2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) 2017
DOI: 10.1109/mfi.2017.8170397
|View full text |Cite
|
Sign up to set email alerts
|

Fast point cloud segmentation based on flood-fill algorithm

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 16 publications
(9 citation statements)
references
References 10 publications
0
9
0
Order By: Relevance
“…Thus, we resort to the volumetric grids as an intermediate representation to acquire the occupancy field for each part shape. Specifically, the whole object is first voxelized followed by a flood‐fill algorithm [CCPC17] to achieve solid voxlization. We then sample points on the mesh surface of the object parts.…”
Section: Methodsmentioning
confidence: 99%
“…Thus, we resort to the volumetric grids as an intermediate representation to acquire the occupancy field for each part shape. Specifically, the whole object is first voxelized followed by a flood‐fill algorithm [CCPC17] to achieve solid voxlization. We then sample points on the mesh surface of the object parts.…”
Section: Methodsmentioning
confidence: 99%
“…As mentioned above, the nonground points are obtained after applying the segmentation algorithm. In the first step, the nonground points are segmented into separate objects based on a flood-fill algorithm proposed elsewhere [37]. In the second step, a fast object tracking algorithm [38] is applied to obtain a list of dynamic objects.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…However, DATMO systems are time-consuming because of the high computation complexity. Therefore, in this study, we employed our previous DATMO system [36][37][38] to detect dynamic objects and collect points on the dynamic objects in previous frames. In addition, because of the dynamic environment, an algorithm is required to eliminate the traces of dynamic objects.…”
Section: Related Workmentioning
confidence: 99%
“…After labeling the nonground points, they are clustered by the flood-fill algorithm [27]. The flood-fill algorithm is composed of two steps.…”
Section: B Roi Produced By Flood-fill Algorithmmentioning
confidence: 99%