Abstract
| Original language | English |
|---|---|
| Title of host publication | IEEE Conference on Computer Vision and Pattern Recognition |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 4603-4611 |
| Volume | 07-12-June-2015 |
| ISBN (Print) | 9781467369640 |
| DOIs | |
| Publication status | Published - 2015 |
| Event | Separating objects and clutter in indoor scenes - Boston, Massachusetts, USA Duration: 1 Jan 2015 → … |
Conference
| Conference | Separating objects and clutter in indoor scenes |
|---|---|
| Period | 1/01/15 → … |
Fingerprint
Cite this
}
Separating objects and clutter in indoor scenes. / Khan, S.H.; He, X.; Bannamoun, Mohammed; Sohel, Ferdous; Togneri, Roberto.
IEEE Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 4603-4611.Research output: Chapter in Book/Conference paper › Conference paper
TY - GEN
T1 - Separating objects and clutter in indoor scenes
AU - Khan, S.H.
AU - He, X.
AU - Bannamoun, Mohammed
AU - Sohel, Ferdous
AU - Togneri, Roberto
PY - 2015
Y1 - 2015
N2 - © 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.
AB - © 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.
U2 - 10.1109/CVPR.2015.7299091
DO - 10.1109/CVPR.2015.7299091
M3 - Conference paper
SN - 9781467369640
VL - 07-12-June-2015
SP - 4603
EP - 4611
BT - IEEE Conference on Computer Vision and Pattern Recognition
PB - IEEE, Institute of Electrical and Electronics Engineers
ER -