2014 IEEE International Conference on Robotics and Automation (ICRA) 2014
DOI: 10.1109/icra.2014.6907236
|View full text |Cite
|
Sign up to set email alerts
|

Dense 3D semantic mapping of indoor scenes from RGB-D images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
223
1

Year Published

2015
2015
2019
2019

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 250 publications
(224 citation statements)
references
References 14 publications
0
223
1
Order By: Relevance
“…Hermans et al [9] use a random forest classifier and a dense 2D CRF, transfer the resulting marginals into 3D and [4] out only Valentin et al [12] Häne et al [8] N/A Kundu et al [11] Hermans et al [9] Hu et al [27] Ours solve a 3D CRF to refine the predictions. Other shortcomings aside (see Tab.…”
Section: B Semantic Segmentationmentioning
confidence: 99%
See 1 more Smart Citation
“…Hermans et al [9] use a random forest classifier and a dense 2D CRF, transfer the resulting marginals into 3D and [4] out only Valentin et al [12] Häne et al [8] N/A Kundu et al [11] Hermans et al [9] Hu et al [27] Ours solve a 3D CRF to refine the predictions. Other shortcomings aside (see Tab.…”
Section: B Semantic Segmentationmentioning
confidence: 99%
“…Dense reconstructions working on a regular voxel grid [18]- [20] are limited to small volumes due to memory requirements. This has been addressed by approaches that use scalable data structures and stream data between GPU and CPU memory [21], [22], but they use Kinect-like cameras that only work indoors [9], [10]. Approaches working outdoors usually take significant time to run [4], [8], [11], [23], do not work incrementally [12] or rely on LIDAR data [24].…”
Section: Introductionmentioning
confidence: 99%
“…We use the semantic segmentation method of Husain et al [4], which is a feature learning approach similar to Eigen and Fergus [17] and Long et al [18]. Other approaches for semantic segmentation introduce hand-crafted features in their model such as gradient, colour, local binary pattern, depth gradient, spin, surface normals by Wu et al [19] and pixel value comparison and oriented gradients by Hermans et al [20]. Our method combines the final segmentation result and does not rely on any particular feature, hence it is compatible with any approach that clearly separates the object classes.…”
Section: Related Workmentioning
confidence: 99%
“…RELATED WORK The conventional approach to semantic labeling is carried out in multiple stages [4,[15][16][17][18][19]. This involves presegmenting the scene into smaller patches followed by feature extraction and classification.…”
Section: Introductionmentioning
confidence: 99%