferred format for content providers, but the challenge lies in converting HDR content to standard dynamic range (SDR). Many tone mapping operators (TMOs) based on deep learning have been proposed, but lack of truthful datasets hinders accurate TMO training. A new high-quality 4K HDR-SDR dataset and a TMO based on the generative adversarial network architecture are introduced in this paper, achieving high perceptual quality and better color representation.
2023 INTERNATIONAL CONFERENCE ON COMPUTING, NETWORKING AND COMMUNICATIONS, ICNC
(2023)
Article
Computer Science, Information Systems
Yipeng Deng, Qin Liu, Takeshi Ikenaga
Summary: In this paper, a new attention-guided network is proposed to improve the efficiency of high dynamic range (HDR) image reconstruction through inverse tone-mapping guided up-sampling. By using low-resolution low dynamic range images and inverse tone-mapping, high-quality HDR results are achieved in challenging scenes, while reducing the consumption of computational resources.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Ajay Kumar Reddy Poreddy, Peter A. Kara, Roopak R. Tamboli, Aniko Simon, Balasubramanyam Appina
Summary: In this paper, an unsupervised, blind, no-reference stereoscopic (S3D) image quality prediction model is proposed to assess the perceptual quality of natural S3D images. The joint dependencies between color and depth features of S3D images are empirically modeled using a bivariate generalized Gaussian distribution. The proposed model demonstrates consistent and robust performance on various S3D image datasets. It is completely blind and does not require training on subjective scores or reference S3D images.
Article
Computer Science, Information Systems
Imran Mehmood, Xinye Shi, Muhammad Usman Khan, Ming Ronnier Luo
Summary: One of the key challenges in tone mapping is to preserve the perceptual quality of high dynamic range (HDR) images when mapping them to standard dynamic range (SDR) displays. This research proposes a new tone mapping operator (TMOz) that leverages CIECAM16 perceptual attributes to achieve more optimal colorfulness reproduction. Both objective and subjective evaluations show that the proposed model outperforms existing TMO algorithms.
Article
Chemistry, Analytical
Ivana Shopovska, Ana Stojkovic, Jan Aelterman, David Van Hamme, Wilfried Philips
Summary: Intelligent driver assistance systems are increasingly popular and have the ability to detect vulnerable road users. However, standard imaging sensors perform poorly in strong illumination contrast conditions. This study focuses on the use of HDR imaging sensors and the need for tone mapping in vehicle perception systems. The proposed DI-TM method achieves the best performance in terms of detection metrics in challenging dynamic range conditions, with a 13% improvement compared to existing methods.
Article
Computer Science, Information Systems
Chen Li, Li Song, Shuai Chen, Rong Xie, Wenjun Zhang
Summary: In this paper, we propose a deep learning based sensor-driven method for online video stabilization. Our method utilizes Euler angles and acceleration values estimated from sensors to reconstruct stable videos. We introduce two sub-networks for trajectory optimization, which detect shooting scenarios and predict smooth camera paths. Experimental results show that our method outperforms other state-of-the-art offline methods in shaky video clips, and it can effectively reduce running times without performing image content analysis.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Engineering, Civil
Xing Liang, Zhuoran Lu, Fei Ye, Wenjun Zhang
Summary: The design of entrances to Chinese metro stations has mainly focused on satisfying functions, lacking innovative ideas and the promotion of urban culture. This study aims to propose design concepts suitable for China's national conditions as examples for future metro stations.
PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-MUNICIPAL ENGINEER
(2023)
Article
Electrochemistry
Xi Du, Wenjun Zhang, Maliang Zhang, Kunmei Su, Zhenhuan Li
Summary: To achieve carbon peaking and carbon neutrality, developing a circular economy is crucial, with solid waste pollution control being a key focus. In this study, a method is proposed to convert discarded industrial polyphenylene sulfide (PPS) non-woven fabric fiber into value-added hierarchical porous carbon (HPC) for superior supercapacitor performance. The resulting ONS-HPC-0.5 material possesses a well-organized honeycomb-like structure with ultra-high specific surface area (3112.2 m2 g-1) and abundant heteroatoms oxygen (10.85 atom%), nitrogen (4.93 atom%), and sulfur (5.33 atom%) doping. The ONS-HPC-0.5 electrode exhibits high specific capacitance (301 F g-1 at 0.5 A g-1), excellent rate capability, and electrochemical stability in alkaline electrolyte. Moreover, the assembled ONS-HPC-0.5//ONS-HPC-0.5 symmetric supercapacitor achieves remarkable energy density (21.87 Wh kg-1) and power density (450 W kg -1), demonstrating the material's promising application in the supercapacitor industry and unveiling a new circular economy model for industrial solid waste recycling.
ELECTROCHIMICA ACTA
(2023)
Article
Engineering, Electrical & Electronic
Hang Li, Chao Fu, Lei Shi, Chaorong Li, Jiaqi Pan, Wenjun Zhang
Summary: CuI hole transporter-based perovskite solar cells prepared via a low-temperature in situ deposition method demonstrate better stability, efficient hole extraction, and carrier recombination inhibition, resulting in enhanced incident photon-to-electron conversion efficiency.
SEMICONDUCTOR SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Environmental
Yuanyan Jiang, Jiawei Huang, Wei Luo, Kejin Chen, Wenrou Yu, Wenjun Zhang, Chuan Huang, Junjun Yang, Yingzhou Huang
Summary: In this study, machine learning models (Random Forest, XGBoost, LightGBM) were established to predict the production of odors from domestic waste based on four factors (weight, wet composition, temperature, and fermentation time). The Random Forest model showed the highest accuracy with a R2 value of 0.8958. Furthermore, the impact of microbial fermentation on odor production from domestic waste was discussed.
