Difference between revisions of "Network and Multimedia Systems Lab (NMSL)"

From NMSL
 
(173 intermediate revisions by 13 users not shown)
Line 1: Line 1:
 
__NOTOC__
 
__NOTOC__
  
−
'''Welcome to the Network Systems Lab at SFU!'''
+
'''Welcome to the Network and Multimedia Systems Lab (NMSL) at SFU!'''
  
 +
The Network and Multimedia Systems Lab is led by [http://www.cs.sfu.ca/~mhefeeda/ Dr. Mohamed Hefeeda,] and it is located in the TASC1 building, room 8208.
  
−
We are interested in the broad area of computer networking and distributed systems. We develop algorithms and protocols to enhance the performance of networks, especially the Internet, and to efficiently distribute multimedia content (e.g., video and audio objects) to large-scale user communities. The Network Systems Lab is led by [http://www.cs.sfu.ca/~mhefeeda/ Dr. Mohamed Hefeeda], and is affiliated with the [http://www.cs.sfu.ca/research/groups/NML/ Network Modeling Group] at SFU.
+
We are interested in the broad areas of multimedia systems, machine learning, and computer networks. We develop algorithms and systems to efficiently distribute multimedia content to large-scale user communities over wired and wireless networks. We design machine learning models to address important and challenging problems in multimedia and network systems. Our current research projects include hyperspectral imaging, datacenter networking, scalable multicast systems, cloud gaming, multimedia forensics, mobile multimedia, and AR/VR content processing and streaming. In most of our works, we develop prototypes and testbeds to demonstrate the practicality of our solutions and show their performance in actual environments.
  
−
Our current research interests include multimedia networking, peer-to-peer systems, wireless sensor networks, and network security. Brief description and links to currently active projects are given below.
+
At a high level, our current research interests include:
  
−
== '''Multimedia Networking''' ==
+
'''<big>Machine Learning for Multimedia:</big>''' We design learning-based solutions to address complex real-life problems that involve multiple modalities and entities, such as:   
 +
* '''''Multimedia Forensics:''''' detecting makeup attacks in biometric systems using generative adversarial models, fighting content forgery and deepfake using deep watermarking, and detecting food fraud using hyperspectral imaging and deep-learning models. 
 +
* '''''Content Enhancement:''''' removing reflection in images using unsupervised learning models, and up-sampling of rendered contents in cloud gaming using deep learning.
  
−
We are focusing on distributed streaming in dynamic environments and for heterogeneous clients.  Our
 
−
goal is to analyze and understand scalable coding techniques, and to design several optimization and streaming algorithms to make the best possible use of them in real multimedia systems. This will yield better quality for users, and more efficient utilization of network and server resources. We are also  designing algorithms to optimize streaming quality for wireless and mobile clients.
 
  
−
* '''[[Scalable Multimedia Streaming]]'''  
+
'''<big>Multimedia Networking:</big>''' We design systems for efficient encoding, processing, and delivery of immersive (3D, AR, and VR) multimedia content, such as:
 +
* '''''Augmented and Virtual Reality (AR/VR):''''' automatically converting 2D videos to 3D and VR, and adaptively streaming AR/VR content to heterogeneous receivers.
 +
* '''''Cloud Gaming:''''' designing next-generation cloud gaming systems that optimize video quality, player engagement, and required computing and bandwidth resources. 
  
−
* '''[[Streaming to Wireless and Mobile Devices]]'''
 
  
−
* '''[[Content-Aware Adaptive Streaming]]'''
+
'''<big>Network Protocols and Systems:</big>'''  We design protocols and systems to efficiently manage the resources of different networks and support the growing computation and communication demands of machine learning models, such as: 
−
   
+
* '''''Datacenter Multicast:''''' designing scalable multicast systems for datacenters to support efficient group communications patterns common in training machine learning models.  
−
== '''Peer-to-Peer Systems''' ==
+
* '''''ISP and CDN Traffic Management:''''' developing algorithms to support multicast traffic engineering in ISP and CDN networks.
 +
* '''''Datacenter Task Scheduling:''''' designing in-network, fine-grain, schedulers for micro-second scale tasks to support interactive workloads. 
  
−
We are exploring the applicability of the P2P paradigm to build cost-effective content distribution systems.  Problems such as sender selection, adaptive object replication,  and content caching are being studied. We are also developing models to analyze the new characteristics of the P2P traffic and the impact of these characteristics on the cache replacement policies and object replication strategies.
 
−
Furthermore, we are devising analytic models  to study the dynamics of the system capacity and the impact of various parameters on it.
 
  
−
* '''[[pCDN|pCDN: Peer-assisted Content Distribution Network]]'''
+
We publish papers in reputable conferences and journals. Most of our Journal Publications are in the premier IEEE and ACM transactions in our areas, such as IEEE Trans. on MM, ACM Trans. on MM, and IEEE/ACM Trans. on Networking. Similarly, most of our Conference Publications are in selective and high-quality conferences, including MM, NSDI, MobiCom, INFOCOM, ICNP, and MMSys.
  
