Search results

Images taken from construction site interiors often suffer from low illumination and poor natural colors, which restrict their application for high-level site management purposes. The state-of-the-art low-light image enhancement method provides promising image enhancement results. However, they generally require a longer execution time to complete the enhancement. This study aims to develop a refined image enhancement approach to improve execution efficiency and performance accuracy.

To develop the refined illumination enhancement algorithm named enhanced illumination quality (EIQ), a quadratic expression was first added to the initial illumination map. Subsequently, an adjusted weight matrix was added to improve the smoothness of the illumination map. A coordinated descent optimization algorithm was then applied to minimize the processing time. Gamma correction was also applied to further enhance the illumination map. Finally, a frame comparing and averaging method was used to identify interior site progress.

The proposed refined approach took around 4.36–4.52 s to achieve the expected results while outperforming the current low-light image enhancement method. EIQ demonstrated a lower lightness-order error and provided higher object resolution in enhanced images. EIQ also has a higher structural similarity index and peak-signal-to-noise ratio, which indicated better image reconstruction performance.

The proposed approach provides an alternative to shorten the execution time, improve equalization of the illumination map and provide a better image reconstruction. The approach could be applied to low-light video enhancement tasks and other dark or poor jobsite images for object detection processes.

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In our pilot study published in, Sakkos:SKIMA 2019, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly but also features semantic transformations of illumination which enhance the generalisation of the model.

In our pilot study published in SKIMA 2019, the proposed framework successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. In this paper, we further enhance the data augmentation framework by proposing new variations in image appearance both locally and globally.

Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place.

Such data augmentation allows us to effectively train an illumination-invariant deep learning model for BGS. We further propose a post-processing method that removes noise from the output binary map of segmentation, resulting in a cleaner, more accurate segmentation map that can generalise to multiple scenes of different conditions. We show that it is possible to train deep learning models even with very limited training samples. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation

This paper aims to investigate how different knitted structures affect the illuminative effect of polymeric optical fibres (POFs).

Knit prototypes were constructed using a 7-gauge industrial hand flat knitting machine. The textile prototype swatches developed in this study tested POF illumination in three types of knitting structures: intervallic knit and float stitch structures; POF inlaid into double plain and full cardigan structures; and double plain and partial knitting structures. The illuminative effects of the POFs in seven prototype swatches were analysed and compared.

It is possible to use an industrial hand flat knitting machine to knit POFs. Longer floats expose more POFs, which boosts illumination but limits the textile’s horizontal stretchability. The openness of the full cardigan structure maximises POF exposure and contributes to even illumination. The partial knitting in different sections achieves the most complete physical integration of POFs into the knitted textiles but constrains the horizontal stretchability of the textiles.

The integration of POFs into knitted textiles provides a functional illuminative effect. Applications include but are not limited to fashion, architecture and interior design.

This study is novel, as it investigates new POF knitted textiles with different loop structures. This study examines how knit stitches affect POFs in intervallic knit and float stitch, inlaid POF double knit, double plain and partial knit and the illuminative effects of the knitted textile.

The purpose of this paper is to investigate the economics of supplying energy needs for illumination requirements by hawkers using alternatives like compact fluorescent lamps battery lamps, liquefied petroleum gas mantle lamps or supply from mini‐grids supported by local diesel generators. Further, the prevailing business models like the lamp rental and the mini‐grid models, which epitomise informal electricity markets, are also analysed.

Three localities in Kanpur city are identified and data on techno‐economic characteristics of illumination options used by hawkers are collected. To compare the available options with varying capital life‐span, equivalent annual cost approach is utilized. This is used to calculate the levelised cost of 1 kiloWalthour energy used for providing illumination.

The daily user cost of illumination ranges from Rs 6.1 to 17 (for four hours) across the four existing models studied in the paper. This translates to Rs 31.3 to 312.5 per kWh of electricity use. The technology choice by hawkers is influenced by lack of initial capital and inconvenience associated with cheaper options than overall economics of the alternative option is found.

The paper highlights the absence of financial and institutional intervention that can help significantly reduce the cost of electricity access by such users and also help adoption of greener options like solar lanterns or solar battery bank charging stations. A practical solution may include a greater role of micro‐finance institutions. Greater awareness and capacity building needs of local entrepreneurs as well as of end‐users also need attention.

This is perhaps one of the few attempts to unravel the informal electricity markets in India and help identify issues that need attention so as to address needs of millions of consumers at the margin of the electricity grid in the country.

This study aims to investigate the spectral illumination characteristics and geometric features of bicycle parts and proposes an image stitching method for their automatic visual inspection.

The unrealistic color casts of feature inspection is removed using white balance for global adjustment. The scale-invariant feature transforms (SIFT) is used to extract and detect the image features of image stitching. The Hough transform is used to detect the parameters of a circle for roundness of bicycle parts.

Results showed that maximum errors of 0°, 10°, 20°, 30°, 40° and 50° for the spectral illumination of white light light-emitting diode arrays with differential shift displacements are 4.4, 4.2, 7.8, 6.8, 8.1 and 3.5 per cent, respectively. The deviation error of image stitching for the stem accessory in x and y coordinates are 2 pixels. The SIFT and RANSAC enable to transform the stem image into local feature coordinates that are invariant to the illumination change.

This study can be applied to many fields of modern industrial manufacturing and provide useful information for automatic inspection and image stitching.

The purpose of this research is to investigate natural illumination properties of one of the classrooms in the School of Architecture at Izmir Institute of Technology, located in Turkey, which is the northern hemisphere.

