UIALN: Enhancement for Underwater Image With Artificial Light

Li, Mengyao; Wang, Kun; Shen, Liquan; Lin, Yufei; Wang, Zhengyong; Zhao, Qijie

doi:10.1109/tcsvt.2023.3237993

Cited by 11 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For underwater SR activities, Shi et al 43 proposed an effective and lightweight Dual-Aware Integrated Network (DAIN) made up of several Dual-Aware Enhancement Modules (DAEMs). Three components make up the Realistic LR image Generation Module (RLGM), the Dual-degradation Estimation Module (DEM), and the Enhancement and Super-Resolution Module (ESRM) that Li et al 44 presented as the realistic UIESR network (RUIESR) through proposing a paired test Test-206 dataset containing 206 pairs of LR-HR images. For underwater SR, Liu et al 45 suggested a Frequency-domain Enhanced Attention Network (FEAN) and Multiscale Attention Enhancement Block (MAEB) that is both efficient and lightweight.…”

Section: Sesrmentioning

confidence: 99%

Underwater simultaneous enhancement and super-resolution impact evaluation on object detection

Awad,

Zahan,

Lucas

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

Underwater imagery often exhibits significant degradation and poor quality as compared to outdoor imagery. To compensate for this, Single-Image Super-Resolution (SISR) and enhancement algorithms are used to lessen this degradation and produce high-resolution images. In this study, we apply state-of-the-art Simultaneous Enhancement and Super-Resolution (SESR) and SISR models to different sets of downscaled images from the comprehensive RUOD dataset. We then conduct a qualitative and quantitative analysis of the upscaled and enhanced images using standard underwater image quality metrics (IQMs). Subsequently, we evaluate the robustness of the state-of-the-art YOLO-NAS detector against image sets with varying downscaled spatial resolutions. Lastly, we examine the impact that the SISR and SESR models has on YOLO-NAS detector performance. The findings reveal a decline in the detection performance on the downscaled test images and a further decline on the upscaled and enhanced images produced by SISR and SESR models, suggesting a negative relationship between such models and detection.

show abstract

Section: Sesrmentioning

confidence: 99%

Underwater simultaneous enhancement and super-resolution impact evaluation on object detection

Awad,

Zahan,

Lucas

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

show abstract

“…A lightweight super neural network termed as best of both the worlds (Boths) [66] was proposed to enhance degraded underwater images. The image portion where the influences of the artificial light was enhanced using a new network called UIALN [67] to avoid over exposures. The gap between the inter domain and intra domain was reduced simultaneously using a two phase network called TUDA [68] to enhance the degraded images.…”

Section: Introductionmentioning

confidence: 99%

Adjustment of Pixel Intensity for Removal of Color Casts in Underwater Images

Kanagavel,

Thanikaiselvan

2024

IEEE Access

View full text Add to dashboard Cite

This article introduces a new color correction method based on the adjustment of pixel intensity to remove color casts in underwater images. As the underwater images are captured in non-homogeneous with nonuniform illumination, the Gray-World Assumption (GWA) causes red artefacts. The method mainly aims to overcome the drawback of GWA for white balancing the underwater images. Before employing GWA, the underwater image is preprocessed by adding a color inferiority-reducing factor to the inferior channels to increase the pixel intensity level. The GWA is applied to preserve the information for substantially removing color casts. The image is adjusted by saturating the 1% top and bottom intensity levels pixels to remove the water haze. The color dominancy balanced image is finetuned by multi-scale image fusion technique with three derived inputs. The proposed method outperforms qualitatively and quantitatively based on the comparative analysis with four existing methods.

show abstract