Title :
Real-time road lane detection with commodity hardware
Author :
Sakjiraphong, Somchok ; Pinho, Andre ; Dailey, Matthew N. ; Ekpanyapong, Mongkol ; Tavares, Adriano
Author_Institution :
Comput. Sci. & Inf. Manage., Asian Inst. of Technol., Pathumthani, Thailand
Abstract :
We present a real-time algorithm for lane boundary estimation based on matched filters and a RANSAC-based method for boundary marking identification. The algorithm is designed to run with minimal assumptions about the environment using a single monocular camera sensor and low-cost commodity compute hardware. With GPU acceleration and TBB, the algorithm runs in less than 25 ms on average on images of size 640 × 480 comparing with 0.12 seconds running on CPU baseline.
Keywords :
image sensors; road traffic; traffic engineering computing; video signal processing; GPU acceleration; RANSAC-based method; TBB; boundary marking identification; lane boundary estimation; low-cost commodity compute hardware; real-time road lane detection; single monocular camera sensor; Arrays; Cameras; Convolution; Estimation; Graphics processing units; Instruction sets; Real-time systems;
Conference_Titel :
Electrical Engineering Congress (iEECON), 2014 International
DOI :
10.1109/iEECON.2014.7088793
