Adaptation Luminance Research Articles

An Adaptive Vehicle Detection Model for Traffic Surveillance of Highway Tunnels Considering Luminance Intensity.

Vehicle detection is essential for road traffic surveillance and active safety management. Deep learning methods have recently shown robust feature extraction capabilities and achieved improved detection results. However, vehicle detection models often perform poorly under abnormal lighting conditions, especially in highway tunnels. We proposed an adaptive vehicle detection model that accounts for varying luminance intensities to address this issue. The model categorizes the image data into abnormal and normal luminance scenarios. We employ an improved CycleGAN with edge loss as the adaptive luminance adjustment module for abnormal luminance scenarios. This module adjusts the brightness of the images to a normal level through a generative network. Finally, YOLOv7 is utilized for vehicle detection. The experimental results demonstrate that our adaptive vehicle detection model effectively detects vehicles under abnormal luminance scenarios in highway tunnels. The improved CycleGAN can effectively mitigate edge generation distortion. Under abnormal luminance scenarios, our model achieved a 16.3% improvement in precision, a 1.7% improvement in recall, and a 9.8% improvement in mAP_0.5 compared to the original YOLOv7. Additionally, our adaptive luminance adjustment module is transferable and can enhance the detection accuracy of other vehicle detection models.

5‐1: Adaptive Luminance Display Technology based on Neural Network

5‐1: Adaptive Luminance Display Technology based on Neural Network

Color-preserving visible and near-infrared image fusion for removing fog

With the unavailability of scene depth information, single-sensor dehazing methods based on deep learning or prior information do not effectively work in dense foggy scenes. An effective approach is to remove the dense fog by fusing visible and near-infrared images. However, the current dehazing algorithms based on near-infrared and visible images experience color distortion and information loss. To overcome these challenges, we proposed a color-preserving dehazing method that fuses near-infrared and visible images by introducing a dataset (VN-Haze) of visible and near-infrared images captured under hazy conditions. A two-stage image enhancement (TSE) method that can effectively rectify the color of visible images affected by fog was proposed to prevent the introduction of distorted color information. Furthermore, we proposed an adaptive luminance mapping (ALM) method to prevent color bias in fusion images caused by excessive differences in brightness between visible and near-infrared images that occur in vegetation areas. The proposed visible-priority fusion strategy reasonably allocates weights for visible and near-infrared images, minimizing the loss of important features in visible images. Compared with existing dehazing algorithms, the proposed algorithm generates images with natural colors and less distortion and retains important visible information. Moreover, it demonstrates remarkable performance in objective evaluations.

Core-attributes enhanced generative adversarial networks for robust image enhancement

Automated image enhancement algorithms have a profound impact on human life today. To solve the problems of luminance, lack of detail information, and overall color tone bias of images taken by mobile devices, a novel framework of core-attributes enhanced generative adversarial network (CAE-GAN) is designed to improve these core attributes of enhanced images. The generator in CAE-GAN mainly consists of a luminance correction encoder (LCE) and a high-frequency supplementary decoder (HFSD). To target the adaptive luminance improvement for each location, the encoder based on LCE is designed by combining the extracted prior knowledge of luminance. Meanwhile, a decoder based on HFSD is proposed to fill in missing edge details during the image reconstruction process. In addition, a multi-scale statistical characteristics distinction branch (MSCDB) is proposed to correct the overall tone. Moreover, an upgrade adversarial loss function is designed to focus on the discrimination of both multi-scale and multi-perspective. The generator and discriminator are iteratively trained under the constraints of the total loss function, resulting in the generator that automatically improves the visualization of the images. Extensive experiments have shown that our CAE-GAN is capable of achieving excellent results in several evaluation metrics and subjective results. The source code of the proposed CAE-GAN is available at https://github.com/SWU-CS-MediaLab/CAE-GAN.

