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

Tracking and modeling unknown rigid objects in the environment play a crucialrole in autonomous unmanned systems and virtual-real interactive applications.However, many existing Simultaneous Localization, Mapping and Moving ObjectTracking (SLAMMOT) methods focus solely on estimating specific object poses andlack estimation of object scales and are unable to effectively track unknownobjects. In this paper, we propose a novel SLAM backend that unifies ego-motiontracking, rigid object motion tracking, and modeling within a jointoptimization framework. In the perception part, we designed a pixel-levelasynchronous object tracker (AOT) based on the Segment Anything Model (SAM) andDeAOT, enabling the tracker to effectively track target unknown objects guidedby various predefined tasks and prompts. In the modeling part, we present anovel object-centric quadric parameterization to unify both static and dynamicobject initialization and optimization. Subsequently, in the part of objectstate estimation, we propose a tightly coupled optimization model for objectpose and scale estimation, incorporating hybrids constraints into a novel dualsliding window optimization framework for joint estimation. To our knowledge,we are the first to tightly couple object pose tracking with light-weightmodeling of dynamic and static objects using quadric. We conduct qualitativeand quantitative experiments on simulation datasets and real-world datasets,demonstrating the state-of-the-art robustness and accuracy in motion estimationand modeling. Our system showcases the potential application of objectperception in complex dynamic scenes.

UniQuadric: A SLAM Backend for Unknown Rigid Object 3D Tracking and Light-Weight Modeling