Superpixel Segmentation using Depth

Similar documents
Superpixel Segmentation: An Evaluation

arxiv: v1 [cs.cv] 14 Sep 2015

Generating Object Candidates from RGB-D Images and Point Clouds

Superpixel Segmentation Based Gradient Maps on RGB-D Dataset

DEPTH-ADAPTIVE SUPERVOXELS FOR RGB-D VIDEO SEGMENTATION. Alexander Schick. Fraunhofer IOSB Karlsruhe

Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds

SCALP: Superpixels with Contour Adherence using Linear Path

Resolution-independent superpixels based on convex constrained meshes without small angles

SCALP: Superpixels with Contour Adherence using Linear Path

Content-based Image and Video Retrieval. Image Segmentation

This is an author-deposited version published in : Eprints ID : 15223

SUPERPIXELS: THE END OF PIXELS IN OBIA. A COMPARISON OF STATE-OF-THE- ART SUPERPIXEL METHODS FOR REMOTE SENSING DATA

Compact Watershed and Preemptive SLIC: On improving trade-offs of superpixel segmentation algorithms

Superpixel Segmentation using Linear Spectral Clustering

Cluster Sensing Superpixel and Grouping

Superpixels and Polygons using Simple Non-Iterative Clustering

Accelerated gslic for Superpixel Generation used in Object Segmentation

Growing Depth Image Superpixels for Foliage Modeling

Image Segmentation. Lecture14: Image Segmentation. Sample Segmentation Results. Use of Image Segmentation

Edge-Based Split-and-Merge Superpixel Segmentation

SMURFS: Superpixels from Multi-scale Refinement of Super-regions

Superpixels Generating from the Pixel-based K-Means Clustering

Depth SEEDS: Recovering Incomplete Depth Data using Superpixels

Graph based Image Segmentation using improved SLIC Superpixel algorithm

CRF Based Point Cloud Segmentation Jonathan Nation

Segmentation in electron microscopy images

Discrete-Continuous Gradient Orientation Estimation for Faster Image Segmentation

Superpixels: An Evaluation of the State-of-the-Art

Superpixels via Pseudo-Boolean Optimization

Superpixels: An Evaluation of the State-of-the-Art

Towards Spatio-Temporally Consistent Semantic Mapping

Multiscale Superpixels and Supervoxels Based on Hierarchical Edge-Weighted Centroidal Voronoi Tessellation

Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels

Temporal Superpixels Based on Proximity-Weighted Patch Matching

IFT-SLIC: A general framework for superpixel generation based on simple linear iterative clustering and image foresting transform

Superpixels and Supervoxels in an Energy Optimization Framework

Grouping and Segmentation

arxiv: v1 [cs.cv] 16 Sep 2013

Image partitioning into convex polygons

Maximum Cohesive Grid of Superpixels for Fast Object Localization

EIKONAL-BASED VERTICES GROWING AND ITERATIVE SEEDING FOR EFFICIENT GRAPH-BASED SEGMENTATION. P. Buyssens, M. Toutain, A. Elmoataz, O.

Recap from Monday. Visualizing Networks Caffe overview Slides are now online

Keywords Image Segmentation, Pixels, Superpixels, Superpixel Segmentation Methods

CS381V Experiment Presentation. Chun-Chen Kuo

Object Recognition and Segmentation in Indoor Scenes from RGB-D Images

CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep

Learning Superpixels with Segmentation-Aware Affinity Loss

Superpixel Optimization using Higher-Order Energy

3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field

PAPER Special Section on Machine Vision and its Applications Homogeneous Superpixels from Markov Random Walks

3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field

FAST 3D POINT CLOUD SEGMENTATION USING SUPERVOXELS WITH GEOMETRY AND COLOR FOR 3D SCENE UNDERSTANDING

Semantic Instance Labeling Leveraging Hierarchical Segmentation

Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction

Learning Depth-Sensitive Conditional Random Fields for Semantic Segmentation of RGB-D Images

Real-time Stereo and Flow-based Video Segmentation with Superpixels

Robotics Programming Laboratory

SymmSLIC: Symmetry Aware Superpixel Segmentation

LEARNING BOUNDARIES WITH COLOR AND DEPTH. Zhaoyin Jia, Andrew Gallagher, Tsuhan Chen

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Robot localization method based on visual features and their geometric relationship

Medial Features for Superpixel Segmentation

Structure-sensitive Superpixels via Geodesic Distance

A Video Representation Using Temporal Superpixels

Sparse Point Cloud Densification by Using Redundant Semantic Information

Fusion of colour and depth partitions for depth map coding

Segmentation and Grouping

Title: Adaptive Region Merging Segmentation of Airborne Imagery for Roof Condition Assessment. Abstract:

Semantic Parsing for Priming Object Detection in RGB-D Scenes

Video Segmentation. Jason J. Corso! Chenliang Xu! Irfan Essa! Matthias Grundmann! Google Research! Georgia Tech! University of Michigan!

