Towards unsupervised semantic segmentation of street scenes from motion cues

Authors:
Hajar Sadeghi Sokeh;Stephen Gould
Affiliations:
The Australian National University, Canberra, ACT;The Australian National University, Canberra, ACT
Venue:
Proceedings of the 27th Conference on Image and Vision Computing New Zealand
Year:
2012

Citing 9
Cited 1

Single View Metrology

International Journal of Computer Vision
Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Latent dirichlet allocation

The Journal of Machine Learning Research
A Bayesian Hierarchical Model for Learning Natural Scene Categories

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Pan-tilt-zoom camera calibration and high-resolution mosaic generation

Computer Vision and Image Understanding - Special issue on omnidirectional vision and camera networks
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

International Journal of Computer Vision
Probabilistic Modeling of Scene Dynamics for Applications in Visual Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning semantic scene models by trajectory analysis

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Moving Cast Shadows Detection Using Ratio Edge

IEEE Transactions on Multimedia

Efficient extraction and representation of spatial information from video data

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motion provides a rich source of information about the world. It can be used as an important cue to analyse the behaviour of objects in a scene and consequently identify interesting locations within it. In this paper, given an unannotated video sequence of a dynamic scene from fixed viewpoint, we first present a set of useful motion features that can be efficiently extracted at each pixel by optical flow. Using these features, we then develop an algorithm that can extract motion topic models and identify semantically significant regions and landmarks in a complex scene from a short video sequence. For example, by watching a street scene our algorithm can extract meaningful regions such as roads and important landmarks such as parking spots. Our method is robust to complicating factors such as shadows and occlusions.