3/6/2015 PortoICIAR’20041 Adaptive Methods for Motion Characterization and Segmentation of MPEG Compressed Frame Sequences C. Doulaverakis, S. Vagionitis,

Slides:



Advertisements
Similar presentations
Video Dissolve and Wipe Detection via Spatio-Temporal Images of Chromatic Histogram Differences Presentation by Kenton Anderson CMPT 820 March 3 rd, 2005.
Advertisements

CIS 581 Course Project Heshan Lin
Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC.
Automated Shot Boundary Detection in VIRS DJ Park Computer Science Department The University of Iowa.
SmartPlayer: User-Centric Video Fast-Forwarding K.-Y. Cheng, S.-J. Luo, B.-Y. Chen, and H.-H. Chu ACM CHI 2009 (international conference on Human factors.
B. Prabhakaran1 Multimedia Metadata Multimedia information needs to be “interpreted” Popular example: “A picture is worth thousand words” Who will “write”
1 Video Processing Lecture on the image part (8+9) Automatic Perception Volker Krüger Aalborg Media Lab Aalborg University Copenhagen
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Content-based Video Indexing and Retrieval
Human-Computer Interaction Human-Computer Interaction Segmentation Hanyang University Jong-Il Park.
Video Shot Boundary Detection at RMIT University Timo Volkmer, Saied Tahaghoghi, and Hugh E. Williams School of Computer Science & IT, RMIT University.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Matching with Invariant Features
ICME 2008 Huiying Liu, Shuqiang Jiang, Qingming Huang, Changsheng Xu.
Ai-Mei Huang and Truong Nguyen Image Processing (ICIP), th IEEE International Conference on 1.
Golnaz Abdollahian, Cuneyt M. Taskiran, Zygmunt Pizlo, and Edward J. Delp C AMERA M OTION -B ASED A NALYSIS OF U SER G ENERATED V IDEO IEEE TRANSACTIONS.
1Ellen L. Walker Segmentation Separating “content” from background Separating image into parts corresponding to “real” objects Complete segmentation Each.
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues David R. Martin Charless C. Fowlkes Jitendra Malik.
A Data-Driven Approach to Quantifying Natural Human Motion SIGGRAPH ’ 05 Liu Ren, Alton Patrick, Alexei A. Efros, Jassica K. Hodgins, and James M. Rehg.
Efficient MPEG Compressed Video Analysis Using Macroblock Type Information Soo-Chang Pei, Yu-Zuong Chou IEEE TRANSACTIONS ON MULTIMEDIA, DECEMBER,1999.
A Robust Scene-Change Detection Method for Video Segmentation Chung-Lin Huang and Bing-Yao Liao IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY.
Segmentation by Clustering Reading: Chapter 14 (skip 14.5) Data reduction - obtain a compact representation for interesting image data in terms of a set.
Optical Flow
MPEG-7 Motion Descriptors. Reference ISO/IEC JTC1/SC29/WG11 N4031 ISO/IEC JTC1/SC29/WG11 N4062 MPEG-7 Visual Motion Descriptors (IEEE Transactions on.
CS 376b Introduction to Computer Vision 04 / 01 / 2008 Instructor: Michael Eckmann.
Stockman MSU Fall Computing Motion from Images Chapter 9 of S&S plus otherwork.
E.G.M. PetrakisVideo Processing1  Video is a rich information source  frames (individual images)  links between frames (cuts, fades, dissolves)  changes.
1 Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or.
Low-level Motion Activity Features for Semantic Characterization of Video Kadir A. Peker, A. Aydin Alatan, Ali N. Akansu International Conference on Multimedia.
Video Trails: Representing and Visualizing Structure in Video Sequences Vikrant Kobla David Doermann Christos Faloutsos.
Real Time Abnormal Motion Detection in Surveillance Video Nahum Kiryati Tammy Riklin Raviv Yan Ivanchenko Shay Rochel Vision and Image Analysis Laboratory.
Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.
MSU Fall Computing Motion from Images Chapter 9 of S&S plus otherwork.
Shot boundary detection based on frame histograms analysis Vakulenko M.D. 1, Kovalenko D.A. 2, Tolkunov S.V. 2, Master Students Gr. 1 -8BM10, 2 -8VM13.
Human-Computer Interaction Human-Computer Interaction Tracking Hanyang University Jong-Il Park.
Methods of Video Object Segmentation in Compressed Domain Cheng Quan Jia.
High-Resolution Interactive Panoramas with MPEG-4 발표자 : 김영백 임베디드시스템연구실.
Introduction EE 520: Image Analysis & Computer Vision.
Performance Characterization of Video-Shot-Change Detection Methods U. Gargi, R. Kasturi, S. Strayer Presented by: Isaac Gerg.
An Efficient Search Strategy for Block Motion Estimation Using Image Features Digital Video Processing 1 Term Project Feng Li Michael Su Xiaofeng Fan.
MOTION ESTIMATION IMPLEMENTATION IN RECONFIGURABLE PLATFORMS
Expectation-Maximization (EM) Case Studies
Implementation, Comparison and Literature Review of Spatio-temporal and Compressed domains Object detection. By Gokul Krishna Srinivasan Submitted to Dr.
Video Tracking G. Medioni, Q. Yu Edwin Lei Maria Pavlovskaia.
Detection of Illicit Content in Video Streams Niall Rea & Rozenn Dahyot
CSSE463: Image Recognition Day 29 This week This week Today: Surveillance and finding motion vectors Today: Surveillance and finding motion vectors Tomorrow:
A. R. Jayan, P. C. Pandey, EE Dept., IIT Bombay 1 Abstract Perception of speech under adverse listening conditions may be improved by processing it to.
CS 376b Introduction to Computer Vision 03 / 31 / 2008 Instructor: Michael Eckmann.
Tracking Groups of People for Video Surveillance Xinzhen(Elaine) Wang Advisor: Dr.Longin Latecki.
1/39 Motion Adaptive Search for Fast Motion Estimation 授課老師:王立洋老師 製作學生: M 蔡鐘葳.
Narration/dialogue: Camera motion: Video effect: Audio effect: Shot duration: Transition to next scene: Storyboard Panel #
Compression and Security of Surveillance Videos Exercise 6 – Shot Change Detection M 陳威佑.
Introduction To Computational and Biological Vision Max Binshtok Ohad Greenshpan March 2006 Shot Detection in video.
Date of download: 6/3/2016 Copyright © ASME. All rights reserved. From: Quantifying Function in the Early Embryonic Heart J Biomech Eng. 2013;135(4):
Student Gesture Recognition System in Classroom 2.0 Chiung-Yao Fang, Min-Han Kuo, Greg-C Lee, and Sei-Wang Chen Department of Computer Science and Information.
Chapter 10 Image Segmentation
Automatic Video Shot Detection from MPEG Bit Stream
Students Liav Viner Omri Ravid Supervisors Dr. Ofer Hadar
Presenter: Ibrahim A. Zedan
Conversion of Standard Broadcast Video Signals for HDTV Compatibility
Signal processing.
User-Oriented Approach in Spatial and Temporal Domain Video Coding
Vehicle Segmentation and Tracking in the Presence of Occlusions
CSSE463: Image Recognition Day 29
DC Image Extraction and Shot Segmentation
An enhanced estimation: motion and rotation estimation
Image and Video Processing
Student: Mallesham Dasari Faculty Advisor: Dr. Maggie Cheng
CSSE463: Image Recognition Day 29
동영상 처리.
Presentation transcript:

