A Lightweight Road Detection Algorithm Based on Multiscale Convolutional Attention Network and Coupled Decoder Head

Automatic road detection from remote sensing images has always been a significant research topic. It is of great value to many practical applications. However, there are still some problems that need to be solved. First, most of the existing road detection methods are inefficient because of sequenti...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2023, Vol.20, p.1-5
Main Authors: Liu, Dongyang, Zhang, Junping, Qi, Yunxiao, Zhang, Ye
Format: Article
Language:English
Subjects:
Algorithms
Burrs
Detection
Feature extraction
Lightweight
Methods
Occlusion
Receptive field
Remote sensing
Road surface
Roads
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic road detection from remote sensing images has always been a significant research topic. It is of great value to many practical applications. However, there are still some problems that need to be solved. First, most of the existing road detection methods are inefficient because of sequential processing of the decoder head. Second, some existing methods are unable to detect occluded road areas effectively. For this reason, we focus on the speed and occlusion problems in road detection network and propose a new lightweight road detection method based on multiscale convolutional attention network (MSCAN) and coupled decoder head, LRDNet. In particular, LRDNet adopts MSCAN with large receptive field for feature extraction to solve the occlusion problem and decode the road surface, road edge, and road centerline in a coupled way to improve the speed of road detection and ensure that the road surface detection results have fewer burrs at the road edge. We have performed several experiments on the RoadNet benchmark dataset (RNBD). Compared with some state-of-the-art methods, the experimental results prove the validity of the proposed LRDNet. The code will be released soon on the site of https://github.com/dyl96/LRDNet .
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2023.3266054