Road detection via a dual-task network based on cross-layer graph fusion modules

TL;DR

This paper introduces a dual-task network with a novel cross-layer graph fusion module for improved road detection in remote sensing images, enhancing feature diversity and fusion effectiveness to achieve better detection accuracy.

Contribution

It proposes a dual-task network with a new cross-layer graph fusion module, addressing limitations of existing feature fusion methods in road detection.

Findings

Improved detection accuracy on three public datasets.

Effective feature fusion through complex graph patterns.

Enhanced feature diversity via dual-task architecture.

Abstract

Road detection based on remote sensing images is of great significance to intelligent traffic management. The performances of the mainstream road detection methods are mainly determined by their extracted features, whose richness and robustness can be enhanced by fusing features of different types and cross-layer connections. However, the features in the existing mainstream model frameworks are often similar in the same layer by the single-task training, and the traditional cross-layer fusion ways are too simple to obtain an efficient effect, so more complex fusion ways besides concatenation and addition deserve to be explored. Aiming at the above defects, we propose a dual-task network (DTnet) for road detection and cross-layer graph fusion module (CGM): the DTnet consists of two parallel branches for road area and edge detection, respectively, while enhancing the feature diversity by fusing features between two branches through our designed feature bridge modules (FBM). The CGM improves the cross-layer fusion effect by a complex feature stream graph, and four graph patterns are evaluated. Experimental results on three public datasets demonstrate that our method effectively improves the final detection result.