Abstract: This paper proposes a novel stereo vision technique
for top view book scanners which provide us with dense 3d point
clouds of page surfaces. This is a precondition to dewarp bound
volumes independent of 2d information on the page. Our method is
based on algorithms, which normally require the projection of pattern
sequences with structured light. We use image sequences of the
moving stripe lighting of the top view scanner instead of an additional
light projection. Thus the stereo vision setup is simplified without
losing measurement accuracy. Furthermore we improve a surface
model dewarping method through introducing a difference vector
based on real measurements. Although our proposed method is hardly
expensive neither in calculation time nor in hardware requirements
we present good dewarping results even for difficult examples.
Abstract: Dedicated Short Range Communication (DSRC) is a
key enabling technology for the next generation of
communication-based safety applications. One of the important
problems for DSRC deployment is maintaining high performance
under heavy channel load. Many studies focus on congestion control
mechanisms for simulating hundreds of physical radios deployed on
vehicles. The U.S. department of transportation-s (DOT) Intelligent
Transportation Systems (ITS) division has a plan to chosen prototype
on-board devices capable of transmitting basic “Here I am" safety
messages to other vehicles. The devices will be used in an IntelliDrive
safety pilot deployment of up to 3,000 vehicles. It is hard to log the
information of 3,000 vehicles. In this paper we present the designs and
issues related to the DSRC Radio Testbed under heavy channel load.
The details not only include the architecture of DSRC Radio Testbed,
but also describe how the Radio Interfere System is used to help for
emulating the congestion radio environment.
Abstract: Recently, in some places, optical-fibre access
networks have been used with GPON technology belonging to
organizations (in most cases public bodies) that act as neutral
operators. These operators simultaneously provide network services
to various telecommunications operators that offer integrated voice,
data and television services. This situation creates new problems
related to quality of service, since the interests of the users are
intermingled with the interests of the operators. In this paper, we
analyse this problem and consider solutions that make it possible to
provide guaranteed quality of service for voice over IP, data services
and interactive digital television.
Abstract: The modern telecommunication industry demands
higher capacity networks with high data rate. Orthogonal frequency
division multiplexing (OFDM) is a promising technique for high data
rate wireless communications at reasonable complexity in wireless
channels. OFDM has been adopted for many types of wireless
systems like wireless local area networks such as IEEE 802.11a, and
digital audio/video broadcasting (DAB/DVB). The proposed research
focuses on a concatenated coding scheme that improve the
performance of OFDM based wireless communications. It uses a
Redundant Residue Number System (RRNS) code as the outer code
and a convolutional code as the inner code. Here, a direct conversion
of analog signal to residue domain is done to reduce the conversion
complexity using sigma-delta based parallel analog-to-residue
converter. The bit error rate (BER) performances of the proposed
system under different channel conditions are investigated. These
include the effect of additive white Gaussian noise (AWGN),
multipath delay spread, peak power clipping and frame start
synchronization error. The simulation results show that the proposed
RRNS-Convolutional concatenated coding (RCCC) scheme provides
significant improvement in the system performance by exploiting the
inherent properties of RRNS.
Abstract: Using vision based solution in intelligent vehicle application often needs large memory to handle video stream and image process which increase complexity of hardware and software. In this paper, we present a FPGA implement of a vision based lane departure warning system. By taking frame of videos, the line gradient of line is estimated and the lane marks are found. By analysis the position of lane mark, departure of vehicle will be detected in time. This idea has been implemented in Xilinx Spartan6 FPGA. The lane departure warning system used 39% logic resources and no memory of the device. The average availability is 92.5%. The frame rate is more than 30 frames per second (fps).
Abstract: To investigate the correspondence of theory and
practice, a successfully implemented Knowledge Management
System (KMS) is explored through the lens of Alavi and Leidner-s
proposed KMS framework for the analysis of an information system
in knowledge management (Framework-AISKM). The applied KMS
system was designed to manage curricular knowledge in a distributed
university environment. The motivation for the KMS is discussed
along with the types of knowledge necessary in an academic setting.
Elements of the KMS involved in all phases of capturing and
disseminating knowledge are described. As the KMS matures the
resulting data stores form the precursor to and the potential for
knowledge mining. The findings from this exploratory study indicate
substantial correspondence between the successful KMS and the
theory-based framework providing provisional confirmation for the
framework while suggesting factors that contributed to the system-s
success. Avenues for future work are described.
Abstract: We present a system that finds road boundaries and
constructs the virtual lane based on fusion data from a laser and a
monocular sensor, and detects forward vehicle position even in no lane
markers or bad environmental conditions. When the road environment
is dark or a lot of vehicles are parked on the both sides of the road, it is
difficult to detect lane and road boundary. For this reason we use
fusion of laser and vision sensor to extract road boundary to acquire
three dimensional data. We use parabolic road model to calculate road
boundaries which is based on vehicle and sensors state parameters and
construct virtual lane. And then we distinguish vehicle position in each
lane.
