摘要
为解决传统插值方法对采集的视频图像放大时易出现块效应和细节退化的问题,在高级RISC微处理器(advanced RISC microprocessor,ARM)平台上设计并搭建基于小波变换算法的嵌入式超分辨率复原系统.以ARM Cortex TM-A8处理器(S5PV210)为核心搭建硬件平台,采用嵌入式Linux系统搭建软件开发环境,设计基于V4L2接口的视频图像采集程序.最后将基于小波变换的超分辨率复原算法植入系统.实验证明,该系统处理的视频图像,比传统插值方法处理的视频图像取得了更高的峰值信噪比,能够恢复出更多细节信息.
In order to overcome the disadvantage of the traditional methods for magnifying collected video images by interpolation,we design an embedded super-resolution restoration system based on advanced RISC microprocessor（ ARM） and a wavelet transform algorithm. The hardware platform is an ARM Cortex TM-A8 processor（ S5PV210）as the core processor and the software development environment is embedded Linux. We implement a video image collecting program based on V4L2 and a super-resolution restoration algorithm based on wavelet transformation.Experimental results show that the peak signal to noise ratio（ PSNR） is better than those processed by frequently used interpolation methods,and more detail in the images can be restored.
出处
《深圳大学学报（理工版）》
EI
CAS
CSCD
北大核心
2015年第3期311-316,共6页
Journal of Shenzhen University(Science and Engineering)
基金
国家重大科学仪器设备开发专项基金资助项目(2014YQ230659)~~
关键词
图像处理
超分辨率复原
高级RISC微处理器
小波变换
LINUX
V4L2接口
视频图像采集程序
峰值信噪比
image processing
super-resolution restoration
advanced RISC microprocessor（ARM）
wavelet transform
Linux
video for Linux two（V4L2） port
program for video image collecting
peak signal to noise ratio
