object segmentation based on multiple features fusion and conditional random field

17
Object Segmentation Based on Multiple Features Fusion and Conditional Random Field CASIA_IGIT National Laboratory of Pattern Recognition(NLPR) Institute of Automation, Chinese Academy of Sciences(CASIA) Reporter Kun Ding 丁丁丁 () 2013.10.17

Upload: irving

Post on 23-Feb-2016

34 views

Category:

Documents


0 download

DESCRIPTION

Object Segmentation Based on Multiple Features Fusion and Conditional Random Field. CASIA_IGIT National Laboratory of Pattern Recognition(NLPR) Institute of Automation, Chinese Academy of Sciences(CASIA). Reporter: Kun Ding (丁昆) 2013.10.17. Outline. System Overview System Characteristics - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Object Segmentation Based on Multiple Features Fusion and Conditional Random Field

CASIA_IGIT

National Laboratory of Pattern Recognition(NLPR)Institute of Automation, Chinese Academy of Sciences(CASIA)

Reporter: Kun Ding(丁昆)2013.10.17

Page 2: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Outline• System Overview

• System Characteristics

•Results and Conclusions

Page 3: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Outline• System Overview

• System Characteristics

•Results and Conclusions

Page 4: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Overview

•Object Segmentation Pipeline

FeatureEngineering

Superpixel Segmentation

Superpixels Features Probabilistic Output Final ResultsInput Image

Feature Extraction SVM Classification GrabCut

Stage 1 : Superpixel Classification

Stage 2 : Pixel-based CRF Smoothing

Page 5: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Overview

• Superpixel Classification• Superpixel Segmentation • Graph-based image segmentation

• Feature Extraction: • To be detailed in next section

• SVM Classification[1]• RBF kernel with Probabilistic Output

Page 6: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Overview

•Pixel-Based CRF Smoothing• Fusing several kinds of information as data term• Solving with GrabCut with only a few iterations

SVM Probabilistic Output CRF Smoothing Output

BinarizeFirst Iteration

SecondIteration

Page 7: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Outline

• System Overview

• System Characteristics

•Results and Conclusions

Page 8: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Characteristics • Superpixel Segmentation -- Efficient Graph-Based Image Segmentation[2]• Fast, property of edge-preserving• Speeding up the whole procedure• Improving the separability between foreground and

background

Superpixels and their edge-preserving property

Page 9: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Characteristics • Feature Engineering – Superpixel-Based Multiple Features Fusion

Gradient

Texture

Color and skin

Geometrical

Saliency

Results of Object Detection

PCA

Dense SIFT[3][4] dictionary with Bag-of-Words description

Multi-scale LBP histogram

RGB histogram and HS histogram with skin detection

Position, direction and roundness

Color spatial distribution, multi-scale local and global contrast

Probability derived from AdaBoost, with manifold ranking[6] refinement

Page 10: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Characteristics • Feature Engineering – Superpixel-Based Multiple Features Fusion• Illustration of object detection

Object Detection result Rectangle Density as Probability Refined with Manifold Ranking

Page 11: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

System Characteristics •Pixel-Based CRF Smoothing – GrabCut[7]•Modified data term • Solving by maxflow iteratively

SVM Result Object Detection Result

GMM Result for Foreground and Background

CRF Smoothing Output

Page 12: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Outline• System Overview

• System Characteristics

•Results and Conclusions

Page 13: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Conclusion and Results Exhibition•Results Exhibition

Page 14: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Conclusion and Results Exhibition•Conclusion• Superpixel classification• Feature fusion works• CRF smoothing improves the results of SVM

• Object parts sometimes lost• Context information is inadequate

Page 15: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

[1] C.-C. Chang and C.-J. Lin. LIBSVM: a library for support vector machines, 2001. Software available at http: //www.csie.ntu.edu.tw/˜cjlin/libsvm.[2] Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004, 59(2): 167-181.[3] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.[4] Vedaldi A, Fulkerson B. VLFeat: An open and portable library of computer vision algorithms[C]//Proceedings of the international conference on Multimedia. ACM, 2010: 1469-1472.

Selected References

Page 16: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Selected References[5] Liu T, Yuan Z, Sun J, et al. Learning to detect a salient object[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2011, 33(2): 353-367.[6] Chuan Yang, Lihe Zhang, Huchuan Lu, Minghsuan Yang, Saliency Detection via Graph-Based Manifold Ranking, CVPR2013, P3166-3173[7] Rother C, Kolmogorov V, Blake A. Grabcut: Interactive foreground extraction using iterated graph cuts[C]//ACM Transactions on Graphics (TOG). ACM, 2004, 23(3): 309-314.

Page 17: Object Segmentation Based on  Multiple Features Fusion and Conditional Random Field

Thank you very much!Any questions?

CASIA_IGIT

Leader: Ying Wang (王颖)Members: Kun Ding (丁昆)

Huxiang Gu (谷鹄翔)Yongchao Gong (宫永超)

E-mails: {ywang, kding, hxgu, yongchao.gong}@nlpr.ia.ac.cn