TY - GEN
T1 - Consistent 3D Background Model Estimation from Multi-viewpoint Videos
AU - Tsekourakis, Iraklis
AU - Mordohai, Philippos
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/11/20
Y1 - 2015/11/20
N2 - We present an approach for estimating the 3D background model of a scene from a collection of synchronized videos. Unlike previous work, our method is fully automatic, does not require empty frames depicting just the background, and makes very mild assumptions about the foreground. The constraint on the cameras is that they should have sufficiently narrow baselines to enable multi-view stereo matching. Using the images and primarily the depth maps as inputs, our algorithm detects potential background pixels to generate initial per-camera background models, which are then fused to form the final, consistent 3D background model. We show results on diverse video sequences captured using different camera configurations. Despite the challenges posed by the input videos, in which some parts of the background are always occluded in the images, we are able to extract accurate models of the background that are effective in foreground segmentation. This would have been impossible using conventional background subtraction methods that operate on the frames of each camera separately. Moreover, fusion makes the per-camera background models consistent.
AB - We present an approach for estimating the 3D background model of a scene from a collection of synchronized videos. Unlike previous work, our method is fully automatic, does not require empty frames depicting just the background, and makes very mild assumptions about the foreground. The constraint on the cameras is that they should have sufficiently narrow baselines to enable multi-view stereo matching. Using the images and primarily the depth maps as inputs, our algorithm detects potential background pixels to generate initial per-camera background models, which are then fused to form the final, consistent 3D background model. We show results on diverse video sequences captured using different camera configurations. Despite the challenges posed by the input videos, in which some parts of the background are always occluded in the images, we are able to extract accurate models of the background that are effective in foreground segmentation. This would have been impossible using conventional background subtraction methods that operate on the frames of each camera separately. Moreover, fusion makes the per-camera background models consistent.
KW - Cameras
KW - Image color analysis
KW - Image reconstruction
KW - Image segmentation
KW - Solid modeling
KW - Three-dimensional displays
KW - Videos
UR - http://www.scopus.com/inward/record.url?scp=84961700542&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961700542&partnerID=8YFLogxK
U2 - 10.1109/3DV.2015.24
DO - 10.1109/3DV.2015.24
M3 - Conference contribution
AN - SCOPUS:84961700542
T3 - Proceedings - 2015 International Conference on 3D Vision, 3DV 2015
SP - 144
EP - 152
BT - Proceedings - 2015 International Conference on 3D Vision, 3DV 2015
A2 - Brown, Michael
A2 - Kosecka, Jana
A2 - Theobalt, Christian
T2 - 2015 International Conference on 3D Vision, 3DV 2015
Y2 - 19 October 2015 through 22 October 2015
ER -