Joint Color and Depth Segmentation Based on Region Merging and Surface Fitting

What Happened to the Representations of Perception? Cornelia Fermüller Computer Vision Laboratory University of Maryland

GLASS OBJECT SEGMENTATION BY LABEL TRANSFER ON JOINT DEPTH AND APPEARANCE MANIFOLDS. Tao Wang, Xuming He, Nick Barnes

A Survey on Segmentation of Spine MR Images Using Superpixels

Segmentation and Grouping

Object Partitioning using Local Convexity

Superframes, A Temporal Video Segmentation

Separating Objects and Clutter in Indoor Scenes

Segmentation and Grouping April 19 th, 2018

SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications

Joint Semantic and Geometric Segmentation of Videos with a Stage Model

Lecture 16 Segmentation and Scene understanding

Robust Segmentation of Cluttered Scenes Using RGB-Z Images

Closing the Loop for Edge Detection and Object Proposals

A Feature Clustering Approach Based on Histogram of Oriented Optical Flow and Superpixels

Semantic Classification of Boundaries from an RGBD Image

Segmentation & Clustering

Direction Matters: Depth Estimation with a Surface Normal Classifier

Superpixel-based Color Transfer

Saliency Detection in Aerial Imagery

ECSE 626 Course Project : A Study in the Efficient Graph-Based Image Segmentation

CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu. Lectures 21 & 22 Segmentation and clustering

Martian lava field, NASA, Wikipedia

Homogeneous Superpixels from Random Walks

Improving an Object Detector and Extracting Regions using Superpixels

Fast Border Ownership Assignment with Bio-Inspired Features

Human Upper Body Pose Estimation in Static Images

Urban Scene Segmentation, Recognition and Remodeling. Part III. Jinglu Wang 11/24/2016 ACCV 2016 TUTORIAL

Estimating the 3D Layout of Indoor Scenes and its Clutter from Depth Sensors

Object Tracking using Superpixel Confidence Map in Centroid Shifting Method

Transcription:

Superpixel Segmentation using Depth Information Superpixel Segmentation using Depth Information David Stutz June 25th, 2014 David Stutz June 25th, 2014 01

Introduction - Table of Contents 1 Introduction Oversegmentation and Superpixels Motivation 2 SEEDS Hierarchy and Histograms Iterations Parameters 3 Results Qualitative 4 Depth Information David Stutz June 25th, 2014 2

Introduction - Oversegmentation and Superpixels Oversegmentation and Superpixels Segmentation and Oversegmentation are not clearly defined throughout the literature... Notion (Superpixel) The term superpixel is used to describe the oversegmentation of an image into groups of pixels using low-level features. Well, but what is the difference between usual segmentation and oversegmentation? David Stutz June 25th, 2014 3

Introduction - Oversegmentation and Superpixels Oversegmentation and Superpixels Figure: Original image. David Stutz June 25th, 2014 4

Introduction - Oversegmentation and Superpixels Oversegmentation and Superpixels Figure: Ground truth segmentation one segment per object. David Stutz June 25th, 2014 5

Introduction - Oversegmentation and Superpixels Oversegmentation and Superpixels Figure: Superpixel segmentation multiple superpixels per object. David Stutz June 25th, 2014 6

Introduction - Motivation Motivation There is a whole bunch of superpixel algorithms out there [4] [1] [13] [16] [15] [10] [3] [12]... Only few provide near-realtime [4] [1]... Some of them utilize depth information [1] [10] [15]... SEEDS [4] provides state of the art performance and near-realtime runtime on 2D data! Goal: integrate depth information into SEEDS. David Stutz June 25th, 2014 7

SEEDS - Table of Contents 1 Introduction Oversegmentation and Superpixels Motivation 2 SEEDS Hierarchy and Histograms Iterations Parameters 3 Results Qualitative 4 Depth Information David Stutz June 25th, 2014 8

SEEDS - Overview Overview Given an initial superpixel segmentation, SEEDS iteratively refines this segmentation by... exchanging blocks of pixels between neighboring superpixels (block updates), and exchanging pixels between neighboring superpixels (pixel updates). The initial superpixel segmentation will be a uniform grid. This grid is subdivided to define blocks of pixels. David Stutz June 25th, 2014 9

SEEDS - Overview Overview Figure: Initial superpixel segmentation. David Stutz June 25th, 2014 10

