一种利用飞艇航拍视频的运动车辆检测方法  

Vehicle Detection Algorithm with Video from Airborne Camera

作　　者：王文龙[1,2] 唐炉亮[1,2] 李清泉[1,2] 雷波[1,2] 

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,武汉市珞喻路129号430079 [2]武汉大学交通研究中心,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2010年第7期786-789,共4页Geomatics and Information Science of Wuhan University

基　　金：国家科技支撑计划资助项目(2008BAK49B02);国家863计划资助项目(2007AA12Z241);武汉大学测绘遥感信息工程国家重点实验室专项研究基金资助项目

摘　　要：针对低空飞行器(飞艇)为平台获取的高清晰交通视频数据,通过对交通视频序列数据进行运动补偿与配准,提出了一个在复杂变化背景下基于帧差法的运动目标(车辆)快速检测与提取方法。实验结果验证了本方法的准确与可靠性。Currently,the conflict between vehicle and road is becoming increasingly serious.How to implement advanced technology to obtain traffic information fast and accurately becomes a key point to upgrade the level of transport management and services.Access dynamic traffic information rapidly based on the low-altitude aircraft becomes an improtant expansion of conventional collection means.This paper aimes at low-altitude aircraft（airship） as a platform to obtain the high-definition video data,and proposes a method for detecting moving targets（vehicles） quickly and accurately in the complex situation.Finally,massive video data were acquired by low-altitude aircraft platform,and the results prove the proposed method is capable of detecting moving vehicles fast and reliably.

关 键 词：飞艇平台 交通数据采集 视频数据 运动车辆检测 

分 类 号：P208[天文地球—地图制图学与地理信息工程]