Ground Segmentation Based on Loopy Belief Propagation for Sparse 3D Point Clouds

Zhang, Mingfang; Morris, Daniel; Fu, Rui

doi:10.1109/3dv.2015.76

Cited by 41 publications

(63 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experiments we used the 60m limit by default (and the 30m limit in the time performance 4 http://caffe.berkeleyvision.org/ test). In order to make fair evaluation, we computed the accuracy of our method for both the maximal range set to 60m (same conditions as for [1]) and the unlimited range (to illustrate behavior for more distant measurements). Also, since the Zhang's method has no threshold/parameter for tuning the false positives to false negatives ratio, only a single precision/recall value can be computed instead of the whole PR curve.…”

Section: Methodsmentioning

confidence: 99%

“…We compared CNNs which were trained either by using the human-made annotations only (label human-only), or just automatically annotated dataset (automatic-only), or using both datasets together (label both). Moreover, we evaluated , precision, recall and the best F-score of the proposed networks compared to [1]. *The precision (and the recall) were estimated for points where recall (and precision respectively) is the same as the results of [1] (also displayed in Fig.…”

Section: Methodsmentioning

confidence: 99%

“…TE01020415), and the IT4IXS IT4Innovations Excellence project (LQ1602). **We would like to thank Mingfang Zhang for sharing her source code [1], making evaluation of both approaches feasible. Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CNN for very fast ground segmentation in velodyne LiDAR data

Veľas

Španěl

Hradiš

et al. 2018

2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

This paper presents a novel method for ground segmentation in Velodyne point clouds. We propose an encoding of sparse 3D data from the Velodyne sensor suitable for training a convolutional neural network (CNN). This general purpose approach is used for segmentation of the sparse point cloud into ground and non-ground points. The LiDAR data are represented as a multi-channel 2D signal where the horizontal axis corresponds to the rotation angle and the vertical axis the indexes channels (i.e. laser beams). Multiple topologies of relatively shallow CNNs (i.e. 3-5 convolutional layers) are trained and evaluated using a manually annotated dataset we prepared. The results show significant improvement of performance over the state-of-the-art method by Zhang et al. in terms of speed and also minor improvements in terms of accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

CNN for very fast ground segmentation in velodyne LiDAR data

Veľas

Španěl

Hradiš

et al. 2018

2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

show abstract

“…Hence, many studies have been conducted relating to it. 14,20 In this section, some existing studies are noted and are primarily grouped into two types.…”

Section: Related Workmentioning

confidence: 99%

“…If the number of points in the seeds is smaller than minPts, then the current points can be regarded as noise and it should be denoted as noise point (Algorithm 2, lines [13][14]. Otherwise, a valid label is assigned to all points in the seeds and the current points (Algorithm 2, lines [15][16][17][18][19][20]. For every points in seeds, their k neighboring positions are also searched (Algorithm 2, line 21); if the number of neighboring points within ep from a given point in seeds is greater than minPts, those points will also be labeled with the same label (Algorithm 2, lines 26-37).…”

Section: Non-ground Object Clustering Processmentioning

confidence: 99%

Range image-based density-based spatial clustering of application with noise clustering method of three-dimensional point clouds

Wen

Cho

Chae

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Clustering plays an important role in processing light detection and ranging points in the autonomous perception tasks of robots. Clustering usually occurs near the start of processing three-dimensional point clouds obtained from light detection and ranging for detection and classification. Therefore, errors caused by clustering will directly affect the detection and classification accuracy. In this article, a clustering method is presented that combines density-based spatial clustering of application with noise and two-dimensional range image composed by scan lines of light detection and ranging based on the order of generation time. The results show that the proposed method achieves state-of-the-art performance in aspect of time efficiency and clustering accuracy. A ground extraction method based on scan line is also presented in this article, which has strong ability to separate ground points and non-ground points.

show abstract

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Xue

Liang³

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

For autonomous driving, traversability analysis is one of the most basic and essential tasks. In this paper, we propose a novel LiDAR‐based terrain modeling approach, which could output stable, complete, and accurate terrain models and traversability analysis results. As terrain is an inherent property of the environment that does not change with different view angles, our approach adopts a multiframe information fusion strategy for terrain modeling. Specifically, a normal distributions transform mapping approach is adopted to accurately model the terrain by fusing information from consecutive LiDAR frames. Then the spatial‐temporal Bayesian generalized kernel inference and bilateral filtering are utilized to promote the stability and completeness of the results while simultaneously retaining the sharp terrain edges. Based on the terrain modeling results, the traversability of each region is obtained by performing geometric connectivity analysis between neighboring terrain regions. Experimental results show that the proposed method could run in real‐time and outperforms state‐of‐the‐art approaches.

show abstract

Ground Segmentation Based on Loopy Belief Propagation for Sparse 3D Point Clouds

Cited by 41 publications

References 25 publications

CNN for very fast ground segmentation in velodyne LiDAR data

CNN for very fast ground segmentation in velodyne LiDAR data

Range image-based density-based spatial clustering of application with noise clustering method of three-dimensional point clouds

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Contact Info

Product

Resources

About