Abstract: To illustrate diversity of methods used to extract relevant (where the concept of relevance can be differently defined for different applications) visual data, the paper discusses three groups of such methods. They have been selected from a range of alternatives to highlight how hardware and software tools can be complementarily used in order to achieve various functionalities in case of different specifications of “relevant data". First, principles of gated imaging are presented (where relevance is determined by the range). The second methodology is intended for intelligent intrusion detection, while the last one is used for content-based image matching and retrieval. All methods have been developed within projects supervised by the author.
Abstract: In general, image-based 3D scenes can now be found in many popular vision systems, computer games and virtual reality tours. So, It is important to segment ROI (region of interest) from input scenes as a preprocessing step for geometric stricture detection in 3D scene. In this paper, we propose a method for segmenting ROI based on tensor voting and Dirichlet process mixture model. In particular, to estimate geometric structure information for 3D scene from a single outdoor image, we apply the tensor voting and Dirichlet process mixture model to a image segmentation. The tensor voting is used based on the fact that homogeneous region in an image are usually close together on a smooth region and therefore the tokens corresponding to centers of these regions have high saliency values. The proposed approach is a novel nonparametric Bayesian segmentation method using Gaussian Dirichlet process mixture model to automatically segment various natural scenes. Finally, our method can label regions of the input image into coarse categories: “ground", “sky", and “vertical" for 3D application. The experimental results show that our method successfully segments coarse regions in many complex natural scene images for 3D.
Abstract: In this article the accumulated results out of the effects
and length of the manufacture and production projects in the
university and research standard have been settled with the usefulness
definition of the process of project management for the accessibility
to the proportional pattern in the “time and action" stages. Studies
show that many problems confronted by the researchers in these
projects are connected to the non-profiting of: 1) autonomous timing
for gathering the educational theme, 2) autonomous timing for
planning and pattern, presenting before the construction, and 3)
autonomous timing for manufacture and sample presentation from the
output. The result of this study indicates the division of every
manufacture and production projects into three smaller autonomous
projects from its kind, budget and autonomous expenditure, shape
and order of the stages for the management of these kinds of projects.
In this case study real result are compared with theoretical results.
Abstract: This research aims to examine the key success factors
for the diffusion of mobile entertainment services in Malaysia. The
drivers and barriers observed in this research include perceived
benefit; concerns pertaining to pricing, product and technological
standardization, privacy and security; as well as influences from
peers and community. An analysis of a Malaysian survey of 384
respondents between 18 to 25 years shows that subscribers placed
greater importance on perceived benefit of mobile entertainment
services compared to other factors. Results of the survey also show
that there are strong positive correlations between all the factors,
with pricing issue–perceived benefit showing the strongest
relationship. This paper aims to provide an extensive study on the
drivers and barriers that could be used to derive architecture for
entertainment service provision to serve as a guide for telcos to
outline suitable approaches in order to encourage mass market
adoption of mobile entertainment services in Malaysia.
Abstract: One important objective in Precision Agriculture is to minimize the volume of herbicides that are applied to the fields through the use of site-specific weed management systems. In order to reach this goal, two major factors need to be considered: 1) the similar spectral signature, shape and texture between weeds and crops; 2) the irregular distribution of the weeds within the crop's field. This paper outlines an automatic computer vision system for the detection and differential spraying of Avena sterilis, a noxious weed growing in cereal crops. The proposed system involves two processes: image segmentation and decision making. Image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and the weeds. From these attributes, a hybrid decision making approach determines if a cell must be or not sprayed. The hybrid approach uses the Support Vector Machines and the Fuzzy k-Means methods, combined through the fuzzy aggregation theory. This makes the main finding of this paper. The method performance is compared against other available strategies.
Abstract: This paper presents a new feature based dense stereo
matching algorithm to obtain the dense disparity map via dynamic
programming. After extraction of some proper features, we use some
matching constraints such as epipolar line, disparity limit, ordering
and limit of directional derivative of disparity as well. Also, a coarseto-
fine multiresolution strategy is used to decrease the search space
and therefore increase the accuracy and processing speed. The
proposed method links the detected feature points into the chains and
compares some of the feature points from different chains, to
increase the matching speed. We also employ color stereo matching
to increase the accuracy of the algorithm. Then after feature
matching, we use the dynamic programming to obtain the dense
disparity map. It differs from the classical DP methods in the stereo
vision, since it employs sparse disparity map obtained from the
feature based matching stage. The DP is also performed further on a
scan line, between any matched two feature points on that scan line.
Thus our algorithm is truly an optimization method. Our algorithm
offers a good trade off in terms of accuracy and computational
efficiency. Regarding the results of our experiments, the proposed
algorithm increases the accuracy from 20 to 70%, and reduces the
running time of the algorithm almost 70%.
