DeepRoadNet: A deep residual based segmentation network for road map detection from remote aerial image

Prerequisites and Run

This code has been implemented in python language using Keras library with tensorflow backend and tested.

Data

Download the Massachusets and Ottawa road datasets from this link https://www.cs.toronto.edu/~vmnih/data/.

EFF7+residualNET_Weights: https://drive.google.com/drive/folders/156OLmZ6ra0GbDIAT0Y92QLxxf9XkcKIu?usp=sharing

EFF6+residualNET_Weights: https://drive.google.com/file/d/1SBwDJJMPKtDf75TzwKYPrRfndmOQuh1H/view?usp=drive_link

EFF5+residualNET_Weights: https://drive.google.com/file/d/1_ISBCTMhIGr8xUAoR_113TS8lxaMDsxd/view?usp=sharing

EFF4+residualNET_Weights: https://drive.google.com/file/d/1M4tp8Hg5x_5SxUqwI1gtpE66S1aqBwGL/view?usp=sharing

EFF0+residualNET_Weights: https://drive.google.com/file/d/1txvg898aF_IM3XkcbXMKt7kQNsTSsATT/view?usp=sharing

Cite this paper:

Ahmed, M.I., Foysal, M., Chaity, M.D., Hossain, A.B.M.A.: DeepRoadNet: A deep residual based segmentation network for road map detection from remote aerial image. IET Image Process. 00, 1–15 (2023). DOI: https://doi.org/10.1049/ipr2.12948