Visual-Inertial Localization With Prior LiDAR Map Constraints

Zuo, Xingxing; Geneva, Patrick; Yang, Yulin; Ye, Wenlong; Liu, Yong; Huang, Guoquan

doi:10.1109/lra.2019.2927123

Cited by 50 publications

(29 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evidence is more obvious in the composite positioning technologies. For instance, WiFi and vision [1], inertia and vision [2], Lidar and vision [3], hybrid localization technology [4]. Visual localization is a key role in their system architecture, respectively.…”

Section: A Background and Significancementioning

confidence: 99%

A Visual Fingerprint Update Algorithm Based On Crowdsourced Localization And Deep Learning For Smart IoV

Yin

Sun

2021

Preprint

View full text Add to dashboard Cite

Recently, the deep learning and vision-based technologies has shown their great significance for the prospective development of smart Internet of Vehicle (IoV). When the smart vehicle enters the indoor parking of a shopping mall, the vision-based localization technology can provide reliable parking service. As known, the vision-based technique relies on a visual map without a change in the position of the reference object. Although, some researchers have proposed a few automatic visual fingerprinting (AVF) methods, which are aiming at reducing the cost of building the visual map database. However, the AVF method still costs too much under such situation, since it is impossible to determine the specific location of the displaced object. In view of the smart IoV and the development of deep learning approach, we propose a crowdsourcing and deep learning based algorithm for solving the problem in this paper. Firstly, we propose a Region-based Fully Convolutional Network (R-FCN) based method with the feedback of crowdsourced images to locate the specific displaced object in the visual map database. Secondly, we propose a method based on quadratic programming (QP) for solving the translation vector of the displaced objects, which finally solves the problem of updating the visual map database. The simulation results show that our method can provide a higher detection sensitivity and correction accuracy as well as the relocation results. It means that our proposed algorithm outperforms the compared one, which is verified by both synthetic and real data simulation.

show abstract

Section: A Background and Significancementioning

confidence: 99%

A Visual Fingerprint Update Algorithm Based On Crowdsourced Localization And Deep Learning For Smart IoV

Yin

Sun

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In this work, we propose an approach for real-time lightweight monocular camera localization in prior 3D LiDAR maps using direct 2D-3D geometric line correspondences. We assume a coarse pose initialization is given and focus on the pose tracking in maps, which follows the related works [4], [5]. For geometric concurrent feature extraction, 3D line segments are detected offline from LiDAR maps while robust 2D line segments are extracted online from video sequences.…”

Section: Vins-monomentioning

confidence: 99%

“…Similarly in [14], 3D structural descriptors are used for matching LiDAR maps with sparse visual reconstructed point clouds. In [8], [5], dense local point clouds are reconstructed from a stereo camera to match with the 3D LiDAR maps, and then the matching results are loosely or tightly coupled into the VO and VIO system for optimizing camera poses. These localization methods by 3D registration obtain feasible results compared with vision-only based methods.…”

Section: Related Workmentioning

confidence: 99%

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

Zhen

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO&VIO) techniques are welldeveloped for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using directly estimated 2D-3D line correspondences. To handle the appearance differences and modality gaps between untextured point clouds and images, geometric 3D lines are extracted offline from LiDAR maps while robust 2D lines are extracted online from video sequences. With the pose prediction from VIO, we can efficiently obtain coarse 2D-3D line correspondences. After that, the camera poses and 2D-3D correspondences are iteratively optimized by minimizing the projection error of correspondences and rejecting outliers. The experiment results on the EurocMav dataset and our collected dataset demonstrate that the proposed method can efficiently estimate camera poses without accumulated drifts or pose jumps in urban environments. The code and our collected data are available at https://github.com/levenberg/2D-3D-posetracking.

show abstract

“…Point cloud map [24], [25], [26], [27], [28], [29], [30], [31], [32] is a novel map source that provides dense and accurate 3D reference points. Compared with the OSM and satellite images, a point cloud map well supports the 3D localization, which makes it popular in modern vehicle localization algorithms.…”

Section: Introductionmentioning

confidence: 99%

CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map

Lyu¹,

Huang²,

Zhang³

2021

Preprint

View full text Add to dashboard Cite

LiDAR odometry and localization has attracted increasing research interest in recent years. In the existing works, iterative closest point (ICP) is widely used since it is precise and efficient. Due to its non-convexity and its local iterative strategy, however, ICP-based method easily falls into local optima, which in turn calls for a precise initialization. In this paper, we propose CoFi, a Coarse-to-Fine ICP algorithm for LiDAR localization. Specifically, the proposed algorithm downsamples the input point sets under multiple voxel resolution, and gradually refines the transformation from the coarse point sets to the fine-grained point sets. In addition, we propose a map based LiDAR localization algorithm that extracts semantic feature points from the LiDAR frames and apply CoFi to estimate the pose on an efficient point cloud map. With the help of the Cylinder3D algorithm for LiDAR scan semantic segmentation, the proposed CoFi localization algorithm demonstrates the state-of-the-art performance on the KITTI odometry benchmark, with significant improvement over the literature.

show abstract

Visual-Inertial Localization With Prior LiDAR Map Constraints

Cited by 50 publications

References 36 publications

A Visual Fingerprint Update Algorithm Based On Crowdsourced Localization And Deep Learning For Smart IoV

A Visual Fingerprint Update Algorithm Based On Crowdsourced Localization And Deep Learning For Smart IoV

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map

Contact Info

Product

Resources

About