多分辨率下资源感知的图像目标自适应缩放检测  

Resource-aware Based Adaptive-scaling Image Target Detection Under Multi-resolution Scenario

作　　者：张开强 蒋从锋[1] 程小兰 贾刚勇[1] 张纪林[2] 万健 ZHANG Kai-qiang;JIANG Cong-feng;CHENG Xiao-lan;JIA Gang-yong;ZHANG Ji-lin;WAN Jian(School of Computer Science and Technology,Hangzhou Dianzi University,Hangzhou 310018,China;School of Cyber Science and Engineering,Hangzhou Dianzi University,Hangzhou 310018,China;School of Information and Electronic Engineering,Zhejiang University of Science and Technology,Hangzhou 310023,China)

机构地区：[1]杭州电子科技大学计算机学院,杭州310018 [2]杭州电子科技大学网络空间安全学院,杭州310018 [3]浙江科技学院信息与电子工程学院,杭州310023

出　　处：《计算机科学》2021年第4期180-186,共7页Computer Science

基　　金：国家自然科学基金面上项目(61972118,61972358);浙江省重点研发计划项目(2019C01059)。

摘　　要：边缘视频处理可以降低云平台视频处理系统的视频传输时延、视频处理开销和存储成本,但是视频参数(分辨率、帧率等)的多样性容易导致边缘视频处理的效果不尽人意。通常,在图像预处理阶段会先对图像进行缩放变换再进行后续处理,以保障图像处理的最佳效果,但是在视频监控等具有不确定性的场景中对所有分辨率的图像直接成倍缩小容易降低目标检测率。基于以上问题,把图像水平像素点和垂直像素点的缩放倍数记作图像缩放因子,对于不同分辨率的视频数据,分析了图像缩放因子对视频数据处理效果的影响,提出了图像缩放因子动态设置方案。该方案以系统性能指标(服务器端系统功耗和内存使用率)为视频处理性能指标(人脸检测率)的约束条件,获取该分辨率下人脸检测率最优时对应的图像缩放因子。实验结果表明,对于不同分辨率的视频数据,图像缩放因子动态设置方案可以在保证视频处理性能的基础上,减少系统功耗和内存使用率,提高视频处理效率。Edge video processing can reduce the video transmission delay,video processing overhead and storage cost in the video processing system of cloud platform,but the diversity of video parameters(resolution,frame rate,etc.)will lead to unsatisfactory effect of edge video processing.Usually,in the stage of image pre-processing,image scaling and transformation will be applied to ensure the best effect of image processing.However,in uncertain scenes such as video monitoring,the target detection rate can be reduced largely by directly scaling down the resolution of all the images.According to the problems mentioned above,this paper chooses the scaling ratio of the horizontal and vertical pixels as image scaling factor.For the video data with different resolutions,it analyzes the influence of the image scaling factor on the performance of video data processing and puts forward the dynamically-setting scheme of image scaling factor.In this scheme,the system performance index(system power consumption and memory utilization of the server-side)is taken as the constraint condition of video processing performance index(face detection rate),to get the image scaling factor corresponding to the optimal face detection rate with this resolution.Experimental results show that for video data with different resolutions,the dynamic setting scheme of image scaling factor can reduce system power consumption and memory utilization,improve video processing efficiency and capability while guaranteeing video processing performance.

关 键 词：边缘计算 视频处理 视频参数 图像缩放 人脸检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]