Download presentation
Presentation is loading. Please wait.
1
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
2
Outline Introduction CRF Formulation of Static Salient Object Strong Contrast Center-Surround Histogram Color Spatial-Distribution Learning & Inference for the Model Formulation of Dynamic Salient Object Results Conclusion References
3
Introduction Image Labeling Problem Sky Building Lawn Plane Tree
4
Introduction Which kinds of information can be used for labeling? Features from individual sites Intensity, color, texture, … Interactions with neighboring sites Contextual information Vegetation Sky or Building?
5
Introduction Contextual information: 2 types of interactions Interaction with neighboring labels (Spatial smoothness of labels) neighboring sites tend to have similar labels(except at the discontinuities) Interactions with neighboring observed data Building Sky
6
Introduction Let be the label of the node of the image set S, and N i be the neighboring nodes of node i. Three kinds of information for image labeling Features from local node Interaction with neighboring labels Interaction with neighboring observed data node iS-{i}NiNi
7
Introduction General formulation: where and are called association potential and interaction potential.
8
Introduction Labels in Spatial Data are NOT independent! – spatially adjacent labels are often the same (Markov Random Fields and Conditional Random Fields) – spatially adjacent elements that have similar features often receive the same label (Conditional Random Fields) – spatially adjacent elements that have different features may not have correlated labels (Conditional Random Fields)
9
Salient Object? Salience Map?
10
Formulation of Static Salient Object Detection CRF model (static image): Salient object featurePairwise feature Strong contrast Center- surround histogram Color spatial- distribution Maximize!! Minimize!!
11
Strong Contrast Generate contrast map for each level of 6- level Gaussian pyramid. Then do linear combination. Input imageLevel 1 Level 4
12
Center-Surround Histogram Salient object usually has a “huge” difference from local area. ……. More different between 2 rectangles !
13
Center-Surround Histogram where …... ??
14
Color Spatial-Distribution The wider a color is distributed in the image, the less possible a salient object contains this color. Each pixel is assigned to a color component with the probability:
15
Color Spatial-Distribution Then the feature can be defined as a weighted sum:
16
Formulation of Static Salient Object Detection CRF model (static image): Salient object featurePairwise feature Strong contrast Center- surround histogram Color spatial- distribution Maximize!! Minimize!!
17
Learning & Inference for the Model The goal of CRF learning is to estimate the linear weights. Gradient descent Training images
18
Learning & Inference for the Model A training image for example: where An training image Label inferred this iterate Possible label Label per pixel
19
Learning & Inference for the Model Gradient descent: How to use ground-truth information? Where is the labeled ground-truth. t: iteration
20
Learning & Inference for the Model Situations: Ground-truth mistake!!!
21
Ground-Truth Mistake Solution: apply Gaussian function to weight every pixel in the rectangle.
22
Inference We should find the most probable labeling to maximize in training & detection. BP – Max-product Belief Propagation [Pearl ‘86] + Can be applied to any energy function – In vision results are usually worse than that of graph cuts – Does not always converge TRW - Max-product Tree-reweighted Message Passing [Wainwright, Jaakkola, Willsky ‘02], [Kolmogorov ‘05] + Can be applied to any energy function + Convergence guarantees for the algorithm in [Kolmogorov ’05]
23
Formulation of Dynamic Salient Object Detection Similar as static salient object detection! Static Salient feature Maximize!! Contrast of motion Center- surround histogram Spatial- distribution of motion Penalty term of motion
24
Results From left to right: input image, multi-scale contrast, center- surround histogram, color spatial distribution, and binary mask by CRF.
25
Results From left to right: Fuzzy growing based method Salience map Their approach Ground-truth
26
Results 1. multi-scale contrast 2. center-surround histogram 3. color spatial distribution 4. combination all Image set AImage set B 1. FG 2. SM 3. their approach
27
Conclusion They model the salient object detection by CRF, where a group of salient features are combined through CRF learning. It’s a set of novel local, regional & global salient features to define a generic salient object. Multi-object & no object cases are left as future work.
28
References (paper & book) “Learning to Detect A Salient Object”, CVPR 2007, PAMI 2010. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.91.4387&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.91.4387&rep=rep1&type=pdf “A Model of Saliency-Based Visual Attention for Rapid Scene Analysis”, PAMI, 1998. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.65.2199&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.65.2199&rep=rep1&type=pdf “Pattern Recognition and Machine Learning”, C. M. Bishop. http://www.library.wisc.edu/selectedtocs/bg0137.pdf http://www.library.wisc.edu/selectedtocs/bg0137.pdf
29
References (about CRF) “Discriminative Random Fields”, IJCV, 2006. http://citeseerx.ist.psu.edu/viewdoc/download?do i=10.1.1.116.4695&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?do i=10.1.1.116.4695&rep=rep1&type=pdf “Conditional Random Fields: An Introduction”, H. M. Wallach. http://citeseerx.ist.psu.edu/viewdoc/download?do i=10.1.1.64.436&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?do i=10.1.1.64.436&rep=rep1&type=pdf “Log-linear models & conditional random fields”, C. Elkan, 2008. http://cseweb.ucsd.edu/~elkan/250B/cikmtutoria l.pdf http://cseweb.ucsd.edu/~elkan/250B/cikmtutoria l.pdf
30
References (about TRW) “MAP estimation via agreement on (hyper) trees: Message-passing and linear programming approaches”, IEEE transaction on Information Theory, 2005. http://arxiv.org/pdf/cs/0508070 http://arxiv.org/pdf/cs/0508070 “Convergent Tree-Reweighted Message Passing for Energy Minimization”, PAMI, 2006. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1. 100.2409&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1. 100.2409&rep=rep1&type=pdf “A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors”, PAMI, 2008. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1. 142.4997&rep=rep1&type=pdf http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1. 142.4997&rep=rep1&type=pdf
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.