Fast planar surface 3D SLAM using LIDAR

Lenac, Kruno; Kitanov, Andrej; Cupec, Robert; Petrović, Ivan

doi:10.1016/j.robot.2017.03.013

Cited by 43 publications

(24 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Utilizing 3D point clouds for loop closure or relocalization is a challenging problem that has attracted increasing attention in the autonomous driving field. Lenac et al [21] proposed a loop detection method that uses planar surface segments in point clouds as features in maps. The proposed method can achieve accurate and efficient SLAM in structured scenarios but not in unstructured environments.…”

Section: Related Workmentioning

confidence: 99%

ClusterMap Building and Relocalization in Urban Environments for Unmanned Vehicles

Pan

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

Map building and map-based relocalization techniques are important for unmanned vehicles operating in urban environments. The existing approaches require expensive high-density laser range finders and suffer from relocalization problems in long-term applications. This study proposes a novel map format called the ClusterMap, on the basis of which an approach to achieving relocalization is developed. The ClusterMap is generated by segmenting the perceived point clouds into different point clusters and filtering out clusters belonging to dynamic objects. A location descriptor associated with each cluster is designed for differentiation. The relocalization in the global map is achieved by matching cluster descriptors between local and global maps. The solution does not require high-density point clouds and high-precision segmentation algorithms. In addition, it prevents the effects of environmental changes on illumination intensity, object appearance, and observation direction. A consistent ClusterMap without any scale problem is built by utilizing a 3D visual–LIDAR simultaneous localization and mapping solution by fusing LIDAR and visual information. Experiments on the KITTI dataset and our mobile vehicle illustrates the effectiveness of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

ClusterMap Building and Relocalization in Urban Environments for Unmanned Vehicles

Pan

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…For registering point clouds captured on dynamic platforms, the coarse alignment process is usually replaced by the introduction of hardware sensors, namely GNSS receivers and IMUs [53]. Points [35,[54][55][56][57][58][59][60][61][62], lines [63][64][65][66], planes [23,47,[67][68][69][70][71], voxels [72,73], and the selections of them [19,[74][75][76] are used to recover the positioning and orienting changes in the dynamic process and achieve fine registration. Since the limited number of planes extracted and the poor quality of planes may result in failures in aligning low-resolution single-frame point clouds, a highly robust and reliable plane extraction method is required for highly dynamic mobile mapping in indoor environments.…”

Section: Related Workmentioning

confidence: 99%

A Novel Method for Plane Extraction from Low-Resolution Inhomogeneous Point Clouds and its Application to a Customized Low-Cost Mobile Mapping System

Fan¹,

Shi²,

Xiang³

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Over the last decade, increasing demands for building interior mapping have brought the challenge of effectively and efficiently acquiring geometric information. Most mobile mapping methods rely on the integration of Simultaneous Localization And Mapping (SLAM) and costly Inertial Measurement Units (IMUs). Meanwhile, the methods also suffer misalignment errors caused by the low-resolution inhomogeneous point clouds captured using multi-line Mobile Laser Scanners (MLSs). While point-based alignments between such point clouds are affected by the highly dynamic moving patterns of the platform, plane-based methods are limited by the poor quality of the planes extracted, which reduce the methods’ robustness, reliability, and applicability. To alleviate these issues, we proposed and developed a method for plane extraction from low-resolution inhomogeneous point clouds. Based on the definition of virtual scanlines and the Enhanced Line Simplification (ELS) algorithm, the method extracts feature points, generates line segments, forms patches, and merges multi-direction fractions to form planes. The proposed method reduces the over-segmentation fractions caused by measurement noise and scanline curvature. A dedicated plane-to-plane point cloud alignment workflow based on the proposed plane extraction method was created to demonstrate the method’s application. The implementation of the coarse-to-fine procedure and the shortest-path initialization strategy eliminates the necessity of IMUs in mobile mapping. A mobile mapping prototype was designed to test the performance of the proposed methods. The results show that the proposed workflow and hardware system achieves centimeter-level accuracy, which suggests that it can be applied to mobile mapping and sensor fusion.

show abstract

“…In scenarios, such as autonomous driving, LIDAR is an indispensable sensor which provides highly reliable depth measures in the 3D point cloud. Some previous works, such as [1, 2], conduct accurate object detection and surroundings reconstruction basing on the LIDAR point cloud. These works are the basic components for solving more complex tasks such as motion planning, navigation, and mapping.…”

Section: Introductionmentioning

confidence: 99%

RTL3D: real‐time LIDAR‐based 3D object detection with sparse CNN

Lin

Belyaev

et al. 2020

IET Computer Vision

View full text Add to dashboard Cite

LIDAR (light detection and ranging) based real‐time 3D perception is crucial for applications such as autonomous driving. However, most of the convolutional neural network (CNN) based methods are time‐consuming and computation‐intensive. These drawbacks are mainly attributed to the highly variable density of LIDAR point cloud and the complexity of their pipelines. To find a balance between speed and accuracy for 3D object detection from LIDAR, authors propose RTL3D, a computationally efficient Real‐time LIDAR‐based 3D detector. In RTL3D, an effective voxel‐wise feature representation is utilised to organise unstructured point cloud. By employing a sparse feature learning network (SFLN) on voxelised 3D data, RTL3D exploits the sparsity of point cloud and down‐samples 3D data into 2D. Basing on the generated 2D feature map, an optimised dense detection network (DDN) is applied to regress the oriented bounding box without relying on any predefined anchor boxes. The authors also introduce an incremental data augmentation approach which greatly improves the performance of RTL3D. Empirical experiments on public KITTI benchmark demonstrate that RTL3D achieves a competitive performance with state‐of‐the‐art works on 3D detection task. Owning to the simplicity of its single‐stage and anchor‐free design, RTL3D has a real‐time inference speed of 40 FPS.

show abstract

Fast planar surface 3D SLAM using LIDAR

Cited by 43 publications

References 27 publications

ClusterMap Building and Relocalization in Urban Environments for Unmanned Vehicles

ClusterMap Building and Relocalization in Urban Environments for Unmanned Vehicles

A Novel Method for Plane Extraction from Low-Resolution Inhomogeneous Point Clouds and its Application to a Customized Low-Cost Mobile Mapping System

RTL3D: real‐time LIDAR‐based 3D object detection with sparse CNN

Contact Info

Product

Resources

About