Pre-fetching based on video analysis for interactive region-of- interest streaming of soccer sequences Authors: Aditya Mavlankar and Bernd Girod Information.

Slides:



Advertisements
Similar presentations
SHA-1 Secure Hash Algorithm 1. SHA-1 – Brief Introduction 家族是美國國家安全局 (NSA) 設計,美國國家標 準與技術研究院 (NIST) 發佈的一系列密碼雜湊函 數,發表於 1993 年 從一個最大 2 64 位元的訊息中產生一串 160.
Advertisements

DETECTING REGIONS OF INTEREST IN DYNAMIC SCENES WITH CAMERA MOTIONS.
1 Approximated tracking of multiple non-rigid objects using adaptive quantization and resampling techniques. J. M. Sotoca 1, F.J. Ferri 1, J. Gutierrez.
Pricing and Power Control in a Multicell Wireless Data Network Po Yu Chen October, 2001 IEEE Journal on Select Areas in Communications.
An Improved 3DRS Algorithm for Video De-interlacing Songnan Li, Jianguo Du, Debin Zhao, Qian Huang, Wen Gao in IEEE Proc. Picture Coding Symposium (PCS),
Compressed-domain-based Transmission Distortion Modeling for Precoded H.264/AVC Video Fan li Guizhong Liu IEEE transactions on circuits and systems for.
A Quality-Driven Decision Engine for Live Video Transmission under Service-Oriented Architecture DALEI WU, SONG CI, HAIYAN LUO, UNIVERSITY OF NEBRASKA-LINCOLN.
1 Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion (IEEE 2009) Junlan Yang University of Illinois,Chicago.
: Factstone Benchmark ★★☆☆☆ 題組: Problem Set Archive with Online Judge 題號: : Factstone Benchmark 解題者:鐘緯駿 解題日期: 2006 年 06 月 06 日 題意: 假設 1960.
Review of Chapter 3 - 已學過的 rules( 回顧 )- 朝陽科技大學 資訊管理系 李麗華 教授.
:New Land ★★★★☆ 題組: Problem Set Archive with Online Judge 題號: 11871: New Land 解題者:施博修 解題日期: 2011 年 6 月 8 日 題意:國王有一個懶兒子,為了勞動兒子,他想了一個 辦法,令他在某天早上開始走路,直到太陽下山前,靠.
: OPENING DOORS ? 題組: Problem Set Archive with Online Judge 題號: 10606: OPENING DOORS 解題者:侯沛彣 解題日期: 2006 年 6 月 11 日 題意: - 某間學校有 N 個學生,每個學生都有自己的衣物櫃.
Lecture Note of 9/29 jinnjy. Outline Remark of “Central Concepts of Automata Theory” (Page 1 of handout) The properties of DFA, NFA,  -NFA.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
Video Transmission Adopting Scalable Video Coding over Time- varying Networks Chun-Su Park, Nam-Hyeong Kim, Sang-Hee Park, Goo-Rak Kwon, and Sung-Jea Ko,
Analyzing Algorithms Based on: 1. 物件導向資料結構 — 使用 Java 語言, 江振 瑞 著, 松崗圖書公司, Introduction to the Design and Analysis of Algorithms -- A strategic.
Wavelet transform and SPIHT 林明德. Wavelet transform & SPIHT Wavelet transform  濾波器組  程式功能  額外資訊 SPIHT  將不同功能的 SPIHT 做整合  用於各種長寬的圖檔  適用於 DSC 的 SPIHT.
Efficient Motion Vector Recovery Algorithm for H.264 Based on a Polynomial Model Jinghong Zheng and Lap-Pui Chau IEEE TRANSACTIONS ON MULTIMEDIA, June.
: The Battle II ★★★☆☆ 題組: Problem Set Archive with Online Judge 題號: 11098: The Battle II 解題者:許桓偉 解題日期: 2007 年 3 月 13 日 題意:給一連串炸彈座標、半徑、爆炸範 圍 (Xi,Yi,Ri,Ei)
Robust Audio Tool (RAT) Speaker : Wei-Shin Pan DATE : 09/07/02.
: The largest Clique ★★★★☆ 題組: Contest Archive with Online Judge 題號: 11324: The largest Clique 解題者:李重儀 解題日期: 2008 年 11 月 24 日 題意: 簡單來說,給你一個 directed.
Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