Article
Engineering, Electrical & Electronic
Yizhe Zhang, Wen He, Dazhi He, Yin Xu, Yunfeng Guan, Wenjun Zhang
Summary: In this paper, we proposed the use of reconfigurable intelligent surface (RIS) to improve the reception quality in the LDM system, especially in the edge area. By jointly optimizing power control and pairing mechanism using the convex-concave procedure, we addressed the problem of maximizing the minimum SINR. We also explored the high-mobility scenario and used Brownian Motion to model terminal positions and improve the successful reception probability.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Engineering, Electrical & Electronic
Yan Huang, Jun Xu, Chen Zhu, Li Song, Wenjun Zhang
Summary: This paper proposes a VVC-based encoding complexity control scheme, which achieves precise control of encoding time by controlling the maximum depth of encoding complexity and designing top-down and bottom-up allocation and feedback. Experimental results show that the proposed scheme outperforms state-of-the-art works based on HEVC.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Engineering, Marine
Ye Li, Jiayu He, Hailong Shen, Wenjun Zhang, Yanying Li
Summary: This article investigates the practical prescribed-time trajectory tracking control problem for AUVs with parametric uncertainties under tracking error constraints and velocity constraints. The proposed control method ensures that the tracking error converges to an adjustably small residual set within the prescribed time with a continuous control action. The feasibility conditions are eliminated and the requirements of constrained boundary functions are relaxed by transforming the problem of velocity constraints.
Article
Computer Science, Information Systems
Junyuan Gao, Yongpeng Wu, Tianya Li, Wenjun Zhang
Summary: This letter investigates the energy efficiency of massive unsourced random access (URA) in multiple-input multiple-output quasi-static Rayleigh fading channels. Specifically, we derive achievability and converse bounds on the minimum required energy-per-bit under the per-user probability of error constraint, where the converse bounds contain two parts: one is general and the other is a weaker ensemble bound. Numerical evaluation shows that the gap between our achievability and converse bounds is less than 5 dB in the considered regime. Some practical schemes are energy-inefficient compared with our bounds especially when there are many users. Moreover, we observe that in contrast to the sourced random access paradigm, the URA paradigm achieves higher spectral efficiency.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2023)
Article
Electrochemistry
Wenjun Zhang, Yongzhong Jin, Zhengquan Zhang, Ge Chen, Dongwei Jiang
Summary: In this study, a two-step method was used to prepare a composite anode material consisting of SnS2 nanoparticles and helical carbon nanofibers. The composite anode exhibited superior reversible discharge specific capacity, higher capacity retention rate, and excellent ultra-long cycle capacity. The outstanding electrochemical performance was attributed to the synergistic contribution between the helical carbon nanofibers and SnS2.
ELECTROCHIMICA ACTA
(2023)
Article
Engineering, Electrical & Electronic
Xiaowu Ou, Yin Xu, Hanjiang Hong, Dazhi He, Yiyan Wu, Yihang Huang, Wenjun Zhang
Summary: With the increasing demand for data services, the spectrum has become a valuable resource. The cooperative transmission mechanism, which allows broadcast and unicast to share the same spectrum, can effectively alleviate this issue. A flexible LDM scheme with a variable power injection ratio is proposed to further improve radio resource utilization. Through a DRL-based algorithm, the optimal scheduling scheme is obtained, and the Lyapunov optimization method is applied to convert the problem to a more conducive form for the agent to learn the optimal strategy. Simulation results show significant improvement in system throughput while ensuring the quality of the broadcast service.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Computer Science, Information Systems
Qiang Ji, Liangxiao Jiang, Wenjun Zhang
Summary: In this article, a dual-view noise correction (DVNC) algorithm is proposed, which enhances the effect of noise correction by fully utilizing the joint information of the original attribute view and multiple noisy label view.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Huan Zhang, Liangxiao Jiang, Wenjun Zhang, Chaoqun Li
Summary: In this study, a new model called multi-view attribute weighted naive Bayes (MAWNB) is proposed to portray data characteristics more comprehensively. By constructing two label views from raw attributes and optimizing attribute weights, MAWNB can predict class labels for test instances with high accuracy. Extensive experiments demonstrate the superiority of MAWNB compared to NB and other state-of-the-art competitors.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Engineering, Ocean
Wenjun Zhang, Luting Lv, Yusen Gong, Ye Li, Teng Ma
Summary: Underwater terrain-aided navigation (TAN) has potential for accurate navigation of autonomous underwater vehicles. This paper proposes a method to restrict the size of the observation area in TAN systems based on terrain entropy and difference of normals. The TAN algorithm is implemented in an embedded system architecture to reduce power consumption and the effectiveness is demonstrated through experiments.
MARINE TECHNOLOGY SOCIETY JOURNAL
(2023)
Article
Engineering, Civil
Fei Ye, Haolan Feng, Xingbo Han, Xiaoming Liang, Haidong Sun, Wenjun Zhang, Xiaoyong Cao
Summary: This study presents the phenomenon of abnormal shutdown and the measures to mitigate problems in an underwater shield tunnel project. The analysis reveals that a sudden change in stratum and an increase in slurry pressure can cause slurry leakage and increase the risk of breakdown at shield tail brushes. The retraction of jacks and the expansion of segments can also affect the tightness and increase the risk of slurry leakage. The study suggests observing slurry leakage degree during retraction and timely taking measures to reduce the risk of large-scale leakage accidents.