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

Han, Junyu; Dong, Ruifang; Kan, Jiangming

doi:10.1002/rob.21992

Cited by 11 publications

(12 citation statements)

References 40 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have observed that this can be the result of wrong line detections between consecutive frames, which are due to the bad quality of the images and the corresponding perceptual aliasing that occurs among those lines, leading to a subsequent decrease in the pipeline performance. Notice that our proposal also outperforms (Gomez-Ojeda et al 2019;Han et al 2021), which are the solutions most similar to LiPo-LCD ++ , given that they are the only ones that combine points and lines for loop closure detection.…”

Section: Comparison With Other Solutionsmentioning

confidence: 89%

“…Some SLAM approaches (Pumarola et al 2017;Zhang et al 2019) have benefited from the combination of points and lines for image description. However, during the LCD stage, they only rely on point features, discarding line information that can be useful for some environments, unlike our approach (Company-Corcoles et al 2020), and others that adopt a dual scheme for LCD (Gomez-Ojeda et al 2019;Zuo et al 2017;Han et al 2021). Our approach resembles the idea of combining lines and points described in these works, though it differs in multiple aspects, such as (1) the point features that are employed, (2) how the visual vocabularies are built, (3) how image scores are calculated from the visual vocabularies and later combined, and (4) the spatial verification process.…”

Section: Related Workmentioning

confidence: 99%

“…As an alternative, the on-line approach builds the visual vocabulary incrementally, as the robot navigates, which helps to solve the aforementioned issues. A fusion strategy is additionally required to obtain a consolidated list of loop closure candidates when different sorts of features are involved, maybe by means of several BoW instances, one for each kind of feature (Zuo et al 2017;Gomez-Ojeda et al 2019;Han et al 2021).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Appearance-based loop closure detection combining lines and learned points for low-textured environments

2022

View full text Add to dashboard Cite

Hand-crafted point descriptors have been traditionally used for visual loop closure detection. However, in low-textured environments, it is usually difficult to find enough point features and, hence, the performance of such algorithms degrade. Under this context, this paper proposes a loop closure detection method that combines lines and learned points to work, particularly, in scenarios where hand-crafted points fail. To index previous images, we adopt separate incremental binary Bag-of-Words (BoW) schemes for points and lines. Moreover, we adopt a binarization procedure for features’ descriptors to benefit from the advantages of learned features into a binary BoW model. Furthermore, image candidates from each BoW instance are merged using a novel query-adaptive late fusion approach. Finally, a spatial verification stage, which integrates appearance and geometry perspectives, allows us to enhance the global performance of the method. Our approach is validated using several public datasets, outperforming other state-of-the-art solutions in most cases, especially in low-textured scenarios.

show abstract

Section: Comparison With Other Solutionsmentioning

confidence: 89%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Appearance-based loop closure detection combining lines and learned points for low-textured environments

2022

View full text Add to dashboard Cite

show abstract

“…Bampis et al (2016Bampis et al ( , 2018 combined the visual words' occurrences of sequence segments, that is, groups-of-images, to assist the matching process. Recently, points and lines were combined based on information entropy to realize accurate loop closure detection (Han et al, 2021).…”

Section: Approaches Using Hand-crafted Featuresmentioning

confidence: 99%

“…However, the noisy sensor measurements, modeling inaccuracies, and errors due to field abnormalities affect the performance of SLAM. Identifying known locations in the traversed route based on camera information to rectify the incremental pose drift is widely known as visual loop closure detection (Botterill et al, 2011;Han et al, 2021;Mei et al, 2010;Tsintotas, Bampis, & Gasteratos, 2018;Zhang, 2011). This operation is highly related to image retrieval, as the system tries to find the most similar visual entry within a visual database, which is explicitly built using camera measurements gathered along a trajectory.…”

Section: Introductionmentioning

confidence: 99%

Fast and incremental loop closure detection with deep features and proximity graphs

Zhu

Wei

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

In recent years, the robotics community has extensively examined methods concerning the place recognition task within the scope of simultaneous localization and mapping applications. This article proposes an appearance‐based loop closure detection pipeline named “Fast and Incremental Loop closure Detection (FILD++). First, the system is fed by consecutive images and, via passing them twice through a single convolutional neural network, global and local deep features are extracted. Subsequently, a hierarchical navigable small‐world graph incrementally constructs a visual database representing the robot's traversed path based on the computed global features. Finally, a query image, grabbed each time step, is set to retrieve similar locations on the traversed route. An image‐to‐image pairing follows, which exploits local features to evaluate the spatial information. Thus, in the proposed article, we propose a single network for global and local feature extraction in contrast to our previous work (FILD), while an exhaustive search for the verification process is adopted over the generated deep local features avoiding the utilization of hash codes. Exhaustive experiments on eleven publicly available data sets exhibit the system's high performance (achieving the highest recall score on eight of them) and low execution times (22.05 ms on average in New College, which is the largest one containing 52,480 images) compared to other state‐of‐the‐art approaches.

show abstract

Automatic vocabulary and graph verification for accurate loop closure detection

Yue

Miao

Chen

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

Localizing previously visited places during long‐term localization and mapping, that is, loop closure detection (LCD), is a crucial technique to correct accumulated inconsistencies. In common bag‐of‐words (BoW) model, a visual vocabulary is built to associate features for detecting loops. Currently, methods that build vocabularies off‐line determine scales of the vocabulary by trial‐and‐error, which results in unreasonable feature association. Moreover, the detection precision of the algorithm declines due to perceptual aliasing given that the BoW‐based method ignores the positions of visual features. To build the optimal vocabulary automatically and eliminate human heuristics, we propose a natural convergence criterion based on the comparison between the radii of nodes and the drifts of feature descriptors in vocabulary construction. Furthermore, a novel topological graph verification method is proposed for validating loop candidates, which can effectively distinguish visual ambiguities by involving geometrical position of features and thus improve the precision of LCD. Experiments on various public datasets verify the effectiveness of our proposed approach.

show abstract

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

Abstract: Visual simultaneous localization and mapping (visual-SLAM) is a prominent technology for autonomous navigation of mobile robots. As a significant requirement for visual-SLAM, loop closure detection (LCD) involves recognizing a revisited place,

Cited by 11 publications

References 40 publications

Appearance-based loop closure detection combining lines and learned points for low-textured environments

Appearance-based loop closure detection combining lines and learned points for low-textured environments

Fast and incremental loop closure detection with deep features and proximity graphs

Automatic vocabulary and graph verification for accurate loop closure detection

Contact Info

Product

Resources

About