Robust Method for Removing Dynamic Objects from Point Clouds

Pagad, Shishir; Agarwal, Divya; Narayanan, S.; Rangan, Kasturi; Kim, Hyungjin; Yalla, Ganesh

doi:10.1109/icra40945.2020.9197168

Cited by 66 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, these methods consume a lot of memory and computing resources. Even if the latest method [5] uses deep-learning and GPU acceleration, it can only maintain a maximum octree depth of 16 and voxel size of 0.3 meters.…”

Section: Related Workmentioning

confidence: 99%

“…The previous approaches based on the static environment assumption will fail. Moreover, it is also challenging to extract road markers, traffic signs, and other critical static features in the point cloud map, as ghost tracks of moving objects may occlude them [5]. Therefore, it is essential to improve the performance of SLAM in dynamic environments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RF-LIO: Removal-First Tightly-coupled Lidar Inertial Odometry in High Dynamic Environments

Qian¹,

Zhao-hong²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) is considered to be an essential capability for intelligent vehicles and mobile robots. However, most of the current lidar SLAM approaches are based on the assumption of a static environment. Hence the localization in a dynamic environment with multiple moving objects is actually unreliable. The paper proposes a dynamic SLAM framework RF-LIO, building on LIO-SAM, which adds adaptive multi-resolution range images and uses tightly-coupled lidar inertial odometry to first remove moving objects, and then match lidar scan to the submap. Thus, it can obtain accurate poses even in high dynamic environments. The proposed RF-LIO is evaluated on both self-collected datasets and open Urbanloco datasets. The experimental results in high dynamic environments demonstrate that, compared with LOAM and LIO-SAM, the absolute trajectory accuracy of the proposed RF-LIO can be improved by 90% and 70%, respectively. RF-LIO is one of the state-of-the-art SLAM systems in high dynamic environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

RF-LIO: Removal-First Tightly-coupled Lidar Inertial Odometry in High Dynamic Environments

Qian¹,

Zhao-hong²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…coneshaped used by Pomerleau et al [22]. Recently, Pagad et al [20] propose an occupancy map-based method to remove dynamic points in LiDAR scans. They first build occupancy maps using object detection and then use the voxel traversal method to remove the moving objects.…”

Section: Related Workmentioning

confidence: 99%

Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

Chen,

Li,

Mersch

et al. 2021

Preprint

View full text Add to dashboard Cite

The ability to detect and segment moving objects in a scene is essential for building consistent maps, making future state predictions, avoiding collisions, and planning. In this paper, we address the problem of moving object segmentation from 3D LiDAR scans. We propose a novel approach that pushes the current state of the art in LiDAR-only moving object segmentation forward to provide relevant information for autonomous robots and other vehicles. Instead of segmenting the point cloud semantically, i.e., predicting the semantic classes such as vehicles, pedestrians, buildings, roads, etc., our approach accurately segments the scene into moving and static objects, i.e., distinguishing between moving cars vs. parked cars. Our proposed approach exploits sequential range images from a rotating 3D LiDAR sensor as an intermediate representation combined with a convolutional neural network and runs faster than the frame rate of the sensor. We compare our approach to several other state-of-the-art methods showing superior segmentation quality in urban environments. Additionally, we created a new benchmark for LiDAR-based moving object segmentation based on SemanticKITTI. We publish it to allow other researchers to compare their approaches transparently and we will publish our code.

show abstract

“…Unfortunately, because scan data presents a snapshot of the surroundings, scan data in urban environments inevitably includes representations of dynamic objects, such as vehicles, pedestrians, and so forth [13]- [16]. Moreover, because a 3D point cloud map is the product of sequential accumulations of the scan data, there might be traces of dynamic objects, or the ghost trail effect [8], [13], as shown in Fig. 1 on the left.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…Occupancy grid [17] and Octomap [12] are typical methods that use ray tracing, which count hits and misses of scans in the gridmap space and decide the occupancy of the space. By extension, Schauer and Nüchter [14] proposed the removal of dynamic points by traversing a voxel occupancy grid and Pagad et al [13] suggested a combinination of object detection and Octomap. However, ray tracing-based methods are computationally expensive, which led to the introduction of visibility-based methods to reduce the computational cost [8], [10], [15].…”

Section: Introduction and Related Workmentioning

confidence: 99%

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

Lim,

Hwang,

Myung

2021

Preprint

View full text Add to dashboard Cite

Scan data of urban environments often include representations of dynamic objects, such as vehicles, pedestrians, and so forth. However, when it comes to constructing a 3D point cloud map with sequential accumulations of the scan data, the dynamic objects often leave unwanted traces in the map. These traces of dynamic objects act as obstacles and thus impede mobile vehicles from achieving good localization and navigation performances. To tackle the problem, this paper presents a novel static map building method called ERASOR, Egocentric RAtio of pSeudo Occupancy-based dynamic object Removal, which is fast and robust to motion ambiguity. Our approach directs its attention to the nature of most dynamic objects in urban environments being inevitably in contact with the ground. Accordingly, we propose the novel concept called pseudo occupancy to express the occupancy of unit space and then discriminate spaces of varying occupancy. Finally, Region-wise Ground Plane Fitting (R-GPF) is adopted to distinguish static points from dynamic points within the candidate bins that potentially contain dynamic points. As experimentally verified on SemanticKITTI, our proposed method yields promising performance against state-of-the-art methods overcoming the limitations of existing ray tracing-based and visibility-based methods.

show abstract

Robust Method for Removing Dynamic Objects from Point Clouds

Cited by 66 publications

References 16 publications

RF-LIO: Removal-First Tightly-coupled Lidar Inertial Odometry in High Dynamic Environments

RF-LIO: Removal-First Tightly-coupled Lidar Inertial Odometry in High Dynamic Environments

Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

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

Contact Info

Product

Resources

About