dc.contributor.author |
Hasan, Md Mahbub |
|
dc.date.accessioned |
2020-03-05T11:20:00Z |
|
dc.date.available |
2020-03-05T11:20:00Z |
|
dc.date.issued |
2019-12 |
|
dc.identifier.uri |
http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/3802 |
|
dc.description.abstract |
Road surface monitoring is mostly done manually in cities Being an intensive process of time consuming and labor work. The intention of this paper is to research on road damage detection
and classification from road surface images using object detection method. this paper applied multiple convolutional neural network (CNN) algorithm to classify road damage and find out which algorithm perform better in road damage detection and classification. We classify damages in three categories pothole, crack and revealing. For this work we collected data from street of Dhaka city using smartphone camera and prepossessed the data like image resize, white balance, contrast transformation, labeling. Our study applies R-CNN and faster R-CNN for object detection of road damages and apply Support vector Machine (SVM) for classification and gets a better result from previous study. We calculated loses using different loss function. We got the highest 99.08 % accuracy and the lowest loss is 0. |
en_US |
dc.language.iso |
en_US |
en_US |
dc.publisher |
Daffodil International University |
en_US |
dc.relation.ispartofseries |
;P15037 |
|
dc.subject |
Software engineering |
en_US |
dc.subject |
Road surface monitoring |
en_US |
dc.title |
Detection and Classification of Road Damage Using R-CNN and Faster R-CNN: A Deep Learning Approach |
en_US |
dc.type |
Other |
en_US |