A System for Vehicle Detection and Tracking at Nighttime with the Light Blob Detection Technique
| Autor: | Tse Yang, 楊擇 |
|---|---|
| Rok vydání: | 2017 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 105 In this thesis, for the Advanced Driver Assistance System (ADAS), which is able to improve driving safety, we propose a system for vehicle detection and tracking at nighttime with the light blob detection technique to identify and track a vehicle by recognizing its lamps. Specifically, we detect the headlights of crossing vehicles in the way of low exposure setting. As for recognizing the taillights of distant lead vehicles, we first exploit the RGB color space with the red channel only as well as establishing the region of interest, and then measure the similarity between lamps by the horizontal flip technique to have each lamp image paired with the one with the highest similarity for improving the accuracy of detection. In particular, we consider that obstacles such as other vehicles, streetlamps, and shop signs may block vehicle lamps, and so on. Hence, we use the Kalman filter to track lamps for not missing any one, and find the correlation between the past and current frames with Hungarian algorithm to improve the accuracy of tracking. According to the results of simulation experiments, the method proposed by us not only can achieve a high recognition rate on both highways and ordinary roads, but also can eliminate much interference from lights in urban areas. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|