Skip to main content

2015 | Buch

Nature of Computation and Communication

International Conference, ICTCC 2014, Ho Chi Minh City, Vietnam, November 24-25, 2014, Revised Selected Papers

insite
SUCHEN

Über dieses Buch

This book constitutes the thoroughly refereed post-conference proceedings of the International Conference on Nature of Computation and Communication, ICTCC 2014, held in November 2014 in Ho Chi Minh City, Vietnam. The 34 revised full papers presented were carefully reviewed and selected from over 100 submissions. The papers cover formal methods for self-adaptive systems and discuss natural approaches and techniques for computation and communication.

Inhaltsverzeichnis

Frontmatter

Formal Methods for Self-Adaptive Systems

Frontmatter
Modular Design and Verification of Distributed Adaptive Real-Time Systems

We present and apply a design pattern for distributed adaptive real-time systems using the process calculus Timed CSP. It provides a structured modelling approach that is able to cope with the complexity of distributed adaptive real-time systems caused by the interplay of external stimuli, internal communication and timing dependencies. The pattern allows to differentiate between functional data and adaptive control data. Furthermore, we enable the modular verification of functional and adaptation behaviour using the notion of process refinement in Timed CSP. The verification of refinements and crucial properties is automated using industrial-strength proof tools.

Thomas Göthel, Björn Bartels
Modeling Swarm Robotics with KnowLang

Swarm robotics has emerged as a paradigm whereby intelligent agents are considered to be autonomous entities that interact either cooperatively or non-cooperatively. The concept is biologically-inspired and offers many advantages compared with single-agent systems, such as: greater redundancy, reduced costs and risks, and the ability to distribute the overall work among swarm members, which may result in greater efficiency and performance. The distributed and local nature of these systems is the main factor in the high degree of parallelism displayed by their dynamics that often results in adaptation to changing environmental conditions and robustness to failure. This paper presents a formal approach to modeling self-adaptive behavior for swarm robotics. The approach relies on the KnowLang language, a formal language dedicated to knowledge representation for self-adaptive systems.

Emil Vassev, Mike Hinchey
Reasoning on Data Streams: An Approach to Adaptation in Pervasive Systems

Urban environments are increasingly invaded by devices that acquire sensor information and pave the way for innovative forms of context awareness. Collecting knowledge from loosely-structured data streams and reasoning about changes are two key elements of the process. This paper illustrates a possible way to combine these two elements in a coordinated way. We make use of a recently-developed framework for classifying data streams with service-oriented, reconfigurable components. Furthermore, we embed the KnowLang Reasoner, allowing logical and statistical reasoning on the acquired knowledge aiming to achieve self-adaptation.

Nicola Bicocchi, Emil Vassev, Franco Zambonelli, Mike Hinchey
Autonomic Computing Software for Autonomous Space Vehicles

Current space missions increasingly demand more autonomy in control architectures for Unmanned Space Vehicles (USVs), so unmanned long-term missions can be afforded. Continuous assurance of effective adaptation to unpredictable internal and external changes, along with efficient management of resources is essential for such requirements. One of the attractive solutions is that inspired by the physiology of living systems, where self-regulation helps to achieve continuous adaptation to the environment by changing internal conditions. The physiological functions are performed by nervous system reflexes that are the foundations for self-regulatory mechanisms such as homeostasis. Building artificial self-regulation similar to biological ones into USVs makes them highly-viable and ultra-stable in order to support very long missions. This paper presents aspects of how to endow USVs with Artificial Nervous Reflexes (ANRs) by means of applying physiological principles of self-regulation to the USV’s control architecture, so resilience and persistence can be supported. A case study of a composite orbiter is presented. The studied ANRs are needed to guarantee the self-regulation of response time (latency), operation temperature (thermoregulation), and power consumption (energy balance). Results from a cross-checked analysis of the above self-regulation mechanisms are also presented.

Carlos C. Insaurralde, Emil Vassev
Logic-Based Modeling of Information Transfer in Cyber-Physical Multi-Agent Systems

In modeling multi-agent systems, the structure of their communication is typically one of the most important aspects, especially for systems that strive toward self-organization or collaborative adaptation. Traditionally, such structures have often been described using logic-based approaches as they provide a formal foundation for many verification methods. However, these formalisms are typically not well suited to reflect the stochastic nature of communication in a cyber-physical setting. In particular, their level of abstraction is either too high to provide sufficient accuracy or too low to be practicable in more complex models. Therefore, we propose an extension of the logic-based modeling language SALMA, which we have introduced recently, that provides adequate high-level constructs for communication and data propagation, explicitly taking into account stochastic delays and errors. In combination with SALMA’s tool support for simulation and statistical model checking, this creates a pragmatic approach for verification and validation of cyber-physical multi-agent systems.

