A deployable architecture of Intelligent Transportation System — A developing country perspective
ABSTRACT Being an indicator of economic growth, the deployment of an Intelligent Transportation System (ITS) became an imperative necessity of a country, whether developed or developing. Emergence of innovative technologies in the areas of Computer Science, ICT and Digital Image Processing paved way to the implementation and the deployment of such a system in a cost effective and economic manner. Introduction of a system with minimal disturbance of the heterogeneous environment with minimum cost and time in R&D and deployment will be an important criteria in the selection of such a system for a developing country. The intelligent Transportation System can be considered to be constituted with multiple layers of integrated innovative technologies. The recent advancements in third and fourth generation wireless data communication as one of the access technologies and the deployment of high-speed secure information highway established with a national level computer backbone network in developing countries made the deployment of such a system in an efficient manner which form the physical layer of ITS. The technological layer of ITS can be formed with IP based Sophisticated intelligent Camera technologies and with the application of intelligent algorithms on advanced digital image processing techniques, which can be implemented in a multi-layer architecture and deployed in multiple stages, which will make the system robust and will be making the environment gradually standardised, without much disturbances. The standardised vehicle licence plate is the raw data of ITS, which may or may not be standardised in developing countries. The introduction of the concept of a repository of non-standardised licence plates left after the application of layered advanced digital image processing algorithms injected in ITS will enable the gradual standardisation of the environment. The advanced application programs and databases implemented in the Open-Source Technology Stream deployed in -
Open Source Operating Systems form the application layer of ITS which will further reduce the development and deployment cost. The ITS can be implemented with a distributed architecture of regional ITS databases and state level vehicle databases managed with a DBMS with catalogue management capable of handling such sophisticated architecture. This literature delivers a conceptual framework of an Intelligent Transportation System for developing countries, its subsystems, design specifications and deployment strategies. The multi-tier architecture and multiphase deployment will ensure the high success rate and enhance the robustness of such an distributed system in a heterogeneous environment. The overall architectural view of such a system will enable the uniform distribution of design and deployment complexities in subsystems. This literature is an attempt in that direction.
- SourceAvailable from: Dimo Todorov Dimov[show abstract] [hide abstract]
ABSTRACT: The paper represents the automatic plate localization component of a Car License Plate Recognition system. The approach concerns stages of preprocessing, edge detection, filtering, detection of the plate's position, slope evaluation, and character segmentation and recognition. Single frame gray-level images are used as the only source of information. In the experiments Israeli and Bulgarian license plates were used, camera obtained at different daytime and whether conditions. The results derived have shown that the approach is robust to illumination, plate slope, scale, and is insensitive to plate's country peculiarities. These results could be also usable for other applications in the input-output transport systems, where automatic recognition of registration plates, shields, signs, etc., is often necessary.01/2003;
- [show abstract] [hide abstract]
ABSTRACT: Overlay text brings important semantic clues in video content analysis such as video information retrieval and summarization, since the content of the scene or the editor's intention can be well represented by using inserted text. Most of the previous approaches to extracting overlay text from videos are based on low-level features, such as edge, color, and texture information. However, existing methods experience difficulties in handling texts with various contrasts or inserted in a complex background. In this paper, we propose a novel framework to detect and extract the overlay text from the video scene. Based on our observation that there exist transient colors between inserted text and its adjacent background, a transition map is first generated. Then candidate regions are extracted by a reshaping method and the overlay text regions are determined based on the occurrence of overlay text in each candidate. The detected overlay text regions are localized accurately using the projection of overlay text pixels in the transition map and the text extraction is finally conducted. The proposed method is robust to different character size, position, contrast, and color. It is also language independent. Overlay text region update between frames is also employed to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.IEEE Transactions on Image Processing 01/2009; 18(2):401-11. · 3.20 Impact Factor