GPU-accelerated adaptive unstructured road detection using close range stereo vision


Thesis Type: Postgraduate

Institution Of The Thesis: Orta Doğu Teknik Üniversitesi, Faculty of Engineering, Department of Mechanical Engineering, Turkey

Approval Date: 2013

Student: KADRİ BUĞRA ÖZÜTEMİZ

Co-Supervisor: AHMET BUĞRA KOKU, ERHAN İLHAN KONUKSEVEN

Abstract:

Detection of road regions is not a trivial problem especially in unstructured and/or off-road domains since traversable regions of these environments do not have common properties unlike urban roads or highways. In this thesis a novel unstructured road detection algorithm that can continuously learn the road region is proposed. The algorithm gathers close-range stereovision data and uses this information to estimate the long-range road region. The experiments show that the algorithm gives satisfactory results even under changing light conditions. In addition to the algorithm structure, the massive parallel implementation on GPU with CUDA is proposed. The speed-up of the CUDA implementation with experiments done is analyzed.