Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance

Park, Seungcheol; Wang, Shuyu; Lim, Hun-Jung; Kang, Un-Gu

doi:10.1109/iros40897.2019.8968026

Cited by 26 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First of all, we should have lidar calibrated, and then, radar is calibrated based on the lidar. For 3D point clouds, the curvedvoxel clustering method is firstly used to cluster non-ground point clouds (Park et al, 2019). Then we use L-Shape fitting method (Zhang et al, 2017) to extract objects' features.…”

Section: Multi-layer Self-calibrationmentioning

confidence: 99%

Obstacle detection based on depth fusion of lidar and radar in challenging conditions

Xie

Zhang

Zhao³

et al. 2021

View full text Add to dashboard Cite

Purpose To the industrial application of intelligent and connected vehicles (ICVs), the robustness and accuracy of environmental perception are critical in challenging conditions. However, the accuracy of perception is closely related to the performance of sensors configured on the vehicle. To enhance sensors’ performance further to improve the accuracy of environmental perception, this paper aims to introduce an obstacle detection method based on the depth fusion of lidar and radar in challenging conditions, which could reduce the false rate resulting from sensors’ misdetection. Design/methodology/approach Firstly, a multi-layer self-calibration method is proposed based on the spatial and temporal relationships. Next, a depth fusion model is proposed to improve the performance of obstacle detection in challenging conditions. Finally, the study tests are carried out in challenging conditions, including straight unstructured road, unstructured road with rough surface and unstructured road with heavy dust or mist. Findings The experimental tests in challenging conditions demonstrate that the depth fusion model, comparing with the use of a single sensor, can filter out the false alarm of radar and point clouds of dust or mist received by lidar. So, the accuracy of objects detection is also improved under challenging conditions. Originality/value A multi-layer self-calibration method is conducive to improve the accuracy of the calibration and reduce the workload of manual calibration. Next, a depth fusion model based on lidar and radar can effectively get high precision by way of filtering out the false alarm of radar and point clouds of dust or mist received by lidar, which could improve ICVs’ performance in challenging conditions.

show abstract

Section: Multi-layer Self-calibrationmentioning

confidence: 99%

Obstacle detection based on depth fusion of lidar and radar in challenging conditions

Xie

Zhang

Zhao³

et al. 2021

View full text Add to dashboard Cite

show abstract

“…(2) Distance to the sensor: The point cloud collected at close range is dense, but the distant object only has sporadic point clouds. With the same angular resolution, the farther the distance is, the greater the distance between the same included angles is [36]. So an object's point cloud density depends on the distance to the sensor.…”

Section: Lidar Data Characteristicsmentioning

confidence: 99%

“…At the same time, the accuracy of clustering results is related to the subsequent recognition task. It is necessary to ensure that more than 85% of a point cloud of a particular object can be correctly classified, and the running time of some excellent methods can be less than 40 ms [13,16,36].…”

Section: Introductionmentioning

confidence: 99%

Two-Layer-Graph Clustering for Real-Time 3D LiDAR Point Cloud Segmentation

et al. 2020

View full text Add to dashboard Cite

The perception system has become a topic of great importance for autonomous vehicles, as high accuracy and real-time performance can ensure safety in complex urban scenarios. Clustering is a fundamental step for parsing point cloud due to the extensive input data (over 100,000 points) of a wide variety of complex objects. It is still challenging to achieve high precision real-time performance with limited vehicle-mounted computing resources, which need to balance the accuracy and processing time. We propose a method based on a Two-Layer-Graph (TLG) structure, which can be applied in a real autonomous vehicle under urban scenarios. TLG can describe the point clouds hierarchically, we use a range graph to represent point clouds and a set graph for point cloud sets, which reduce both processing time and memory consumption. In the range graph, Euclidean distance and the angle of the sensor position with two adjacent vectors (calculated from continuing points to different direction) are used as the segmentation standard, which use the local concave features to distinguish different objects close to each other. In the set graph, we use the start and end position to express the whole set of continuous points concisely, and an improved Breadth-First-Search (BFS) algorithm is designed to update categories of point cloud sets between different channels. This method is evaluated on real vehicles and major datasets. The results show that TLG succeeds in providing a real-time performance (less than 20 ms per frame), and a high segmentation accuracy rate (93.64%) for traffic objects in the road of urban scenarios.

show abstract

“…Paiva et al combined the hierarchical watershed algorithm with the curvature analysis in the region growth method to obtain more suitable seeds and improve the robustness of point cloud segmentation using the region growth method [16]. To obtain more appropriate seeds, Paiva et al integrated the watershed algorithm and curvature analysis into the region growing method [17]. This approach improves the robustness of point cloud segmentation when using the region growing method.…”

Section: Introductionmentioning

confidence: 99%

An inter-frame motion solving method based on semantic assistance

Liu,

Wang,

Jia

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Lidar and camera are the two most frequently used types of sensors in the fields of autonomous driving and mobile robots. The data fusion of ontology positioning and mapping has become a popular research direction in the field of simultaneous localization and mapping. Considering the characteristics of a planar mobile robot, this paper proposes an image semantics-based method to solve the inter-frame motion of the laser point cloud to achieve the fast real-time positioning of a mobile robot. First, the image cascade network is used to convert image samples to different resolutions, and network branches of different complexity are gradually fused into the final finer semantic segmentation result. Then, through the rapid segmentation and processing of the laser point cloud data, key points and surfels are extracted. The unified framework of semantic-assisted inter-frame motion estimation is established using semantic image data and point-cloud key-feature information. Finally, the stability of feature extraction, the accuracy of motion estimation, and the efficiency measured by calculation time are verified experimentally. The experimental results show that the standard deviation of the estimated motion is less than 0.0025, and the single operation time of the whole system is about 38 ms.

show abstract

Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance

Cited by 26 publications

References 12 publications

Obstacle detection based on depth fusion of lidar and radar in challenging conditions

Obstacle detection based on depth fusion of lidar and radar in challenging conditions

Two-Layer-Graph Clustering for Real-Time 3D LiDAR Point Cloud Segmentation

An inter-frame motion solving method based on semantic assistance

Contact Info

Product

Resources

About