Background Subtraction 15-463: Rendering and Image Processing Alexei Efros.

Slides:

Advertisements

Similar presentations

Computer graphics & visualization. Image Synthesis – WS 07/08 Dr. Jens Krüger – Computer Graphics and Visualization Group Our GPU Photon Tracing Pipeline.

Advertisements

Production Process What events happen during the production process?

Some problems... Lens distortion  Uncalibrated structure and motion recovery assumes pinhole cameras  Real cameras have real lenses  How can we.

Sequence-to-Sequence Alignment and Applications. Video > Collection of image frames.

Actions in video Monday, April 25 Kristen Grauman UT-Austin.

- Recovering Human Body Configurations: Combining Segmentation and Recognition (CVPR’04) Greg Mori, Xiaofeng Ren, Alexei A. Efros and Jitendra Malik -

Eyes for Relighting Extracting environment maps for use in integrating and relighting scenes (Noshino and Nayar)

Computational Photography, Fall 2013

Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.

Light Field Rendering Shijin Kong Lijie Heng.

Robust Multi-Pedestrian Tracking in Thermal-Visible Surveillance Videos Alex Leykin and Riad Hammoud.

Andrea Colombari and Andrea Fusiello, Member, IEEE.

Matting and Transparency : Computational Photography Alexei Efros, CMU, Fall 2007.

Shadow removal algorithms Shadow removal seminar Pavel Knur.

Multi video camera calibration and synchronization.

Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.

Video: savior, or “more of the same”? : Learning-Based Methods in Vision A. Efros, CMU, Spring 2009 © A.A. Efros.

Background Subtraction and Matting : Computational Photography Alexei Efros, CMU, Fall 2006 © Yuri Bonder.

Midterm review: Cameras Pinhole cameras Vanishing points, horizon line Perspective projection equation, weak perspective Lenses Human eye Sample question:

Image-Based Rendering Produce a new image from real images. Combining images Interpolation More exotic methods.

Highlights Lecture on the image part (10) Automatic Perception 16

CSE 291 Final Project: Adaptive Multi-Spectral Differencing Andrew Cosand UCSD CVRR.

Deriving Intrinsic Images from Image Sequences Mohit Gupta Yair Weiss.

Linear View Synthesis Using a Dimensionality Gap Light Field Prior

Face Collections : Rendering and Image Processing Alexei Efros.

Frequency Analysis and Sheared Reconstruction for Rendering Motion Blur Kevin Egan Yu-Ting Tseng Nicolas Holzschuch Frédo Durand Ravi Ramamoorthi Columbia.

[cvPONG] A 3-D Pong Game Controlled Using Computer Vision Techniques Quan Yu and Chris Wagner.

Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques

Behavior Analysis Midterm Report Lipov Irina Ravid Dan Kotek Tommer.

Video Trails: Representing and Visualizing Structure in Video Sequences Vikrant Kobla David Doermann Christos Faloutsos.

David Luebke Modeling and Rendering Architecture from Photographs A hybrid geometry- and image-based approach Debevec, Taylor, and Malik SIGGRAPH.

ICCV 2003UC Berkeley Computer Vision Group Recognizing Action at a Distance A.A. Efros, A.C. Berg, G. Mori, J. Malik UC Berkeley.

Recognizing Action at a Distance A.A. Efros, A.C. Berg, G. Mori, J. Malik UC Berkeley.

COMP 175: Computer Graphics March 24, 2015

Flow Based Action Recognition Papers to discuss: The Representation and Recognition of Action Using Temporal Templates (Bobbick & Davis 2001) Recognizing.

Real-time object tracking using Kalman filter Siddharth Verma P.hD. Candidate Mechanical Engineering.

1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.

Video Textures Arno Schödl Richard Szeliski David Salesin Irfan Essa Microsoft Research, Georgia Tech.

Background Subtraction for Urban Traffic Monitoring using Webcams Master Graduation Project Progress Presentation Supervisor: Rein van den Boomgaard Mark.

