English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Road detection based on remote sensing images is of great significance tointelligent traffic management. The performances of the mainstream roaddetection methods are mainly determined by their extracted features, whoserichness and robustness can be enhanced by fusing features of different typesand cross-layer connections. However, the features in the existing mainstreammodel frameworks are often similar in the same layer by the single-tasktraining, and the traditional cross-layer fusion ways are too simple to obtainan efficient effect, so more complex fusion ways besides concatenation andaddition deserve to be explored. Aiming at the above defects, we propose adual-task network (DTnet) for road detection and cross-layer graph fusionmodule (CGM): the DTnet consists of two parallel branches for road area andedge detection, respectively, while enhancing the feature diversity by fusingfeatures between two branches through our designed feature bridge modules(FBM). The CGM improves the cross-layer fusion effect by a complex featurestream graph, and four graph patterns are evaluated. Experimental results onthree public datasets demonstrate that our method effectively improves thefinal detection result.

Road Detection via a Dual-Task Network Based on Cross-Layer Graph Fusion Modules