A robust tracking approach for vision-based forward vehicle detection

Author

Fu-Hsaing Chi ; Chih-Li Huo ; Yu-Hsaing Yu ; Tsung-Ying Sun

Author_Institution

Dept. of Electr. Eng., Nat. Dong Hwa Univ., Hualien, Taiwan

fYear

2012

fDate

16-18 Nov. 2012

Firstpage

244

Lastpage

248

Abstract

Based on the lane marking tracking, this study presents a robust tracking approach for vision-based forward vehicle detection. Following vanishing point of lane which is according to lane detection point and linear regression analysis, five scan lines created as region of interest (ROI) for tracking is adopted to reduce the computational cost in detection process. The proposed algorithm implemented on TI DM648 DSP platform, and get very well results for various road environments.

Keywords

computer vision; digital signal processing chips; object detection; object tracking; regression analysis; road vehicles; traffic engineering computing; TI DM648 DSP platform; digital signal processor; lane detection point; lane marking tracking; lane vanishing point; linear regression analysis; road environment; robust tracking approach; vision-based forward vehicle detection; Computer architecture; Educational institutions; Image segmentation; Roads; Sun; Vehicle detection; Vehicles; Forward vehicle detection and tracking; Lane-marking tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Theory and it's Applications (iFUZZY), 2012 International Conference on

Conference_Location

Taichung

Print_ISBN

978-1-4673-2057-3

Type

conf

DOI

10.1109/iFUZZY.2012.6409709

Filename

6409709