· 2018
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
- 929citations
- 2018year
Short summary
D-LinkNet, a semantic segmentation network, achieved IoU scores of 0.6466 (validation) and 0.6342 (test) in the CVPR DeepGlobe 2018 Road Extraction Challenge by incorporating dilated convolutions and a pretrained encoder into the LinkNet architecture.
AI-generated from the title and abstract; the full text is not read.
Key points
- D-LinkNet is a semantic segmentation neural network designed for road extraction from satellite imagery.
- It utilizes a LinkNet architecture with dilated convolution layers in its central part.
- Dilated convolutions expand the receptive field without reducing feature map resolution.
- The network achieved IoU scores of 0.6466 (validation) and 0.6342 (test) in the CVPR DeepGlobe 2018 Road Extraction Challenge.
AI-generated from the title and abstract; the full text is not read.
Abstract
Road extraction is a fundamental task in the field of remote sensing which has been a hot research topic in the past decade. In this paper, we propose a semantic segmentation neural network, named D-LinkNet, which adopts encoderdecoder structure, dilated convolution and pretrained encoder for road extraction task. The network is built with LinkNet architecture and has dilated convolution layers in its center part. Linknet architecture is efficient in computation and memory. Dilation convolution is a powerful tool that can enlarge the receptive field of feature points without reducing the resolution of the feature maps. In the CVPR DeepGlobe 2018 Road Extraction Challenge, our best IoU scores on the validation set and the test set are 0.6466 and 0.6342 respectively.
The authors' abstract, as published at the source., 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Ocean Engineering
Ocean EngineeringEngineering