ERASOR: Egocentric Ratio of Pseudo Occupancy-Based Dynamic Object Removal for Static 3D Point Cloud Map Building

Lim, Hyungtae; Hwang, Sungu; Myung, Hyun

doi:10.1109/lra.2021.3061363

Cited by 152 publications

(110 citation statements)

References 25 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…Meanwhile, grid representation-based methods have been widely utilized to leverage expressibility compared with singular plane model-based methods [4], [9]. In particular, polar grid representation, which treats a point cloud in cylindrical coordinates, is commonly employed these days because it naturally compensates for the geometric characteristics of 3D LiDAR sensors [11], [12], [14], [16], [21]. In practice, Thrun et al [5] presented a grid cell-based binary ground classification method in a probabilistic way to predict the movable area for autonomous driving in the DARPA challenge.…”

Section: Scan Representationmentioning

confidence: 99%

“…Sharing their views of region-wise fitting yet improving robustness, other researchers have conducted region-wise plane fitting-based approaches [8], [12], [14], [16]. For instance, Zermas et al [8] divided a point cloud into three parts along the x-axis of the body frame, which is the forward direction of a vehicle.…”

Section: F Multiple Plane Fitting-based Ground Segmentationmentioning

confidence: 99%

“…The other purpose, on which this paper places more emphasis, is the segmentation of a point cloud to recognize or track moving objects. Terrestrial vehicles or humans inevitably come into contact with the ground [14]; ideally, dynamic objects can be recognized in a simple way, such as through Euclidean clustering if the ground is well estimated [8], [15]. Furthermore, because most cloud points belong to the ground, ground segmentation can significantly reduce computational power when one is performing object segmentation or detection in a preprocessing stage [16].…”

Section: Introductionmentioning

confidence: 99%

“…In this study, as presented in Fig. 1, we propose a novel Concentric Zone Model (CZM)-based region-wise ground segmentation method, called Patchwork, which is an extension of Region-wise Ground Plane Fitting (R-GPF) in our previous study [14]. The aim of R-GPF in our previous study was to estimate the ground points for static map building purposes, whereas here, we focus only on ground segmentation on a 3D point cloud.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

Lim¹,

Oh²,

Myung³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Ground segmentation is crucial for terrestrial mobile platforms to perform navigation or neighboring object recognition. Unfortunately, the ground is not flat, as it features steep slopes; bumpy roads; or objects, such as curbs, flower beds, and so forth. To tackle the problem, this paper presents a novel ground segmentation method called Patchwork, which is robust for addressing the under-segmentation problem and operates at more than 40 Hz. In this paper, a point cloud is encoded into a Concentric Zone Model-based representation to assign an appropriate density of cloud points among bins in a way that is not computationally complex. This is followed by Region-wise Ground Plane Fitting, which is performed to estimate the partial ground for each bin. Finally, Ground Likelihood Estimation is introduced to dramatically reduce false positives. As experimentally verified on SemanticKITTI and rough terrain datasets, our proposed method yields promising performance compared with the state-of-the-art methods, showing faster speed compared with existing plane fitting-based methods. Code is available: https://github.com/LimHyungTae/patchwork

show abstract

Section: Scan Representationmentioning

confidence: 99%

Section: F Multiple Plane Fitting-based Ground Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

Lim¹,

Oh²,

Myung³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The conventional RGB-D SLAM algorithms assume the neighboring environments are static [11] throughout the SLAM process. Therefore, these algorithms are vulnerable to errors in the real world since features from the dynamic objects exist [9], [12]. In particular, the dynamic objects are mainly divided into high-dynamic and low-dynamic objects.…”

Section: Introductionmentioning

confidence: 99%

G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments

et al. 2022

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a generalized grouping and pruning method for RGB-D SLAM in low-dynamic environments. The conventional grouping and pruning methods successfully reject the effect of dynamic objects in pose graph optimization (PGO). However, these methods sometimes fail when high-dynamic objects are dominant in the images captured by RGB-D sensors. Furthermore, once it is determined whether the features from dynamic objects are included in some nodes, the corresponding nodes are entirely removed even though these nodes partially include true constraints, which leads to an inaccurate PGO. To tackle these problems, we propose a novel method with intra-grouping, inter-grouping, and selective pruning, called G2P-SLAM. Accordingly, our method successfully rejects false constraints from dynamic objects selectively, thus preserving true constraints from static objects as many as possible. As experimentally verified on both our own datasets and public datasets, our proposed method shows promising performance compared with the state-of-the-art methods. Furthermore, experimental results corroborate that our G2P-SLAM enables robust PGO in both dynamic and low-dynamic environments.INDEX TERMS Computer vision, Mobile robots, Robot vision systems, Simultaneous localization and mapping.

show abstract

M2CS: A Multimodal and Campus‐Scapes Dataset for Dynamic SLAM and Moving Object Perception

Zhao,

Yao,

Zhao

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

The deployment of the robotic system that executes specific task is being challenged by the prevalence of dynamic objects in real‐world scenes. Two robotic tasks sparked by this challenge, known as dynamic Simultaneous Localization and Mapping (SLAM) and moving object perception, are crucial for enhancing system robustness and reinforcing environment awareness. Existing public datasets are diverse in platforms, sensor combinations, scenarios, and label annotations, but few adequately benchmark the above tasks. To fill this gap, we introduce the multimodal and campus‐scapes (M2CS) dataset, providing robot‐centric synchronized LiDAR‐Inertial‐Visual‐GNSS data with 3D moving object annotation in specific dynamic scenarios. The dataset exhibits variation in dynamic object types and densities, annotating over 160,000 Light Detection and Ranging (LiDAR) scans and releasing ground truth of trajectories acquired by the GNSS‐RTK/INS system. The dataset evaluates existing SLAM and moving object perception methods, driving relevant research to overcome this challenge. We publish the M2CS dataset on the website (https://github.com/Zhaohuanfeng/M2CS) and hope it promotes research on robotics in complex environment.

show abstract

ERASOR: Egocentric Ratio of Pseudo Occupancy-Based Dynamic Object Removal for Static 3D Point Cloud Map Building

Cited by 152 publications

References 25 publications

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments

M2CS: A Multimodal and Campus‐Scapes Dataset for Dynamic SLAM and Moving Object Perception

Contact Info

Product

Resources

About