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

LiDAR-based SLAM algorithms are extensively studied to providing robust andaccurate positioning for autonomous driving vehicles (ADV) in the past decades.Satisfactory performance can be obtained using high-grade 3D LiDAR with 64channels, which can provide dense point clouds. Unfortunately, the high pricesignificantly prevents its extensive commercialization in ADV. Thecost-effective 3D LiDAR with 16 channels is a promising replacement. However,only limited and sparse point clouds can be provided by the 16 channels LiDAR,which cannot guarantee sufficient positioning accuracy for ADV in challengingdynamic environments. The high-resolution image from the low-cost camera canprovide ample information about the surroundings. However, the explicit depthinformation is not available from the image. Inspired by the complementarinessof 3D LiDAR and camera, this paper proposes to make use of the high-resolutionimages from a camera to enrich the raw 3D point clouds from the low-cost 16channels LiDAR based on a state-of-the-art deep learning algorithm. An ERFNetis firstly employed to segment the image with the aid of the raw sparse 3Dpoint clouds. Meanwhile, the sparse convolutional neural network is employed topredict the dense point clouds based on raw sparse 3D point clouds. Then, thepredicted dense point clouds are fused with the segmentation outputs fromERFnet using a novel multi-layer convolutional neural network to refine thepredicted 3D point clouds. Finally, the enriched point clouds are employed toperform LiDAR SLAM based on the state-of-the-art normal distribution transform(NDT). We tested our approach on the re-edited KITTI datasets: (1)the sparse 3Dpoint clouds are significantly enriched with a mean square error of 1.1m MSE.(2)the map generated from the LiDAR SLAM is denser which includes more detailswithout significant accuracy loss.

LiDAR Data Enrichment Using Deep Learning Based on High-Resolution Image: An Approach to Achieve High-Performance LiDAR SLAM Using Low-cost LiDAR