A dual channel decomposition and remapping fusion model for low illumination images with a wide field of view

In this paper, we investigate the problem of low illumination image enhancement under wide field of view condition. Our contribution consists of two parts: Firstly, we propose an adaptive two-parameter luminance remapping enhancement function (A2BREF) based on biological visual properties. Secondly, we propose a simple and effective noise suppression method for composite weighted map. In this paper, an image decomposition method based on the total variational energy is used to decompose the input image into structure and detail components. We apply luminance enhancement to the structure component and noise suppression to the detail component. The two components are processed in parallel without interfering with each other. First, we transform the structure component from RGB space to HSV space, and A2BREF combines the global and local luminance information of the input image to perform an adaptive luminance remapping of the V component. Then, the mapping result and the initial V component are fused with PCA in a specific order to enhance the image brightness. Secondly, the detail component contains a lot of noise and detail information of the input image. In this paper, we extract two weight maps from different stages of the detail component by means of improved adaptive Gaussian filters, and the two weight maps are combined to obtain the final weight map. After multiplying the weight maps with the initial detail components and stretching the contrast, the ideal detail components are obtained. Finally, the processed structure and detail components are combined to obtain the final result. The experimental results show that the proposed method has advantages over the contrast algorithm in terms of both subjective visual and objective metrics.

Using relative visual performance to predict performance of an interpersonal evaluation task with variation in adaptation luminance, observer age, skin tone, pavement reflection and interpersonal distance

This study concerns road lighting for pedestrians. Many experiments have been conducted to determine how changes in lighting affect the ability to make interpersonal evaluations, usually considering variations in light level or light spectrum. Here, we consider an alternative approach, predicting performance using an existing model, Relative Visual Performance. The results show that face evaluation ability is affected by adaptation luminance, pavement surface reflectance, observer age, and skin tone of the observed person. Previous experimental studies have tended to use young test participants to evaluate Caucasian or Asian faces: if the situation instead involved an elderly person evaluating a face of South African skin tone, then the current analysis predicts that for optimal performance the light level would need to be doubled.

A readability model of letters with various letter size, luminance contrast and adaptation luminance levels for seniors

In ageing societies, it is necessary to make the visual environment more appropriate for the elderly so that they can maintain visual performance as long as possible. To this end, we aimed at developing guidelines to determine appropriate adaptation luminance and luminance contrast for given letter sizes for the elderly. In this study, we first measured the contrast sensitivities of older participants. Second, we conducted an experiment in which the same participants evaluated the degrees of readability of Japanese sentences with various letter sizes, luminance contrasts and adaptation luminances. Based on the evaluations, we developed a readability model consisting of equal-readability-level contour lines that represent the average of older peoples’ readability scores. From the model, we found we could improve readability by increasing adaptation luminance while the adaptation luminance was lower than 200 cd/m2. However, an increase in luminance contrast became more helpful to improve readability than an increase in adaptation luminance when the adaptation luminance was higher than 200 cd/m2. We also found large individual deviations in readability evaluation among older participants depending on the contrast sensitivity. We divided the participants into three groups based on their contrast sensitivity levels and compared readability models among the three groups.

An Investigation of the Implications of Visual Impairment for Illumination Requirements

Introduction The present contribution mainly focuses on the evaluation of the visual performance of people with impaired vision and, for comparison purposes, individuals with typical vision under different lighting conditions. Methods: A monitor with adjustable brightness facilitated various test runs to determine the visual performance as a function of the adaptation luminance and glare. In addition, the subjective impressions of the participants with impaired vision were queried via interviews. The study included 98 people with impaired vision and 38 people without visual impairments. Results: The interview results suggest that most people with visual impairments require special lighting conditions. An increased lighting requirement is observed amongst 50% of this group. Moreover, 75% of this group display increased glare sensitivity. Likewise, adaptation problems and critical issues related to nonuniform lighting are manifest. Individuals with impaired vision included in this study display a greatly reduced contrast threshold and a higher subjective level of discomfort compared to individuals with typical vision.Discussion: Most visually impaired participants state that they require a higher degree of brightness to achieve their maximum personal visual performance. However, about a quarter of the participants reported that they achieve a better visual performance at lower brightness, while displaying an increased sensitivity to glare. In general, glare has a decisive influence on the visual performance of the participants with impaired vision in our study. Implications for Practitioners: The study reconfirms the essential importance of glare-free and uniform general lighting strategies (e.g., via predominantly indirect lighting) as well as avoiding abrupt spatiotemporal luminance changes (e.g., via provision of a transition zone between locations with very different luminance levels).

