Road Extraction from Aerial Images
dc.contributor.author | Sirefelt, Rickard | |
dc.contributor.department | Chalmers tekniska högskola / Institutionen för tillämpad mekanik | sv |
dc.contributor.department | Chalmers University of Technology / Department of Applied Mechanics | en |
dc.date.accessioned | 2019-07-03T13:49:10Z | |
dc.date.available | 2019-07-03T13:49:10Z | |
dc.date.issued | 2015 | |
dc.description.abstract | Road extraction from aerial images is essential to everyday life having several useful application in for example urban planning and automotive navigation. Roads are currently extracted using methods that requires a lot of manual work conducted by humans which is both time consuming and error prone. The aim of this thesis is to develop a robust algorithm that can automatically extract roads from aerial images. It was concluded, based on a literature review, that the most suitable method for automatic road extraction is a machine learning approach based on stacked convolutional neural networks. The method was implemented and evaluated against four different road images in the vicinity of the motorway E6 in southern Sweden. The best network achieved a recall of 0.845, precision of 0.878 and quality of 0.760 over a test set of previously unseen images. Considering that the method used was relatively simple, the result is to be considered competitive compared to other published works. | |
dc.identifier.uri | https://hdl.handle.net/20.500.12380/223677 | |
dc.language.iso | eng | |
dc.relation.ispartofseries | Diploma work - Department of Applied Mechanics, Chalmers University of Technology, Göteborg, Sweden : 2015:82 | |
dc.setspec.uppsok | Technology | |
dc.subject | Annan maskinteknik | |
dc.subject | Other Mechanical Engineering | |
dc.title | Road Extraction from Aerial Images | |
dc.type.degree | Examensarbete för masterexamen | sv |
dc.type.degree | Master Thesis | en |
dc.type.uppsok | H | |
local.programme | Complex adaptive systems (MPCAS), MSc |
Ladda ner
Original bundle
1 - 1 av 1
Hämtar...
- Namn:
- 223677.pdf
- Storlek:
- 3.09 MB
- Format:
- Adobe Portable Document Format
- Beskrivning:
- Fulltext