More Web Proxy on the site http://driver.im/

article

Integrating low-level and semantic features for object consistent segmentation

Authors:

Guoping QiuAuthors Info & Claims

Neurocomputing, Volume 119

Pages 74 - 81

https://doi.org/10.1016/j.neucom.2012.01.050

Published: 01 November 2013 Publication History

Abstract

The aim of semantic segmentation is to assign each pixel a semantic label. Numerous methods for semantic segmentation have been proposed in recent years and most of them chose pixel or superpixel as the processing primitives. However, as the information contained in a pixel or a superpixel is not discriminative enough, the outputs of these algorithms are usually not object consistent. To tackle this problem, we introduce the concept of object-like regions as a new and higher level processing primitive. We first experimentally showed that using groundtruth segments as processing primitives can boost semantic segmentation accuracy, and then proposed a novel method to produce regions that resemble the groundtruth regions, which we named them as 'object-like regions'. We achieve this by integrating state of the art low-level segmentation algorithms with typical semantic segmentation algorithms through a novel semantic feature feedback mechanism. We present experimental results on the publicly available image understanding dataset MSRC21 and stanford background dataset, showing that the new method can achieve relatively good semantic segmentation results with far fewer processing primitives.

References

[1]

Viola, P. and Jones, M.J., Robust real-time face detection. Int. J. Comput. Vision. v57. 137-154.

[2]

Gonfaus, J.M.J., Boix, X., Weijer, J.V.D., Bagdanov, A.D., Serrat, J., Jordi, G., van de Weijer, J. and Gonzalez, J., Harmony potentials for joint classification and segmentation. Int. J. Comput. Vision.

[3]

S. Gould, R. Fulton, D. Koller, Decomposing a scene into geometric and semantically consistent regions, in: ICCV, IEEE, 2009.

[4]

J. Shotton, J. Winn, C. Rother, A. Criminisi, TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation, in: ECCV, Springer, 2006.

[5]

T. Malisiewicz, A.A. Efros, Improving spatial support for objects via multiple segmentations, in: BMVC, BMVA, 2007.

[6]

B. Russell, W. Freeman, A. Efros, J. Sivic, A. Zisserman, Using multiple segmentations to discover objects and their extent in image collections, in: CVPR, IEEE, 2006, pp. 1605-1614.

[7]

J. Lafferty, A. McCallum, F. Pereira, Conditional random fields: probabilistic models for segmenting and labeling sequence data, in: ICML, 2001, Morgan Kaufmann Publisher, 2001.

Digital Library

[8]

T.H. Kim, K.M. Lee, S.U. Lee, Learning full pairwise affinities for spectral segmentation, in: CVPR, IEEE, 2010.

[9]

L. Ladicky, C. Russell, P. Kohli, P.H.S. Torr, Associative hierarchical CRFs for object class image segmentation, in: ICCV, IEEE, 2009, pp. 739-746.

[10]

J. Carreira, C. Sminchisescu, Constrained parametric min-cuts for automatic object segmentation, in: CVPR, October, IEEE, 2010.

[11]

Everingham, M., Gool, L., Williams, C.K.I., Winn, J. and Zisserman, A., The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision. v88. 303-338.

Digital Library

[12]

V. Lempitsky, A. Blake, C. Rother, Image segmentation by branch-and-mincut, in: ECCV, Springer, 2008, pp. 15-29.

[13]

B. Alexe, T. Deselaers, V. Ferrari, ClassCut for unsupervised class segmentation, in: ECCV, Springer, 2010.

[14]

S. Vicente, V. Kolmogorov, C. Rother, Cosegmentation revisited: models and optimization, in: ECCV, Springer, 2010.

[15]

B.C.B. Russell, A.A. Efros, J. Sivic, W.T.W. Freeman, A. Zisserman, Segmenting scenes by matching image composites, in: NIPS, 2009.

[16]

L.-j. Li, H. Su, E.P. Xing, L. Fei-fei, Object bank: a high-level image representation for scene classification and semantic feature sparsification, in: NIPS, 2010.

Digital Library

[17]

L. Torresani, M. Szummer, A. Fitzgibbon, Efficient object category recognition using classemes, in: ECCV, Springer, 2010.

[18]

Z. Tu, Auto-context and its application to high-level vision tasks, in: CVPR, IEEE, 2008.

[19]

S.K. Divvala, A.a. Efros, M. Hebert, Can similar scenes help surface layout estimation?, in: IEEE Workshop on Internet Vision, at CVPR'08, IEEE, 2008.

[20]

D. Martin, C. Fowlkes, D. Tal, J. Malik, A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, in: ICCV, July, IEEE, 2001, pp. 416-423.

