基于深度学习的海量航拍视频智能处理技术  

Intelligent Processing Technology of Massive Aerial Video Based on Deep Learning

作　　者：武林伟[1] 闫婧 WU Lin-wei;YAN Jing(The 27th Research Institute of China Electronics Technology Group Corporation,Zhengzhou 450047,China)

机构地区：[1]中国电子科技集团公司第二十七研究所,郑州450047

出　　处：《电光系统》2022年第1期32-36,共5页Electronic and Electro-optical Systems

摘　　要：针对现阶段处理航拍视频数据工作量大、处理工作繁琐、人工成本高、重点目标信息提取效率低等问题,研究了基于深度学习的海量航拍视频处理技术,提出以目标自动检测和智能分割为基础的视频处理技术,该技术实现目标自动检测识别、视频智能分割、视频特征分类以及视频快速检索等功能,并完成了航拍视频智能化处理软件设计。通过工程实践应用,证明了该技术可以有效减少作业人员重复性工作,提高视频处理作业效率。Aiming at the problems of heavy workload,cumbersome processing,high labor cost and low efficiency of key target information extraction at the present stage,this paper studies the massive aerial video processing technology based on deep learning and puts forward the video processing technology based on automatic target detection and intelligent segmentation,which realizes automatic target detection and recognition,intelligent video segmentation,video feature classification and video fast retrieval.Also the design of aerial video intelligent processing software is completed.Through engineering practice,it is proved that this technology can effectively reduce the repetitive work of operators and improve the efficiency of video processing.

关 键 词：深度学习 海量航拍视频 智能处理 视频分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]