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

Unreliable feature extraction and matching in handcrafted features underminethe performance of visual SLAM in complex real-world scenarios. While learnedlocal features, leveraging CNNs, demonstrate proficiency in capturinghigh-level information and excel in matching benchmarks, they encounterchallenges in continuous motion scenes, resulting in poor generalization andimpacting loop detection accuracy. To address these issues, we present DK-SLAM,a monocular visual SLAM system with adaptive deep local features. MAMLoptimizes the training of these features, and we introduce a coarse-to-finefeature tracking approach. Initially, a direct method approximates the relativepose between consecutive frames, followed by a feature matching method forrefined pose estimation. To counter cumulative positioning errors, a novelonline learning binary feature-based online loop closure module identifies loopnodes within a sequence. Experimental results underscore DK-SLAM's efficacy,outperforms representative SLAM solutions, such as ORB-SLAM3 on publiclyavailable datasets.

DK-SLAM: Monocular Visual SLAM with Deep Keypoints Adaptive Learning, Tracking and Loop-Closing