Prediction model for discomfort luminance levels of head‐mounted displays

AbstractTo predict the luminance threshold of head‐mounted displays (HMDs), which can cause discomfort due to excessive brightness, a psychophysical experiment was conducted with 20 participants through a yes/no task under a wide luminance range (2–284 cd/m2). The participants were asked to adapt to the luminance of the HMD and further answer whether the test luminance of the HMD caused discomfort. The discomfort threshold was determined for each individual at each adaptation luminance, and a prediction model was proposed based on the mean value of each participant's discomfort luminance level. The proposed model represents that individuals may experience discomfort using an HMD with a luminance of about 280 cd/m2, regardless of whether they are provided time to adapt to the luminance for 2 min.

Making a Display look like Paper: the Effects of Adaptation Duration and Luminance

Making a Display look like Paper: the Effects of Adaptation Duration and Luminance

Perceptual difference between the discomfort luminance level and the brightness of a head-mounted display (HMD)

A psychophysical experiment was conducted to compare the discomfort luminance level and the brightness of a head-mounted display (HMD). The results showed that as the size of the HMD stimulus increased, both the discomfort luminance level of the HMD and the brightness of the HMD decreased, but the influence of the size change was more dramatic on the discomfort luminance level than on the brightness. This study showed that to provide a comfortable luminance level for HMDs, the adaptation luminance level and the size of the HMD stimulus should be considered. However, it cannot be predicted in terms of brightness.

On the Relation between the Astronomical and Visual Photometric Systems in Specifying the Brightness of the Night Sky for Mesopically Adapted Observers

ABSTRACT Due to the typical ambient light levels in inhabited places and light pollution of the night sky, most naked-eye astronomical observations are performed nowadays under mesopic conditions. The luminance (cd/m2) associated with the brightness of the night sky specified in the astronomical logarithmic scale of magnitudes per square arcsecond (mag/arcsec2) is strongly dependent on the spectrum of the sky, because the spectral sensitivity of the human visual system is not coincident with the standard photometric bands used in astronomy. The conversion between these two families of photometric systems was previously analyzed for observers presumed to be either fully photopically or scotopically adapted. In this work, we deduce the transformation equations between the astronomical and visual photometric systems for specifying and reporting the sky brightness in the mesopic range, within the framework of the MES-2 system for visual performance-based mesopic photometry. It is shown that the dependence of the conversion factors on the correlated color temperature of the night sky reaches a minimum spread for adaptation luminances of 0.5–1.0 cd/m2. The sky luminances corresponding to 22.0 mag/arcsec2 in the Johnson-Cousins V band (the assumed brightness of a natural night sky devoid of light pollution) span, for 1.0 cd/m2 adaptation, a relatively small range of ~195–215 μcd/m2 in the absolute (AB) magnitude system and ~210–225 μcd/m2 in the Vega-referenced one.

Rib chest radiographs for detection of the cancer using double stage adaptive processing

This paper suggests elegant two enhancement approaches for rib chest images. The first approach is based on adaptive contrast and luminance model (ACLM).The second approach is depended on mixing the Exponential Contrast Limited Adaptive Histogram Equalization model (ECLAHE) with the Local Histogram Equalization (LHE). The idea of this approach is depended on applying on rib chest radiograph and make optimization for clip limit for ECLAHE. This second algorithm has helped rib chest radiograph details are more important for the detection of cancerous cells. The performance qualities of the suggested models are entropy, average gradient, contrast factor, Sobel magnitude, lightness order error and the similarity of edges point of views. The second approach presents enhancement of rib chest images with better resolution visual details and quality metrics point of views with comparing the first approach.

