Details
| Original language | English |
|---|---|
| Pages (from-to) | 870-883 |
| Number of pages | 14 |
| Journal | Image and vision computing |
| Volume | 32 |
| Issue number | 11 |
| Publication status | Published - 27 Jul 2014 |
Abstract
Given a surveillance video of a moving person, we present a novel method of estimating layout of a cluttered indoor scene. We propose an idea that trajectories of a moving person can be used to generate features to segment an indoor scene into different areas of interest. We assume a static uncalibrated camera. Using pixel-level color and perspective cues of the scene, each pixel is assigned to a particular class either a sitting place, the ground floor, or the static background areas like walls and ceiling. The pixel-level cues are locally integrated along global topological order of classes, such as sitting objects and background areas are above ground floor into a conditional random field by an ordering constraint. The proposed method yields very accurate segmentation results on challenging real world scenes. We focus on videos with people walking in the scene and show the effectiveness of our approach through quantitative and qualitative results. The proposed estimation method shows better estimation results as compared to the state of the art scene layout estimation methods. We are able to correctly segment 90.3% of background, 89.4% of sitting areas and 74.7% of the ground floor.
Keywords
- Conditional random field, Scene layout, Scene segmentation, Semantic context, Trajectory
ASJC Scopus subject areas
- Computer Science(all)
- Signal Processing
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Image and vision computing, Vol. 32, No. 11, 27.07.2014, p. 870-883.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Estimating layout of cluttered indoor scenes using trajectory-based priors
AU - Shoaib, Muhammad
AU - Yang, Michael Ying
AU - Rosenhahn, Bodo
AU - Ostermann, Joern
PY - 2014/7/27
Y1 - 2014/7/27
N2 - Given a surveillance video of a moving person, we present a novel method of estimating layout of a cluttered indoor scene. We propose an idea that trajectories of a moving person can be used to generate features to segment an indoor scene into different areas of interest. We assume a static uncalibrated camera. Using pixel-level color and perspective cues of the scene, each pixel is assigned to a particular class either a sitting place, the ground floor, or the static background areas like walls and ceiling. The pixel-level cues are locally integrated along global topological order of classes, such as sitting objects and background areas are above ground floor into a conditional random field by an ordering constraint. The proposed method yields very accurate segmentation results on challenging real world scenes. We focus on videos with people walking in the scene and show the effectiveness of our approach through quantitative and qualitative results. The proposed estimation method shows better estimation results as compared to the state of the art scene layout estimation methods. We are able to correctly segment 90.3% of background, 89.4% of sitting areas and 74.7% of the ground floor.
AB - Given a surveillance video of a moving person, we present a novel method of estimating layout of a cluttered indoor scene. We propose an idea that trajectories of a moving person can be used to generate features to segment an indoor scene into different areas of interest. We assume a static uncalibrated camera. Using pixel-level color and perspective cues of the scene, each pixel is assigned to a particular class either a sitting place, the ground floor, or the static background areas like walls and ceiling. The pixel-level cues are locally integrated along global topological order of classes, such as sitting objects and background areas are above ground floor into a conditional random field by an ordering constraint. The proposed method yields very accurate segmentation results on challenging real world scenes. We focus on videos with people walking in the scene and show the effectiveness of our approach through quantitative and qualitative results. The proposed estimation method shows better estimation results as compared to the state of the art scene layout estimation methods. We are able to correctly segment 90.3% of background, 89.4% of sitting areas and 74.7% of the ground floor.
KW - Conditional random field
KW - Scene layout
KW - Scene segmentation
KW - Semantic context
KW - Trajectory
UR - http://www.scopus.com/inward/record.url?scp=84906738702&partnerID=8YFLogxK
U2 - 10.1016/j.imavis.2014.07.003
DO - 10.1016/j.imavis.2014.07.003
M3 - Article
AN - SCOPUS:84906738702
VL - 32
SP - 870
EP - 883
JO - Image and vision computing
JF - Image and vision computing
SN - 0262-8856
IS - 11
ER -