TY - GEN
T1 - Robust probabilistic occupancy grid estimation from positive and negative distance fields
AU - Hu, Xiaoyan
AU - Mordohai, Philippos
PY - 2012
Y1 - 2012
N2 - We present an approach for estimating occupancy grids with an emphasis on robotics applications, where collision avoidance and robustness to severe noise are of more importance than high resolution. We build upon probabilistic techniques, typically used in robotics, and techniques based on signed distance fields, typically used in computer vision, to obtain an approach that is robust and also allows probabilistic reasoning on free and occupied space. The uniqueness of our method lies in the use of separate accumulators for positive and negative evidence for the occupancy of each voxel. This enables our representation to capture the uncertainty due to potential conflicts among the measurements instead of allowing contradictory evidence to cancel each other out. We show occupancy grids computed from multi-view stereo inputs on precisely and imprecisely calibrated image sequences. The ground truth that is available with the former dataset allows quantitative evaluation of the performance of our algorithm.
AB - We present an approach for estimating occupancy grids with an emphasis on robotics applications, where collision avoidance and robustness to severe noise are of more importance than high resolution. We build upon probabilistic techniques, typically used in robotics, and techniques based on signed distance fields, typically used in computer vision, to obtain an approach that is robust and also allows probabilistic reasoning on free and occupied space. The uniqueness of our method lies in the use of separate accumulators for positive and negative evidence for the occupancy of each voxel. This enables our representation to capture the uncertainty due to potential conflicts among the measurements instead of allowing contradictory evidence to cancel each other out. We show occupancy grids computed from multi-view stereo inputs on precisely and imprecisely calibrated image sequences. The ground truth that is available with the former dataset allows quantitative evaluation of the performance of our algorithm.
KW - 3D reconstruction
KW - occupancy grids
KW - stereo vision
UR - http://www.scopus.com/inward/record.url?scp=84872045490&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84872045490&partnerID=8YFLogxK
U2 - 10.1109/3DIMPVT.2012.58
DO - 10.1109/3DIMPVT.2012.58
M3 - Conference contribution
AN - SCOPUS:84872045490
SN - 9780769548739
T3 - Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
SP - 539
EP - 546
BT - Proceedings - 2nd Joint 3DIM/3DPVT Conference
T2 - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
Y2 - 13 October 2012 through 15 October 2012
ER -