About AMP Lab        Projects        Downloads        Publications        People        Links

Group Member

[Research Interests]        [Project]      [Publications] 

Cross-layer Optimization for Video Streaming over Wireless Networks:

My research interests lie on all topics about cross-layer optimization for wireless video streaming. We believe a cross-layer view instead of conventional individual prospective is a must for an efficient solution on wireless video streaming. 

• Algorithm for Content-aware Adaptive Retry on 802.11 WLANs

We design a content-aware adaptive retry (CAR) mechanism for video streaming over 802.11 wireless LAN environments. CAR considers the error propagation characteristics as well as video play-out schedule so as to improve user-perceived video quality. The CAR-aided MAC can improve wireless  video streaming significantly.

• Algorithms for Rate Adaptation on 802.11 WLANs

Rate adaptation (RA) to dynamically adjust data rate during transmission has improved channel throughput on wireless networks. However, conventional RA algorithms try to solve this problem by maximize channel throughput in a saturate manner, rather than consider the characteristics of data. For video streaming applications, RA has to account for the delay sensitive property and adapt accordingly. Here we propose an advanced RA algorithm for wireless video streaming so as to take advantage of frame dependency and avoid outdated packets.

• Cross-layer optimized wireless video streaming system

We implement a cross-layer optimized real-time H.263 video decoder/player on Linux platform. The Prism2 hostap driver is modified to support the content-aware adaptive retry feature. The collaboration of application and link layer demonstrate a better visual quality in bandwidth-limited, error-prone wireless environment.  

  Top of this page

Content-aware Adaptive Retry for Video Streaming on 802.11 WLANs Robust video streaming over wireless LAN (WLAN) poses many challenges. In order to maximize channel throughput, rate adaptation (RA) to dynamically select the transmission rate at a given time has been recognized as an effective way to improve the performance of 802.11 WLANs. However, extra retransmission for channel probing during RA also causes additional delay and possible packet loss. For video streaming, we believe this overhead should be placed on less important packets so as to minimize quality distortion on the receiver side. We propose a content-aware adaptive retry mechanism for video streaming over 802.11 WLANs, where retry decision is made dynamically according to packet importance and its play-out schedule. Simulation results show that the proposed mechanism significantly improves video quality as well as saves transmission bandwidth. We also implement the above concept into a real system on Linux platform. Please refer to the Content-aware Adaptive Retry on 802.11 WLANs for more details.

.

Top of this page

Journal Papers: 

• M. Lu, P. Steenkiste, and T. Chen, "CAR: A Content-aware Adaptive Retry Strategy for Video Streaming in 802.11 WLANs,"  submitted to Wireless Communications and Mobile Computing, Special Issue on Video Communications for 4G Wireless Systems, June 2006.

Conference Papers: 

• M. Lu, P. Steenkiste, and T. Chen, "Design, Implementation, and Evaluation of an Efficient Opportunistic Retransmission Protocol,"  MobiCom, 2009. 

• M. Lu and T. Chen, "CMUseum: A Location-aware Wireless Video Streaming System,"  submitted to IEEE International Conference on Multimedia and Expo (ICME), July 2006. 

• M. Lu, P. Steenkiste, and T. Chen, "Video Streaming over 802.11 WLANs with Content-aware Adaptive Retry,"  IEEE International Conference on Multimedia and Expo (ICME), July 2005. 

• T. Chen, M. Lu, J. Huang, "Design and Implementation of an H.323 Multimedia Conference System", Proceedings of 1999 Workshop on Distributed System Technologies & Applications, Tainan, Taiwan,  May 1999. 

• T. Chen, M. Lu, J. Huang, "Real-time Multimedia Synchronization on H.323 Multimedia Conference System", Proceedings of 1999 Multimedia Technology and Application Symposium, Kaohsiung, Taiwan, March 1999.

Top of this page