3/6/2015 PortoICIAR’20041 Adaptive Methods for Motion Characterization and Segmentation of MPEG Compressed Frame Sequences C. Doulaverakis, S. Vagionitis, M. Zervakis, E. Petrakis Technical University of Crete (TUC) Chania Crete Greece

3/6/2015 PortoICIAR’20042 Problem Definition  Video segmentation  Abrupt (cuts) & Gradual transitions  Zoom, Pan/Tilt  Contribution: segmentation and identification of camera effects  Processing on MPEG video  Partially decompressed block data  DC intensity approximation for blocks  Coherent motion vectors for I, P, B frames

3/6/2015 PortoICIAR’20043 Twin Comparison (TC)  Shot boundaries peaks on histogram differences  Thresholds: Ta, Tb  Ta = μ + α σ  Τb = bμ  Requires pre- processing,does not adapt to signal Τα Tb

3/6/2015 PortoICIAR’20044 Sliding Window (SW)  Processing over W frames  One Threshold: Ta(i) = μ(i) + α σ(i)  Cut: < 5 frames  Gradual: > 5 frames  No preprocessing, adapts to signal Ta

3/6/2015 PortoICIAR’20045 Adaptive Method (AM)  Ta(i) = μ(i) + α σ(i) μ(i) =μ(i-1)-c(μ(i-1)–D(i)) σ(i) = |μ(i) 2 – λ(i)| 1/2 λ(i)=λ(i-1)–c (λ(i-1)–D(i)) 2 c=0.05  Ta is computed at each i and depends on previous values  No preprocessing, adapts to signal Ta

3/6/2015 PortoICIAR’20046 Direction Histogram  Histogram of angles of motion vectors  8 angles multiples of π/4 for moving vectors  Plus 0-th value for static vectors |v| < 1 static moving

3/6/2015 PortoICIAR’20047 Motion Characterization  Analysis of variance σ motion histogram  Normalized by number of intracoded vectors  Zooming: the vectors are spread uniformely (max σ)  Panning-Tilting: the vectors are concentrated at a single bin (min σ)  Static camera: the vectors are concentrated at bin 0

3/6/2015 PortoICIAR’20048 Example pan pan zoom static camera Ta

3/6/2015 PortoICIAR’20049 Video Segmentation Method  Cuts: the number of intracoded vectors in frame exceeds threshold  Gradual transitions: combines motion and intensity information  Difference of intensity histogram exceeds threshold  Magnitude of motion vectors exceed threshold

3/6/2015 PortoICIAR’ Experiments  Measurements over 17 videos  Competitive methods correspond to thresholding by TC, SW, AM  Each method is represented by its precision/recall curve as a function of the threshold parameter a

3/6/2015 PortoICIAR’ Abrupt Transitions (cuts)

3/6/2015 PortoICIAR’ Gradual Transitions

3/6/2015 PortoICIAR’ Future Work  More accurate threshold estimation  SW or AM gets trapped in local minima  Detection of Cuts is fairly stable  More elaborate methods for detection of gradual transitions and for cleaning- up false positives due to camera effects

3/6/2015 PortoICIAR’ Zoom Detection α=4.5 α=2

3/6/2015 PortoICIAR’ Pan/Tilt Detection α=2 α=4.5