Christian Kroiß, Tomáš Bureš

Nature of Computation and Communication

Frontmatter
Categorical Structures of Self-adaptation in Collective Adaptive Systems

An adaptive system is currently on spot: collective adaptive system (CAS), which is inspired by the socio-technical systems. CASs are characterized by a high degree of adaptation, giving them resilience in the face of perturbations. In CASs, highest degree of adaptation is

self-adaptation

. The overarching goal of CAS is to realize systems that are tightly entangled with humans and social structures. Meeting this grand challenge of CASs requires a fundamental approach to the notion of self-adaptation. To this end, taking advantage of the categorical approach we construct, in this paper, algebraic structures of self-adaptation in CASs.

Phan Cong Vinh
Self-adaptive Traits in Collective Adaptive Systems

An adaptive system is currently on spot: collective adaptive system (CAS), which is inspired by the socio-technical systems. In CASs, highest degree of adaptation is self-adaptation consisting of

self-adaptive traits

. The overarching goal of CAS is to realize systems that are tightly entangled with humans and social structures. Meeting this grand challenge of CASs requires a fundamental approach to the notion of self-adaptive trait. To this end, taking advantage of the coinductive approach we construct self-adaptation monoid to shape series of self-adaptive traits in CASs and some significant relations.

Phan Cong Vinh, Nguyen Thanh Tung
A Context-Aware Traffic Engineering Model for Software-Defined Networks

Software-Defined Networking is a novel paradigm, based on the separation of the data plane from the control plane. It facilitates direct access to the forwarding plane of a network switch or router over the network. Though it has a lot advantages, the SDN technology leaves considerable room for improvement. Research problems like efficient techniques for customization and optimization for SDN networks are under investigation. This paper aims at proposing a model for traffic engineering in SDN-based networks.

Phuong T. Nguyen, Hong Anh Le, Thomas Zinner
Efficient k-Nearest Neighbor Search for Static Queries over High Speed Time-Series Streams

In this paper, we propose a solution to the multi-step

k

-nearest neighbor (

k-

NN) search. The method is the reduced tolerance-based

k

-NN search for static queries in streaming time-series. A multi-scale filtering technique combined with a multi-resolution index structure is used in the method. We compare the proposed method to the traditional multi-step

k-

NN search in terms of the CPU search time and the number of distance function calls in the post-processing step. The results reveal that the reduced tolerance-based

k

-NN search outperforms the traditional

k

-NN search. Besides, applying multi-threading to the proposed method enables the system to have a fast response to high speed time-series streams for the

k

-NN search of static queries.

Bui Cong Giao, Duong Tuan Anh
Reconstructing Low Degree Triangular Parametric Surfaces Based on Inverse Loop Subdivision

In this paper, we present an efficient local geometric approximate method for reconstruction of a low degree triangular parametric surface using inverse Loop subdivision scheme. Our proposed technique consists of two major steps. First, using the inverse Loop subdivision scheme to simplify a given dense triangular mesh and employing the result coarse mesh as a control mesh of the triangular Bézier surface. Second, fitting this surface locally to the data points of the initial triangular mesh. The obtained parametric surface is approximate to all data points of the given triangular mesh after some steps of local surface fitting without solving a linear system. The reconstructed surface has the degree reduced to at least of a half and the size of control mesh is only equal to a quarter of the given mesh. The accuracy of the reconstructed surface depends on the number of fitting steps

k

, the number of reversing subdivision times

i

at each step of surface fitting and the given distance tolerance

ε

. Through some experimental examples, we also demonstrate the efficiency of our method. Results show that this approach is simple, fast, precise and highly flexible.

Nga Le-Thi-Thu, Khoi Nguyen-Tan, Thuy Nguyen-Thanh
Maximizing the Lifetime of Wireless Sensor Networks with the Base Station Location

Nowadays, wireless sensor networks (WSNs) have been increasingly applied in many different areas and fields. However, one major defect of WSNs is limited energy resources, which affects the network lifetime strongly. A wireless sensor network includes a sensor node set and a base station. The initial energy of each sensor node will be depleted gradually during data transmission to the base station either directly or through other sensor nodes, depending on the distance between the sending node and the receiving node. This paper considers specifying a location for the base station such that it can minimize the consumed energy of each sensor node in transmitting data to that base station, in other words, maximizing the network lifetime. We propose a nonlinear programming model for this optimal problem. Four methods, respectively named as the centroid, the smallest total distances, the smallest total squared distances and greedy method, for finding the base station location are also presented, experimented and compared to each other over 30 data sets that are created randomly. The experimental results show that a relevant location for the base station is essential.

