Vassili Loumos
National Technical University of Athens
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Vassili Loumos.
IEEE Transactions on Intelligent Transportation Systems | 2006
Christos-Nikolaos Anagnostopoulos; Ioannis Anagnostopoulos; Vassili Loumos; Eleftherios Kayafas
In this paper, a new algorithm for vehicle license plate identification is proposed, on the basis of a novel adaptive image segmentation technique (sliding concentric windows) and connected component analysis in conjunction with a character recognition neural network. The algorithm was tested with 1334 natural-scene gray-level vehicle images of different backgrounds and ambient illumination. The camera focused in the plate, while the angle of view and the distance from the vehicle varied according to the experimental setup. The license plates properly segmented were 1287 over 1334 input images (96.5%). The optical character recognition system is a two-layer probabilistic neural network (PNN) with topology 108-180-36, whose performance for entire plate recognition reached 89.1%. The PNN is trained to identify alphanumeric characters from car license plates based on data obtained from algorithmic image processing. Combining the above two rates, the overall rate of success for the license-plate-recognition algorithm is 86.0%. A review in the related literature presented in this paper reveals that better performance (90% up to 95%) has been reported, when limitations in distance, angle of view, illumination conditions are set, and background complexity is low
IEEE Transactions on Intelligent Transportation Systems | 2008
Christos-Nikolaos Anagnostopoulos; Ioannis Anagnostopoulos; Ioannis Psoroulas; Vassili Loumos; Eleftherios Kayafas
License plate recognition (LPR) algorithms in images or videos are generally composed of the following three processing steps: 1) extraction of a license plate region; 2) segmentation of the plate characters; and 3) recognition of each character. This task is quite challenging due to the diversity of plate formats and the nonuniform outdoor illumination conditions during image acquisition. Therefore, most approaches work only under restricted conditions such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds. Numerous techniques have been developed for LPR in still images or video sequences, and the purpose of this paper is to categorize and assess them. Issues such as processing time, computational power, and recognition rate are also addressed, when available. Finally, this paper offers to researchers a link to a public image database to define a common reference point for LPR algorithmic assessment.
Waste Management & Research | 2007
Nikolaos V. Karadimas; Katerina Papatzelou; Vassili Loumos
In the present paper, the Ant Colony System (ACS) algorithm is used for the identification of optimal routes in the case of municipal solid waste (MSW) collection. The proposed MSW management system is based on a geo-referenced spatial database supported by a geographic information system (GIS). The GIS takes into account all the required parameters for solid waste collection. These parameters include static and dynamic data, such as the positions of waste bins, the road network and the related traffic, as well as the population density in the area under study. In addition, waste collection schedules, truck capacities and their characteristics are also taken into consideration. Spatio-temporal statistical analysis is used to estimate inter-relations between dynamic factors, like network traffic changes in residential and commercial areas. The user, in the proposed system, is able to define or modify all of the required dynamic factors for the creation of alternative initial scenarios. The objective of the system is to identify the most cost-effective scenario for waste collection, to estimate its running cost and to simulate its application. Finally, the results of the ACS algorithm are compared with the empirical method currently used by the Municipality of Athens.
Waste Management & Research | 2008
Nikolaos V. Karadimas; Vassili Loumos
In the present paper, an innovative model for the estimation of municipal solid waste generation and collection is proposed. This model is part of an extended solid waste management system and uses a spatial Geodatabase, integrated in a GIS environment. It takes into consideration several parameters of waste generation, such as population density, commercial activities, road characteristics and their influence on the location and allocation of waste bins. Ground-based analysis was applied for the estimation of the inter-relations between the aforementioned factors and the variations in waste generation between residential and commercial areas. Therefore, the proposed model follows a unified categorization approach for residential and commercial activities and focuses on the dominant factors that determine waste generation in the area under study. The most important result of the research work presented in the current paper is an accurate estimation of the optimal number of waste bins and their allocation. A new methodology and an appropriate algorithm have been developed for this purpose in order to facilitate routing and waste collection. By using these results, municipalities aware of social, economical and environmental factors, related to waste management, can achieve optimal usage of their resources and offer the best possible services to their citizens.
Information Systems | 2004
Nikolaos V. Karadimas; Vassili Loumos; Ourania D. Mavrantza
In the present paper, a framework for the design and implementation of a system aiming to guarantee the quality of services for urban solid waste management is proposed. This system consists of a geo-referenced spatial database, built in the environment of a geographic information system (GIS), which includes all required parameters for waste management. These parameters involve point sources of waste collection, road network and related traffic data of the area under study, as well as the location and capacity of landfills, incinerators and recycling units. In addition dynamic data for population density, time schedule of labor workers, transportation facilities location measured by Global Positioning System (GPS), etc., are considered. Spatio-temporal analysis is implemented in order to represent the interrelations between urban growth, and consequently, increase of wastes and the collection-transport-disposal subsystems of waste management. The spatial database is accessed through a graphical user interface facilitating component entering and system operation simulation and monitoring. The user is able to input all required parameters, and to invoke a nonlinear programming model for initial cost calculation and optimization by generating alternative scenarios. The main goals of the proposed system are the calculation of total cost for transport and disposal, for a specific scenario, the identification of the most cost-effective alternative scenario and the monitoring of its application. The end-users of the aforementioned system are the regional authorities and their requirements and needs for waste management are adopted in the design and implementation of this system.
