Abstract: In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (FST) features based on the combination of the local phase information with the texture features. Since the phase of the signal conveys more structural information than the magnitude, the phase congruency concept is used to capture the structural features. On the other hand, the Center-Symmetric Local Binary Pattern (CSLBP) approach is used to capture the texture information of the image. The dimension less quantity of the phase congruency and the robustness of the CSLBP operator on the flat images, as well as the blur and illumination changes, lead the proposed descriptor to be more robust and less sensitive to the light variations. The proposed descriptor can be formed by extracting the phase congruency and the CSLBP values of each pixel of the image with respect to its neighborhood. The histogram of the oriented phase and the histogram of the CSLBP values for the local regions in the image are computed and concatenated to construct the FST descriptor. Several experiments were conducted on INRIA and the low resolution DaimlerChrysler datasets to evaluate the detection performance of the pedestrian detection system that is based on the FST descriptor. A linear Support Vector Machine (SVM) is used to train the pedestrian classifier. These experiments showed that the proposed FST descriptor has better detection performance over a set of state of the art feature extraction methodologies.
Abstract: Recently, traffic monitoring has attracted the attention
of computer vision researchers. Many algorithms have been
developed to detect and track moving vehicles. In fact, vehicle
tracking in daytime and in nighttime cannot be approached with the
same techniques, due to the extreme different illumination conditions.
Consequently, traffic-monitoring systems are in need of having a
component to differentiate between daytime and nighttime scenes. In
this paper, a HSV-based day/night detector is proposed for traffic
monitoring scenes. The detector employs the hue-histogram and the
value-histogram on the top half of the image frame. Experimental
results show that the extraction of the brightness features along with
the color features within the top region of the image is effective for
classifying traffic scenes. In addition, the detector achieves high
precision and recall rates along with it is feasible for real time
applications.
Abstract: Background modeling and subtraction in video
analysis has been widely used as an effective method for moving
objects detection in many computer vision applications. Recently, a
large number of approaches have been developed to tackle different
types of challenges in this field. However, the dynamic background
and illumination variations are the most frequently occurred problems
in the practical situation. This paper presents a favorable two-layer
model based on codebook algorithm incorporated with local binary
pattern (LBP) texture measure, targeted for handling dynamic
background and illumination variation problems. More specifically,
the first layer is designed by block-based codebook combining with
LBP histogram and mean value of each RGB color channel. Because
of the invariance of the LBP features with respect to monotonic
gray-scale changes, this layer can produce block wise detection results
with considerable tolerance of illumination variations. The pixel-based
codebook is employed to reinforce the precision from the output of the
first layer which is to eliminate false positives further. As a result, the
proposed approach can greatly promote the accuracy under the
circumstances of dynamic background and illumination changes.
Experimental results on several popular background subtraction
datasets demonstrate very competitive performance compared to
previous models.
Abstract: At the present work, highly transparent strip type
quasi-solid state dye-sensitized solar cells (DSSCs) were fabricated
through inkjet printing using nanocomposite TiO2 inks as raw
materials and tested under outdoor illumination conditions. The cells,
which can be considered as the structural units of large area modules,
were fully characterized electrically and electrochemically and after
the evaluation of the received results a large area DSSC module was
manufactured. The module design was a sandwich Z-interconnection
where the working electrode is deposited on one conductive glass and
the counter electrode on a second glass. Silver current collective
fingers were printed on the conductive glasses to make the internal
electrical connections and the adjacent cells were connected in series
and finally insulated using a UV curing resin to protect them from the
corrosive (I-/I3-) redox couple of the electrolyte. Finally, outdoor tests
were carried out to the fabricated dye-sensitized solar module and its
performance data were collected and assessed.
Abstract: In recent years, the power system has been changed
and a flexible power pricing system such as demand response has been
sought in Japan. The demand response system works simply in the
household sector and the owner as the decision-maker, can benefit
from power saving. On the other hand, the execution of demand
response in the office building is more complex than in the household
because various people such as owners, building administrators and
occupants are involved in the decision-making process. While the
owners benefit from demand saving, the occupants are exposed to
restricted benefits of a demand-saved environment. One of the reasons
is that building systems are usually under centralized management and
each occupant cannot choose freely whether to participate in demand
response or not. In addition, it is unclear whether incentives give
occupants the motivation to participate. However, the recent
development of IT and building systems enables the personalized
control of the office environment where each occupant can control the
lighting level or temperature individually. Therefore, it can be possible
to have a system which each occupant can make a decision of whether
or not to participate in demand response in the office building. This study investigates personal responses to demand response
requests, under the condition where each occupant can adjust their
brightness individually in their workspace. Once workers participate
in the demand response, their desk-lights are automatically turned off.
