• 생물환경조절학회지
• /
• 제12권1호
• /
• pp.17-21
• /
• 2003

참외재배시 저광도 조건시 상품수량의 급격한 저하를 막기 위하여 본 연구가 수행되었다. 과실 비대기에 해당되는 착과후 10일부터 400 $\mu$mol$.$m$^{-}$2$.$S$^{-1}$정도의 저광도 조건이 지속되면 광합성 속도도 떨어지고, 엽록소 함량도 낮았으며 특히 요소 무엽면시비구의 광합성속도는 크게 저하되었다 당도에 있어서는 자연광에 비해 저광도 처리구가 전반적으로 낮았는데, 착과수가 많고 무엽면시비구일수록 낮았다. 발효과 발생률은 요소 엽면시비 유무에 관계없이 자연광에서는 4% 미만으로 발생되었는데, 저광도 조건에서는 10% 이상 발생되었다. 특히 저광도 조건에서 적과수를 적게 한 처리구일수록 발효과 발생률이 높았는데, 적과를 하지 않은 처리구는 각각 39와 48%로 매우 높은 발생율을 보였다. 수확시기 지연은 요소 엽면시비 유무와 관계없이 자연광에 비해 저광도 조건에서 늦어지는 경향을 보였는데, 적과수가 적을수록 지연정도는 심했다 주당 상품수량에 있어서는 저광도 조건하에서 자연광에 비해 16∼34% 수준 정도로 매우 낮은 수량을 보였는데, 요소 0.5% 액을 엽면시비하고 2개를 적과한 처리구가 34%수준으로 자연광에 비해 다른 처리보다 높은 상품수량을 보였다. 따라서 참외재배시 과실 착과후 10일경부터 강우 등에 의해 장기간 저광도 조건이 지속될 것으로 전망되면 상품수량의 급격한 저하를 막기 위하여 주당 6개의 착과 과실중에서 2개를 적과하고, 요소 0.5%액을 2회 정도 엽면시비 해주는 것이 바람직 할 것으로 사료된다.

• 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.

• 센서학회지
• /
• 제29권3호
• /
• pp.180-186
• /
• 2020

In this study, we applied edge-pulse modulation to prevent the flicker of light-emitting diode (LED) light in a visible light identification system. In the visible light transmitter, positive pulses were transmitted at the edges of the low-to-high transition points, and negative pulses were transmitted at the edges of the high-to-low transition points of the non-return-to-zero (NRZ) data waveforms. In the visible light receiver, the NRZ waveforms were regenerated by making low-to-high and high-to-low transitions at the point of the positive and negative pulses, respectively. This method has two advantages. First, it ensures that the LED light is flicker-free because the average optical power of the LED was kept constant during data transmission in the transmitter. Second, the 120 Hz optical noise from the adjacent lighting lamps was easily cut off using a simple RC-high pass filter in the receiver.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2006년도 추계 학술발표회 논문집
• /
• pp.905-908
• /
• 2006

In this study examines physical and mechanical properties the use of domestic low grade meta-kaolin in light weight porous concrete. For this purpose light weight porous concrete incorporating low grade meta-kaolin admixture, was tested for tensile strength and acoustic characteristics. Checking tensile strength of cement and low grade meta-kaolin mixture was used to determine the optimum mix proportion of the low grade meta-kaolin admixture. In this paper sound absorbing material has been investigated by using the light weight porous concrete.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.575-586
• /
• 2022

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

• 터널과지하공간
• /
• 제34권3호
• /
• pp.208-217
• /
• 2024

AI영상 기반 건설현장 안전관리 모니터링 시스템 개발 및 적용하는 추세에 다양한 환경변화에 따른 위험 객체 탐지 딥러닝 모델 개발에 많은 연구적 관심이 쏟아지고 있다. 여러 환경 변화요인 중 저조도 조건에서 객체 검출 모델의 정확도는 현저히 감소하며, 저조도 환경을 고려한 학습을 수행하더라도 일관적인 객체 탐지 정확도를 확보할 수 없다. 이에 따라 저조도 영상을 강화하는 영상 전처리 기술의 필요성이 대두된다. 따라서, 본 논문은 취득된 건설 현장 영상 데이터를 활용하여 다양한 딥러닝 기반 저조도 영상 강화 모델(GLADNet, KinD, LLFlow, Zero-DCE)을 학습하고, 모델별 저조도 영상 강화 성능을 비교 검증실험을 진행하였다. 저조도 강화된 영상을 시각적으로 검증하였고, 영상품질 평가 지수(PSNR, SSIM, Delta-E)를 도입하여 정량적으로 분석하였다. 실험 결과, GLADNet의 저조도 영상 강화 성능이 정량·정성적 평가에서 우수한 결과를 보여줬으며, 저조도 영상 강화 모델로 적합한 것으로 분석되었다. 향후 딥러닝 기반 객체 검출 모델에 저조도 영상 강화 기법이 전처리 단계로 적용한다면, 저조도 환경에서 일관된 객체 검출 성능을 확보할 것으로 예상된다.

• Journal of Electrical Engineering and Technology
• /
• 제10권6호
• /
• pp.2334-2342
• /
• 2015

This paper proposes an LED driving circuit with a digital controller, power factor correct (PFC) function, and low light flicker. The key topology of the proposed circuit is a conventional Flyback combined with a pre-stage. As a result, there will be less light flicker than with other one-stage PFC circuits. A digital controller, implemented using a low-cost microcontroller, dsPIC30F2020, will meet PFC and low light flicker. The experimental results validate the functionality of the proposed circuit.

• 전기전자학회논문지
• /
• 제22권3호
• /
• pp.585-589
• /
• 2018

Consumer demand for high quality image/video services led to growing trend in image quality enhancement study. Therefore, recent years was a period of substantial progress in this research field. Through careful observation of the image quality after processing by image enhancement algorithms, we perceived that the dark region in the image usually suffered loss of contrast to a certain extent. In this paper, the low-light stretch preprocessing algorithm is, hence, proposed to resolve the aforementioned issue. The proposed approach is evaluated qualitatively and quantitatively against the well-known histogram equalization and Photoshop curve adjustment. The evaluation results validate the efficiency and superiority of the low-light stretch over the benchmarking methods. In addition, we also propose the 255MHz-capable hardware implementation to ease the process of incorporating low-light stretch into real-time imaging systems, such as aerial surveillance and monitoring with drones and driving aiding systems.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2483-2504
• /
• 2023

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.