LiDAR Iris for Loop-Closure Detection

Wang, Ying; Sun, Zezhou; Xu, Cheng‐Zhong; Sarma, Sanjay E.; Yang, Jian; Kong, Hui

doi:10.1109/iros45743.2020.9341010

Cited by 132 publications

(67 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our L3D-based loop detection approach outperforms the state-of-the-art methods OverlapNet [10] and LiDAR Iris [8], which are validated using the LiDAR point clouds from the KITTI odometry dataset [19] 1 . We use the same evaluation strategy presented in OverlapNet [10].…”

Section: Introductionmentioning

confidence: 73%

“…While in 2D one can use visual representations extracted from keyframe images based on, e.g., bags of binary words [3], [4] or fern-based bag of words [2], [5], to detect loops, in 3D one can match geometric or semantic representations between pairs of point clouds across time [6]- [10]. Representations can be built by aggregating local geometric information [6] or by globally encoding the whole point cloud into a signature [7], [8], [10], [11]. Local geometries can be encoded as bag-of-words, extracted from randomly sampled 3D points and matched through similarity Vision (TeV) Unit, Fondazione Bruno Kessler, Italy, poiesi@fbk.eu measures (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…L2 norm) [6]. Global methods often exploit the 2D projections of point clouds, and quantify the overlap of two point clouds using either handcrafted measures [7], [8], or via a deep neural network [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Loop closure detection using local 3D deep descriptors

Zhou¹,

Wang²,

Poiesi³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learned from data using a deep learning algorithm. We propose a novel overlap measure for loop detection by computing the metric error between points that correspond to mutually-nearest-neighbour descriptors after registering the loop candidate point cloud by its estimated relative pose. This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps. We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-theart loop closure detection accuracy. Additionally, we embed our loop closure approach in RESLAM, a recent edge-based SLAM system, and perform the evaluation on real-world RGBD-TUM and synthetic ICL datasets. Our approach enables RESLAM to achieve a better localisation accuracy compared to its original loop closure strategy.

show abstract

Section: Introductionmentioning

confidence: 73%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Loop closure detection using local 3D deep descriptors

Zhou¹,

Wang²,

Poiesi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Yan et al [42] propose a sparse semantic map building method and utilize the semantic map to generate special texture features for scene recognition. LiDAR-Iris [25] generates a global descriptor based on a binary signature image obtained from the point cloud. DELIGHT [26] leverages LiDAR intensity information and encodes the information into a representative descriptor.…”

Section: Related Workmentioning

confidence: 99%

WADE-Net: Weighted Aggregation with Density Estimation for Point Cloud Place Recognition

Liu¹,

Wang²,

Peng³

et al. 2021

APM

View full text Add to dashboard Cite

Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly, to preserve the prior distributions and local geometric structures, we fuse learned hidden features with handcrafted features in the beginning. Secondly, we further extract and aggregate adaptively weighted features concerning density and relative spatial information from these fused features, named Weighted Aggregation with Density Estimation (WADE) module. Then, we conduct the WADE block iteratively to group the latent manifold structures. Finally, comparison results on two public datasets Oxford Robotcar and KITTI show that the proposed approach exceeds the comparison approaches on recall rate averagely 7% -8%.

show abstract

“…Compared with matching the visual observations or raw point clouds, this manner will greatly decrease the computational complexity. A lot of existing point cloud feature description approaches can be used to obtain D i , including the traditional approaches (Dubé et al , 2017; Wang et al , 2020) and learning-based ones (Liu et al , 2019; Suo et al , 2020). In this paper, we use the LPD-Net presented in our previous work (Liu et al , 2019) to generate the place descriptor.…”

Section: System Designmentioning

confidence: 99%

Map-less long-term localization in complex industrial environments

Liu

Qiao

Suo

et al. 2021

View full text Add to dashboard Cite

Purpose This paper aims to study the localization problem for autonomous industrial vehicles in the complex industrial environments. Aiming for practical applications, the pursuit is to build a map-less localization system which can be used in the presence of dynamic obstacles, short-term and long-term environment changes. Design/methodology/approach The proposed system contains four main modules, including long-term place graph updating, global localization and re-localization, location tracking and pose registration. The first two modules fully exploit the deep-learning based three-dimensional point cloud learning techniques to achieve the map-less global localization task in large-scale environment. The location tracking module implements the particle filter framework with a newly designed perception model to track the vehicle location during movements. Finally, the pose registration module uses visual information to exclude the influence of dynamic obstacles and short-term changes and further introduces point cloud registration network to estimate the accurate vehicle pose. Findings Comprehensive experiments in real industrial environments demonstrate the effectiveness, robustness and practical applicability of the map-less localization approach. Practical implications This paper provides comprehensive experiments in real industrial environments. Originality/value The system can be used in the practical automated industrial vehicles for long-term localization tasks. The dynamic objects, short-/long-term environment changes and hardware limitations of industrial vehicles are all considered in the system design. Thus, this work moves a big step toward achieving real implementations of the autonomous localization in practical industrial scenarios.

show abstract

LiDAR Iris for Loop-Closure Detection

Cited by 132 publications

References 20 publications

Loop closure detection using local 3D deep descriptors

Loop closure detection using local 3D deep descriptors

WADE-Net: Weighted Aggregation with Density Estimation for Point Cloud Place Recognition

Map-less long-term localization in complex industrial environments

Contact Info

Product

Resources

About