基于Zynq的视频实时拼接系统

Real-time video stitching system based on Zynq

针对目前视频拼接系统实时性不高、拼接效果不理想、成本高等问题,对传统的ORB算法进行了改进,并采用软硬件协同设计的方法,在Zynq平台上实现了一款视频实时拼接系统。该系统利用Zynq的PS搭建嵌入式Linux系统,进行用户界面开发,实现任务调度;利用Vivado HLS工具将改进的视频拼接算法进行硬件加速并部署到Zynq的PL中。实验结果表明,该视频拼接系统拼接后的图像清晰度高、无拼接缝隙,而且基于Zynq和改进ORB算法的视频拼接方案使视频拼接速度获得到了很大的提升,满足实时性的要求。

Aiming at the existing problems of low real-time performance,unsatisfactory stitching effect and high cost in video stitching system at present,a real-time video stitching system was implemented on Xilinx Zynq platform using software and hardware collaborative design method after improving traditional ORB algorithm.The system used PS on Zynq to build an embedded Linux system,develop user interface programs,and implement task scheduling.The improving video stitching algorithm was packaged into an IP core that can be deployed into the PL on Zynq through Vivado HLS tools to achieve hardware accelerated processing.Experimental results showed that stitched video image had high clarity and no stitching gap,while this Zynq-based software and hardware collaborative processing architecture had greatly improved the speed of video stitching,which can meet the requirements of real-time processing.