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

Download

index.pdf

Date

2013

Author

Özütemiz, Kadri Buğra

Metadata

Show full item record

Item Usage Stats

90
views

63
downloads

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.

Subject Keywords

Vehicles, Remotely piloted., Remote control., Critical path analysis., Graphics processing units., Stereoscopic cameras., Unstructured Roads.

URI

http://etd.lib.metu.edu.tr/upload/12616158/index.pdf
https://hdl.handle.net/11511/22701

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Adaptive unstructured road detection using close range stereo vision ÖZÜTEMİZ, Kadri Bugra; Hacinecipoglu, AKİF; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (2013-06-26) 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 paper 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 result...
Parallel Hybrid Genetic Algorithm and GIS-Based Optimization for Municipal Solid Waste Collection Routing Düzgün, H. Şebnem; Uşkay, S. Onur; Aksoy, Ayşegül (American Society of Civil Engineers (ASCE), 2016-01-01) A vast majority of studies on municipal solid waste (MSW) collection routing do not consider the constraints pertinent to actual road networks such as unidirectional roads and terrain characteristics. As a result, good practices such as the avoidance of U-turns cannot be used. This study introduces geographic information system (GIS)-integrated software (RouteSW) for the optimization of MSW collection routes by considering path constraints. The software uses a parallelized hybrid genetic algorithm (PHGA) to...
Self-learning Road Detection with Stereo Vision Ozutemiz, Kadri Bugra; Hacinecipoglu, Akif; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (2013-04-26) It is a hard to solve problem to detect traversable or road regions especially in unstructured roads or paths. In mobile robot applications, robots usually enter these kinds of roads and regions. To successfully complete its mission, it is important to find roads in these environments reliably. In this paper a novel unstructured road detection algorithm with the capability of learning road regions continuously is proposed.
GIS-based evaluation of the speed limit increase on urban arterial traffic safety in Ankara Kibar, Funda Ture; Tüydeş Yaman, Hediye (Springer Science and Business Media LLC, 2020-06-14) Setting safe speed limit is very critical and complex phenomenon, which has to be decided based on the road hierarchy that categorizes roads according to their functions and capacities, and poses certain restrictions in the design process. However, this is challenging in urban regions of developing countries, where rapid city growth forces high-speed intercity roads to serve as urban arterials, along which traditional 50 km/h limit is not practically possible. To lower the speed variation (and provide mobil...
Spatio-Temporal Pedestrian Accident Analysis to Improve Urban Pedestrian Safety: The case of the Eskisehir Motorway Kaygisiz, Omur; Yildiz, Ahmet; Duzgun, Sebnem (2015-01-01) Determining pedestrian accident hotspots on road segments is a crucial part of the pedestrian safety assessment as it is used to prioritize problematic parts of a road network for in particularly planning and implementation strategies. Moreover, the spatial pattern of the pedestrian accidents may change over time due to several factors. In order to better understand pedestrian safety conditions, pedestrian accident patterns have to be analysed with regard to both space and time. This paper adapts such a spa...

Citation Formats

K. B. Özütemiz, “GPU-accelerated adaptive unstructured road detection using close range stereo vision,” M.S. - Master of Science, Middle East Technical University, 2013.