Pavement crack detection is an important procedure in road maintenanceand traffic safety. Traditionally, the road inventory was performed by field inspection, now it is replaced by the evaluation of mobile mapping system images. The acquired images are still a significant source of temporal condition of thepavement surface. The automatisation of crack detection is highly necessarybecause it could decrease workload, and therefore, maintenance costs. Two methods for automatic crack detection from mobile mapping imageswere tested: step by step pixel based image intensity analysis, and deep learning. The objective of this thesis is to develop and test the workflow for the streetview image crack detection and reduce image database by detecting no-cracksurfaces. To examine the performance of the methods, their classification precisionwas compared. The best-acquired precision with the trained deep learningmodel was 98% that is 3% better than with the other method and it suggeststhat the deep learning is the most appropriate for the application. Furthermore, there is a need for faster and more precise detection methods, and deep learningholds promise for the further implementation. However, future studies areneeded and they should focus on full-scale image crack detection, disturbingobject elimination and crack severity classification.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-189245 |
| Date | January 2016 |
| Creators | Some, Liene |
| Publisher | KTH, Geodesi och satellitpositionering |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | TRITA-GIT EX ; 16-011 |
Page generated in 0.0023 seconds