: Happy Number ★ ? 題組: Problem Set Archive with Online Judge 題號: 10591: Happy Number 解題者:陳瀅文 解題日期: 2006 年 6 月 6 日 題意:判斷一個正整數 N 是否為 Happy Number.
Johnson’s algorithm Johnson’s演算法可用於計算All pairs shortest path問題。
: THE SAMS' CONTEST ☆☆★★★ 題組: Problem Set Archive with Online Judge 題號: 10520: THE SAMS' CONTEST 解題者:陳相廷,林祺光 解題日期: 2006 年 5 月 22 日 題意:依以下式子,給定 n.
: GCD - Extreme II ★★★★☆ 題組: Contest Archive with Online Judge 題號: 11426: GCD - Extreme II 解題者:蔡宗翰 解題日期: 2008 年 9 月 19 日 題意: 最多 20,000 組測資,題目會給一個數字.
845: Gas Station Numbers ★★★ 題組: Problem Set Archive with Online Judge 題號: 845: Gas Station Numbers. 解題者:張維珊 解題日期: 2006 年 2 月 題意: 將輸入的數字,經過重新排列組合或旋轉數字,得到比原先的數字大,
Bernd Girod: Image Compression and Graphics 1 Image Compression and Graphics: More Than a Sum of Parts? Bernd Girod Collaborators: Peter Eisert, Marcus.
1 523: Minimum Transport Cost ★★★☆☆ 題組: Problem Set Archive with Online Judge 題號: 523: Minimum Transport Cost 解題者:林祺光 解題日期: 2006 年 6 月 12 日 題意:計算兩個城市之間最小的運輸成本,運輸.
Wireless FGS video transmission using adaptive mode selection and unequal error protection Jianhua Wu and Jianfei Cai Nanyang Technological University.
Investigation of Motion-Compensated Lifted Wavelet Transforms Information Systems Laboratory Department of Electrical Engineering Stanford University Markus.
冷凍空調自動控制 - 系統性能分析 李達生. Focusing here … 概論 自動控制理論發展 自控系統設計實例 Laplace Transform 冷凍空調自動控制 控制系統範例 控制元件作動原理 控制系統除錯 自動控制理論 系統穩定度分析 系統性能分析 PID Controller 自動控制實務.
A robust associative watermarking technique based on similarity diagrams Source: Pattern Recognition, Vol. 40, No. 4, pp , 2007 Authors: Jau-Ji.
: Searching for Nessy ★☆☆☆☆ 題組: Problem Set Archive with Online Judge 題號: 11044: Searching for Nessy 解題者:王嘉偉 解題日期: 2007 年 5 月 22 日 題意: 給定 case 數量.
: Finding Paths in Grid ★★★★☆ 題組: Contest Archive with Online Judge 題號: 11486: Finding Paths in Grid 解題者:李重儀 解題日期: 2008 年 10 月 14 日 題意:給一個 7 個 column.
09/24/02ICIP20021 Drift Management and Adaptive Bit Rate Allocation in Scalable Video Coding H. Yang, R. Zhang and K. Rose Signal Compression Lab ECE Department.
An Adaptive Predictor for Media Playout Buffering Phillip DeLeon New Mexico State University Cormac J. Sreenan AT&T Labs ICASSP 99’
Cloud Services for Improved User Experience in Sharing Mobile Videos Authors: Dejan Kovachev, Yiwei Cao and Ralf Klamma Advanced Community Information.
Abstract Some Examples The Eye tracker project is a research initiative to enable people, who are suffering from Amyotrophic Lateral Sclerosis (ALS), to.
1 Efficient Reference Frame Selector for H.264 Tien-Ying Kuo, Hsin-Ju Lu IEEE CSVT 2008.
A New High Speed, Low Power Adder; Using Hybrid Analog-Digital Circuit Taherinejad, N.; Abrishamifar, A.; Circuit Theory and Design, ECCTD 2009.
Introduction Compression Performance Conclusions Large Camera Arrays Capture multi-viewpoint images of a scene/object. Potential applications abound: surveillance,
MULTIMEDIA PROCESSING (EE 5359) SPRING 2011 DR. K. R. RAO PROJECT PROPOSAL Error concealment techniques in H.264 video transmission over wireless networks.
Learning Wavelet Transform by MATLAB Toolbox Professor : R.J. Chang Student : Tsung-Lin Wu Date :2012/12/14.
