camera networks dimensioning and scheduling with quasi
play

Camera Networks Dimensioning and Scheduling with Quasi Worst-Case - PowerPoint PPT Presentation

Oct 28, 2023 •344 likes •1.07k views

Camera Networks Dimensioning and Scheduling with Quasi Worst-Case Transmission Time Viktor Edpalm Alexandre Martins Martina Maggio Karl-Erik rzn Axis Communications Axis Communications | Lund University Lund University Lund University

  1. Camera Networks Dimensioning and Scheduling with Quasi Worst-Case Transmission Time Viktor Edpalm Alexandre Martins Martina Maggio Karl-Erik Årzén Axis Communications Axis Communications | Lund University Lund University Lund University

  2. Who are we ? Swedish company ● Since 1996 / Canon since 2015 ● ~3000 employees & 179 countries ● Development offices: ● Lund ○ Linköping ○ Paris ○ Shanghai ○ ~835 million € sales revenue ● We do (mainly) network cameras ! ● (and we are the world's number 2 at it)

  3. Network dimensioning ? Dimensioning <> "long term" How to design a system of cameras ? How to estimate ? Storage space ? ● Network bandwidth ? ● Peak capacity ? ● Knowing that: Each camera is unique ● … but somewhat similar Each set-up/time period is unique ● … but belongs to a limited category list

  4. Network scheduling ? Scheduling <> "short term" How to estimate ? Maximum bandwidth ? ● Delay ? ● Peak capacity ? ● Knowing that: Each camera is unique ● … but somewhat similar Each set-up/time period is unique ● … but belongs to a limited category list

  5. Video

  6. H.264 MJPEG ... ... Frame Frame Frame Frame Frame Frame H.26x * We consider B-frames equivalent to P-frames * We consider I-frames as IDR frames Group of picture I-frame I-frame P ... P ... P P

  7. H.264

  8. H.264

  9. H.264 I-frame P ... P P

  10. H.264 MJPEG H.264

  11. H.264 and scheduling Multiframe model + Many cameras: each generates a separate load ● I-frames ● B/P-frames → Paradigm: non-preemptive scheduling with multi-frame tasks I-frame I-frame P ... P ... P P

  12. How do we dimension ? Dimensioning Steps Characterize a reference camera model: in lab, in real scenarios ● Characterize other camera models: in lab, (in real scenarios) ● Characterize scene types : in real scenarios for different cameras ● Gather scene/video parameters (motion, light level, zoom, GOP, fps…) ● Measurable in real time ○ Estimated from usage/placement ○ Extrapolate expected frame sizes and bandwidth ●

  13. How do we dimension ? 1. Parameters

  14. How do we dimension ? 1. Parameters measured in laboratory measured at runtime

  15. How do we dimension ? 1. Parameters Camera measured in laboratory measured at runtime

  16. How do we dimension ? 1. Parameters Camera Scene measured in laboratory measured at runtime

  17. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  18. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  19. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  20. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  21. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  22. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  23. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  24. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  25. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  26. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  27. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  28. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame) +

  29. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame) + =

  30. How do we dimension ? 2. I-frames I C <> size of each I pixel Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame)

  31. How do we dimension ? 2. I-frames Size of average object ( lens, zoom… ) Camera detail capability (how much does the camera retains details) Dynamic range Image width & height Scene light level (how much light) Nature factor (amount of nature) Camera noise factor (how much noise from the camera) Scene detail level (how complex is the scene) Compression scaling (I-frame) I C QP I-frame QP +1 <> quantization step + 12%

  32. How do we dimension ? 3. P-frames Motion encoder efficiency (how good to find motion) Parenthesis part of I Image width & height Frame rate & reference frame rate (how much changed) Camera noise factor (how much noise from the camera) Motion level Compression scaling (P-frame)

  33. How do we dimension ? 3. P-frames Motion encoder efficiency (how good to find motion) Parenthesis part of I Image width & height Frame rate & reference frame rate (how much changed) Camera noise factor (how much noise from the camera) Motion level Compression scaling (P-frame)

  34. How do we dimension ? 3. P-frames Motion encoder efficiency (how good to find motion) Parenthesis part of I Image width & height Frame rate & reference frame rate (how much changed) Camera noise factor (how much noise from the camera) Motion level Compression scaling (P-frame)

  35. How do we dimension ? 3. P-frames Motion encoder efficiency (how good to find motion) Parenthesis part of I Image width & height Frame rate & reference frame rate (how much changed) Camera noise factor (how much noise from the camera) Motion level Compression scaling (P-frame)