In this study, the definitions of the basic terms in daylighting, such as daylight factor, illuminance, glazing ratio, are given first. Then, a luxmeter and a lighting simulation software, Velux, are used in order to calculate variable lighting factors during daytime, at different storeys, at different directions, for the classes. Velux is a proprietary software and it enables natural lighting analysis practically.

Chosen classrooms are examined regarding their having sufficient natural illumination. The height of windows from the floor is changed, and the resultant effects on natural lighting in the classrooms are determined by using the lighting simulation program, Velux. The study shows that daylight factor and illumination near the window decreases as the height of the window above the floor increases. However, the illumination increases away from the window, giving greater uniformity to the lighting. At the same time, the usable depth of the classroom increases. The tall and narrow windows bring the daylight near themselves.

Practical window design decisions can help architects to provide effective and healthy natural lighting for interiors.

Adjustment of the dimensions of the windows is important in order to balance the energy consumption of buildings. This study investigates natural lighting depending on both experimental measurements and simulation software, Velux.

In order to solve the problem that the performance of the existing local feature descriptors in uncontrolled environment is greatly affected by illumination, background, occlusion and other factors, we propose a novel face recognition algorithm in uncontrolled environment which combines the block central symmetry local binary pattern (CS-LBP) and deep residual network (DRN) model.

The algorithm first extracts the block CSP-LBP features of the face image, then incorporates the extracted features into the DRN model, and gives the face recognition results by using a well-trained DRN model. The features obtained by the proposed algorithm have the characteristics of both local texture features and deep features that robust to illumination.

Compared with the direct usage of the original image, the usage of local texture features of the image as the input of DRN model significantly improves the computation efficiency. Experimental results on the face datasets of FERET, YALE-B and CMU-PIE have shown that the recognition rate of the proposed algorithm is significantly higher than that of other compared algorithms.

The proposed algorithm fundamentally solves the problem of face identity recognition in uncontrolled environment, and it is particularly robust to the change of illumination, which proves its superiority.

An accurate detection of overhead ground wire under open surroundings with varying illumination is the premise of reliable line grasping with the off-line arm when the inspection robot cross obstacle automatically. This paper aims to propose an improved approach which is called adaptive homomorphic filter and supervised learning (AHSL) for overhead ground wire detection.

First, to decrease the influence of the varying illumination caused by the open work environment of the inspection robot, the adaptive homomorphic filter is introduced to compensation the changing illumination. Second, to represent ground wire more effectively and to extract more powerful and discriminative information for building a binary classifier, the global and local features fusion method followed by supervised learning method support vector machine is proposed.

Experiment results on two self-built testing data sets A and B which contain relative older ground wires and relative newer ground wire and on the field ground wires show that the use of the adaptive homomorphic filter and global and local feature fusion method can improve the detection accuracy of the ground wire effectively. The result of the proposed method lays a solid foundation for inspection robot grasping the ground wire by visual servo.

This method AHSL has achieved 80.8 per cent detection accuracy on data set A which contains relative older ground wires and 85.3 per cent detection accuracy on data set B which contains relative newer ground wires, and the field experiment shows that the robot can detect the ground wire accurately. The performance achieved by proposed method is the state of the art under open environment with varying illumination.

Purpose – The purpose of this study was to determine the efficacy value of national street lighting on energy conservation and carbon dioxide (CO₂) emission reduction.

Design/Methodology/Approach – The methods used are the measurement of electrical parameters (low voltage network), the national road illumination level with SON lamp specification, 400 W, 180 W, and 110 Lumen/W, the simulation of energy conservation calculation, and the CO₂ emission reduction obtained by utilizing panel solar cells as a source of energy and LED lights for illumination.

Finding – The results show the efficacy of a 100-W light bulb at an altitude of 8 m for the following specification of light bulbs: LED, 130 Lumens/W, SON, 110 Lumen/W, and MBF, 53 Lumen/W gives the illumination level respectively 13,913 Lux, 11,773 Lux, and 5,672 Lux. By replacing the 180 W SON lamp with an LED, 100 W, of energy conservation by 3.171 GW h is obtained, which is equivalent to a CO₂ emission reduction of 3.641 kTon CO₂.

Originality/Value – This study is a continuation of a study of energy conservation with the utilization of solar cells as an electrical power source for an LED bulb that replaces low-voltage networks as a power source for the bulb type SON.

Properly planned road illumination systems are collectively a public wealth and the commissioning of such systems may require extensive planning, simulation and testing. The purpose of this simulative work is to offer a simple approach to facilitate luminance-based road lighting calculations that can be easier to comprehend and apply to practical designing problems when compared to complex multi-objective algorithms and other convoluted simulative techniques.

Road illumination systems were photometrically simulated with a created model in a validated software platform for specified system design configurations involving high-pressure sodium (HPS) and light-emitting diode (LED) luminaires. Multiple regression analyses were conducted with the simulatively obtained data set to propound a linear model of estimating average luminance, overall uniformity of luminance and energy efficiency of lighting installations, and the simulatively obtained data set was used to explore luminaire power–road surface average luminance characteristics for common geometric design configurations involving HPS and LED luminaires, and four categories of road surfaces.

The six linear equations of the propounded linear model were found to be well-fitted with their corresponding observation sets. Moreover, it was found that the luminaire power–road surface average luminance characteristics were well-fitted with linear trendlines and the increment in road surface average luminance level per watt increment of luminaire power was marginally higher for LEDs.

This neoteric approach of estimating road surface luminance parameters and energy efficiency of lighting installations, and the compendia of luminaire power–road surface average luminance characteristics offer new insights that can prove to be very useful for practical purposes.