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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Robust road segmentation is a key challenge in self-driving research. Thoughmany image-based methods have been studied and high performances in datasetevaluations have been reported, developing robust and reliable roadsegmentation is still a major challenge. Data fusion across different sensorsto improve the performance of road segmentation is widely considered animportant and irreplaceable solution. In this paper, we propose a novelstructure to fuse image and LiDAR point cloud in an end-to-end semanticsegmentation network, in which the fusion is performed at decoder stage insteadof at, more commonly, encoder stage. During fusion, we improve the multi-scaleLiDAR map generation to increase the precision of the multi-scale LiDAR map byintroducing pyramid projection method. Additionally, we adapted the multi-pathrefinement network with our fusion strategy and improve the road predictioncompared with transpose convolution with skip layers. Our approach has beentested on KITTI ROAD dataset and has competitive performance.

Road Segmentation with Image-LiDAR Data Fusion