Nguyen Thanh Tung, Dinh Ha Ly, Huynh Thi Thanh Binh
Establishing Operational Models for Dynamic Compilation in a Simulation Platform

In this paper we introduce a new approach to dynamic converting conceptual models in a simulation platform as the GAMA platform (represented in form of GAML syntax) into corresponding operational models (represented in form of Java syntax). This approach aims at providing a more flexible solutions to actual simulation models implemented in a simulation platform as the GAMA. This new approach will facilitate the exhibits of a simulation platform to work with different types of simulation models represented in different forms of syntax.

Nghi Quang Huynh, Tram Huynh Vo, Hiep Xuan Huynh, Alexis Drogoul
MetaAB - A Novel Abundance-Based Binning Approach for Metagenomic Sequences

Metagenomics is a research discipline of microbial communities that studies directly on genetic materials obtained from environmental samples without isolating and culturing single organisms in laboratory. One of the crucial tasks in metagenomic projects is the identification and taxonomic characterization of DNA sequences in the samples. In this paper, we present an unsupervised binning of metagenomic reads, called MetaAB, which can be able to identify and classify reads into groups of genomes using the information of genome abundances. The method is based on a proposed reduced-dimension model that is theoretically proved to have less computational time. Besides, MetaAB detects the number of genome abundances in data automatically by using the Bayesian Information Criterion. Experimental results show that the proposed method achieves higher accuracy and run faster than a recent abundance-based binning approach. The software implementing the algorithm can be downloaded at

http://it.hcmute.edu.vn/bioinfo/metaab/index.htm

Van-Vinh Le, Tran Van Lang, Tran Van Hoai
An Application of PCA on Uncertainty of Prediction

Principal component analysis (PCA) has been widely used in many applications. In this paper, we present the problem of computational complexity in prediction, which increases as more input of predicting event’s information is provided. We use the information theory to show that the PCA method can be applied to reduce the computational complexity while maintaining the uncertainty level of the prediction. We show that the percentage increment of uncertainty is upper bounded by the percentage increment of complexity. We believe that the result of this study will be useful for constructing predictive models for various applications, which operate with high dimensionality of data.

Santi Phithakkitnukoon
Sensing Urban Density Using Mobile Phone GPS Locations: A Case Study of Odaiba Area, Japan

Today, the urban computing scenario is emerging as a concept where humans can be used as a component to probe city dynamics. The urban activities can be described by the close integration of ICT devices and humans. In the quest for creating sustainable livable cities, the deep understanding of urban mobility and space syntax is of crucial importance. This research aims to explore and demonstrate the vast potential of using large-scale mobile-phone GPS data for analysis of human activity and urban connectivity. A new type of mobile sensing data called “Auto-GPS” has been anonymously collected from 1.5 million people for a period of over one year in Japan. The analysis delivers some insights on interim evolution of population density, urban connectivity and commuting choice. The results enable urban planners to better understand the urban organism with more complete inclusion of urban activities and their evolution through space and time.

Teerayut Horanont, Santi Phithakkitnukoon, Ryosuke Shibasaki
Co-modeling: An Agent-Based Approach to Support the Coupling of Heterogeneous Models

Coupling models is becoming more and more important in the fields where modeling relies on interdisciplinary collaboration. This in particular the case in modeling complex systems which often require to either integrate different models at different spatial and temporal scales or to compare their outcomes. The goal of this research is to develop an original agent-based approach to support the coupling heterogeneous models. The architecture that we have designed is implemented in the GAMA modeling and simulation platform [

6

]. The benefits of our approach is to support coupling and combining various models of heterogeneous types (agent-based, equation-based, cellular automata ) in a flexible and explicit way. It also support the dynamic execution of the models which are supposed to be combined during experiments. We illustrate its use and powerfulness to solve existing problems of coupling between an agent-based model, equation-based model and GIS based model. The outcomes of the simulation of these three models show results compatible with the data observed in reality and demonstrate the interest of our approach for building large, multi-disciplinary models.

Nghi Quang Huynh, Hiep Xuan Huynh, Alexis Drogoul, Christophe Cambier
Adaptive Distributed Systems with Cellular Differentiation Mechanisms

This paper proposes a bio-inspired middleware for self-adaptive software agents on distributed systems. It is unique to other existing approaches for software adaptation because it introduces the notions of differentiation, dedifferentiation, and cellular division in cellular slime molds, e.g., dictyostelium discoideum, into real distributed systems. When an agent delegates a function to another agent coordinating with it, if the former has the function, this function becomes less-developed and the latter’s function becomes well-developed.

Ichiro Satoh
Slowdown-Guided Genetic Algorithm for Job Scheduling in Federated Environments

Large-scale federated environments have emerged to meet the requirements of increasingly demanding scientific applications. However, the seemingly unlimited availability of computing resources and heterogeneity turns the scheduling into an NP-hard problem. Unlike exhaustive algorithms and deterministic heuristics, evolutionary algorithms have been shown appropriate for large-scheduling problems, obtaining near optimal solutions in a reasonable time. In the present work, we propose a Genetic Algorithm (GA) for scheduling job-packages of parallel task in resource federated environments. The main goal of the proposal is to determine the job schedule and package allocation to improve the application performance and system throughput. To address such a complex infrastructure, the GA is provided with knowledge based on slowdown predictions for the application runtime, obtained by considering heterogeneity and bandwidth issues. The proposed GA algorithm was tuned and evaluated using real workload traces and the results compared with a range of well-known heuristics in the literature.

Eloi Gabaldon, Josep L. Lerida, Fernando Guirado, Jordi Planes
Measurement of Cloud Computing Services Availability

Recently we are witnessing the engagement of cloud computing services such as emails, web services, mobile application, sharing data-stores and many others. Huge number of companies, customers and public institutions are considering the migration to the cloud services. The topical questions behind this effort is the efficiency and measurement of the QoS – Quality of Services of the cloud computing utilisation. This paper is focused on the problematic of measuring and monitoring service availability in Cloud Computing. It deals with the Service-Level Agreement (SLA) monitoring approaches and frameworks. Furthermore it presents a new approach of the cloud service availability monitoring from the client-centric perspective. On the basis of the client-centric approach a new solution was designed, implemented and tested on a sample cloud environment.

Jakub Pavlik, Vladimir Sobeslav, Ales Komarek
Security Aspects of Cloud Based Mobile Health Care Application

As mobile computing has become very common, a new vulnerabilities and security threads appeared. Cloud computing is a new distribution model of services for various technologies and solutions including the mobile applications. Mobile cloud computing benefits from the interconnection of these two areas. This approach brings many assets, but on the other hand, also the security risks and potential problems. This paper discuss

s

ecurity aspects of mobile cloud computing with a focus on the developed health care mobile application using cloud computation services. Personal data about health of the person are one of the most confidential thus need to be secured against different types of threats. Proposed solution is based on the smartphone as a client gathering data and the cloud servers as a computational platform for data storage and analysing.

Richard Cimler, Jan Matyska, Ladislav Balik, Josef Horalek, Vladimir Sobeslav
New NHPP SRM Based on Generalized S-shaped Fault-Detection Rate Function

Software reliability modelling (SRM) is a mathematics technique to estimate some measures of computer system that relate to software reliability. One group of existing models is using non-homogeneous Poisson process (NHPP) whose fault-number and failure-rate are constant or time-dependent functions. A few studies have been manipulated S-shaped curve to construct their models. However, those works remain some limitations. In this study, we introduce a new model that is based on a generalised S-shaped curve and evaluate it by real data set. After installing it in real code of Matlab and using MLE method to estimate parameter with a range of initial solution, we prove that our model converge to the most basic model of NHPP group, Goel-Okumoto model.

Nguyen Hung-Cuong, Huynh Quyet-Thang
Enhancement of Innovation Co-creation Processes and Ecosystems Through Mobile Technologies

The process of value creation was traditionally driven almost exclusively within the firm. The role of the consumer was seen only at the end of the product development process. However, as the emergence of the Internet and its related technologies resulted in greater product variety there was a need for accelerating the innovation process. The concept of co-creation has been presented as a highly valuable trend and the next progression in open innovation. While extensive research has been conducted on innovation co-creation between firms and consumers, a coherent understanding of its application in the mobile environments has not been achieved. This paper explores the general evolution of the innovation co-creation paradigm and the opportunities mobile technologies bring in further developing this. An innovation co-creation framework is proposed along with a roadmap that provides a more detailed understanding of how to implement the components to realise the necessary innovation co-creation ecosystem.

