• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.135-145
• /
• 2020

Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.991-998
• /
• 2022

Recently, object recognition using image/video signals is rapidly spreading on autonomous driving and mobile phones. However, the actual input image/video signals are easily exposed to a poor illuminance environment. A recent researches for improving illumination enable to estimate and compensate the illumination parameters. In this study, we propose VE-DCE (video enhancement zero-reference deep curve estimation) to improve the illumination of low-light images. The proposed VE-DCE uses unsupervised learning-based zero-reference deep curve, which is one of the latest among learning based estimation techniques. Experimental results show that the proposed method can achieve the quality of low-light video as well as images compared to the previous method. In addition, it can reduce the computational complexity with respect to the existing method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• 로봇학회논문지
• /
• 제18권1호
• /
• pp.66-71
• /
• 2023

As cameras have become primary sensors for mobile robots, vision based Simultaneous Localization and Mapping (SLAM) has achieved impressive results with the recent development of computer vision and deep learning. However, vision information has a disadvantage in that a lot of information disappears in a low-light environment. To overcome the problem, we propose an image enhancement method to perform visual SLAM in a low-light environment. Using the deep generative adversarial models and modified gamma correction, the quality of low-light images were improved. The proposed method is less sharp than the existing method, but it can be applied to ORB-SLAM in real time by dramatically reducing the amount of computation. The experimental results were able to prove the validity of the proposed method by applying to public Dataset TUM and VIVID++.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권1호
• /
• pp.60-67
• /
• 2015

This paper proposes an image-dependent color image enhancement method that uses adaptive luminance enhancement and color emphasis. It effectively enhances details of low-light regions while maintaining well-balanced luminance and color information. To compare the structure similarity and naturalness, we used the tone mapped image quality index (TMQI). The proposed method maintained better structure similarity in the enhanced image than did the space-variant luminance map (SVLM) method or the adaptive and integrated neighborhood dependent approach for nonlinear enhancement (AINDANE). The proposed method required the smallest computation time among the three algorithms. The proposed method can be easily implemented using the field-programmable gate array (FPGA), with low hardware resources and with better performance in terms of similarity.

• 한국해양공학회지
• /
• 제34권6호
• /
• pp.442-453
• /
• 2020

Underwater color images suffer from low visibility and color cast effects caused by light attenuation by water and floating particles. This study applied single image enhancement techniques to enhance the quality of underwater images and compared their performance with real underwater images taken in Korean waters. Dark channel prior (DCP), gradient transform, image fusion, and generative adversarial networks (GAN), such as cycleGAN and underwater GAN (UGAN), were considered for single image enhancement. Their performance was evaluated in terms of underwater image quality measure, underwater color image quality evaluation, gray-world assumption, and blur metric. The DCP saturated the underwater images to a specific greenish or bluish color tone and reduced the brightness of the background signal. The gradient transform method with two transmission maps were sensitive to the light source and highlighted the region exposed to light. Although image fusion enabled reasonable color correction, the object details were lost due to the last fusion step. CycleGAN corrected overall color tone relatively well but generated artifacts in the background. UGAN showed good visual quality and obtained the highest scores against all figures of merit (FOMs) by compensating for the colors and visibility compared to the other single enhancement methods.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권1호
• /
• pp.8-16
• /
• 2012

An image obtained from a low light environment results in a low-exposure problem caused by non-ideal camera settings, i.e. aperture size and shutter speed. Of particular note, the multiple color-filter aperture (MCA) system inherently suffers from low-exposure problems and performance degradation in its image classification and registration processes due to its finite size of the apertures. In this context, this paper presents a novel method for the color enhancement of low-exposure images and its application to color shift model-based MCA system for image refocusing. Although various histogram equalization (HE) approaches have been proposed, they tend to distort the color information of the processed image due to the range limits of the histogram. The proposed color enhancement algorithm enhances the global brightness by analyzing the basic cause of the low-exposure phenomenon, and then compensates for the contrast degradation artifacts by using an adaptive histogram specification. We also apply the proposed algorithm to the preprocessing step of the refocusing technique in the MCA system to enhance the color image. The experimental results confirm that the proposed method can enhance the contrast of any low-exposure color image acquired by a conventional camera, and is suitable for commercial low-cost, high-quality imaging devices, such as consumer-grade camcorders, real-time 3D reconstruction systems, digital, and computational cameras.

• 전기전자학회논문지
• /
• 제25권1호
• /
• pp.139-147
• /
• 2021

본 논문에서는 저조도 영상을 개선하기 위한 영상 분해 기반 심층 학습 방법 및 분해 채널 특성에 따른 손실함수를 제안한다. 기존 기법들의 문제점인 색신호 왜곡 및 할로 현상을 제거하기 위해, 입력 영상의 휘도 채널을 반사 성분과 조도 성분으로 분해하고, 반사 성분, 조도 성분 및 색차 신호를 신호 특성에 적합한 심층학습 과정을 적용하는 분해 기반 다중 구조 심층 학습 방법을 제안한다. 더불어, 분해 채널들의 특성에 따른 혼합 놈 기반의 손실함수를 정의하여 복원 영상의 안정성을 증대하고 열화 현상을 제거하기 위한 기법에 대해 기술한다. 실험 결과를 통해 제안한 방법이 다양한 저조도 영상을 효과적으로 개선하였음을 확인할 수 있었다.

• 한국산학기술학회논문지
• /
• 제19권7호
• /
• pp.36-41
• /
• 2018

미광증폭장비는 밤과 같이 어두운 환경에서 주로 가시광선 대역의 약한 빛을 증폭시켜 육안으로 관측할 수 있을 정도의 밝기로 만들어주는 장비이다. 이러한 방식은 어느 정도의 약한 빛이 존재하는 환경에서는 그 증폭 효과를 제대로 발휘하여 선명한 영상을 얻을 수 있지만, 달빛조차 존재하지 않는 극 저조도 환경에서는 기본적으로 증폭시킬 빛이 부족하여 출력 영상에 많은 노이즈로 인하여 화면의 선명도가 저하된다. 본 연구에서는 이러한 극 저조도 환경에서 발생하는 미광증폭 장비의 출력 노이즈를 다중 필터와 이방성 확산을 이용하여 화질을 개선하는 방법을 제안하였다. 실험을 위하여 극 저조도 조건에 맞는 환경을 구성한 상태에서 미광증폭장비의 출력 영상을 촬영한 후, 화질 개선을 위한 신호처리를 하였다. 신호처리를 위한 필터의 구성은 영상에 나타나는 주된 노이즈인 점 노이즈 제거와 가우시안 노이즈의 효과적인 제거를 위하여 메디안 필터, 위너 필터를 적용시킨 후 이방성 확산을 이용하였다. 실험 결과 화질이 개선됨을 육안으로 확인할 수 있었고, 정량 지표인 PSNR 및 SSIM으로 비교하여 측정한 방법에서도 모두 개선된 값을 보여주었다.

• 한국멀티미디어학회논문지
• /
• 제21권9호
• /
• pp.1044-1051
• /
• 2018

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.