Human-Assisted Motion Annotation Ce Liu William T. Freeman Edward H. Adelson Massachusetts Institute of Technology Yair Weiss The Hebrew University of.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Fast and Accurate Optical Flow Estimation
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
CISC 489/689 Spring 2009 University of Delaware
Motion.
The fundamental matrix F
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Investigation Into Optical Flow Problem in the Presence of Spatially-varying Motion Blur Mohammad Hossein Daraei June 2014 University.
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
Robust statistical method for background extraction in image segmentation Doug Keen March 29, 2001.
What makes an image memorable?
Stereo Vision Reading: Chapter 11
Francisco Barranco Cornelia Fermüller Yiannis Aloimonos Event-based contour motion estimation.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Computer Vision REU Week 2 Adam Kavanaugh. Video Canny Put canny into a loop in order to process multiple frames of a video sequence Put canny into a.
Computer Vision Optical Flow
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Recent progress in optical flow
Announcements Quiz Thursday Quiz Review Tomorrow: AV Williams 4424, 4pm. Practice Quiz handout.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
High-Quality Video View Interpolation
Optical flow and Tracking CISC 649/849 Spring 2009 University of Delaware.
Virtual Control of Optical Axis of the 3DTV Camera for Reducing Visual Fatigue in Stereoscopic 3DTV Presenter: Yi Shi & Saul Rodriguez March 26, 2008.
Lecture 19: Optical flow CS6670: Computer Vision Noah Snavely
High Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning Jeff Michels Ashutosh Saxena Andrew Y. Ng Stanford University ICML 2005.
3D Rigid/Nonrigid RegistrationRegistration 1)Known features, correspondences, transformation model – feature basedfeature based 2)Specific motion type,
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
Image Subtraction for Real Time Moving Object Extraction Shahbe Mat Desa, Qussay A. Salih, CGIV’04.
EE392J Final Project, March 20, Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
A Local Adaptive Approach for Dense Stereo Matching in Architectural Scene Reconstruction C. Stentoumis 1, L. Grammatikopoulos 2, I. Kalisperakis 2, E.
Optical Flow Donald Tanguay June 12, Outline Description of optical flow General techniques Specific methods –Horn and Schunck (regularization)
EECS 274 Computer Vision Motion Estimation.
#MOTION ESTIMATION AND OCCLUSION DETECTION #BLURRED VIDEO WITH LAYERS
CS 4487/6587 Algorithms for Image Analysis
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
Recognizing Action at a Distance Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik Computer Science Division, UC Berkeley Presented by Pundik.
Computer Vision, Robert Pless
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
Learning to Perceive Transparency from the Statistics of Natural Scenes Anat Levin School of Computer Science and Engineering The Hebrew University of.
Effective Optical Flow Estimation
Over-Parameterized Variational Optical Flow
Joint Tracking of Features and Edges STAN BIRCHFIELD AND SHRINIVAS PUNDLIK CLEMSON UNIVERSITY ABSTRACT LUCAS-KANADE AND HORN-SCHUNCK JOINT TRACKING OF.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Active Frame Selection for Label Propagation in Videos Sudheendra Vijayanarasimhan and Kristen Grauman Department of Computer Science, University of Texas.
High Resolution Surface Reconstruction from Overlapping Multiple-Views
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Today. you will entertain me Enhancing the Throughput of Video Streaming Using Automatic Colorization Sender Automatic Colorization Internet Receiver.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Optical flow and keypoint tracking Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Processing Images and Video for An Impressionist Effect Automatic production of “painterly” animations from video clips. Extending existing algorithms.