Recommend

Access Networks practice Moldovn Istvn Dimensioning IPTV Streaming: multicast

Access Networks practice Moldovn Istvn Dimensioning IPTV Streaming: multicast

Access Networks practice Moldovn Istvn Dimensioning IPTV Streaming: multicast Bandwidth demand = channel * video rate VoD: unicast Bandwidth demand = estimated # of users watching* video rate VoIP Call bandwidth

77 views • 7 slides
# Camera camera = Camera.open(); Camera camera

# Camera camera = Camera.open(); Camera camera

# Camera camera = Camera.open(); Camera camera = Camera.open(); camera.setDisplayOrientation(90); camera.setDisplayOrientation(90); camera.unlock(); SurfaceHolder holder = getHolder();

1.34k views • 45 slides
Dimensioning of Secondary Clarifier CTB3365x Introduc1on to water

Dimensioning of Secondary Clarifier CTB3365x Introduc1on to water

Dimensioning of Secondary Clarifier CTB3365x Introduc1on to water treatment Dr.ir. Merle de Kreuk Dimensioning of Secondary Clarifier Dimensioning of Secondary

536 views • 17 slides
Oversubscription Dimensioning of Next- Generation PONs With Different Service Levels 8/24/2016

Oversubscription Dimensioning of Next- Generation PONs With Different Service Levels 8/24/2016

Oversubscription Dimensioning of Next- Generation PONs With Different Service Levels 8/24/2016 1 Overview Planning PONs using oversubscription concept and shows its applicability in the dimensioning of 1 Gb/s access With 2 types of

542 views • 14 slides
# Camera camera = Camera.open();

# Camera camera = Camera.open();

# Camera camera = Camera.open(); Camera camera = Camera.open(); camera.setDisplayOrientation(90); camera.setDisplayOrientation(90); camera.unlock(); SurfaceHolder holder =

819 views • 33 slides
Basics of Off-Camera Flash Off-Camera Flash www.jedi.com * What is it &amp; why do we use it? *

Basics of Off-Camera Flash Off-Camera Flash www.jedi.com * What is it &amp; why do we use it? *

Basics of Off-Camera Flash Off-Camera Flash www.jedi.com * What is it &amp; why do we use it? * Bouncing on-camera flash to emulate off-camera light * True off-camera flash * Basic examples * Trigger mechanisms * Controlling the amount of

144 views • 11 slides
Spatula: Efficient cross-camera video analytics on large camera networks Xun Zhang Samvit Jain

Spatula: Efficient cross-camera video analytics on large camera networks Xun Zhang Samvit Jain

Spatula: Efficient cross-camera video analytics on large camera networks Xun Zhang Samvit Jain (UC Berkeley) Xun Zhang (Univ of Chicago) Yuhao Zhou (Univ of Chicago) Ganesh Ananthanarayanan (Microsoft Research) Junchen Jiang (Univ of Chicago)

567 views • 19 slides
Scheduling Granularity in Underwater Acoustic Networks Kurtis Kredo II 1 Prasant Mohapatra 2 1

Scheduling Granularity in Underwater Acoustic Networks Kurtis Kredo II 1 Prasant Mohapatra 2 1

Scheduling Granularity in Underwater Acoustic Networks 1/21 Scheduling Granularity in Underwater Acoustic Networks Kurtis Kredo II 1 Prasant Mohapatra 2 1 Electrical and Computer Engineering Department California State University, Chico 2

535 views • 27 slides
Aera%on tank loading and dimensioning CTB3365x Introduc1on to

Aera%on tank loading and dimensioning CTB3365x Introduc1on to

Aera%on tank loading and dimensioning CTB3365x Introduc1on to water treatment Dr.ir. Merle de Kreuk Aera%on tank loading and dimensioning Aera%on tank

381 views • 18 slides
Camera Rongkai Guo Why Camera First? Games have their own visual rules Contrary to other

Camera Rongkai Guo Why Camera First? Games have their own visual rules Contrary to other

Camera Rongkai Guo Why Camera First? Games have their own visual rules Contrary to other kinds of camera Difficult and Expensive to change a poorly designed camera Rules are needed to govern the camera through the whole game

341 views • 10 slides
CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a

CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a

CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a sequence of moves that determines the interleaving of threads. Programs use synchronization to prevent bad moves. but