21st Conference on Modelling and Simulation | 2007
Nikolaos V. Karadimas; Maria Kolokathi; Gerasimoula Defteraiou; Vassili Loumos
In the present paper the ArcGIS Network Analyst Algorithm is introduced for best routing identification applied in municipal waste collection of large items. The proposed application takes into account all the required parameters for the waste collection of large items so as its desktop users to be able to model realistic network conditions and scenarios. In this case, the simulation consists of scenarios of visiting loading spots in the municipality of Athens, in order to collect large items that couldn’t be collected by the standard waste collection trucks, due to size and other prohibitive obstacles. The Network Analyst is used to estimate interrelations between the dynamic factors, like network traffic changes (closed roads due to natural or technical causes, for example, fallen trees, car accidents, etc) in the area under study and to produce optimized solutions. The user is able to define or modify all the required dynamic factors for the creation of an initial scenario, and by modifying these particular parameters, alternative scenarios can be generated leading to several solutions. Finally, the optimal solution is identified by a function that takes into consideration various parameters, for example the shortest distance, road network as well as social and environmental implications.
20th Conference on Modelling and Simulation | 2006
A. Orsoni; N. V. Karadimas; Vassili Loumos
The present paper introduces an innovative model for the estimation of urban solid waste productivity using an intelligent system based on fuzzy logic. The model retrieves the required information from a spatial Geodatabase, integrated in a GIS environment. The model takes into consideration several parameters of waste production, such as population density, maximum building density, commercial traffic, area and type of shops, road network and its relative information (e.g. road width, dead-end streets, etc) linked with the allocation of waste bins. Additionally, ground-based analysis has been applied for the estimation of the interrelations between the aforementioned factors and the variations in waste production between residential and commercial areas. Therefore, the proposed model follows a unified and correlated categorization approach for all commercial and industrial activities in the area of study using a weighting system for all of the considered factors. The first results from testing the system using different regions, show the effectiveness of the system in the estimation process of the optimal number of waste bins in each region.
artificial intelligence applications and innovations | 2007
Nikolaos V. Karadimas; Katerina Papatzelou; Vassili Loumos
In the present paper, the Genetic Algorithm (GA) is used for the identification of optimal routes in the case of Municipal Solid Waste (MSW) collection. The identification of a route for MSW collection trucks is critical since it has been estimated that, of the total amount of money spent for the collection, transportation, and disposal of solid waste, approximately 60–80% is spent on the collection phase. Therefore, a small percentage improvement in the collection operation can result to a significant saving in the overall cost. The proposed MSW management system is based on a geo-referenced spatial database supported by a geographic information system (GIS). The GIS takes into account all the required parameters for solid waste collection. These parameters include static and dynamic data, such as the positions of waste bins, the road network and its related traffic, as well as the population density in the area under study. In addition, waste collection schedules, truck capacities and their characteristics are also taken into consideration. Spatiotemporal statistical analysis is used to estimate inter-relations between dynamic factors, like network traffic changes in residential and commercial areas. The user, in the proposed system, is able to define or modify all of the required dynamic factors for the creation of alternative initial scenarios. The objective of the system is to identify the most cost-effective scenario for waste collection, to estimate its running cost and to simulate its application.
Computer Methods and Programs in Biomedicine | 1994
Georgios Theodoropoulos; Vassili Loumos
The teaching of parasitology is a basic course in all life sciences curricula, and up to now no computer-assisted tutoring system has been developed for this purpose. By using Knowledge Pro, an object-oriented software development tool, a hypermedia tutoring system for teaching parasitology to college students was developed. Generally, a tutoring system contains a domain expert, a student model, a pedagogical expert and the user interface. In this project, particular emphasis was given to the user interface design and the expert knowledge representation. The system allows access to the educational material through hypermedia and indexing at the pace of the student. The hypermedia access is facilitated through key words defined as hypertext and objects in pictures defined as hyper-areas. The indexing access is based on a list of parameters that refers to various characteristics of the parasites, e.g. taxonomy, host, organ, etc. In addition, this indexing access can be used for testing the students level of understanding. The advantages of this system are its user-friendliness, graphical interface and ability to incorporate new educational material in the area of parasitology.
conference on computer as a tool | 2005
Nikolaos V. Karadimas; Ourania D. Mavrantza; Vassili Loumos
In the present paper, an innovative model for the management of urban solid waste is proposed. The model consists of a spatio-temporal geodatabase, integrated in a geographical information system (GIS) environment. This model takes into consideration all the parameters of waste production, such as population density, commercial traffic, road network and the relative information (e.g. road width, etc). Temporal ground-based analysis has been applied for the estimation of the interrelations between the above factors, and the variations in waste production between residential and commercial areas. Therefore, the model takes into account a unified categorization of all the commercial and industrial activities in the area under study. The main goal of this innovative algorithmic approach is to develop an accurate estimation of the solid waste production rate that allows the identification of the optimal number and location of the waste bins. In this way, municipalities aware of social, economical and environmental factors related to waste management can achieve optimal planning for their services