Streaming 3D graphics have been widely used in multimedia applications such as online gaming and virtual reality. However, a gap exists between the zero-loss-tolerance of the existing compression schemes and the lossy network transmissions. In this article, we propose a generic 3D middleware between the 3D application layer and the transport layer for the transmission of triangle-based progressively compressed 3D models. Significant features of the proposed middleware include. 1) handling 3D compressed data streams from multiple progressive compression techniques. 2) considering end user hardware capabilities for effectively saving the data size for network delivery. 3) a minimum cost dynamic reliable set selector to choose the transport protocol for each sublayer based on the real-time network traffic. Extensive simulations with TCP/UDP and SCTP show that the proposed 3D middleware can achieve the dual objectives of maintaining low transmission delay and small distortion, and thus supporting high quality 3D streaming with high flexibility.

Providing Quality of Service (QoS) to users in a wireless ad-hoc network is a key concern for service providers. With the availability of multiple rates in IEEE 802.11a/b/g wireless LANs, it is desirable to improve the network capacity and temporal fairness by sending multiple consecutive frames (also referred as frame concatenation mechanism in [14]) over high rate links, as proposed in opportunistic auto rate (OAR [10]). However, OAR does not consider the effect of frame sizes and may yield unsatisfactory performance for high priority multimedia flows transmitting over low rate links. Therefore, a more appropriate frame concatenation strategy and a corresponding service differentiation scheme should be devised to provide better performance for high priority voice/video flows than low priority data flows, under various channel rate scenarios. In this paper, we first analyze the effect of frame size on the performance of OAR. Then, we propose a general concatenation mechanism (GCM), a more accurate frame concatenation mechanism for multi-rate MAC with better fairness. Finally, we propose two mechanisms: adaptive weighted fair frame concatenation mechanism (AWFCM) and adaptive QoS aware frame concatenation mechanism (AQCM), for supporting service differentiation and QoS in multi-rate wireless ad hoc networks. The primary idea is to adjust the number of concatenated frames based on flow weights/priorities, frame sizes, link rates, and network traffic. Simulation results show that the proposed mechanisms achieve desirable performance on supporting multimedia applications in multi-rate wireless ad-hoc networks.

No abstract