Video Synchronization With Bit-Rate Signals and Correntropy Function
AbstractWe propose an approach for the synchronization of video streams using correntropy. Essentially, the time offset is calculated on the basis of the instantaneous transfer rates of the video streams that are extracted in the form of a univariate signal known as variable bit-rate (VBR). The state-of-the-art approach uses a window segmentation strategy that is based on consensual zero-mean normalized cross-correlation (ZNCC). This strategy has an elevated computational complexity, making its application to synchronizing online data streaming difficult. Hence, our proposal uses a different window strategy that, together with the correntropy function, allows the synchronization to be performed for online applications. This provides equivalent synchronization scores with a rapid offset determination as the streams come into the system. The efficiency of our approach has been verified through experiments that demonstrate its viability with values that are as precise as those obtained by ZNCC. The proposed approach scored
Share & Cite This Article
Pereira, I.; Silveira, L.F.; Gonçalves, L. Video Synchronization With Bit-Rate Signals and Correntropy Function. Sensors 2017, 17, 2021.
Pereira I, Silveira LF, Gonçalves L. Video Synchronization With Bit-Rate Signals and Correntropy Function. Sensors. 2017; 17(9):2021.Chicago/Turabian Style
Pereira, Igor; Silveira, Luiz F.; Gonçalves, Luiz. 2017. "Video Synchronization With Bit-Rate Signals and Correntropy Function." Sensors 17, no. 9: 2021.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.