SOTAVerified

Road Segmentation

Road Segmentation is a pixel wise binary classification in order to extract underlying road network. Various Heuristic and data driven models are proposed. Continuity and robustness still remains one of the major challenges in the area.

Papers

Showing 76–82 of 82 papers

TitleStatusHype
Distantly Supervised Road Segmentation—0
Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields—0
An Enhanced Deep Convolutional Encoder-Decoder Network for Road Segmentation on Aerial Imagery—0
HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images—0
Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery—0
On the Diagnostic of Road Pathway Visibility—0
Accurate Urban Road Centerline Extraction from VHR Imagery via Multiscale Segmentation and Tensor Voting—0
Show:102550
← PrevPage 4 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1U-Net (ResNet-18)DWR46.5—Unverified
2DeepLabV3+ (ResNet-18)DWR46.1—Unverified
3U-Net (ResNet-50)DWR45.7—Unverified
4FCNDWR10.7—Unverified
#ModelMetricClaimedVerifiedStatus
1CoANet + PRNmIoU70.6—Unverified
2SPIN Road Mapper (ours)APLS0.74—Unverified
3D-LinkNetIoU0.64—Unverified
#ModelMetricClaimedVerifiedStatus
1RSM-SSIoU67.35—Unverified
2SPIN Road Mapper (ours)IoU65.24—Unverified