Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection

no code implementations • 12 Dec 2023 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jorg S. Wicker

With the advancement in robotics, it is becoming increasingly common for large factories and warehouses to incorporate visual SLAM (vSLAM) enabled automated robots that operate closely next to humans.

Loop Closure Detection

Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes

no code implementations • 24 Sep 2022 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jörg S. Wicker

However, they are unable to exploit spatial information of local visual features and lack a structure that unifies semantic objects and visual features, therefore limiting the symbiosis between the two components.

Graph Matching Loop Closure Detection +1

SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words

no code implementations • 21 Oct 2021 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jörg S. Wicker

Many state-of-the-art loop closure detection (LCD) algorithms use visual Bag-of-Words (vBoW), which is robust against partial occlusions in a scene but cannot perceive the semantics or spatial relationships between feature points.

Loop Closure Detection Simultaneous Localization and Mapping