Loading...

An Efficient GPS-based System for Reliable Infraction Detection in Highways

Amoabedini, Alireza | 2010

739 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 40882 (52)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Manzuri, Mohammad Taghi
  7. Abstract:
  8. In this research we explain a new method for detection of infraction behavior of drivers in highways. There are different approaches to find and register such abnormal and illegal behaviors, such as a camera-based monitoring system and Radar-based infraction detectors. But none of them can recognize and register the weave through traffic or spiral motions of vehicles, because the radar-based systems do not have adequate latitudinal–resolution while their longitudinal-accuracy is moderate. Moreover, the locations of radars are fixed and, the drivers adapt the velocity of their vehicles based on the position of the known radars. Consequently, these systems are inherently not suitable for our applications. On the other hand, the camera-based systems have an acceptable latitudinal–resolution but a poor longitudinal-accuracy. Recently, the embedded GPS-based systems are applied to monitor the location and speed of the vehicle. In most of these applications the monitoring is offline, and is not capable of detecting snake motions or weaving through traffic. In this work, we present a new infraction detection system which can distinguish the abnormal behavior of vehicles. In this system we fuse the output data of a normal GPS sensor, with the output of a highway camera. Here, we receive the instantaneous-speed and longitudinal location of the vehicle from the GPS, with accurate precision, and its latitudinal location is obtained from highway cameras. Next, we generated a data base from different abnormal snake motions. Using this data base, we trained a neural network, and used it to determine the abnormality of a variety of new motions and classified them. The results were very promising and the system could recognize snake motions and infractions with a minimum accuracy of 90 percent.
  9. Keywords:
  10. Global Position System (GPS) ; Intelligent Transportation System (ITS) ; Highways ; Spiral Movement ; Infraction Detection

 Digital Object List

 Bookmark

No TOC