Tracey Yuan Ting Wong, Gabrielle Peko, David Sundaram
Design and Implementation of Sustainable Social Shopping Systems

Sustainability is one of the most often discussed topics in our society. Although no one argues that individuals are the main players in changing society and the environment, individuals have always been treated as just actors and decision makers who transform the organizational, societal, national, and/or global sustainability practices. However, our fundamental belief is that individual and personal sustainability are at the heart of organizational and societal sustainability. One of the key activities that humans undertake that has an overwhelming influence on the economic, environmental, and health facets of their life is shopping. In this paper, we explore the possibility of using the concepts and principles of decision-making, habit formation, social networks, and benchmarking to influence consumer behavior towards sustainable shopping. We propose a framework and architecture for Sustainable Social Shopping Systems. We are in the process of prototyping and implementing them in the context of a purely online supermarket.

Claris Yee Seung Chung, Roman Proskuryakov, David Sundaram
Developing Method for Optimizing Cost of Software Quality Assurance Based on Regression-Based Model

In this paper we present a method for Optimizing Cost of Software Quality Assurance base on Regression-based Model proposed by Omar AlShathry [

1

,

2

]. Based on the regression-based model, regression analysis to estimate the number of defects in software, we propose an optimal method for software quality assurance based on the constraint conditions using linear programming techniques. The results of a detailed analysis of the theoretical and empirical models are presented and evaluated.

Vu Dao-Phan, Thang Huynh-Quyet, Vinh Le-Quoc
Un-normlized and Random Walk Hypergraph Laplacian Un-supervised Learning

Most network-based clustering methods are based on the assumption that the labels of two adjacent vertices in the network are likely to be the same. However, assuming the pairwise relationship between vertices is not complete. The information a group of vertices that show very similar patterns and tend to have similar labels is missed. The natural way overcoming the information loss of the above assumption is to represent the given data as the hypergraph. Thus, in this paper, the two un-normalized and random walk hypergraph Laplacian based un-supervised learning methods are introduced. Experiment results show that the accuracy performance measures of these two hypergraph Laplacian based un-supervised learning methods are greater than the accuracy performance measure of symmetric normalized graph Laplacian based un-supervised learning method (i.e. the baseline method of this paper) applied to simple graph created from the incident matrix of hypergraph.

Loc Hoang Tran, Linh Hoang Tran, Hoang Trang
Graph Based Semi-supervised Learning Methods Applied to Speech Recognition Problem

Speech recognition is the important problem in pattern recognition research field. In this paper, the un-normalized, symmetric normalized, and random walk graph Laplacian based semi-supervised learning methods will be applied to the network derived from the MFCC feature vectors of the speech dataset. Experiment results show that the performance of the random walk and the symmetric normalized graph Laplacian based methods are at least as good as the performance of the un-normalized graph Laplacian based method. Moreover, the sensitivity measures of these three semi-supervised learning methods are much better than the sensitivity measure of the current state of the art Hidden Markov Model method in speech recognition problem.

Hoang Trang, Loc Hoang Tran
Updating Relational Databases with Linguistic Data Based on Hedge Algebras

Relational Databases (DB) with linguistic data based on hedge algebras (HA) were introduced, following this approach, data manipulation (include linguistic data) is simpler and more efficient, practical than the other one. On this basis, in this paper, we will present the update operations on relational databases with linguistic data based on HA. Update operations are built by mean of semantically quantifying mapping (SQM) and similarity relation of depth k, where k is the length of a linguistic value that belongs to the values domain of an attribute.

Le Ngoc Hung, Vu Minh Loc, Hoang Tung
Primacy of Fuzzy Relational Databases Based on Hedge Algebras

Databases (DB) based on fuzzy set (FST), possibility (PT) and extended possibility theory (EPT)…which have many problems that need to be discussed in capturing, representing, storing and manipulating with fuzzy data because these approaches have difficulty implementing. Fuzzy relational databases based on hedge algebras (HA) have approach naturally. So, we will not worry about representing, storing and manipulating fuzzy data. In this paper we will investigate fuzzy relational database based on hedge algebras to clarify three primacies of which: easy to present, update and query data.

