Results 71 to 80 of about 691 (187)

Deep Learning Approaches for Effective Fog Detection

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
This paper presents an innovative system for detecting foggy road scenarios and classifying visibility levels to provide timely alerts to drivers, thereby enhancing road safety. The authors introduce two new image datasets, Foggy‐Ceit 2023 and an extended Foggy CityScapes – DBF, and evaluate the performance of classical vision techniques and deep ...
Olatz Iparraguirre, Frank A. Ricardo, Alfonso Brazalez, Diego Borro   +3 more
wiley   +1 more source

Entropy–Fidelity Optimization With Deep White‐Balance for Perceptually Consistent Low‐Light Image Enhancement

Journal of Electrical and Computer Engineering, Volume 2026, Issue 1, 2026.
Low‐light image enhancement is one of the fundamental challenges in computer vision, aiming to improve brightness, contrast, and color balance under insufficient illumination. In this work, we present a novel entropy–fidelity and deep white‐balance (EF–WB) framework that integrates information‐theoretic optimization with deep learning‐based color ...
Shahad J. Shahbaz, Hazim G. Daway, Ahlam M. Kadhim, Gongping Yang   +3 more
wiley   +1 more source

SINGLE IMAGE DEHAZING USING PHYSICS-INFORMED CONVOLUTIONAL AUTOENCODER

Модели, системы, сети в экономике, технике, природе и обществе
Background. Generally, haze can be considered to be one of the most fundamental phenomena causing image visibility degradation. Numerous haze removal approaches have been proposed and most of them have achieved significant progress.
A.V. Kozhevnikova, M.A. Mitrokhin
doaj   +1 more source

A Lightweight YOLOv7‐Based Algorithm for Detecting Foreign Objects on Coal Conveyors

Energy Science &Engineering, Volume 13, Issue 11, Page 5495-5509, November 2025.
During the coal mining, large foreign objects may block coal conveyors, leading to a series of safety accidents. The existing models for detecting foreign objects in coal conveyors perform poorly in low‐light environments, resulting in false or missed detections of foreign objects.
Zhang Mei, Sun Zilong, Zhang Yifan
wiley   +1 more source

An effective ship detection approach combining lightweight networks with supervised simulation‐to‐reality domain adaptation

Computer-Aided Civil and Infrastructure Engineering, Volume 40, Issue 27, Page 4732-4757, 14 November 2025.
Abstract Computer vision‐based ship detection using extensively labeled images is crucial for visual maritime surveillance. However, such data collection is labor‐intensive and time‐demanding, which hinders the practical application of newly built ship inspection systems. Additionally, well‐trained detectors are usually deployed on resource‐constrained
Ruixuan Liao, Yiming Zhang, Hao Wang, Linjun Lu, Zhengyi Chen, Xiaoyou Wang, Wenqiang Zuo   +6 more
wiley   +1 more source

Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification

Heliyon
Diagnosing liver disease presents a significant medical challenge in impoverished countries, with over 30 billion individuals succumbing to it each year.
Rashid Khan, Liyilei Su, Asim Zaman, Haseeb Hassan, Yan Kang, Bingding Huang   +5 more
doaj   +1 more source

Circular Polarimetric Imaging with a Metamaterial Integrated Long‐Wavelength Infrared Focal Plane Array

Advanced Science, Volume 12, Issue 39, October 20, 2025.
A quantum well infrared photodetector based long‐wavelength infrared division‐of‐focal‐plane‐array circular polarimeter featuring a 320 × 256 pixel array integrated with a chiral meta‐mirror structure array is established. The device achieves a circular polarization extinction ratio of 5.67, a 9.13‐fold enhancement in responsivity, a noise equivalent ...
Tianyun Zhu, Ling Wang, Wenji Jing, Jie Deng, Jiexian Ye, Yujie Zhang, Zeshi Chu, Jing Zhou, Xiaoshuang Chen, Xiangyang Li, Wei Lu, Xuechu Shen   +11 more
wiley   +1 more source

Semantic Single-Image Dehazing

, 2018
Single-image haze-removal is challenging due to limited information contained in one single image. Previous solutions largely rely on handcrafted priors to compensate for this deficiency. Recent convolutional neural network (CNN) models have been used to learn haze-related priors but they ultimately work as advanced image filters.
Cheng, Ziang, You, Shaodi, Ila, Viorela, Li, Hongdong   +3 more
openaire   +2 more sources

Increasing Soil Organic Carbon but Decoupling of Ecological Attributes After Loss of Dominant Functional Groups in Alpine Meadow

Ecology and Evolution, Volume 15, Issue 10, October 2025.
The loss of dominant species or functional groups both leads to an increase in soil organic carbon (SOC), with the loss of dominant species having a stronger effect than that of functional groups. While the removal of dominant species enhances SOC accumulation, it also preserves some coupling among ecosystem attributes, whereas the loss of dominant ...
Xue Hu, Li Ma, Ruimin Qin, Qiang Zhang, A. Dehaze, Zhen Wang, Zhonghua Zhang, Jingjing Wei, Hongye Su, Shan Li, Zhengchen Shi, Huakun Zhou   +11 more
wiley   +1 more source

Manipulating optical properties of MXene/TiN with strong nonmetallic plasmonic coupling for multifunctional imaging attenuation

InfoMat, Volume 7, Issue 9, September 2025.
Plasmonic materials enable flexible optical manipulation owing to their unique plasmon resonance, making them highly promising for photoelectronic imaging attenuation. This study theoretically designed and experimentally prepared a unique dual nonmetallic plasmonic Ti3C2Tx/TiN hybrid.
Jing‐Wen Zou, Yi‐Hua Hu, Wei‐Bing Sun, Yu‐Hao Xia, Qing Ye, Hao Huang, Liang Ma, Ying Chen, Yu‐Shuang Zhang   +8 more
wiley   +1 more source