High-Resolution Video Streaming with Interactive Region-of-Interest Aditya Mavlankar and Piyush Agrawal {maditya, Information Systems.
Adaptive Multi-path Prediction for Error Resilient H.264 Coding Xiaosong Zhou, C.-C. Jay Kuo University of Southern California Multimedia Signal Processing.
Sadaf Ahamed G/4G Cellular Telephony Figure 1.Typical situation on 3G/4G cellular telephony [8]
Improvements to the JPEG-LS prediction scheme Authors: S. Bedi, E. A. Edirisinghe, and G. Grecos Source : Image and Vision Computing. Vol. 22, No. 1, 2004,
Adaptive Rate Control for HEVC Visual Communications and Image Processing (VCIP), 2012 IEEE Junjun Si, Siwei Ma, Xinfeng Zhang, Wen Gao 1.
Compression video overview 演講者:林崇元. Outline Introduction Fundamentals of video compression Picture type Signal quality measure Video encoder and decoder.
Rate-distortion Optimized Mode Selection Based on Multi-channel Realizations Markus Gärtner Davide Bertozzi Classroom Presentation 13 th March 2001.
Figure 1.a AVS China encoder [3] Video Bit stream.
Media Processor Lab. Media Processor Lab. High Performance De-Interlacing Algorithm for Digital Television Displays Media Processor Lab.
A NOVEL PREFETCHING METHOD FOR SCENE-BASED MOBILE SOCIAL NETWORK SERVICE 作者 :Song Li, Wendong Wang, Yidong Cui, Kun Yu, Hao Wang 報告者 : 饒展榕.
Rate-distortion Optimized Mode Selection Based on Multi-path Channel Simulation Markus Gärtner Davide Bertozzi Project Proposal Classroom Presentation.
 Present by 陳群元.  Introduction  Previous work  Predicting motion patterns  Spatio-temporal transition distribution  Discerning pedestrians  Experimental.
Transcoding based optimum quality video streaming under limited bandwidth *Michael Medagama, **Dileeka Dias, ***Shantha Fernando *Dialog-University of.
Resource Allocation Policy to Avoid Interference between Cellular and D2D Links/ and D2D Links in Mobile Networks 報告人:王姿穎 學號:MA4G0202.
Video Quality Assessment and Comparative Evaluation of Peer-to-Peer Video Streaming Systems Aditya Mavlankar Pierpaolo Baccichet Bernd Girod Stanford University.
1 Yu Liu 1, Feng Wu 2 and King Ngi Ngan 1 1 Department of Electronic Engineering, The Chinese University of Hong Kong 2 Microsoft Research Asia, Beijing,
Human Activity Recognition Based on Silhouette Directionality IEEE TRANSACTIONS ON CIRCUITS AND SYATEM FOR VEDIO TECHNOLOGY, VOL.18, NO.9, SEPTEMBER 2008.
A NOVEL PREFETCHING METHOD FOR SCENE- BASED MOBILE SOCIAL NETWORK SERVICE 作者 :SONG LI, WENDONG WANG, YIDONG CUI, KUN YU, HAO WANG 報告者 : 饒展榕.
Aditya Mavlankar, Pierpaolo Baccichet, David Varodayan and Bernd Girod
Injong Rhee ICMCS’98 Presented by Wenyu Ren
Aditya Mavlankar and David Varodayan
User-Oriented Approach in Spatial and Temporal Domain Video Coding
Streaming To Mobile Users In A Peer-to-Peer Network
Research Topic Error Concealment Techniques in H.264/AVC for Wireless Video Transmission Vineeth Shetty Kolkeri EE Graduate,UTA.
Viewport-based 360 Video Streaming:
Viewport-based 360 Video Streaming:
Presentation transcript:

