Adaptive Near-Infrared and Visible Fusion for Fast Image Enhancement

Awad, Mohamed; Elliethy, Ahmed; Aly, Hussein A.

doi:10.1109/tci.2019.2956873

Cited by 41 publications

(14 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of the proposed algorithm, several contrast experiments were carried out with the state-ofthe-art VIS and NIR image fusion methods, including Image Restoration Via Scale Map (VSM) [17] , Spectrum Characteristics Preservation (SCP) [8] , adaptive and fast image enhancement (LC) [18] , Guided Filter for Fusion (GFF) [19] , and fusion using Laplacian-Gaussian Pyramid Decomposition (LGPD) [2] . To demonstrate that the algorithm can achieve good results in both noisy and noise-free environments, we test it in the noise-free environment Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Structural similarity index measure (SSIM) defines structure information from the perspective of image composition, which is different from brightness, contrast, and reflects the attributes of object structure in the scene. LGPD [2] (d)GFF [19] (e) LC [18] (f) SCP [8] (g)VSM [17] (h) OUR. LGPD [2] (d)GFF [19] (e)LC [18] (f)SCP [8] (g)VSM [17] (h)OUR.…”

Section: Structural Similarity Index Measure (Ssim)mentioning

confidence: 99%

See 1 more Smart Citation

Visible and near infrared image fusion based on texture information

Wu,

Zhang,

Qin

et al. 2023

Fourth International Conference on Signal Processing and Computer Science (SPCS 2023)

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Structural Similarity Index Measure (Ssim)mentioning

confidence: 99%

Visible and near infrared image fusion based on texture information

Wu,

Zhang,

Qin

et al. 2023

Fourth International Conference on Signal Processing and Computer Science (SPCS 2023)

View full text Add to dashboard Cite

“…To evaluate the performance of the proposed algorithm, a series of contrast experiments are conducted with the state-of-the-art RGB and NIR image fusion methods, including Image Restoration Via Scale Map(VSM) [10], Spectrum Characteristics Preservation(SCP) [7], adaptive and fast image en-hancement(LC) [8], Guided Filter for Fusion(GFF) [19], and fusion using Laplacian-Gaussian Pyramid Decomposition(LGPD) [1]. To demonstrate that the algorithm can achieve good results in both noisy and noisefree environments, we test it in the noise-free environment Fig.…”

Section: Resultsmentioning

confidence: 99%

“…However, it causes partial loss of NIR texture information. Mohamed Awad et al [8] adopted the method of extracting spatial details of NIR image and adaptively transferring available details into RGB image to enhance fusion image. This method can retain the spectral characteristics of the image and enhance the structural information of the image.…”

Section: Introductionmentioning

confidence: 99%

Visible and Near Infrared Image Fusion Based on Texture Information

Zhang¹,

Sun²,

Qi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-sensor fusion is widely used in the environment perception system of the autonomous vehicle. It solves the interference caused by environmental changes and makes the whole driving system safer and more reliable. In this paper, a novel visible and near-infrared fusion method based on texture information is proposed to enhance unstructured environmental images. It aims at the problems of artifact, information loss and noise in traditional visible and near infrared image fusion methods. Firstly, the structure information of the visible image (RGB) and the near infrared image (NIR) after texture removal is obtained by relative total variation (RTV) calculation as the base layer of the fused image; secondly, a Bayesian classification model is established to calculate the noise weight and the noise information and the noise information in the visible image is adaptively filtered by joint bilateral filter; finally, the fused image is acquired by color space conversion. The experimental results demonstrate that the proposed algorithm can preserve the spectral characteristics and the unique information of visible and near-infrared images without artifacts and color distortion, and has good robustness as well as preserving the unique texture.

show abstract

“…H UMAN vision system (HVS) is always influenced by ambient light. Images captured in low-light environment always have less detail and low contrast, which is difficult for HVS to perceive [1], [2]; also, the low-light image could seriously affect other computer vision tasks that highly rely on target visibility, including saliency detection [3], semantic segmentation [4], and object tracking [5], etc. Therefore, in X. Li is with the School of Information Science and Engineering, Yunnan University, Kunming 650091, China (email: lxxwxy@outlook.com).…”

Section: Introductionmentioning

confidence: 99%

Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement

Li,

Guo,

Mei

et al. 2020

Preprint

View full text Add to dashboard Cite

Low-light image enhancement is a promising solution to tackle the problem of insufficient sensitivity of human vision system (HVS) to perceive information in low light environments. Previous Retinex-based works always accomplish enhancement task by estimating light intensity. Unfortunately, single light intensity modelling is hard to accurately simulate visual perception information, leading to the problems of imbalanced visual photosensitivity and weak adaptivity. To solve these problems, we explore the precise relationship between light source and visual perception and then propose the visual perception (VP) model to acquire a precise mathematical description of visual perception. The core of VP model is to decompose the light source into light intensity and light spatial distribution to describe the perception process of HVS, offering refinement estimation of illumination and reflectance. To reduce complexity of the estimation process, we introduce the rapid and adaptive β and γ functions to build an illumination and reflectance estimation scheme. Finally, we present a optimal determination strategy, consisting of a cycle operation and a comparator. Specifically, the comparator is responsible for determining the optimal enhancement results from multiple enhanced results through implementing the cycle operation. By coordinating the proposed VP model, illumination and reflectance estimation scheme, and the optimal determination strategy, we propose a rapid and adaptive framework for lowlight image enhancement. Extensive experiment results demenstrate that the proposed method achieves better performance in terms of visual comparison, quantitative assessment, and computational efficiency, compared with the currently stateof-the-arts. A MATLAB implementation will be provided to facilitate the future research of low-light image enhancement field.

show abstract

Adaptive Near-Infrared and Visible Fusion for Fast Image Enhancement

Cited by 41 publications

References 42 publications

Visible and near infrared image fusion based on texture information

Visible and near infrared image fusion based on texture information

Visible and Near Infrared Image Fusion Based on Texture Information

Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement

Contact Info

Product

Resources

About