Manhattan scene understanding using monocular, stereo, and 3D features

Authors:
Alex Flint;David Murray;Ian Reid
Affiliations:
Active Vision Laboratory, Oxford University, UK;Active Vision Laboratory, Oxford University, UK;Active Vision Laboratory, Oxford University, UK
Venue:
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Year:
2011

Citing 0
Cited 4

Capturing indoor scenes with smartphones

Proceedings of the 25th annual ACM symposium on User interface software and technology
Self-similar sketch

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Efficient exact inference for 3d indoor scene understanding

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Building facade detection, segmentation, and parameter estimation for mobile robot stereo vision

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through structure-from-motion. We combine geometric and photometric cues in a Bayesian framework, building on recent successes leveraging the indoor Manhattan assumption in monocular vision. We focus on indoor environments and show how to extract key boundaries while ignoring clutter and decorations. To achieve this we present a graphical model that relates photometric cues learned from labeled data, stereo photo-consistency across multiple views, and depth cues derived from structure-from-motion point clouds. We show how to solve MAP inference using dynamic programming, allowing exact, global inference in ~100 ms (in addition to feature computation of under one second) without using specialized hardware. Experiments show our system out-performing the state-of-the-art.