A Plane-Based Approach to Mondrian Stereo Matching
Summary of “Efficient Deep Learning for Stereo Matching”
A Closed Form Solution to Direct Motion Segmentation
Motion and Optical Flow
Robust Visual Motion Analysis: Piecewise-Smooth Optical Flow
Nonparametric Semantic Segmentation
Representing Moving Images with Layers
Representing Moving Images with Layers
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Announcements more panorama slots available now
Analysis of Contour Motions
Motion-Based Analysis of Spatial Patterns by the Human Visual System
Coupled Horn-Schunck and Lukas-Kanade for image processing
Announcements more panorama slots available now
Presentation transcript:

Human-Assisted Motion Annotation Ce Liu William T. Freeman Edward H. Adelson Massachusetts Institute of Technology Yair Weiss The Hebrew University of Jerusalem Motivations Existing motion databases are either synthetic or limited to indoor, experimental setups [1]. Can we have ground-truth motion for arbitrary, real-world videos? Humans are an expert at segmenting moving objects and perceiving difference between two frames. Can we have a computer vision system to quantify human perception of motion and generate ground-truth for motion analysis? Several issues need to addressed: 1.Is human labeling reliable (compared to the veridical ground-truth) and consistent (across subjects)? 2.How to efficiently label every pixel at every frame for hundreds of real- world videos? Our work We designed a human-in-loop system to annotate motion for real-world videos [2]: Semiautomatic layer segmentationThe user labels contours using polygons, and the system automatically propagates the contours to other frames. The system can also propagate users correction across frames. Automatic layer-wise optical flowThe system automatically computes dense optical flow fields for every layer at every frame using user-specified parameters. For each layer, the user picks up the best flow that yields the correct matching and agrees with the smoothness and discontinuities of the image. Semiautomatic motion labelingWhen the flow estimation fails, the user can label sparse correspondences between two frames, and the system automatically interpolates it to a dense flow field. Automatic full-frame motion composition. Our methodology is examined by comparing with veridical ground-truth data and user studies. We created a ground-truth motion database consisting of 10 real-world video sequences (still growing). This database can be used for evaluating motion analysis algorithms as well as other vision and graphics applications. (a) A selected frame(b) Layer labeling(c) User-annotated motion(d) Ground-truth from [1] (e) Difference between (c) and (d) Figure 3. For the RubberWhale sequence in [1], we labeled 20 layers in (b) and obtained the annotated motion in (c). The ground-truth motion from [1] is shown in (d). The error between (c) and (d) is 3.21º in average angular error (AAE) and in average endpoint error (AEP), excluding the outliers (black dots) in (d). (a) (b) (c) (e) (d) Figure 1. The graphical user interface (GUI) of our system: (a) main window for labeling contours and feature points; (b) depth controller to change depth value; (c) magnifier; (d) optical flow viewer; (e) control panel. Figure 5. Some frames of the ground-truth motion database we created. We obtained ground-truth flow fields that are consistent with object boundaries, as shown in column (3) and (4). In comparison, the output of an optical flow algorithm [3] is shown in column (5). From Table 1, the performance of this algorithm on our database is worse than the performance on the Yosemite sequence (1.723° AAE, AEP). References [1] S. Baker, D. Scharstein, J. Lewis, S. Roth, M. J. Black, and R. Szeliski. A database and evaluation methodo- logy for optical flow. In Proc. ICCV, [2]C Liu, W. T. Freeman, E. H. Adelson, Y. Weiss. Human-Assisted Motion Annotation. Submitted to CVPR08. [3] A. Bruhn, J.Weickert,, and C. Schnörr. Lucas/Kanade meets Horn/Schunk: combining local and global optical flow methods. IJCV, 61(3):211–231, (a)(b)(c)(d)(e)(f)(g)(h) AAE8.996º58.905º2.573º5.313º1.924º5.689º5.243º13.306º AEP Figure 4. The marginal ((a)~(h)) and joint ((i)~(n)) statistics of the ground-truth motion from the database we created (log histogram). Symbol u and v denotes horizontal and vertical motion, respectively. From these statistics it is evident that horizontal motion dominates vertical; vertical motion is sparser than horizontal; flow fields are sparser than natural images; spatial derivatives are sparser than temporal derivatives. Table 1. The performance of an optical flow algorithm [3] on our database Figure 2. The consistency of nine subjects annotation. Clockwise from top left: the image frame, mean labeled motion, mean absolute error (red: higher error, white: lower error), and error histogram. Experiment We applied our system to annotating a veridical example from [1] (Figure 3). Our annotation is very close to theirs: 3.21° AAE, AEP. The main difference is on the occluding boundary. We tested the consistency of human annotation (Figure 3). The mean error is 0.989° AAE, AEP. The error magnitude correlates with the blurriness of the image. We created a ground-truth motion database containing 10 real-world videos with 341 frames (Figure 5, Table 1) for both indoor and outdoor scenes. The statistics of the ground-truth motion are plotted in Figure 4. Color map for flow visualization System Features We used the-state-of-the art computer vision algorithms to design our system. Many of the objective functions in contour tracking, flow estimation and flow interpolation have L1 norms for robustness. Techniques such as iterative reweighted least square (IRLS), pyramid-based coarse-to-fine search and occlusion/outlier detection were intensively used for optimizing these nonlinear objective functions. The system was written in C++, and Qt TM 4.3 was used for GUI design (Figure 1). Our system has all the components to make annotation simple and easy, and also gives the user full freedom to label motion manually.