mlsanityData to 14 Oct 2026

LSGDDN-LCD: An Appearance-based Loop Closure Detection using Local Superpixel Grid Descriptors and Incremental Dynamic Nodes

arXiv 2304.03872 ↗First posted 8 Apr 2023cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Loop Closure Detection (LCD) is an essential component of visual simultaneous localization and mapping (SLAM) systems. It enables the recognition of previously visited scenes to eliminate pose and map estimate drifts arising from long-term exploration. However, current appearance-based LCD methods face significant challenges, including high computational costs, viewpoint variance, and dynamic objects in scenes. This paper introduced an online appearance based LCD using local superpixel grids descriptor and dynamic node, i.e, LSGDDN-LCD, to find similarities between scenes via hand-crafted features extracted from LSGD. Unlike traditional Bag-of-Words (BoW) based LCD, which requires pre-training, we proposed an adaptive mechanism to group similar images called textbftextitdynamic textbftextitnode, which incrementally adjusted the database in an online manner, allowing for efficient and online retrieval of previously viewed images without need of the pre-training. Experimental results confirmed that the LSGDDN-LCD significantly improved LCD precision-recall and efficiency, and outperformed several state-of-the-art (SOTA) approaches on multiple typical datasets, indicating its great potential as a generic LCD framework.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 76 references that are in the map. First posted on arXiv 8 Apr 2023.

Builds on

21 of 76 references.

References · 21

  1. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  3. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  4. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  5. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  6. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 423
  7. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  8. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 161
  9. 2018DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenescited by 134
  10. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  11. 2018MAGSAC: marginalizing sample consensuscited by 123
  12. 2022The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detectioncited by 29
9 more
  1. 2018iBoW-LCD: An Appearance-based Loop Closure Detection Approach using Incremental Bags of Binary Wordscited by 20
  2. 2021AirLoop: Lifelong Loop Closure Detectioncited by 11
  3. 2018Joint detection and matching of feature points in multimodal imagescited by 10
  4. 2020Online Visual Place Recognition via Saliency Re-identificationcited by 9
  5. 2020Fast and Incremental Loop Closure Detection with Deep Features and Proximity Graphscited by 6
  6. 2019Fast and Incremental Loop Closure Detection Using Proximity Graphscited by 5
  7. 2018HBST: A Hamming Distance embedding Binary Search Tree for Visual Place Recognitioncited by 4
  8. 2019Robust Photogeometric Localization over Time for Map-Centric Loop Closurecited by 3
  9. 2022DynPL-SVO: A Robust Stereo Visual Odometry for Dynamic Scenescited by 3

Built on by

Not cited yet.