The participation rates in the demand response events are compared
among four groups, which are divided by different motivation, the
presence, or absence of incentives and the method of participation. The
result shows that there are significant differences of participation rates
in demand response event between four groups. The method of
participation has a large effect on the participation rate. The “Opt-out”
groups where the occupants are automatically enrolled in a demand
response event if they do not express non-participation have the
highest participation rate in the four groups. Incentives also have an
effect on the participation rate. This study also reports on the impact of low illumination office
environment on the occupants, such as stress or fatigue. The
electrocardiogram and the questionnaire are used to investigate the
autonomic nervous activity and subjective fatigue symptoms of the
occupants. There is no big difference between dim workspace during
demand response event and bright workspace in autonomic nervous
activity and fatigue.
Abstract: The objective of the study is to assess the
implementation of LED lighting into forest machine work in the dark.
In addition, the paper includes a wide variety of important and
relevant safety and health parameters. In modern, computerized work
in the cab of forest machines, artificial illumination is a demanding
task when performing duties, such as the visual inspections of wood
and computer calculations. We interviewed entrepreneurs and
gathered the following as the most pertinent themes: (1) safety, (2)
practical problems, and (3) work with LED lighting. The most
important comments were in regards to the practical problems of
LED lighting. We found indications of technical problems in
implementing LED lighting, like snow and dirt on the surfaces of
lamps that dim the emission of light. Moreover, service work in the
dark forest is dangerous and increases the risks of on-site accidents.
We also concluded that the amount of blue light to the eyes should be
assessed, especially, when the drivers are working in a semi-dark cab.
Abstract: Background subtraction and temporal difference are
often used for moving object detection in video. Both approaches are
computationally simple and easy to be deployed in real-time image
processing. However, while the background subtraction is highly
sensitive to dynamic background and illumination changes, the
temporal difference approach is poor at extracting relevant pixels of
the moving object and at detecting the stopped or slowly moving
objects in the scene. In this paper, we propose a simple moving object
detection scheme based on adaptive background subtraction and
temporal difference exploiting dynamic background updates. The
proposed technique consists of histogram equalization, a linear
combination of background and temporal difference, followed by the
novel frame-based and pixel-based background updating techniques.
Finally, morphological operations are applied to the output images.
Experimental results show that the proposed algorithm can solve the
drawbacks of both background subtraction and temporal difference
methods and can provide better performance than that of each method.
Abstract: The detection of moving objects from a video image
sequences is very important for object tracking, activity recognition,
and behavior understanding in video surveillance.
The most used approach for moving objects detection / tracking is
background subtraction algorithms. Many approaches have been
suggested for background subtraction. But, these are illumination
change sensitive and the solutions proposed to bypass this problem
are time consuming.
In this paper, we propose a robust yet computationally efficient
background subtraction approach and, mainly, focus on the ability to
detect moving objects on dynamic scenes, for possible applications in
complex and restricted access areas monitoring, where moving and
motionless persons must be reliably detected. It consists of three
main phases, establishing illumination changes invariance,
background/foreground modeling and morphological analysis for
noise removing.
We handle illumination changes using Contrast Limited Histogram
Equalization (CLAHE), which limits the intensity of each pixel to
user determined maximum. Thus, it mitigates the degradation due to
scene illumination changes and improves the visibility of the video
signal. Initially, the background and foreground images are extracted
from the video sequence. Then, the background and foreground
images are separately enhanced by applying CLAHE.
In order to form multi-modal backgrounds we model each channel
of a pixel as a mixture of K Gaussians (K=5) using Gaussian Mixture
Model (GMM). Finally, we post process the resulting binary
foreground mask using morphological erosion and dilation
transformations to remove possible noise.
For experimental test, we used a standard dataset to challenge the
efficiency and accuracy of the proposed method on a diverse set of
dynamic scenes.
Abstract: Thin ZnO films are deposited on glass substrates via
sol–gel method and dip-coating. The films are prepared from zinc
acetate dehydrate as a starting reagent. After that the as-prepared
ZnO sol is aged for different periods (0, 1, 3, 5, 10, 15 and 30 days).
Nanocrystalline thin films are deposited from various sols. The
effect ZnO sols aging time on the structural and photocatalytic
properties of the films is studied. The films surface is studied by
Scanning Electron Microscopy. The effect of the aging time of the
starting solution is studied in the photocatalytic degradation of
Reactive Black 5 (RB5) by UV-vis spectroscopy. The experiments
are conducted upon UV-light illumination and in complete darkness.
