基于贝叶斯分类器的实时视频优化传输方法  

Real-time Video Optimization Transmission Method Based on Bayesian Classifier

作　　者：杨明华[1] 王云会[2] 谭励[2] 苏维均[2] 王振海[3] 

机构地区：[1]北京工商大学计算机与信息工程学院,北京100048 [2]第二炮兵装备研究院,北京100085 [3]海军工程大学,天津300450

出　　处：《计算机工程》2014年第12期251-257,共7页Computer Engineering

基　　金：国家自然科学基金资助项目(61262088);国家"863"计划基金资助项目(2013aa0816);北京市自然科学基金资助项目(4132025)

摘　　要：通用UDP协议传输实时视频时存在延时较长的问题。为此,提出一种基于贝叶斯分类器的自适应视频实时传输方法。在发送图像数据前进行帧内压缩,压缩过程根据网络的实时带宽调整压缩质量因子,进行分组发送。在接收端进行数据包重组并解码,利用贝叶斯准则得出自适应调整的阈值,对使用自适应算法与使用固定因子情况下产生的延时进行比较,分析延时产生的原因。实验结果表明,该方法由于优化了传输数据队列的长度,在不增加网络延时的情况下,局部时间内提高了视频图像的传输质量。Using the common UDP protocol to transmit the real-time video,there is a serious problem of a very long delay,especially in the wireless environment. In response to these problems, this paper proposes an adaptive real-time video transmission method based on Bayesian classifier. Before the network sends the packets,the intraframe image data is compressed. The compression process adjusts timely the compression quality factor based on the network ’ s real-time bandwidth. At the same time, the receiving-end restructures and decodes them. The Bayesian theory gives the adaptive threshold through calculating. This paper compares the transmission delay which uses the adaptive algorithm with that uses fixed factor algorithm,and analyzes the reasons for the delay generated. Results show that,because of the need to optimize data transmission queue length, the adaptive method improves the transmission quality of the video image without increasing the latency of the network.

关 键 词：贝叶斯分类器 JPEG算法 帧内压缩 自适应算法 实时传输 传输延时 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]