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

Unmanned Aerial Vehicles (UAVs) hold immense potential for criticalapplications, such as search and rescue operations, where accurate perceptionof indoor environments is paramount. However, the concurrent amalgamation oflocalization, 3D reconstruction, and semantic segmentation presents a notablehurdle, especially in the context of UAVs equipped with constrained power andcomputational resources. This paper presents a novel approach to addresschallenges in semantic information extraction and utilization within UAVoperations. Our system integrates state-of-the-art visual SLAM to estimate acomprehensive 6-DoF pose and advanced object segmentation methods at the backend. To improve the computational and storage efficiency of the framework, weadopt a streamlined voxel-based 3D map representation - OctoMap to build aworking system. Furthermore, the fusion algorithm is incorporated to obtain thesemantic information of each frame from the front-end SLAM task, and thecorresponding point. By leveraging semantic information, our framework enhancesthe UAV's ability to perceive and navigate through indoor spaces, addressingchallenges in pose estimation accuracy and uncertainty reduction. ThroughGazebo simulations, we validate the efficacy of our proposed system andsuccessfully embed our approach into a Jetson Xavier AGX unit for real-worldapplications.

S3M: Semantic Segmentation Sparse Mapping for UAVs with RGB-D Camera