Assigning Visual Words to Places for Loop Closure Detection

Tsintotas, Konstantinos A.; Bampis, Loukas; Γαστεράτος, Αντώνιος

doi:10.1109/icra.2018.8461146

Cited by 64 publications

(48 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To measure the correctness of our results, we compare them with a provided ground-truth (GT). GT is a binary matrix, whose rows and columns correspond to images at different timestamps (Tsintotas et al, 2018). When GT ij = 1, there is a loop closure event.…”

Section: Ground-truthmentioning

confidence: 99%

“…Considering the approach of creating a BoVW, these appearance‐based methods can be divided into two categories: off‐line and on‐line (Tsintotas et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

“…Finally, a true loop can be detected by utilizing a likelihood function and temporal consistency checks. Tsintotas et al (2018) presents a new approach, assigning visual words to particular places, and assigns VWs through the usage of an on‐line clustering algorithm called GNN (Fritzke, 1994) for a place. The loop closing candidate place is identified by voting and a probability function.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A novel loop closure detection method with the combination of points and lines based on information entropy

Han

Dong

Kan

2020

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

Section: Ground-truthmentioning

confidence: 99%

“…Considering the approach of creating a BoVW, these appearance‐based methods can be divided into two categories: off‐line and on‐line (Tsintotas et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A novel loop closure detection method with the combination of points and lines based on information entropy

Han

Dong

Kan

2020

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…Other approaches that belong to this category were real-time appearance-based mapping (RTAB-Map) using SURF features [19] and appearancebased Loop Closure Detection Approach using Incremental Bags of Binary Words (iBow-LCD) [20]. Tsintotas et al [21] presented a real-time loop closure detection approach based on the on-line clustering of Visual Words (VWs) without the requirement of a pre-trained procedure.…”

Section: A Hand-crafted Representation For Loop Closure Detectionmentioning

confidence: 99%

Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments

Wang

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Detecting loop closures in dynamic environments is a severe challenge for the simultaneous localization and mapping (SLAM) system. Convolutional neural networks (ConvNet) could provide high-level and abstract representations extracted directly from images as image descriptors. Some novel ConvNet-based methods have been presented. In dynamic environments, they perform better than the stateof-the-art methods which use hand-crafted features. In this paper, (1) We proposed a flexible loop closure detection workflow based on the holistic representations; (2) In this workflow, a post-processing method is applied to the raw holistic ConvNet representations for redundant information compression; (3) In addition, a compression ratio is introduced in (2) to determine how much information will be retained depending on background change and moving objects. We evaluated our workflow in four open datasets. The experimental results demonstrate that the proposed workflow performs better than many state-of-the-art methods and ConvNet-based approaches. INDEX TERMS Loop closure detection, holistic representations descriptors, convolutional neural network, compression algorithms.

show abstract

“…requires a re-training step whenever the environment changes with regard to the available, pre-trained visual vocabulary. To overcome this shortcoming, our proposal adopts an incremental dictionary-based approach [1]- [3], [11], [12] that avoids the pre-training. Furthermore, to solve the unavoidable spatial verification process for loop hypothesis validation, our solution relies only on 2D image data, contrary to other studies that require 3D information supplied by either a stereo camera or a previous mapping process [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Towards Robust Loop Closure Detection in Weakly Textured Environments using Points and Lines

Company-Corcoles

Garcia-Fidalgo

Ortiz

2020

2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

View full text Add to dashboard Cite

SLAM approaches rely on loop closure strategies to avoid and/or correct the inconsistencies in the resulting map. These inconsistencies are mainly caused by the effect of sensor noise in odometry sources. For the case of visual SLAM, loop detection typically rely on the repetitive detection and matching of texture-based keypoints. Weakly textured environments, however, can lead to scenes lacking these kind of points and, hence, poor-performing loop detectors. An alternative for these environments is the use of geometrical cues such as line segments, which are frequently present within human-made, structured environments. Under this context, in this work, we introduce a novel appearance-based loop closure detection method that integrates lines and points to enhance performance in these scenarios. For this purpose, we build an incremental Bag-of-Binary-Words scheme for each visual cue to retrieve previously seen images from the two complementary perspectives. Furthermore, we rely on a late fusion strategy to combine the image candidates resulting for both visual vocabularies. An effective mechanism to group similar images close in time is applied next to reduce the effort of the image candidate search. Finally, we propose a novel scheme to validate geometrically the loop candidates, integrating lines into the procedure. The proposed approach compares favourably with other state-of-the-art methods for several datasets.

show abstract

Assigning Visual Words to Places for Loop Closure Detection

Cited by 64 publications

References 21 publications

A novel loop closure detection method with the combination of points and lines based on information entropy

A novel loop closure detection method with the combination of points and lines based on information entropy

Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments

Towards Robust Loop Closure Detection in Weakly Textured Environments using Points and Lines

Contact Info

Product

Resources

About