Low-light Image Enhancement based on Joint Decomposition and Denoising U-Net Network

Deng, Jiawei; Pang, Guangyao; Wan, Li; Yu, Zhenming

doi:10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00136

Cited by 3 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep learning method based on the concept of joint decomposition and denoising was proposed by Deng et al 22 to improve low-light image enhancement. A joint decomposition and denoising enhancement U-Net (JDEU) network is then generated.…”

Section: Related Workmentioning

confidence: 99%

Robust U‐Net: Development of robust image enhancement model using modified U‐Net architecture

Bhavani

Murugan

Goel

2022

Concurrency and Computation

View full text Add to dashboard Cite

The image dehazing stage is used significantly as a preprocessing step for various applications such as remote sensing and long range imaging and automatic driver assistance system. Images acquired under low illumination, fog and snow conditions frequently show qualities like low contrast and low brightness, which genuinely influence the enhanced abstract visualization on natural eyes and extraordinarily limit the exhibition of different machine vision frameworks. The images that are captured in low-light or heavy fog might have salient features that cannot be extracted using standard computer vision systems. A good way to get the enhanced image is to determine the transmission map (haze density or low illumination parameters) of air-light media from each pixel of the input image. In this article, an improved U-Net architecture is proposed to enhance images and provide robust performance metrics against the existing methods. In this model, the pooling operations in generalized U-Net architecture are replaced by discrete wavelet transform based on up and down samplings. An attention module is developed by fusing both up and down samples to identify the missing information of low-level features in up-samples. The proposed architecture for U-Net tested with different datasets: See-in-the-Dark (SID) dataset, Exclusively Dark Image Dataset (ExDark), Realistic Single Image Dehazing (RESIDE) dataset, and few real-time images and achieves superior performance metrics in terms of PSNR, MSE, and SSI when compared to the other state-of-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust U‐Net: Development of robust image enhancement model using modified U‐Net architecture

Bhavani

Murugan

Goel

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…An interesting approach for addressing the analysis of low-light video frames is based on the so called Retinex decomposition. [3,15]. More details in the next paragraphs.…”

Section: Related Workmentioning

confidence: 99%

“…In [15] the authors used a so called "Retinex" decomposition-based solution for lowlight image enhancement with joint decomposition and denoising. They have applied a denoising algorithm through the usage of ad-hoc trained customized U-Net network applied to a properly composed low-light images dataset.…”

Section: Related Workmentioning

confidence: 99%

“…Although the analyzed methods allow us to obtain excellent results in enhancing video frames associated with a low-brightness driving scenario, they often fail to find an optimal trade-off between accuracy, performance, and speed of execution [3,[14][15][16][17]. The method herein proposed tries to balance the above items, providing robust and acceptable performance in a near real-time and sustainable hardware framework.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Real-Time Deep System for Robust Objects Tracking in Low-Light Driving Scenario

Rundo

2021

Computation

View full text Add to dashboard Cite

The detection of moving objects, animals, or pedestrians, as well as static objects such as road signs, is one of the fundamental tasks for assisted or self-driving vehicles. This accomplishment becomes even more difficult in low light conditions such as driving at night or inside road tunnels. Since the objects found in the driving scene represent a significant collision risk, the aim of this scientific contribution is to propose an innovative pipeline that allows real time low-light driving salient objects tracking. Using a combination of the time-transient non-linear cellular networks and deep architectures with self-attention, the proposed solution will be able to perform a real-time enhancement of the low-light driving scenario frames. The downstream deep network will learn from the frames thus improved in terms of brightness in order to identify and segment salient objects by bounding-box based approach. The proposed algorithm is ongoing to be ported over a hybrid architecture consisting of a an embedded system with SPC5x Chorus MCU integrated with an automotive-grade system based on STA1295 MCU core. The performances (accuracy of about 90% and correlation coefficient of about 0.49) obtained in the experimental validation phase confirmed the effectiveness of the proposed method.

show abstract

Enhanced Adaptive Detection of Nearby and Distant Ships in Fog: A Real-Time Multi-Scale Target Detection Strategy

Chen,

Ren,

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

Low-light Image Enhancement based on Joint Decomposition and Denoising U-Net Network

Cited by 3 publications

References 10 publications

Robust U‐Net: Development of robust image enhancement model using modified U‐Net architecture

Robust U‐Net: Development of robust image enhancement model using modified U‐Net architecture

Intelligent Real-Time Deep System for Robust Objects Tracking in Low-Light Driving Scenario

Enhanced Adaptive Detection of Nearby and Distant Ships in Fog: A Real-Time Multi-Scale Target Detection Strategy

Contact Info

Product

Resources

About