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

Freespace detection is an essential component of visual perception forself-driving cars. The recent efforts made in data-fusion convolutional neuralnetworks (CNNs) have significantly improved semantic driving scenesegmentation. Freespace can be hypothesized as a ground plane, on which thepoints have similar surface normals. Hence, in this paper, we first introduce anovel module, named surface normal estimator (SNE), which can infer surfacenormal information from dense depth/disparity images with high accuracy andefficiency. Furthermore, we propose a data-fusion CNN architecture, referred toas RoadSeg, which can extract and fuse features from both RGB images and theinferred surface normal information for accurate freespace detection. Forresearch purposes, we publish a large-scale synthetic freespace detectiondataset, named Ready-to-Drive (R2D) road dataset, collected under differentillumination and weather conditions. The experimental results demonstrate thatour proposed SNE module can benefit all the state-of-the-art CNNs for freespacedetection, and our SNE-RoadSeg achieves the best overall performance amongdifferent datasets.

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection