1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.

Slides:



Advertisements
Similar presentations
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
Advertisements

Spectral graph reduction for image and streaming video segmentation Fabio Galasso 1 Margret Keuper 2 Thomas Brox 2 Bernt Schiele 1 1 Max Planck Institute.
Learning to Combine Bottom-Up and Top-Down Segmentation Anat Levin and Yair Weiss School of CS&Eng, The Hebrew University of Jerusalem, Israel.
Shape Sharing for Object Segmentation
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
ADS lab NCKU1 Michael Maire, Pablo Arbelaez, Charless Fowlkes, and Jitendra Malik university of California, Berkeley – Berkeley university of California,
1 P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI, Student: Hsin-Min Cheng.
Boundary Extraction in Natural Images Using Ultrametric Contour Maps Pablo Arbeláez Université Paris Dauphine Presented by Derek Hoiem.
Computer Vision Group University of California Berkeley Ecological Statistics of Good Continuation: Multi-scale Markov Models for Contours Xiaofeng Ren.
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
Ghunhui Gu, Joseph J. Lim, Pablo Arbeláez, Jitendra Malik University of California at Berkeley Berkeley, CA
Biased Normalized Cuts 1 Subhransu Maji and Jithndra Malik University of California, Berkeley IEEE Conference on Computer Vision and Pattern Recognition.
Lecture 6 Image Segmentation
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Image segmentation. The goals of segmentation Group together similar-looking pixels for efficiency of further processing “Bottom-up” process Unsupervised.
Algorithms & Applications in Computer Vision Lihi Zelnik-Manor Lecture 11: Structure from Motion.
Segmentation. Terminology Segmentation, grouping, perceptual organization: gathering features that belong together Fitting: associating a model with observed.
Computer Vision Group University of California Berkeley 1 Learning Scale-Invariant Contour Completion Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Fast, Multiscale Image Segmentation: From Pixels to Semantics Ronen Basri The Weizmann Institute of Science Joint work with Achi Brandt, Meirav Galun,
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues David R. Martin Charless C. Fowlkes Jitendra Malik.
Understanding Gestalt Cues and Ecological Statistics using a Database of Human Segmented Images Charless Fowlkes, David Martin and Jitendra Malik Department.
Visual Grouping and Recognition Jitendra Malik U.C. Berkeley Jitendra Malik U.C. Berkeley.
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Region-based Voting Exemplar 1 Query 1 Exemplar 2.
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
1 Learning to Detect Natural Image Boundaries David Martin, Charless Fowlkes, Jitendra Malik Computer Science Division University of California at Berkeley.
CVR05 University of California Berkeley 1 Familiar Configuration Enables Figure/Ground Assignment in Natural Scenes Xiaofeng Ren, Charless Fowlkes, Jitendra.
Berkeley Vision GroupNIPS Vancouver Learning to Detect Natural Image Boundaries Using Local Brightness,
CVR05 University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes, Jitendra Malik.
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
A Database of Human Segmented Natural Images and Two Applications David Martin, Charless Fowlkes, Doron Tal, Jitendra Malik UC Berkeley
1 The Ecological Statistics of Grouping by Similarity Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University of California.
Visual Grouping and Recognition David Martin UC Berkeley David Martin UC Berkeley.
WORD-PREDICTION AS A TOOL TO EVALUATE LOW-LEVEL VISION PROCESSES Prasad Gabbur, Kobus Barnard University of Arizona.
1 Segmentation with Scene and Sub-Scene Categories Joseph Djugash Input Image Scene/Sub-Scene Classification Segmentation.
Computational Vision Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
MSRI University of California Berkeley 1 Recovering Human Body Configurations using Pairwise Constraints between Parts Xiaofeng Ren, Alex Berg, Jitendra.
Segmentation and Perceptual Grouping. The image of this cube contradicts the optical image.
On Measuring * the Ecological Validity of Local Figure-Ground Cues Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University.
1 Occlusions – the world is flat without them! : Learning-Based Methods in Vision A. Efros, CMU, Spring 2009.
1 How do ideas from perceptual organization relate to natural scenes?
1 Ecological Statistics and Perceptual Organization Charless Fowlkes work with David Martin and Jitendra Malik at University of California at Berkeley.
Computer Vision Group University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Presentation By Michael Tao and Patrick Virtue. Agenda History of the problem Graph cut background Compute graph cut Extensions State of the art Continued.
Perceptual Organization: Segmentation and Optical Flow.
Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik, U.C. Berkeley We present a model of edge and region grouping.
Heather Dunlop : Advanced Perception January 25, 2006
Graph-based Segmentation
The Three R’s of Vision Jitendra Malik.
MRFs and Segmentation with Graph Cuts Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/24/10.
Recognition using Regions (Demo) Sudheendra V. Outline Generating multiple segmentations –Normalized cuts [Ren & Malik (2003)] Uniform regions –Watershed.
Visual Grouping and Recognition Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Geodesic Saliency Using Background Priors
Efficient Color Boundary Detection with Color-opponent Mechanisms CVPR2013 Posters.
Segmentation & Grouping Tuesday, Sept 23 Kristen Grauman UT-Austin.
Image Segmentation Superpixel methods Speaker: Hsuan-Yi Ko.
Object Recognition by Integrating Multiple Image Segmentations Caroline Pantofaru, Cordelia Schmid, Martial Hebert ECCV 2008 E.
Computational Vision Jitendra Malik University of California, Berkeley.
Representation in Vision Derek Hoiem CS 598, Spring 2009 Jan 22, 2009.
In: Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 30, Nr. 1 (2008), p Group of Adjacent Contour Segments for Object Detection.
Finding Boundaries Computer Vision CS 143, Brown James Hays 09/28/11 Many slides from Lana Lazebnik, Steve Seitz, David Forsyth, David Lowe, Fei-Fei Li,
Image segmentation.
Learning Image Statistics for Bayesian Tracking Hedvig Sidenbladh KTH, Sweden Michael Black Brown University, RI, USA
Contours and Junctions in Natural Images
Learning to Combine Bottom-Up and Top-Down Segmentation
Grouping/Segmentation
Learning complex visual concepts
Presentation transcript:

