Results 51 to 60 of about 1,385 (183)

Depth-Guided Dehazing Network for Long-Range Aerial Scenes

Remote Sensing
Over the past few years, the applications of unmanned aerial vehicles (UAVs) have greatly increased. However, the decrease in clarity in hazy environments is an important constraint on their further development.
Yihu Wang, Jilin Zhao, Liangliang Yao, Changhong Fu   +3 more
doaj   +1 more source

Nighttime Image Dehazing Based on Point Light Sources

Applied Sciences, 2022
Images routinely suffer from quality degradation in fog, mist, and other harsh weather conditions. Consequently, image dehazing is an essential and inevitable pre-processing step in computer vision tasks.
Xin-Wei Yao, Xinge Zhang, Yuchen Zhang, Weiwei Xing, Xing Zhang   +4 more
doaj   +1 more source

Wavelet Quadtree Contrast Limited Adaptive Histogram Equalisation Tablet Enhancement Method for Defect Detection in Low‐Contrast Tablets

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper proposes a novel image enhancement method, WCTE, which integrates Haar wavelet transform and adaptive CLAHE to improve the visibility of low‐contrast tablet images. Combined with the YOLOv11 model, this approach significantly boosts defect detection accuracy, especially for half‐grain and paste tabtal.
Zimei Tu, Qinna Wang, Zhicheng Jiang, Jinhua Jiang   +3 more
wiley   +1 more source

Progressive Knowledge Distillation for Edge‐Deployable Solder Joint Segmentation

IET Image Processing, Volume 20, Issue 1, January/December 2026.
Solder‐Yolo is a lightweight deep learning model based on YOLOv8‐seg, designed for high‐precision solder joint inspection in FPC ribbon cables. It incorporates model pruning, knowledge distillation and a hierarchical context attention module to achieve 96.7% precision and 91.3% mAP while maintaining high inference speed.
Kunhong Li, Xiaolong Guo, Qing Zhao, Yang Chen, Qiang Zhai   +4 more
wiley   +1 more source

Autonomous Single-Image Dehazing: Enhancing Local Texture with Haze Density-Aware Image Blending

Remote Sensing
Single-image dehazing is an ill-posed problem that has attracted a myriad of research efforts. However, virtually all methods proposed thus far assume that input images are already affected by haze. Little effort has been spent on autonomous single-image
Siyeon Han, Dat Ngo, Yeonggyu Choi, Bongsoon Kang   +3 more
doaj   +1 more source

Deep Learning-Enabled Variational Optimization Method for Image Dehazing in Maritime Intelligent Transportation Systems

Journal of Advanced Transportation, 2021
Image dehazing has become a fundamental problem of common concern in computer vision-driven maritime intelligent transportation systems (ITS). The purpose of image dehazing is to reconstruct the latent haze-free image from its observed hazy version.
Xianjun Hu, Jing Wang, Chunlei Zhang, Yishuo Tong   +3 more
doaj   +1 more source

Semantic Single-Image Dehazing

CoRR, 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.
Ziang Cheng, Shaodi You, Viorela Ila, Hongdong Li   +3 more
openaire   +2 more sources

An Image Dehazing Algorithm for Underground Coal Mine Environments Based on Dual‐Channel Prior and Adaptive Contrast Enhancement

IET Image Processing, Volume 20, Issue 1, January/December 2026.
In this paper, we introduce a novel image dehazing algorithm based on dual‐channel prior adaptive contrast‐limited enhancement. The algorithm estimates model parameters from different perspectives based on dual‐channel prior knowledge and fuses the parameters according to the characteristics of each channel.
Chang Su, Dong Bing Xiang, Liang Liang Zhao, Jia Qing Meng, Jian Lu   +4 more
wiley   +1 more source

Pre‐Trained Codebook‐Based Enhancement: A Novel Approach for Clarifying Underwater Images

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This work presents a codebook‐driven enhancement network to tackle colour distortion and detail loss in underwater images. By aligning multi‐scale features with a pre‐trained VQGAN codebook and fusing shallow‐to‐deep cues, the method boosts contrast, edges and clarity without requiring large paired datasets.
Yuanxue Xin, Zhi Qiao, Xinnan Fan, Chen Guo, Bing Zhao   +4 more
wiley   +1 more source

GRA‐Net: Geometry‐ and Response‐Aware Convolutional Network for Nighttime Deflaring

IET Image Processing, Volume 20, Issue 1, January/December 2026.
We propose GRA‐Net, a geometry‐ and response‐aware convolutional network for nighttime flare removal in autonomous driving images. The network achieves unified spatio‐photometric flare rectification by leveraging geometric priors and adaptive illumination responses. Experiments on the Flare7K++ dataset show that GRA‐Net outperforms existing lightweight
Wei Lu, Zihang Shen, Zezheng Zhang, Tao Luo, Jinghui Chu, Peiguang Jing   +5 more
wiley   +1 more source