−
* '''[[Modeling and Caching of P2P Traffic]]'''
+
Brief descriptions and links to some of our active and concluded projects are given below.
  
−
== '''Wireless Sensor Networks''' ==  
+
== '''Hyperspectral Imaging''' ==  
 +
{|
 +
| Hyperspectral cameras capture scenes in many wavelength bands across the spectrum, providing far more information than regular cameras that operate in the visible light range. Hyperspectral imaging can be useful in many commercial/civilian applications such as agricultural research, land-cover mapping, forest monitoring, and mapping of natural disasters, as well as military applications including remote sensing, surveillance, and identification of camouflaged objects.
  
−
We are developing coverage and connectivity maintenance protocols that consider probabilistic (i.e., more realistic) sensing and communication models. We are also designing protocols that provide controllable degrees of coverage (k-coverage).  
+
Despite the substantial potential of hyperspectral imaging, its utilization has been limited to a small subset of large-scale military and industrial applications. The long-term goal of this research is to enable the wide adoption of hyperspectral imaging in many real-life applications.  
  
−
* '''[[Probabilistic Coverage and Connectivity]]'''
+
'''[[Hyperspectral Imaging|Project Page ...]]'''  
  
−
* '''[[K-Coverage and its Application to Forest Fire Detection]]'''
+
|| 
 +
[[File:Hyperspectral signatures.png|thumb|Hyperspctral imaging.|right]]
 +
|}
  
−
== '''Network Security''' ==  
+
== '''Cloud Gaming''' ==
 +
{|
 +
|
 +
Cloud gaming enables users to play games on virtually any device. This is achieved by offloading the game rendering and encoding to cloud datacenters. As game resolutions and frame rates increase, cloud gaming platforms face a major challenge to stream high-quality games due to the high bandwidth and low latency requirements.
  
−
We are exploring network monitoring techniques to detect and thwart intrusion and denial-of-service attacks in their early stages by observing unusual traffic patterns injected by such attacks. We are studying the security of multimedia streaming systems that employ multi-layer and fine-grain scalable video streams.  
+
The goal of this project is to design and implement a comprehensive, end-to-end, framework for next-generation cloud gaming systems to optimize the video quality, bitrate, and end-to-end delay.
  
−
* '''[[Detecting DoS Attacks and Service Violations in QoS-enabled Networks]]'''
+
This project is supported by '''AMD Canada''' and an '''NSERC Alliance''' project.
  
−
* '''[[Security of Scalable Multimedia Streams]]'''
+
'''[[Cloud Gaming | Project Page ...]]'''
 +
 
 +
|| [[File:CloudGaming.png|thumb|Overview of cloud gaming architectures.|right]]
 +
|}
 +
 
 +
== '''Datacenter and ISP Networks''' ==
 +
 
 +
{|
 +
|
 +
We develop algorithms and systems to optimize the performance of datacenter and ISP (Internet Service Provider) Networks. This includes designing scalable multicast systems for datacenters and developing stateless and efficient protocols to support service chaining and multicast traffic engineering in ISP networks.
 +
 
 +
This work was supported by '''Cisco''' and an '''NSERC Strategic''' project.
 +
 
 +
'''[[Scalable Multicast | Project Page ...]]'''
 +
||
 +
[[File:Orca.png|thumb|Design of Orca (multicast system for datacenters). |right]]
 +
|}
 +
 
 +
== '''Immersive and Next-Generation Videos''' ==
 +
{|
 +
| With massive investments in augmented and virtual reality (AR/VR) hardware, companies encounter the challenge of providing VR content.  The current solution for installing and operating VR camera rigs is expensive and not scalable. This project provides novel algorithms and methods to automatically convert standard broadcast 2D video streams to 3D and immersive VR streams of high quality. It also provides algorithms for adaptively streaming AR/VR content over the Internet to large-scale receivers.
 +
||
 +
[[File:VR2.jpg|thumb|right|Generating VR content from 2D videos. ]]
 +
|}
 +
 
 +
'''[[Immersive_Videos|Project Page ...]]'''
 +
 
 +
== '''Multimedia Forensics''' ==
 +
{|
 +
| Recent advances in machine learning have made it easier to create fake images and videos. Users and computing systems are facing increasing difficulties in differentiating forged contents from original ones. In this project, we focus on various aspects of detecting fake content, including detecting makeup attacks in biometrics systems and identifying forged videos and images.
 +
 
 +
 
 +
'''[[Multimedia Forensics | Project Page ...]]'''
 +
 
 +
|| 
 +
[[File:MakeupAttacks.png|thumb|right|Sample makeup attacks. ]]
 +
|}
 +
 
 +
 
 +
= '''''[[Concluded Projects]]''''' =
 +
 
 +
Please check [[Concluded Projects | '''this link''']] for some of our previous projects.

Latest revision as of 13:10, 25 October 2023


Welcome to the Network and Multimedia Systems Lab (NMSL) at SFU!

The Network and Multimedia Systems Lab is led by Dr. Mohamed Hefeeda, and it is located in the TASC1 building, room 8208.

