National Technical University of Athens (NTUA)
Ανάπτυξη αλγορίθμου σύντηξης ετερογενών δεδομένων πολλαπλών αισθητήρων για δυναμική παρακολούθηση και αναγνώριση αντικειμένων εντός οδικού περιβάλλοντος
Abstract
dc:descriptionThe use of multiple, and of different types, sensors in onboard automotive safety systems is gaining continuously acceptance during the last years. Yet, the difficult issue of managing this heterogeneous, multisource, redundant or complementary information has been recognized as a bottleneck in the extension and improvement of these systems. Multiple sensor data fusion has also been acknowledged as the only promising solution for the rational use of this information and the operational and functional extension of advanced automotive safety applications. This work contributes towards this direction with the design and development of a global data fusion algorithm that aims at the successful dynamic recognition and surveillance of neighboring moving vehicles to the also moving sensor equipped platform vehicle. Typical sensors used in this kind of applications and in the systems developed in this work, include long and short range microwave radars, laser scanners and various types of passive vision sensors. Moreover, platform vehicle usually contains movement inertial sensors, position sensors and sometimes data bases of geographic information systems. The proposed distributed data fusion system intends to assign high level of information to the tracked vehicles in the platform-vehicle’s environment exploiting and outclassing the performance of single sensors. The outline of the main systems incorporates the subsystems of: estimation and filtering of platform vehicle’s position and dynamics, preprocessing (tracking) systems of single sensors data and data association which is a subsystem of tracking systems and data fusion as well. The innovative aspects introduced in this work comprise four main issues: (a) management of multisource heterogeneous information (many and of different type sensors) in a moving platform with a generic global algorithm, (b) solution of new data association problems for single and multipoint objects together with multidimensional assignment (more than two sensors), (c) the all-around platform vehicle tracking of other moving vehicles and (d) the development of a sensor tracking algorithm that deals with various topologies (e.g. rear or side looking sensors) and various types of sensors.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2007
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Floudas, Nikolaos
- Φλούδας, Νικόλαος
Subjects
dc:subject × 16- Οδική ασφάλεια
- Ιχνηλασία
- Πολυδιάστατη σύνδεση δεδομένων
- Σύντηξη ετερογενών δεδομένων
- Κυκλική παρακολούθηση
- Ανίχνευση αντικειμένων
- Traffic safety
- Tracking
- Multidimensional data association
- Heterogeneous data fusion
- All around surveillance
- Object detection
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/16958