Experimental implementation of loop closure detection using data dimensionality reduction by spectral method

Moreira, Leandro Arantes; Justel, Cláudia Marcela; Rosa, Paulo Fernando Ferreira

doi:10.1109/icit.2017.7915461

Cited by 1 publication

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that none of these studies uses spectral methods to analyze the loop closure problem, such as it is done in ref. [26]. In that paper, the concept of dominant eigenvector is employed as an image spectral descriptor, and a data dimensionality reduction method 5 is used to detect loop closures in batch mode.…”

Section: Visual Analysis Techniques and Loop Closurementioning

confidence: 99%

“…In this paper, we extend the approach from ref. [26] to perform experiments in real and simulated environments with incremental method, through the combination of sliding window and coordinate transformation concepts.…”

Section: Visual Analysis Techniques and Loop Closurementioning

confidence: 99%

“…The representation in low dimension (s = 3) obtained after applying Diffusion Maps to New College dataset, the matrix representation of detected loop closures by our method and the processing times for this dataset are shown in details in ref. [26].…”

Section: Phase C: Loop Closure In Low Dimensionmentioning

confidence: 99%

See 2 more Smart Citations

Development of a Method for Data Dimensionality Reduction in Loop Closure Detection: An Incremental Approach

Moreira¹,

Justel²,

Oliveira³

et al. 2020

Robotica

Self Cite

View full text Add to dashboard Cite

SUMMARY This article proposes a method for incremental data dimensionality reduction in loop closure detection for robotic autonomous navigation. The approach uses dominant eigenvector concept for: (a) spectral description of visual datasets and (b) representation in low dimension. Unlike most other papers on data dimensionality reduction (which is done in batch mode), our method combines a sliding window technique and coordinate transformation to achieve dimensionality reduction in incremental data. Experiments in both simulated and real scenarios were performed and the results are suitable.

show abstract

Section: Visual Analysis Techniques and Loop Closurementioning

confidence: 99%

Section: Visual Analysis Techniques and Loop Closurementioning

confidence: 99%