Cited By
View all- Wigness MRogers J(2017)Unsupervised Semantic Scene Labeling for Streaming Data2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR.2017.626(5910-5919)Online publication date: Jul-2017
Towards unsupervised semantic segmentation of street scenes from motion cues
Pages 232 - 237
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.
References
[1]
Virat video dataset. http://www.viratdata.org/, 2011.
[2]
D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. Journal of Machine Learning Research, 3: 993--1022, 2003.
[3]
W. Cao, Y. Yan, and S. Li. Unsupervised color-texture image segmentation based on a new clustering method. JNIT, 1(2): 96--102, 2010.
[4]
N. J. Carlos, W. Hongcheng, and F.-F. Li. Unsupervised learning of human action categories using spatial-temporal words. IJCV, 79(3): 299--318, 2008.
[5]
A. Criminisi, I. D. Reid, and A. Zisserman. Single view metrology. IJCV, 40(2): 123--148, 2000.
[6]
L. Fei-Fei and P. Perona. A bayesian hierarchical model for learning natural scene categories. CVPR, pages 524--531, 2005.
[7]
R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2004.
[8]
B. K. P. Horn and B. G. Schunck. Determining optical flow. Artificial Intelligence, 17: 185--203, 1981.
[9]
T. M. Hospedales, S. Gong, and T. Xiang. A markov clustering topic model for mining behaviour in video. In ICCV, pages 1165--1172, 2009.
[10]
C. Li and Y. Zhao. Camera self-calibration method by using three orthogonal vanishing points. AISS: Advances in Information Sciences and Service Sciences, 3(8): 45--52, 2011.
[11]
X.-H. Phan and C.-T. Nguyen. Gibbslda++: A c/c++ implementation of latent dirichlet allocation (lda). http://gibbslda.sourceforge.net/, 2007.
[12]
I. Saleemi, K. Shafique, and M. Shah. Probabilistic modeling of scene dynamics for applications in visual surveillance. IEEE Trans. Pattern Anal. Mach. Intell., 31(8): 1472--1485, 2009.
[13]
J. Seetha, R. Varadharajan, and V. Vaithiyanathan. Unsupervised learning algorithm for color texture segmentation based multiscale image fusion. EJSR, 67(4), 2012.
[14]
S. N. Sinha and M. Pollefeys. Pan-tilt-zoom camera calibration and high-resolution mosaic generation. Comput. Vis. Image Underst., 103: 170--183, 2006.
[15]
J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman. Discovering object categories in image collections. In Proceedings of the International Conference on Computer Vision, 2005.
[16]
D. Sun, S. Roth, and M. J. Black. Secrets of optical flow estimation and their principles. In CVPR, pages 2432--2439, 2010.
[17]
X. Wang and E. Grimson. Spatial latent dirichlet allocation. In NIPS, 2007.
[18]
X. Wang, K. Tieu, and E. Grimson. Learning semantic scene models by trajectory analysis. In In ECCV (3), pages 110--123, 2006.
[19]
W. Zhang, X. Fang, X. K. Yang, and Q. M. J. Wu. Moving cast shadows detection using ratio edge. IEEE Transactions on Multimedia, 9(6): 1202--1214, 2007.
Index Terms
- Towards unsupervised semantic segmentation of street scenes from motion cues
Recommendations
Semantic Segmentation of Street Scenes Using Disparity Information
Image and GraphicsAbstractIn this work, we address the task of semantic segmentation in street scenes. Recent approaches based on convolutional neural networks have shown excellent results on several semantic segmentation benchmarks. Most of them, however, only exploit RGB ...
Rendering cartoon-style motion cues in post-production video
Special issue: Vision and computer graphicsThe contribution of this paper is a novel non-photorealistic rendering (NPR) system capable of rendering motion within a video sequence in artistic styles. A variety of cartoon-style motion cues may be inserted into a video sequence, including ...
Tracking Using Motion Patterns for Very Crowded Scenes
Proceedings, Part II, of the 12th European Conference on Computer Vision --- ECCV 2012 - Volume 7573This paper proposes Motion Structure Tracker MST to solve the problem of tracking in very crowded structured scenes. It combines visual tracking, motion pattern learning and multi-target tracking. Tracking in crowded scenes is very challenging due to ...
Comments
Information & Contributors
Information
Published In
November 2012
547 pages
Copyright © 2012 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
- HRS: Hoare Research Software Ltd.
- Google Inc.
- Dept. of Information Science, Univ.of Otago: Department of Information Science, University of Otago, Dunedin, New Zealand
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 26 November 2012
Check for updates
Author Tags
Qualifiers
- Poster
Conference
IVCNZ '12
Sponsor:
- HRS
- Dept. of Information Science, Univ.of Otago
Acceptance Rates
Overall Acceptance Rate 55 of 74 submissions, 74%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 102Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Feb 2025
Other Metrics
Citations
Cited By
View all- Wigness MRogers J(2017)Unsupervised Semantic Scene Labeling for Streaming Data2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR.2017.626(5910-5919)Online publication date: Jul-2017
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in