Effect Of Chromaticity Of Surrounding Light Sources on Mesopic Adaptation Luminance

This paper presents variations in mesopic adaptation luminance in the presence of ambient light sources along with main light source for outdoor lighting applications. Mesopic photometry system is based on peripheral task, and adaptation luminance is required to compute the effective mesopic radiance for the measured area. Different lighting conditions were considered to determine the effect of chromaticity of bright surrounding sources other than the main light sources to the state of observer adaptation. The veiling luminance caused by the surrounding sources increases the state of observer adaptation, but not the luminance within the measurement field. It has also been observed that in case of cool white surrounding sources, adaptation luminance increases significantly than that of warm white sources.

A Spatial-Frequency Domain Associated Image-Optimization Method for Illumination-Robust Image Matching.

Image matching forms an essential means of data association for computer vision, photogrammetry and remote sensing. The quality of image matching is heavily dependent on image details and naturalness. However, complex illuminations, denoting extreme and changing illuminations, are inevitable in real scenarios, and seriously deteriorate image matching performance due to their significant influence on the image naturalness and details. In this paper, a spatial-frequency domain associated image-optimization method, comprising two main models, is specially designed for improving image matching with complex illuminations. First, an adaptive luminance equalization is implemented in the spatial domain to reduce radiometric variations, instead of removing all illumination components. Second, a frequency domain analysis-based feature-enhancement model is proposed to enhance image features while preserving image naturalness and restraining over-enhancement. The proposed method associates the advantages of the spatial and frequency domain analyses to complete illumination equalization, feature enhancement and naturalness preservation, and thus acquiring the optimized images that are robust to the complex illuminations. More importantly, our method is generic and can be embedded in most image-matching schemes to improve image matching. The proposed method was evaluated on two different datasets and compared with four other state-of-the-art methods. The experimental results indicate that the proposed method outperforms other methods under complex illuminations, in both matching performances and practical applications such as structure from motion and multi-view stereo.

Application of New Multi-Scale Edge Fusion Algorithm in Structural Edge Extraction of Aluminum Foam

Accurate extraction of structural edge information of aluminum foam is an important method to study the complex structural properties of aluminum foam, but the conventional single-scale edge detection method is difficult to achieve complete extraction of structural edge information of aluminum foam. However, the multi-scale fusion edge detection method based on Gaussian smoothing also has some problems, such as strong edge diffusion, weak edge degradation, edge pixel movement and so on. In order to solve the shortcomings of the above methods, this paper proposes a multi-scale edge fusion algorithm based on texture suppression, which can extract the edge information of aluminum foam structure more accurately and completely. Firstly, preprocess the image. The illumination component of the image is extracted by the multi-scale fusion method, and the luminance of the image is corrected by the adaptive luminance correction method based on the two-dimensional gamma function. Secondly, construct multi-scale space. It is proposed to construct the guiding image of the guiding filtering by using the bilateral texture filtering and construct the multi-scale space by changing the scale factor of the guiding filtering. Both bilateral filtering and guided filtering have the function of suppressing the texture information of the image while maintaining the structural edge features of the image. Finally, extract edge seeds and fuse multi-scale edges. A new multi-scale image edge fusion algorithm is proposed, which uses seed edges as a medium to gradually merge multi-scale image edges. In order to extract the edge information of the foam aluminum cross-section structure more accurately and completely, the algorithm further optimizes the edge using gradient direction consistency and non-maximum suppression. In order to verify the feasibility of the proposed algorithm, this paper uses the dataset to test the proposed algorithm and a variety of existing algorithms, and compare the results of various algorithms by quantitative analysis. The experimental results show that the proposed algorithm is feasible and effective, and its performance is better than the comparison algorithm.