1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless Fowlkes, David Martin, Xiaofeng Ren, Michael Maire, Pablo Arbelaez )

2

3 Attneave’s Cat (1954) Line drawings convey most of the information

4 Contours and junctions are fundamental… Key to recognition, inference of 3D scene properties, visually- guided manipulation and locomotion… This goes beyond local, V1-like, edge-detection. Contours are the result of perceptual organization, grouping and figure/ground processing

5 Some computer vision history… Local Edge Detection was much studied in the 1970s and early 80s (Sobel, Rosenfeld, Binford- Horn, Marr-Hildreth, Canny …) Edge linking exploiting curvilinear continuity was studied as well (Rosenfeld, Zucker, Horn, Ullman …) In the 1980s, several authors argued for perceptual organization as a precursor to recognition (Binford, Witkin and Tennebaum, Lowe, Jacobs …)

6 However in the 90s … 1.We realized that there was more to images than edges Biologically inspired filtering approaches (Bergen & Adelson, Malik & Perona..) Pixel based representations for recognition (Turk & Pentland, Murase & Nayar, LeCun …) 2.We lost faith in the ability of bottom-up vision Do minimal bottom up processing, e.g. tiled orientation histograms don’t even assume that linked contours or junctions can be extracted Matching with memory of previously seen objects then becomes the primary engine for parsing an image. √ ?

