12508

11445

كارشناسي ارشد

هوش مصنوعي و رباتيك

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1396

سيزده، 67ص.: مصور، جدول، نمودار

ص. ع. به فارسي و انگليسي

مازيار پالهنگ

داور اختياري: عبدالرضا ميرزايي، مهران صفاياني

1396/04/12

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

ID11445

Vision Based Road Intersection Detection Using a Single Color Camera Bahram Salamat Ravandi b salamat@ec iut ac ir Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Assoc Prof Maziar Palhang palhang@cc iut ac ir Abstract Autonomous driving has become the focus of automatic navigation in recent years Automotiveand military seek benefit of this research area for their purposes Automatic navigation include manyaspects one of key aspect is the localization ability on road network Any information including stopsigns road lines and road intersects can aid this localization The work here attempt to develope arobust and efficent roads and junctions on road networks using computer vision methods by a singlecolor camera mounted on top of a vehicle a single color camera plus to econonmical reasons giveenough information of Environment Established methods mostly use combination of sensors which cost high A few methods use monoc ular camera these methods suffer from assumptions which result in less generality in detection Thiswork here use a combination of color texture coordinate and perspective features of roads image so lead to less assumptions and subsequently more generality to detection purpose also efficiencyand robustness The use of clustering method based on colors and cordinate feature alongside of tex ture feature made a robust method the results of experiment show robustness in conditions such asshadowy ill structured and non paved roads Key Words Machine vision Urban driving Autonomous navigation Road detection

مازيار پالهنگ

داور اختياري: عبدالرضا ميرزايي، مهران صفاياني