Comparisons of Scotopic/Photopic Ratios Using 2- and 10-Degree Spectral Sensitivity Curves

Despite the fact that a 2-degree spectral sensitivity curve (SSC) is extensively used in scientific research and relevant applications, the choice between the 10-degree or the 2-degree photopic SSCs in practical applications for the calculation of scotopic/photopic ratios (S/P ratios) depends on actual needs. We examined S/P ratios for more than 300 light sources for correlated colour temperatures (CCTs) from 2000 K to 8000 K and blackbody radiant spectra from 10000 K to 45000 K using 2- and 10-degree SSCs. Results showed that the ratio of the S/P values calculated using the 10-degree and 2-degree SSCs was approximately equal to 0.916. The average mesopic luminance difference increased from 0% to 5.7% at a photopic adaptation luminance from 0.005 to 5 cd/m2. For most practical applications, the mesopic luminance values calculated using these two SSCs were different by several percentage units, yet these differences could be neglected. At extremely high CCTs over 10000 K, the mesopic luminance difference may approximate the maximum value of 16%. This work proposes the conversion coefficients for S/P ratios and the transforming mesopic luminance values calculated for 2- and 10-degree SSC systems. These results may help researchers clarify differences between the S/P ratios calculated using different SSCs.

Adaptation luminance variation under lamps of different spectral compositions with variable surrounding luminance effects

The mesopic photometry system is expected to enable lighting designers to provide more visually effective lighting designs for appropriate outdoor lighting applications which are supposed to be more energy efficient compared to the photopic system. Studies on the adaptation characteristics are performed to define adaptation luminance and viewing conditions on the basis of peripheral adaptation state of observers for implementation of mesopic photometry system in outdoor lighting. In this work, experimentation is carried out to study the change in adaptation luminance due to various combinations of lamps with different spectral compositions and variable surrounding luminance effects caused by warm white and cool white light sources. The analysis of experimental results reveals that adaptation luminance can be considered instead of mesopic luminance for fixed area of measurement. Spectral composition of surrounding light sources imparts significant contribution on adaptation luminance. Cool white LED lamp shows most effective adaptation luminance under cool white surrounding lighting effect.

회로 및 시스템] LED 디스플레이 장치의 휘도개선을 위한 점등율 향상에 대한 연구

LED 디스플레이 장치의 LED 소자의 전기 광학 특성으로 인한 열화는 고유 휘도 값을 낮추어 휘도 값 및 화질 저하로 인한 휘도 불균형을 초래한다. 따라서 본 논문에서는 휘도 불균형을 보상하기 위해 적응적 휘도 구현 비트와 펄스를 휘도 값 감소에 비례하여 휘도를 증가시켜 픽셀 간의 휘도 불균형을 보상하는 휘도 및 색상 제어 기법을 제안 하였다. A degradation due to the electro-optical characteristics of LED devices in LED display lowers the intrinsic luminance value, resulting in luminance unbalance due to a decrease in luminance value and image quality. Therefore, in this paper, we proposed a luminance and color control technique that applies adaptive luminance implementation bits and pulses to compensate for luminance imbalance between pixels by increasing luminance in proportion to the decreased luminance value to compensate for luminance imbalance caused by degradation, respectively.

Visual Impairment, Adaptation Luminance, and Glare: An Empirical Investigation

Visually impaired people primarily rely on their remaining vision. Unfavorable lighting conditions can further hamper this remaining vision. In this context, the present contribution mainly focuses on the evaluation of the visual performance of visually impaired and normally sighted individuals under different lighting conditions. To investigate the visual performance empirically, we developed a test involving different adaptation luminance values. A monitor with adjustable brightness facilitated various tests to determine the visual performance as a function of the adaptation luminance and glare. In addition, the subjective impressions of the visually impaired participants were captured via interviews. The study included 98 visually impaired people and 38 people without eye-related ailments. The interview results suggest that most people with visual disabilities require special lighting conditions. An increased lighting requirement is observed amongst 50% of this group. Moreover, 75% of this group display increased glare sensitivity. Likewise, adaptation problems and critical issues related to non-uniform lighting are manifest. Visually impaired individuals display significant in the visual performance variance at different brightness levels. Individuals with eye disease display a greatly reduced contrast threshold and a higher subjective level of discomfort compared to individuals with normal vision. Most visually impaired individuals require a higher degree of brightness to achieve their maximum personal visual performance. About a quarter of these individuals achieves the optimal visual performance at lower brightness, while displaying an increased sensitivity to glare. In general, glare has a decisive influence on the visual performance of visually impaired people. For general lighting purposes, a predominantly indirect lighting source better accommodates these individuals' requirements.