7 At Berkeley, we took a contrary view… 1.Collect Data Set of Human segmented images 2.Learn Local Boundary Model for combining brightness, color and texture 3.Global framework to capture closure, continuity 4.Detect and localize junctions 5.Integrate low, mid and high-level information for grouping and figure-ground segmentation

8 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", ICCV, 2001ICCV Berkeley Segmentation DataSet [BSDS]

9

10

11

12

13

14

15 Outline 1.Collect Data Set of Human segmented images 2.Learn Local Boundary Model for combining brightness, color and texture 3.Global framework to capture closure, continuity 4.Detect and localize junctions 5.Integrate low, mid and high-level information for grouping and figure-ground segmentation

16 Contours can be defined by any of a number of cues (P. Cavanagh)

17 Grill-Spector et al., Neuron 1998 Objects from disparity Objects from texture Objects from luminance Cue-Invariant Representations Line drawings Gray level photographs Objects from motion

18 Martin, Fowlkes, Malik PAMI 04 Image Boundary Cues Model PbPb Brightness Color Texture Challenges: texture cue, cue combination Goal: learn the posterior probability of a boundary P b (x,y,  ) from local information only Cue Combination

19 Individual Features 1976 CIE L*a*b* colorspace Brightness Gradient BG(x,y,r,  ) –Difference of L* distributions Color Gradient CG(x,y,r,  ) –Difference of a*b* distributions Texture Gradient TG(x,y,r,  ) –Difference of distributions of V1-like filter responses  r (x,y) These are combined using logistic regression

20 Various Cue Combinations

21 Outline 1.Collect Data Set of Human segmented images 2.Learn Local Boundary Model for combining brightness, color and texture 3.Global framework to capture closure, continuity 4.Detect and localize junctions 5.Integrate low, mid and high-level information for grouping and figure-ground segmentation

22 Exploiting global constraints: Image Segmentation as Graph Partitioning Build a weighted graph G=(V,E) from image V:image pixels E:connections between pairs of nearby pixels Partition graph so that similarity within group is large and similarity between groups is small -- Normalized Cuts [Shi & Malik 97]

23

24 Normalized Cuts as a Spring-Mass system Each pixel is a point mass; each connection is a spring: Fundamental modes are generalized eigenvectors of (D - W) x = Dx

25 Eigenvectors carry contour information

26

27 We do not try to find regions from the eigenvectors, so we avoid the “broken sky” artifacts of Ncuts..

28 The Benefits of Globalization Maire, Arbelaez, Fowlkes, Malik, CVPR 08

29 Comparison to other approaches

30

31 Outline 1.Collect Data Set of Human segmented images 2.Learn Local Boundary Model for combining brightness, color and texture 3.Global framework to capture closure, continuity 4.Detect and localize junctions 5.Integrate low, mid and high-level information for grouping and figure-ground segmentation

32 Detecting Junctions

33

34 Benchmarking corner detection

35

36 Outline 1.Collect Data Set of Human segmented images 2.Learn Local Boundary Model for combining brightness, color and texture 3.Global framework to capture closure, continuity 4.Detect and localize junctions 5.Integrate low, mid and high-level information for grouping and figure-ground segmentation 1.Ren, Fowlkes, Malik, IJCV ‘08 2.Ren, Fowlkes, Malik, ECCV ‘06

37 Ren, Fowlkes, Malik ECCV ‘06 Human subjects label groundtruth figure/ground assignments in natural images. Shapemes encode high-level knowledge in a generic way, capturing local figure/ground cues. A conditional random field incorporates junction cues and enforces global consistency. Grouping / Segmentation Figure/Ground Organization Object and Scene Recognition

38 Better object recognition using previous version of Pb Ferrari, Fevrier, Jurie and Schmid (PAMI 08) Shotton, Blake and Cipolla (PAMI 08)

39 Forty years of contour detection 39 Roberts (1965) Sobel (1968) Prewitt (1970) Marr Hildreth (1980) Canny (1986) Perona Malik (1990) Martin Fowlkes Malik (2004) Maire Arbelaez Fowlkes Malik (2008)

40 Forty years of contour detection 40 ??? (2013) Roberts (1965) Sobel (1968) Prewitt (1970) Marr Hildreth (1980) Canny (1986) Perona Malik (1990) Martin Fowlkes Malik (2004) Maire Arbelaez Fowlkes Malik (2008)