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

Loop closure, as one of the crucial components in SLAM, plays an essentialrole in correcting the accumulated errors. Traditional appearance-basedmethods, such as bag-of-words models, are often limited by local 2D featuresand the volume of training data, making them less versatile and robust inreal-world scenarios, leading to missed detections or false positivesdetections in loop closure. To address these issues, we first propose aobject-level data association method based on multi-level verification, whichcan associate 2D semantic features of current frame with 3D objects landmarksof map. Next, taking advantage of these association relations, we introduce asemantic loop closure method based on quadric-level object map topology, whichrepresents scenes through the topological graph of objects and achievesaccurate loop closure at a wide field of view by comparing differences in thetopological graphs. Finally, we integrate these two methods into a completeobject-aware SLAM system. Qualitative experiments and ablation studiesdemonstrate the effectiveness and robustness of the proposed object-level dataassociation algorithm. Quantitative experiments show that our semantic loopclosure method outperforms existing state-of-the-art methods in terms ofprecision, recall and localization accuracy metrics.

SemanticTopoLoop: Semantic Loop Closure With 3D Topological Graph Based on Quadric-Level Object Map