SEEDS - Hierarchy and Histograms Hierarchy and Histograms Step 1 Set up a hierarchy SEEDS is based on a simple hierarchy consisting of L levels... Group w min h min pixel to form one block on level l = 1; and group 4 blocks at level (l 1) to form one block at level l > 1. The blocks at level L represent the initial superpixel segmentation! Step 2 Compute color histograms for each block at level l > 0. David Stutz June 25th, 2014 11

SEEDS - Hierarchy and Histograms Hierarchy and Histograms Figure: Initial blocks at level three (with a total of four levels). David Stutz June 25th, 2014 12

SEEDS - Hierarchy and Histograms Hierarchy and Histograms Figure: Initial blocks at level two (with a total of four levels). David Stutz June 25th, 2014 13

SEEDS - Iterations Block Updates Step 3 Perform block updates For each level l = L 1,..., 1: For each block at level l: If a neighboring block belongs to a different superpixel (= label), consider changing the label. When to change the label? If the histogram intersection of the block histogram and the superpixel histogram is higher than before... David Stutz June 25th, 2014 14

SEEDS - Iterations Hierarchy and Histograms Figure: Block updates at level three. David Stutz June 25th, 2014 15

SEEDS - Iterations Hierarchy and Histograms Figure: Block updates at level two. David Stutz June 25th, 2014 16

SEEDS - Iterations Hierarchy and Histograms Figure: Block updates at level one. David Stutz June 25th, 2014 17

SEEDS - Iterations Pixel Updates Step 4 Perform pixel updates For each pixel: If a neighboring pixel belongs to a different superpixel (= label), consider changing the label. When to change the label? If the color of the pixel is represented well in the superpixel histogram (= intersection distance on pixel level)... and most pixels in a local neighborhood belong to the new superpixel (smoothing term, optional). David Stutz June 25th, 2014 18

SEEDS - Iterations Pixel Updates Figure: Pixel updates without smoothing term. David Stutz June 25th, 2014 19

SEEDS - Iterations Pixel Updates Figure: Pixel updates with smoothing term. David Stutz June 25th, 2014 20

SEEDS - Iterations Pixel Updates Figure: Pixel updates with smoothing term and based on color means. David Stutz June 25th, 2014 21

SEEDS - Parameters Parameters Step 5 Take some time to choose parameters... How many bins to use for the histograms? How many superpixels to obtain? How to define local neighborhood? David Stutz June 25th, 2014 22

Results - Table of Contents 1 Introduction Oversegmentation and Superpixels Motivation 2 SEEDS Hierarchy and Histograms Iterations Parameters 3 Results Qualitative 4 Depth Information David Stutz June 25th, 2014 23

Results - Qualitative Qualitative Results Well, but what does this actually look like? David Stutz June 25th, 2014 24

Results - Qualitative Easy Examples... Figure: Part of the BSDS500 validation set. David Stutz June 25th, 2014 25

Results - Qualitative Easy Examples... Figure: Superpixel segmentation with 400 superpixels, 6 bins, smoothing term and mean based pixel updates. David Stutz June 25th, 2014 26

Results - Qualitative Easy Examples... Figure: Reconstruction by coloring superpixels according to their mean color. David Stutz June 25th, 2014 27

Results - Qualitative Easy Examples... Figure: Original image. David Stutz June 25th, 2014 28

Results - Qualitative Easy Examples... Figure: Superpixel segmentation. David Stutz June 25th, 2014 29

Results - Qualitative Easy Examples... Figure: Reconstruction. David Stutz June 25th, 2014 30

Results - Qualitative Qualitative Results OK, but these were easy, what about some hard ones? David Stutz June 25th, 2014 31

Results - Qualitative The Hard Ones... Figure: Difficult original image. David Stutz June 25th, 2014 32

Results - Qualitative The Hard Ones... Figure: Superpixel segmentation. David Stutz June 25th, 2014 33

Results - Qualitative The Hard Ones... Figure: Reconstruction. David Stutz June 25th, 2014 34

Results - Qualitative The Hard Ones... Figure: Difficult original image. David Stutz June 25th, 2014 35

Results - Qualitative The Hard Ones... Figure: Superpixel segmentation. David Stutz June 25th, 2014 36

Results - Qualitative The Hard Ones... Figure: Reconstruction. David Stutz June 25th, 2014 37

Depth Information - Table of Contents 1 Introduction Oversegmentation and Superpixels Motivation 2 SEEDS Hierarchy and Histograms Iterations Parameters 3 Results Qualitative 4 Depth Information David Stutz June 25th, 2014 38

Depth Information - Demonstration Depth Information Figure: Image taken form the NYU Depth Dataset V2.. David Stutz June 25th, 2014 39

Depth Information - Demonstration Depth Information Figure: Some boundaries which are really hard to see... at least for the algorithm. David Stutz June 25th, 2014 40

