基于对象的视频摘要算法的实现与加速

Implementation and Acceleration of Object-Based Video Synopsis Algorithm

现有基于对象的视频摘要算法较少考虑计算效率,导致其难以满足大规模安防监控领域的性能要求.为此,文中提出了改进的基于对象的视频摘要算法,通过降低帧率和分辨率、运动片段检测以及基于重心的对象跟踪等策略来提升算法效率.此外,为充分挖掘CPU和GPU的计算能力,设计了相应的多线程算法,并对关键步骤进行GPU优化,以进一步加速算法性能.实验结果表明,改进算法和加速策略可以大幅提升视频摘要的计算速度.

As the existing object-based video synopsis algorithms cannot meet the actual demands in large-scale surveillance field due to the ignorance of computation efficiency,an improved algorithm,which improves the computation efficiency by reducing frame rate and resolution,detecting motion segments and tracking objects on the basis of gravity center,is proposed. Furthermore,in order to utilize the computing power of CPU and GPU fully,a multithread strategy and a GPU programming are conducted to accelerate the execution of the algorithm. Experimental results show that the improved algorithm and the proposed acceleration strategy both improve the computation efficiency of video synopsis greatly.