Le Ngoc Hung, Vu Minh Loc
Reducing Impurities in Medical Images Based on Curvelet Domain

Medical image quality greatly affects the diagnostic process. Most of the tasks of increasing the quality of medical images are deblurring or denoising process. These tasks are the difficult problems in medical image processing because they must keep edge features. In the cases, the medical images that have blur combined with noise are a more difficult problem. In this paper, we proposed a method for reducing impurities in medical images based on curvelet domain. The proposed method uses curvelet coefficient combined with augmented lagrangian function to denoising combined with deblurring in medical images. For evaluating the results of the proposed method, we have compared the results with the other recent methods available in literature.

Vo Thi Hong Tuyet, Nguyen Thanh Binh
Increasing the Quality of Medical Images Based on the Combination of Filters in Ridgelet Domain

In many fields, images become a tool that contains data such as medical images. However, the image not only has blur or noise, but also has blur and noise pair. The aim of deblurring and denoising image is to remove blur and noise detail but this process helps keep edges features and its information. In this paper, we have proposed a method for increasing the quality of medical images based on the combination of filters in ridgelet domain. The proposed method uses ridgelet transform combined with Bayesian thresholding for denoising process and uses Wiener filter for deblurring process in ridgelet domain. For demonstrating the superiority of the proposed method, we have compared the results with the other recent methods available in literature.

Nguyen Thanh Binh, Vo Thi Hong Tuyet, Phan Cong Vinh
Efficient Pancreas Segmentation in Computed Tomography Based on Region-Growing

Pancreas segmentation in computed tomography data is one of difficult problems in medical area. Segmentation of pancreas tissue in computed tomography is difficult even for human, since the pancreas head is always directly connected to the small bowel and can in most cases cannot be visually distinguished. In this paper, an efficient method to extract the pancreas from such computed tomography images is proposed. Histogram equalization is used to enhance the contrast of computed tomography images. After that, region-growing technique is applied to label pancreas region and return the result of segmentation. The proposed method will be experimented and evaluated by using Jaccard index between an extracted pancreas and a true one. For evaluating the proposed method, we have compared the results of our proposed method with the other recent methods available in literature.

Tran Duc Tam, Nguyen Thanh Binh
Object Classification Based on Contourlet Transform in Outdoor Environment

Classification of objects is an important task in computer vision. In the case that the objects are occlusion or outdoor environment, classification of objects is a challenging problem. The primary goal of this paper is to classify the object into two classes: human and car in an outdoor environment. In order to detect object classification, most of existing methods separated detecting object region from pre-defined background model. Here, we propose a method to implement classification of human and car in outdoor environment using contourlet transform combined with support vector machine as a classifier for classification of objects. The proposed method tested on standard dataset like PEST2001 dataset. For demonstrating the superiority of the proposed method, we have compared the results with the other recent methods available in literature.

Nguyen Thanh Binh
Motion Detection Based on Image Intensity Ratio

Motion detection is the first important step in large applications of computer vision. Motion detection extracts moving objects from the background. There are many methods to do that. However, in most methods, if the input video has noise and light change, moving objects will not be extracted accurately. In this paper, we propose the method for motion detection which extracts moving objects from the background based on the image intensity ratio concept that is not affected by light change; therefore, the sensitivity with light change is overcome. The image intensity ratio is computed by the average intensity of current frame and the intensity of every pixel in that frame. The intensity ratio of a pixel is nearly unchanged between two frames. We apply the Lucas-Kanade optical flow method based on that image intensity ratio. Our proposed algorithm has good noise tolerance and is not affected by light change. For demonstrating the superiority of the proposed method, we have compared the results with the other recent methods available in literature.

Pham Bao Quoc, Nguyen Thanh Binh
Vehicle Tracking in Outdoor Environment Based on Curvelet Domain

Vehicle tracking is a difficult part in intelligent traffic system. The images of vehicles on the streets, picked up from cameras, are usually in occlusion because of effecting outdoor environment such as lack light, weather, etc. Therefore, vehicle tracking is a challenging problem. This paper proposed a method for vehicle tracking in an outdoor environment. We use curvelet transform combined with object deformation of contour. The light of background may change from this frame to the other frame. The proposed algorithm has significantly improves the edge accuracy and reduces the wrong position of objects between the frames. For demonstrating the superiority of the proposed method, we have compared the results with the other methods.

Nguyen Thanh Binh
Backmatter
Metadaten
Titel
Nature of Computation and Communication
herausgegeben von
Phan Cong Vinh
Emil Vassev
Mike Hinchey
Copyright-Jahr
2015
Electronic ISBN
978-3-319-15392-6
Print ISBN
978-3-319-15391-9
DOI
https://doi.org/10.1007/978-3-319-15392-6