Depth Information - Demonstration Depth Information Figure: Segmentation using SEEDS Revised purely color based... Could be better! David Stutz June 25th, 2014 41

Depth Information - Demonstration Depth Information Figure: Better! Pixel and block updates are based on depth information a penalty is added if the depth between blocks or pixels differs by more than 10cm. David Stutz June 25th, 2014 42

Depth Information - Conclusion Depth Information Can depth information lead to better oversegmentation? Yes... especially where color fails! But: Color alone already is very good! Well, but how to integrate depth information? Some ideas... David Stutz June 25th, 2014 43

Depth Information - Ideas Ideas Use depth information for mean updates (= integrate depth information into euclidean distance)... Done! Use 3D point coordinates for pixel updates (= integrate (x, y, z) into euclidean distance)... Already done! But SEEDS is based on histograms... Build histograms using... point normals; or use feature histograms for example Fast Point Feature Histograms (FPFH) [18]! David Stutz June 25th, 2014 44

The End - The End Thanks for your attention! Comments? Ideas? Questions? David Stutz June 25th, 2014 45

Appendix - Recall Recall Let G be a ground truth segmentation and S be a superpixel segmentation. Some definitions [7]... True Positives (TP): The number of boundary pixels in G for which there is a boundary pixel in S in range d. False Negatives (FN): The number of boundary pixels in G for which there is no boundary pixel in S in range d. Then Boundary Recall is defined as R(G, S) = T P T P + F N (1) David Stutz June 25th, 2014 46

Appendix - Undersegmentation Error Undersegmentation Error Let G be a ground truth segmentation, S be a superpixel segmentation and N be the total number of pixels. For a superpixel S S and a ground truth segment G G we define S in = S G; and S out = S S G. The Undersegmentation Error is defined as UE(G, S) = 1 N G G min(s in, S out ) (2) S G David Stutz June 25th, 2014 47

Appendix - Compactness Compactness Let G be a ground truth segmentation, S be a superpixel segmentation and N be the total number of pixels. The isoperimetric quotient Q(S) for a superpixel S S with area A S and perimeter L S is defined as Q(S) = 4πA S L 2 S (3) Then the compactness measure is given as CO(S) = 1 Q(S) S (4) N S S David Stutz June 25th, 2014 48

R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Süsstrunk, SLIC Superpixels, Technical report, EPFL, Lausanne, 2010. X. Ren, J. Malik, Learning a classification model for segmentation, ICCV, 2000. P. F. Felzenswalb, D. P. Huttenlocher, Efficient graph-based image segmentation, International Journal of Computer Vision, Volume 59, Number 2, 2004. M. Van den Bergh, X. Boix, G. Roig, B. de Capitani, L. van Gool, SEEDS: superpixels extracted via energy-driven sampling, ECCV, 2012. P. Arbelaez, M. Maire, C. Fowlkes, J. Malik, Contour Detection and Hierarchical Image Segmentation, PAMI, 2011. A. Schick, M. Fischer, R. Stiefelhagen, Measuring and evaluating the compactness of superpixels, ICPR, 2012. P. Neubert, P. Protzel, Superpixel benchmark and comparison, Forum Bildverarbeitung, Regensburg, 2012. David Stutz June 25th, 2014 48

R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Süsstrunk, SLIC superpixels compared to state-of-the-art superpixel methods, PAMI, 2012. A. P. Moore, J. D. Prince, J. Warrell, U. Mohammed, G. Jones, Superpixel lattices, CVPR, 2008. D. Weikersdorfer, D. Gossow, M. Beetz, Depth-adaptive superpixels, ICPR, 2012. C. Conrad, M. Mertz, R. Mester, Contour-relaxed superpixels, Lecture Notes in Computer Science, Volume 8081, 2013. M.-Y. Li, O. Tuzel, S. Ramalingam, R. Chellappa, Entropy rate superpixel segmentation, CVPR, 2011. A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, K. Siddiqi, Turbopixels: fast superpixels using geometric flows, PAMI, 2009. Y. Zhang, R. Hartley, J. Mashford, S. Burn, Superpixels via pseudo-boolean optimization, ICCV, 2011. David Stutz June 25th, 2014 48

J. Papon, A. Abramov, M. Schoeler, F. Worgotter, Voxel cloud connectivity segmentation - supervoxels for point clouds, CVPR, 2013. A. Vedaldi, S. Soatto, Quick shift and kernel methods for mode seeking, ECCV, 2008. N. Silberman, D. Hoiem, P. Kohli, R. Fergus, Indoor segmentation and support inference from RGBD images, ECCV, 2012. R. B. Rusu, N. Blodow, M. Beetz, Fast point feature histograms (FPFH) for 3D registration, ICRA, 2009. David Stutz June 25th, 2014 48