We are interested in the broad areas of multimedia systems, machine learning, and computer networks. We develop algorithms and systems to efficiently distribute multimedia content to large-scale user communities over wired and wireless networks. We design machine learning models to address important and challenging problems in multimedia and network systems. Our current research projects include hyperspectral imaging, datacenter networking, scalable multicast systems, cloud gaming, multimedia forensics, mobile multimedia, and AR/VR content processing and streaming. In most of our works, we develop prototypes and testbeds to demonstrate the practicality of our solutions and show their performance in actual environments.

At a high level, our current research interests include:

Machine Learning for Multimedia: We design learning-based solutions to address complex real-life problems that involve multiple modalities and entities, such as:

  • Multimedia Forensics: detecting makeup attacks in biometric systems using generative adversarial models, fighting content forgery and deepfake using deep watermarking, and detecting food fraud using hyperspectral imaging and deep-learning models.
  • Content Enhancement: removing reflection in images using unsupervised learning models, and up-sampling of rendered contents in cloud gaming using deep learning.


Multimedia Networking: We design systems for efficient encoding, processing, and delivery of immersive (3D, AR, and VR) multimedia content, such as:

  • Augmented and Virtual Reality (AR/VR): automatically converting 2D videos to 3D and VR, and adaptively streaming AR/VR content to heterogeneous receivers.
  • Cloud Gaming: designing next-generation cloud gaming systems that optimize video quality, player engagement, and required computing and bandwidth resources.


Network Protocols and Systems: We design protocols and systems to efficiently manage the resources of different networks and support the growing computation and communication demands of machine learning models, such as:

  • Datacenter Multicast: designing scalable multicast systems for datacenters to support efficient group communications patterns common in training machine learning models.
  • ISP and CDN Traffic Management: developing algorithms to support multicast traffic engineering in ISP and CDN networks.
  • Datacenter Task Scheduling: designing in-network, fine-grain, schedulers for micro-second scale tasks to support interactive workloads.


We publish papers in reputable conferences and journals. Most of our Journal Publications are in the premier IEEE and ACM transactions in our areas, such as IEEE Trans. on MM, ACM Trans. on MM, and IEEE/ACM Trans. on Networking. Similarly, most of our Conference Publications are in selective and high-quality conferences, including MM, NSDI, MobiCom, INFOCOM, ICNP, and MMSys.

Brief descriptions and links to some of our active and concluded projects are given below.

Hyperspectral Imaging

Hyperspectral cameras capture scenes in many wavelength bands across the spectrum, providing far more information than regular cameras that operate in the visible light range. Hyperspectral imaging can be useful in many commercial/civilian applications such as agricultural research, land-cover mapping, forest monitoring, and mapping of natural disasters, as well as military applications including remote sensing, surveillance, and identification of camouflaged objects.

Despite the substantial potential of hyperspectral imaging, its utilization has been limited to a small subset of large-scale military and industrial applications. The long-term goal of this research is to enable the wide adoption of hyperspectral imaging in many real-life applications.

Project Page ...

Hyperspctral imaging.

Cloud Gaming

Cloud gaming enables users to play games on virtually any device. This is achieved by offloading the game rendering and encoding to cloud datacenters. As game resolutions and frame rates increase, cloud gaming platforms face a major challenge to stream high-quality games due to the high bandwidth and low latency requirements.

The goal of this project is to design and implement a comprehensive, end-to-end, framework for next-generation cloud gaming systems to optimize the video quality, bitrate, and end-to-end delay.

This project is supported by AMD Canada and an NSERC Alliance project.

Project Page ...

Overview of cloud gaming architectures.

Datacenter and ISP Networks

We develop algorithms and systems to optimize the performance of datacenter and ISP (Internet Service Provider) Networks. This includes designing scalable multicast systems for datacenters and developing stateless and efficient protocols to support service chaining and multicast traffic engineering in ISP networks.

This work was supported by Cisco and an NSERC Strategic project.

Project Page ...

Design of Orca (multicast system for datacenters).

Immersive and Next-Generation Videos

With massive investments in augmented and virtual reality (AR/VR) hardware, companies encounter the challenge of providing VR content. The current solution for installing and operating VR camera rigs is expensive and not scalable. This project provides novel algorithms and methods to automatically convert standard broadcast 2D video streams to 3D and immersive VR streams of high quality. It also provides algorithms for adaptively streaming AR/VR content over the Internet to large-scale receivers.
Generating VR content from 2D videos.

Project Page ...

Multimedia Forensics

Recent advances in machine learning have made it easier to create fake images and videos. Users and computing systems are facing increasing difficulties in differentiating forged contents from original ones. In this project, we focus on various aspects of detecting fake content, including detecting makeup attacks in biometrics systems and identifying forged videos and images.


Project Page ...

Sample makeup attacks.


Concluded Projects

Please check this link for some of our previous projects.

Retrieved from "https://nmsl.cs.sfu.ca/index.php?title=Network_and_Multimedia_Systems_Lab_(NMSL)&oldid=6812"
Powered by MediaWiki