[21]

C. Sutton, A. McCallum, Piecewise training of undirected models, in: 21st Conference on Uncertainty in Artificial Intelligence, 2005.

[22]

Pearl, J., Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. . 1988. Morgan Kaufmann.

[23]

Zhou, N., Cheung, W., Qiu, G. and Xue, X., A hybrid probabilistic model for unified collaborative and content-based image tagging. IEEE Trans. Pattern Anal. Mach. Intell. v33. 1281-1294.

Digital Library

[24]

Y.J. Lee, K. Grauman, Y. Jae Lee, Object-graphs for context-aware category discovery, in: CVPR, IEEE, 2010.

[25]

P. Gehler, S. Nowozin, On feature combination for multiclass object classification, in: ICCV, IEEE, 2009.

[26]

Felzenszwalb, P.F., Girshick, R.B., McAllester, D. and Ramanan, D., Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. v32. 1627-1645.

Digital Library

[27]

P. Arbelaez, M. Maire, C. Fowlkes, J. Malik, From contours to regions: an empirical evaluation, in: CVPR, IEEE, 2009, pp. 2294-2301.

[28]

Shi, J. and Malik, J., Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. v22. 888-905.

[29]

Zhang, L., Ji, Q. and Member, S., Image segmentation with a unified graphical model. IEEE Trans. Pattern Anal. Mach. Intell. v32. 1406-1425.

Digital Library

[30]

D. Munoz, J.A. Bagnell, M. Hebert, Stacked hierarchical labeling, in: ECCV, Springer, 2010.

Digital Library

[31]

J. Tighe, S. Lazebnik, SuperParsing: scalable nonparametric image parsing with superpixels, in: ECCV, Springer, 2010.

[32]

M. Kumar, D. Koller, Efficiently selecting regions for scene understanding, in: CVPR, IEEE, 2010.

[33]

J. Shotton, M. Johnson, R. Cipolla, Semantic texton forests for image categorization and segmentation, in: CVPR, IEEE, 2008.

[34]

T. Kim, K. Lee, S. Lee, Nonparametric higher-order learning for interactive segmentation, in: CVPR, IEEE, 2010, pp. 3201-3208.

Cited By

Zhang WChen QZhang WHe X(2018)Long-range terrain perception using convolutional neural networksNeurocomputing10.1016/j.neucom.2017.09.012275:C(781-787)Online publication date: 31-Jan-2018
https://dl.acm.org/doi/10.1016/j.neucom.2017.09.012
Yao XHan JGuo LBu SLiu Z(2015)A coarse-to-fine model for airport detection from remote sensing images using target-oriented visual saliency and CRFNeurocomputing10.1016/j.neucom.2015.02.073164:C(162-172)Online publication date: 21-Sep-2015
https://dl.acm.org/doi/10.1016/j.neucom.2015.02.073

Integrating low-level and semantic features for object consistent segmentation
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems

Recommendations

Integrating Low-level and Semantic Features for Object Consistent Segmentation
ICIG '11: Proceedings of the 2011 Sixth International Conference on Image and Graphics

The aim of semantic segmentation is to assign each pixel a semantic label. Numerous methods for semantic segmentation have been proposed in recent years and most of them chose pixel or super pixel as the processing primitives. However, as the ...
Traffic Scene Perception Based on Joint Object Detection and Semantic Segmentation
Abstract
Traffic scene visual perception technology is very important for intelligent transportation. Although the emerging panoptic segmentation is the most desirable sensing technology, object detection and semantic segmentation are relatively more ...
Semantic soft segmentation

Accurate representation of soft transitions between image regions is essential for high-quality image editing and compositing. Current techniques for generating such representations depend heavily on interaction by a skilled visual artist, as creating ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Neurocomputing

Neurocomputing Volume 119, Issue

November, 2013

489 pages

ISSN:0925-2312

Issue’s Table of Contents

Copyright © © 2013.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 November 2013

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhang WChen QZhang WHe X(2018)Long-range terrain perception using convolutional neural networksNeurocomputing10.1016/j.neucom.2017.09.012275:C(781-787)Online publication date: 31-Jan-2018
https://dl.acm.org/doi/10.1016/j.neucom.2017.09.012
Yao XHan JGuo LBu SLiu Z(2015)A coarse-to-fine model for airport detection from remote sensing images using target-oriented visual saliency and CRFNeurocomputing10.1016/j.neucom.2015.02.073164:C(162-172)Online publication date: 21-Sep-2015
https://dl.acm.org/doi/10.1016/j.neucom.2015.02.073

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents