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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate lane detection is critical for navigation in autonomous vehicles,particularly the active lane which demarcates the single road space that thevehicle is currently traveling on. Recent state-of-the-art lane detectionalgorithms utilize convolutional neural networks (CNNs) to train deep learningmodels on popular benchmarks such as TuSimple and CULane. While each of thesemodels works particularly well on train and test inputs obtained from the samedataset, the performance drops significantly on unseen datasets of differentenvironments. In this paper, we present a real-time robust neural networkoutput enhancement for active lane detection (RONELD) method to identify,track, and optimize active lanes from deep learning probability map outputs. Wefirst adaptively extract lane points from the probability map outputs, followedby detecting curved and straight lanes before using weighted least squareslinear regression on straight lanes to fix broken lane edges resulting fromfragmentation of edge maps in real images. Lastly, we hypothesize true activelanes through tracking preceding frames. Experimental results demonstrate an upto two-fold increase in accuracy using RONELD on cross-dataset validationtests.

RONELD: Robust Neural Network Output Enhancement for Active Lane Detection