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

Although traffic sign detection has been studied for years and great progresshas been made with the rise of deep learning technique, there are still manyproblems remaining to be addressed. For complicated real-world traffic scenes,there are two main challenges. Firstly, traffic signs are usually small sizeobjects, which makes it more difficult to detect than large ones; Secondly, itis hard to distinguish false targets which resemble real traffic signs incomplex street scenes without context information. To handle these problems, wepropose a novel end-to-end deep learning method for traffic sign detection incomplex environments. Our contributions are as follows: 1) We propose amulti-resolution feature fusion network architecture which exploits denselyconnected deconvolution layers with skip connections, and can learn moreeffective features for the small size object; 2) We frame the traffic signdetection as a spatial sequence classification and regression task, and proposea vertical spatial sequence attention (VSSA) module to gain more contextinformation for better detection performance. To comprehensively evaluate theproposed method, we do experiments on several traffic sign datasets as well asthe general object detection dataset and the results have shown theeffectiveness of our proposed method.

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection