Adaptive streaming of HD and 360[formula omitted] videos over software defined radios

Abstract

In this paper we study and implement real-time adaptation schemes for video encoding and channel selection that work in tandem to facilitate HD and 360° video streaming for secondary users in a dynamic spectrum access network. Out-of-band feedbacks on instantaneous pathloss of the signal between the transmitter and the receiver, the received signal strength indicator (RSSI) at the receiver, and the quality of the reconstructed video, are used to continuously determine the best possible encoding parameters. Similarly, the radio transmitter continuously adjusts the channel parameters (i.e., center frequency and channel bandwidth) based on the transmission activities of the primary users who are prioritized on these channels. We consider the physical limitations of the encoder and the channel statistics to determine when to change the encoder parameters and when to switch to a new channel. We propose a multi-level threshold based mechanism to find the optimal number of encoding bit rates. We also propose a threshold based algorithm to find the best available channel between the transmitter–receiver pair. We validate our theoretical propositions on an indoor testbed using universal software radio peripherals (USRPs) and GNU Radio. Live videos captured with a web-cam and a 360° VR camera were encoded with open source H.264 software libraries and streamed using GStreamer. The signal was transmitted over the 915 MHz ISM bands with omni-directional antennas. We used two B210s (from Ettus Research) for the transmitter and the receiver. Another B210 was programmed to sense the energy levels on all the channels in order to detect the presence of primary user transmissions. GNU Radio was used to build the initial flow-graph of all the signal processing modules, both at the transmitter and the receiver. We used Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM) to measure the video quality. Experimental results show that (i) the video encoder and the USRP transmitter–receiver pair were able to adapt to the changing RF conditions, (ii) the adaptation schemes yielded better video quality than non-adaptive schemes, and (iii) the USRPs could switch the channels fast enough allowing uninterrupted video streaming even when the primary users preempted the secondary user’s transmission. We also present a simulation study to show that the proposed encoder and channel adaptation algorithms can be scaled to larger networks.