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

Keypoint detection and description play a pivotal role in various roboticsand autonomous applications including visual odometry (VO), visual navigation,and Simultaneous localization and mapping (SLAM). While a myriad of keypointdetectors and descriptors have been extensively studied in conventional cameraimages, the effectiveness of these techniques in the context of LiDAR-generatedimages, i.e. reflectivity and ranges images, has not been assessed. Theseimages have gained attention due to their resilience in adverse conditions suchas rain or fog. Additionally, they contain significant textural informationthat supplements the geometric information provided by LiDAR point clouds inthe point cloud registration phase, especially when reliant solely on LiDARsensors. This addresses the challenge of drift encountered in LiDAR Odometry(LO) within geometrically identical scenarios or where not all the raw pointcloud is informative and may even be misleading. This paper aims to analyze theapplicability of conventional image key point extractors and descriptors onLiDAR-generated images via a comprehensive quantitative investigation.Moreover, we propose a novel approach to enhance the robustness and reliabilityof LO. After extracting key points, we proceed to downsample the point cloud,subsequently integrating it into the point cloud registration phase for thepurpose of odometry estimation. Our experiment demonstrates that the proposedapproach has comparable accuracy but reduced computational overhead, higherodometry publishing rate, and even superior performance in scenarios prone todrift by using the raw point cloud. This, in turn, lays a foundation forsubsequent investigations into the integration of LiDAR-generated images withLO. Our code is available on GitHub:https://github.com/TIERS/ws-lidar-as-camera-odom.

LiDAR-Generated Images Derived Keypoints Assisted Point Cloud Registration Scheme in Odometry Estimation