The variation of the absorption spectra shows the degradation of RB5
dissolved in water, as a result of the reaction, occurring on the surface
of the films and promoted by UV irradiation. The initial
concentrations of dye (5, 10 and 20 ppm) and the effect of the aging
time are varied during the experiments. The results show, that the
increasing aging time of starting solution with respect to ZnO
generally promotes photocatalytic activity. The thin films obtained
from ZnO sol, which is aged 30 days have best photocatalytic
degradation of the dye (97,22%) in comparison with the freshly
prepared ones (65,92%). The samples and photocatalytic
experimental results are reproducible. Nevertheless, all films exhibit
a substantial activity in both UV light and darkness, which is
promising for the development of new ZnO photocatalysts by sol-gel
method.
Abstract: In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation,
style, illumination, and can suffer from perspective distortion.
Pre-processing is performed to make the characters scale and
rotation invariant. Since text degradations can not be appropriately
defined using well-known geometric transformations such
as translation, rotation, affine transformation and shearing, we
use the whole character black pixels as our feature vector.
Classification is performed with minimum distance classifier
using the maximum likelihood criterion, which delivers very
promising Character Recognition Rate (CRR) of 89%. We
achieve considerably higher Word Recognition Rate (WRR) of
99% when using lower level linguistic knowledge about product
words during the recognition process.
Abstract: This research focuses on the optimization of glazed
surfaces and the assessment of possible solar gains in industrial
buildings. Existing window rating methods for single windows were
evaluated and a new method for a simple analysis of energy gains and
losses by single windows was introduced. Furthermore extensive
transient building simulations were carried out to appraise the
performance of low cost polycarbonate multi-cell sheets in
interaction with typical buildings for industrial applications. Mainly
energy saving potential was determined by optimizing the orientation
and area of such glazing systems in dependency on their thermal
qualities. Moreover the impact on critical aspects such as summer
overheating and daylight illumination was considered to ensure the
user comfort and avoid additional energy demand for lighting or
cooling. Hereby the simulated heating demand could be reduced by
up to 1/3 compared to traditional architecture of industrial halls using
mainly skylights.
Abstract: Enhancing the quality of two dimensional signals is one of the most important factors in the fields of video surveillance and computer vision. Usually in real-life video surveillance, false detection occurs due to the presence of random noise, illumination
and shadow artifacts. The detection methods based on background subtraction faces several problems in accurately detecting objects in realistic environments: In this paper, we propose a noise removal algorithm using neighborhood comparison method with thresholding. The illumination variations correction is done in the detected foreground objects by using an amalgamation of techniques like homomorphic decomposition, curvelet transformation and gamma adjustment operator. Shadow is removed using chromaticity estimator with local relation estimator. Results are compared with the existing methods and prove as high robustness in the video surveillance.
Abstract: This paper presents a weighted approach to unconstrained iris recognition. In nowadays, commercial systems are usually characterized by strong acquisition constraints based on the subject’s cooperation. However, it is not always achievable for real scenarios in our daily life. Researchers have been focused on reducing these constraints and maintaining the performance of the system by new techniques at the same time. With large variation in the environment, there are two main improvements to develop the proposed iris recognition system. For solving extremely uneven lighting condition, statistic based illumination normalization is first used on eye region to increase the accuracy of iris feature. The detection of the iris image is based on Adaboost algorithm. Secondly, the weighted approach is designed by Gaussian functions according to the distance to the center of the iris. Furthermore, local binary pattern (LBP) histogram is then applied to texture classification with the weight. Experiment showed that the proposed system provided users a more flexible and feasible way to interact with the verification system through iris recognition.
Abstract: Image processing in today’s world grabs massive attentions as it leads to possibilities of broaden application in many fields of high technology. The real challenge is how to improve existing sorting system applications which consists of two integrated stations of processing and handling with a new image processing feature. Existing color sorting techniques use a set of inductive, capacitive, and optical sensors to differentiate object color. This research presents a mechatronic color sorting system solution with the application of image processing. A 5-DOF robot arm is designed and developed with pick and place operation to act as the main part of the color sorting system. Image processing procedure senses the circular objects in an image captured in real time by a webcam fixed at the end-effector then extracts color and position information out of it. This information is passed as a sequence of sorting commands to the manipulator that has pick-and-place mechanism. Performance analysis proves that this color based object sorting system works accurately under ideal condition in term of adequate illumination, circular objects shape and color. The circular objects tested for sorting are red, green and blue. For non-ideal condition, such as unspecified color the accuracy reduces to 80%.
Abstract: A silicon photomultiplier (SiPM) was designed, fabricated and characterized. The SiPM was based on SACM (Separation of Absorption, Charge and Multiplication) structure, which was optimized for blue light detection in application of positron emission tomography (PET). The achieved SiPM array has a high geometric fill factor of 64% and a low breakdown voltage of about 22V, while the temperature dependence of breakdown voltage is only 17mV/°C. The gain and photon detection efficiency of the device achieved were also measured under illumination of light at 405nm and 460nm wavelengths. The gain of the device is in the order of 106. The photon detection efficiency up to 60% has been observed under 1.8V overvoltage.
Abstract: This study aims to discuss the effect of illumination and the color temperature of the lighting source under the office lighting environment on human psychological and physiological responses. In this study, 21 healthy participants were selected, and the Ryodoraku measurement system was utilized to measure their skin resistance change.The findings indicated that the effect of the color temperature of the lighting source on human physiological responses is significant within 90 min after turning the lights on; while after 90 min the effect of illumination on human physiological responses is higher than that of the color temperature. Moreover, the cardiovascular, digestive and endocrine systems are prone to be affected by the indoor lighting environment. During the long-term exposure to high intensity of illumination and high color temperature (2000Lux -6500K), the effect on the psychological responses turned moderate after the human visual system adopted to the lighting environment. However, the effect of the Ryodoraku value on human physiological responses was more significant with the increase of perceptive time. The effect of long time exposure to a lighting environment on the physiological responses is greater than its effect on the psychological responses. This conclusion is different from the traditional public viewpoint that the effect on the psychological responses is greater.
Abstract: This article reports on the studies of porous GaN prepared by ultra-violet (UV) assisted electrochemical etching in a solution of 4:1:1 HF: CH3OH:H2O2 under illumination of an UV lamp with 500 W power for 10, 25 and 35 minutes. The optical properties of porous GaN sample were compared to the corresponding as grown GaN. Porosity induced photoluminescence (PL) intensity enhancement was found in these samples. The resulting porous GaN displays blue shifted PL spectra compared to the as-grown GaN. Appearance of the blue shifted emission is correlated with the development of highly anisotropic structures in the morphology. An estimate of the size of the GaN nanostructure can be obtained with the help of a quantized state effective mass theory.
Abstract: A robust still image face localization algorithm
capable of operating in an unconstrained visual environment is
proposed. First, construction of a robust skin classifier within a
shifted HSV color space is described. Then various filtering
operations are performed to better isolate face candidates and
mitigate the effect of substantial non-skin regions. Finally, a novel
Bhattacharyya-based face detection algorithm is used to compare
candidate regions of interest with a unique illumination-dependent
face model probability distribution function approximation.
Experimental results show a 90% face detection success rate despite
the demands of the visually noisy environment.
Abstract: During the past several years, face recognition in video
has received significant attention. Not only the wide range of
commercial and law enforcement applications, but also the availability
of feasible technologies after several decades of research contributes
to the trend. Although current face recognition systems have reached a
certain level of maturity, their development is still limited by the
conditions brought about by many real applications. For example,
recognition images of video sequence acquired in an open
environment with changes in illumination and/or pose and/or facial
occlusion and/or low resolution of acquired image remains a largely
unsolved problem. In other words, current algorithms are yet to be
developed. This paper provides an up-to-date survey of video-based
face recognition research. To present a comprehensive survey, we
categorize existing video based recognition approaches and present
detailed descriptions of representative methods within each category.
In addition, relevant topics such as real time detection, real time
tracking for video, issues such as illumination, pose, 3D and low
resolution are covered.
Abstract: AAM has been successfully applied to face alignment,
but its performance is very sensitive to initial values. In case the initial
values are a little far distant from the global optimum values, there
exists a pretty good possibility that AAM-based face alignment may
converge to a local minimum. In this paper, we propose a progressive
AAM-based face alignment algorithm which first finds the feature
parameter vector fitting the inner facial feature points of the face and
later localize the feature points of the whole face using the first
information. The proposed progressive AAM-based face alignment
algorithm utilizes the fact that the feature points of the inner part of the
face are less variant and less affected by the background surrounding
the face than those of the outer part (like the chin contour). The
proposed algorithm consists of two stages: modeling and relation
derivation stage and fitting stage. Modeling and relation derivation
stage first needs to construct two AAM models: the inner face AAM
model and the whole face AAM model and then derive relation matrix
between the inner face AAM parameter vector and the whole face
AAM model parameter vector. In the fitting stage, the proposed
algorithm aligns face progressively through two phases. In the first
phase, the proposed algorithm will find the feature parameter vector
fitting the inner facial AAM model into a new input face image, and
then in the second phase it localizes the whole facial feature points of
the new input face image based on the whole face AAM model using
the initial parameter vector estimated from using the inner feature
parameter vector obtained in the first phase and the relation matrix
obtained in the first stage. Through experiments, it is verified that the
proposed progressive AAM-based face alignment algorithm is more
robust with respect to pose, illumination, and face background than the
conventional basic AAM-based face alignment algorithm.