Pre-fetching based on video analysis for interactive region-of- interest streaming of soccer sequences Authors: Aditya Mavlankar and Bernd Girod Information Systems Laboratory, Department of Electrical Engineering Stanford University, Stanford, CA 94305, USA {maditya, Speaker : 童耀民 MA1G

Outline 1.INTRODUCTION 2.ROI PREDICTION AND PRE-FETCHING  Trajectory Prediction  Prediction Using H.264/AVC Motion Vectors  Prediction Tracking Soccer Ball  Prediction Tracking Soccer Ball and Players 3.EXPERIMENTAL RESULTS 4.CONCLUSIONS 2

INTRODUCTION  We consider a video streaming system in which the user can interactively watch an arbitrary region of a high-spatial-resolution scene.  Region-of-interest (RoI) prediction helps pre-fetch select slices of encoded video. 3

INTRODUCTION  Despite the availability of high- resolution video, challenges in delivering this high-resolution content to the client are posed by the limited resolution of the display and/or limited data rate for communications. 4

INTRODUCTION  The goal of the paper is to find out whether domain-specific techniques can predict the client’s RoI more accurately.  The more accurate the RoI prediction the lower is the percentage of missing pixels. 5

INTRODUCTION  In this paper, we focus on interactive viewing of soccer and investigate whether domain- specific RoI prediction based on semantic video analysis is more accurate than RoI prediction based on general techniques that apply to any type of content. 6

INTRODUCTION 7

ROI PREDICTION AND PRE- FETCHING  As part of earlier work, we have developed a graphical user interface [2,3] to allow the user to select an RoI while watching the video.  The application supports continuous zoom to provide smooth control of the zoom factor. 8

ROI PREDICTION AND PRE- FETCHING  The high-resolution layers are encoded using independent slices.  We choose the high-resolution layer that corresponds closest to the user’s zoom factor. 9

ROI PREDICTION AND PRE- FETCHING  If some required high-resolution slices are unavailable, we conceal the error by upsampling portions of the thumbnail video.  We compare the performance of four RoI predictors in this paper.  10

ROI PREDICTION AND PRE- FETCHING  The goal of each predictor is to predict the RoI in frame n + d when frame n is rendered on screen.  The zoom factor for frame n + d is predicted to be the same as the zoom factor observed for frame n. 11

ROI PREDICTION AND PRE- FETCHING 2.1. Trajectory Prediction  We adapt the autoregressive moving average (ARMA) prediction algorithm of [13] to extrapolate the coordinates of the RoI center.ARMA 12

ROI PREDICTION AND PRE- FETCHING 2.2. Prediction Using H.264/AVC Motion Vectors  This algorithm, proposed in our earlier work [12], exploits the motion vectors (MVs) contained within the encoded bitstream of the thumbnail video frames that are buffered at the client. 13

ROI PREDICTION AND PRE- FETCHING 2.2. Prediction Using H.264/AVC Motion Vectors  The MVs are used to find a plausible propagation of the RoI center pixel in every subsequent frame up to frame n+d. 14

ROI PREDICTION AND PRE- FETCHING 2.3. Prediction Tracking Soccer Ball  The RoI is simply predicted to be centered around the ball. 15

ROI PREDICTION AND PRE- FETCHING 2.4. Prediction Tracking Soccer Ball and Players  We have developed our own algorithm for player tracking using background subtraction and blob tracking based on MVs. 16

EXPERIMENTAL RESULTS  We use the Soccer1 sequence having 2560 × 704 pixels and 25 frames/sec.  The RoI display is 480 × 240 pixels. 17

EXPERIMENTAL RESULTS 18

EXPERIMENTAL RESULTS 19

EXPERIMENTAL RESULTS  PSNR (Peak Signal to Noise Ratio) : 也是訊雜比 , 只是訊號部分的 值 通通改用該訊號度量的最大 值。 以訊號度量範圍為 0 到 255 當作例子來計算 PSNR 時 , 訊 號部分均當成是其能 夠 度量的最大 值, 也就是 255 , 而不是 原來的訊號 20

CONCLUSIONS  For long look-ahead, RoI prediction is very challenging for both kinds of techniques and incurs a large percentage of missing pixels.  Nevertheless, we found that the domain- specific technique performs better though only by about 1 dB, while the drop in PSNR with respect to perfect RoI prediction is more than 3 dB. 21

22

23

24

25

26

27