Abstract: Intelligent technologies are increasingly facilitating
sustainable water management strategies in Australia. While this
innovation can present clear cost benefits to utilities through
immediate leak detection and deference of capital costs, the impact of
this technology on households is less distinct. By offering real-time
engagement and detailed end-use consumption breakdowns, there is
significant potential for demand reduction as a behavioural response
to increased information. Despite this potential, passive
implementation without well-planned residential engagement
strategies is likely to result in a lost opportunity. This paper begins
this research process by exploring the effect of smart water meters
through the lens of three behaviour change theories. The Theory of
Planned Behaviour (TPB), Belief Revision theory (BR) and Practice
Theory emphasise different variables that can potentially influence
and predict household water engagements. In acknowledging the
strengths of each theory, the nuances and complexity of household
water engagement can be recognised which can contribute to
effective planning for residential smart meter engagement strategies.
Abstract: L-system is a tool commonly used for modeling and simulating the growth of fractal plants. The aim of this paper is to join some problems of the computational geometry with the fractal geometry by using the L-system technique to generate fractal plant in 3D. L-system constructs the fractal structure by applying rewriting rules sequentially and this technique depends on recursion process with large number of iterations to get different shapes of 3D fractal plants. Instead, it was reiterated a specific number of iterations up to three iterations. The vertices generated from the last stage of the Lsystem rewriting process are used as input to the triangulation algorithm to construct the triangulation shape of these vertices. The resulting shapes can be used as covers for the architectural objects and in different computer graphics fields. The paper presents a gallery of triangulation forms which application in architecture creates an alternative for domes and other traditional types of roofs.
Abstract: Skin color is an important visual cue for computer
vision systems involving human users. In this paper we combine skin
color and optical flow for detection and tracking of skin regions. We
apply these techniques to gesture recognition with encouraging
results. We propose a novel skin similarity measure. For grouping
detected skin regions we propose a novel skin region grouping
mechanism. The proposed techniques work with any number of skin
regions making them suitable for a multiuser scenario.
Abstract: The amplitude response of infrared (IR) sensors
depends on the reflectance properties of the target. Therefore, in
order to use IR sensor for measuring distances accurately, prior
knowledge of the surface must be known. This paper describes the
Phong Illumination Model for determining the properties of a surface
and subsequently calculating the distance to the surface. The angular
position of the IR sensor is computed as normal to the surface for
simplifying the calculation. Ultrasonic (US) sensor can provide the
initial information on distance to obtain the parameters for this
method. In addition, the experimental results obtained by using
LabView are discussed. More care should be taken when placing the
objects from the sensors during acquiring data since the small change
in angle could show very different distance than the actual one.
Since stereo camera vision systems do not perform well under some
environmental conditions such as plain wall, glass surfaces, or poor
lighting conditions, the IR and US sensors can be used additionally to
improve the overall vision systems of mobile robots.
Abstract: Buckling-Restrained Braced Frame system(BRBFs)
are a new type of steel seismic-load-resisting system that has found
use in several countries because of its efficiency and its promise of
seismic performance far superior to that of conventional braced
frames. The system is addressed in the 2005 edition of the AISC
Seismic Provisions for Structural Steel Buildings, also a set of design
provisions has been developed by NEHRP. This report illustrates the
seismic design of buckling restrained braced frames and compares
the result of design in the application of earthquake load for ordinary
bracing systems and buckling restrained bracing systems to see the
advantage and disadvantages of this new type of seismic resisting
system in comparison with the old Ordinary Concentric Braced
Frame systems (OCBFs); they are defined by the provisions
governing their design.
Abstract: Texture classification is a trendy and a catchy
technology in the field of texture analysis. Textures, the repeated
patterns, have different frequency components along different
orientations. Our work is based on Texture Classification and its
applications. It finds its applications in various fields like Medical
Image Classification, Computer Vision, Remote Sensing,
Agricultural Field, and Textile Industry. Weed control has a major
effect on agriculture. A large amount of herbicide has been used for
controlling weeds in agriculture fields, lawns, golf courses, sport
fields, etc. Random spraying of herbicides does not meet the exact
requirement of the field. Certain areas in field have more weed
patches than estimated. So, we need a visual system that can
discriminate weeds from the field image which will reduce or even
eliminate the amount of herbicide used. This would allow farmers to
not use any herbicides or only apply them where they are needed. A
machine vision precision automated weed control system could
reduce the usage of chemicals in crop fields. In this paper, an
intelligent system for automatic weeding strategy Multi Resolution
Combined Statistical & spatial Frequency is used to discriminate the
weeds from the crops and to classify them as narrow, little and broad
weeds.
Abstract: Using bottom-up image processing algorithms to predict human eye fixations and extract the relevant embedded information in images has been widely applied in the design of active machine vision systems. Scene text is an important feature to be extracted, especially in vision-based mobile robot navigation as many potential landmarks such as nameplates and information signs contain text. This paper proposes an edge-based text region extraction algorithm, which is robust with respect to font sizes, styles, color/intensity, orientations, and effects of illumination, reflections, shadows, perspective distortion, and the complexity of image backgrounds. Performance of the proposed algorithm is compared against a number of widely used text localization algorithms and the results show that this method can quickly and effectively localize and extract text regions from real scenes and can be used in mobile robot navigation under an indoor environment to detect text based landmarks.