621 views • 22 slides
CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a

CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a

CPU Scheduling CPU Scheduling CPU Scheduling 101 CPU Scheduling 101 The CPU scheduler makes a sequence of moves that determines the interleaving of threads. Programs use synchronization to prevent bad moves. but

592 views • 29 slides
Other Camera Controls The LookAt function is only for positioning camera Other ways to

Other Camera Controls The LookAt function is only for positioning camera Other ways to

Other Camera Controls The LookAt function is only for positioning camera Other ways to specify camera position/movement Yaw, pitch, roll Elevation, azimuth, twist Direction angles Flexible Camera Control Sometimes, we

717 views • 26 slides
Other Camera Controls The LookAt function is only for positioning camera Other ways to

Other Camera Controls The LookAt function is only for positioning camera Other ways to

Other Camera Controls The LookAt function is only for positioning camera Other ways to specify camera position/movement Yaw, pitch, roll Elevation, azimuth, twist Direction angles Flexible Camera Control Sometimes, we want

941 views • 29 slides
Scheduling in Wireless Networks With Packet-Level and Flow-Level Dynamics Ramin Khalili Reading

Scheduling in Wireless Networks With Packet-Level and Flow-Level Dynamics Ramin Khalili Reading

Scheduling in Wireless Networks With Packet-Level and Flow-Level Dynamics Ramin Khalili Reading Group: 01.02.2011 1 Outline network model packet-level scheduling flow-level scheduling multi-channel case conclusion 2

328 views • 22 slides
Module 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

Module 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

Module 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms Multiple-Processor Scheduling Real-Time Scheduling Algorithm Evaluation Silberschatz, Galvin, and Gagne 1999 Applied Operating System

731 views • 36 slides
holder.addCallback(this); holder.setType(SurfaceHolder.STP); MediaRecorder r = new

holder.addCallback(this); holder.setType(SurfaceHolder.STP); MediaRecorder r = new

Camera camera = Camera.open(); Camera camera = Camera.open(); camera.setDisplayOrientation(90); camera.setDisplayOrientation(90); camera.unlock(); SurfaceHolder holder = getHolder(); holder.addCallback(this);

324 views • 21 slides
Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera

Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera

Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera projects 3D world points onto the 2D image plane Calibration : Find the internal quantities of the camera that affect this process Image center

908 views • 45 slides
Chapter 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

Chapter 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

Chapter 6: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms Multiple-Processor Scheduling Real-Time Scheduling Algorithm Evaluation Operating System Concepts Silberschatz, Galvin and Gagne 2002

496 views • 17 slides
Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera

Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera

Humanoid Robotics Camera Parameters Maren Bennewitz What is Camera Calibration? A camera projects 3D world points onto the 2D image plane Calibration : Find the internal quantities of the camera that affect this process Image

527 views • 48 slides
CPU Scheduling Schedulers in the OS Structure of a CPU Scheduler Scheduling =

CPU Scheduling Schedulers in the OS Structure of a CPU Scheduler Scheduling =

CPSC 313: Intro to Computer Systems Intro to Scheduling CPU Scheduling Schedulers in the OS Structure of a CPU Scheduler Scheduling = Selection + Dispatching Criteria for scheduling Scheduling Algorithms FIFO/FCFS

863 views • 7 slides
Module 5: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

Module 5: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms

' $ Module 5: CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms Multiple-Processor Scheduling Real-Time Scheduling Algorithm Evaluation &amp; % Silberschatz and Galvin c Operating System Concepts

331 views • 22 slides
CPU Scheduling - I Different Scheduling Algorithms FCFS SJF Priority RR

CPU Scheduling - I Different Scheduling Algorithms FCFS SJF Priority RR

CSE 421/521 - Operating Systems Roadmap Fall 2011 CPU Scheduling Basic Concepts Lecture - V Scheduling Criteria &amp; Metrics CPU Scheduling - I Different Scheduling Algorithms FCFS SJF Priority RR Tevfik

323 views • 5 slides
Scheduling OS Lecture 11 UdS/TUKL WS 2015 MPI-SWS 1 Scheduling What is scheduling and

Scheduling OS Lecture 11 UdS/TUKL WS 2015 MPI-SWS 1 Scheduling What is scheduling and

Scheduling OS Lecture 11 UdS/TUKL WS 2015 MPI-SWS 1 Scheduling What is scheduling and why is it necessary? To share a serially reusable resource among multiple processes. processors, I/O links, bandwidth, memory Schedule :

565 views • 22 slides

More recommend