Examples for the midterm. data = {4,3,6,3,9,6,3,2,6,9} Example 1 Mode = Median = Mean = Standard deviation = Variance = Z scores =

Image-based rendering Michael F. Cohen Microsoft Research.

Deriving Intrinsic Images from Image Sequences Mohit Gupta 04/21/2006 Advanced Perception Yair Weiss.

Video Segmentation Prepared By M. Alburbar Supervised By: Mr. Nael Abu Ras University of Palestine Interactive Multimedia Application Development.

Recognizing Action at a Distance Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik Computer Science Division, UC Berkeley Presented by Pundik.

Action as Space-Time Shapes

Figure ground segregation in video via averaging and color distribution Introduction to Computational and Biological Vision 2013 Dror Zenati.

Gesture Recognition in a Class Room Environment Michael Wallick CS766.

Feature Matching. Feature Space Outlier Rejection.

Multimedia Programming 14: Matting Departments of Digital Contents Sang Il Park.

E VENT D ETECTION U SING AN A TTENTION -B ASED T RACKER 22 Outubro Universidade Federal do Paraná. Gerald Dalley, Xiaogang Wang, and W. Eric L. Grimson.

Yizhou Yu Texture-Mapping Real Scenes from Photographs Yizhou Yu Computer Science Division University of California at Berkeley Yizhou Yu Computer Science.

Presented by: Idan Aharoni

1 Projection: Completing the Camera Model ©Yiorgos Chrysanthou 2001, Anthony Steed

Target Tracking In a Scene By Saurabh Mahajan Supervisor Dr. R. Srivastava B.E. Project.

SUREILLANCE IN THE DEPARTMENT THROUGH IMAGE PROCESSING F.Y.P. PRESENTATION BY AHMAD IJAZ & UFUK INCE SUPERVISOR: ASSOC. PROF. ERHAN INCE.

Matting and Transparency : Computational Photography Alexei Efros, CMU, Spring 2010.

Eigen Texture Method : Appearance compression based method Surface Light Fields for 3D photography Presented by Youngihn Kho.

Hebrew University Image Processing Exercise Class 8 Panoramas – Stitching and Blending Min-Cut Stitching Many slides from Alexei Efros.

Created by: Tonya Jagoe. Measures of Central Tendency & Spread Input the data for these test scores into your calculator to find.

DIGITAL PHOTOGRAPHY Imaging Partnership. LESSON TWO Fine Art Photography.

Detecting Moving Objects, Ghosts, and Shadows in Video Streams

Motion and optical flow

Signal processing.

ECE 692 – Advanced Topics in Computer Vision

Compositional Human Pose Regression

Presented by Omer Shakil

Real-Time Human Pose Recognition in Parts from Single Depth Image

15-463: Rendering and Image Processing Alexei Efros

By Yair Weiss Presented by Peter Sand

Midterm Statistics.

Presentation transcript:

Background Subtraction : Rendering and Image Processing Alexei Efros

Image Stack As can look at video data as a spatio-temporal volume If camera is stationary, each line through time corresponds to a single ray in space We can look at how each ray behaves What are interesting things to ask? t time

Example

Getting the right pixels Average image Median Image

Input Video

Average Image What is happening?

Average Image What can we do with this?

Background Subtraction - =

Crowd Synthesis (with Pooja Nath) 1.Do background subtraction in each frame 2.Find and record “blobs” 3.For synthesis, randomly sample the blobs, taking care not to overlap them

Background Subtraction for matting A very hard problem. But sometimes it works:

Removing Shadows (Weiss, 2001) How does one detect (subtract away) shadows?

Averaging Derivatives

Recovering Shadows

Compositing with Shadows

Figure-centric Representation

Context-based Image Correction Input sequence 3 closest frames median images

Midterm Stats # of people: 11 Total points possible: 120 Mean: 77.1 Median: 76 Max: 98 Min: 56 Std. Div: 13.2 Skewness: Kurtosis: 1.9 The scores: [ ]

Fun with Focal Length (Jim Sherwood)