期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：6
页码：10342
DOI：10.15680/IJIRSET.2015.0506153
出版社：S&S Publications
摘要：The use of Unmanned aerial vehicle (UAV) natural resource application has increased considerably inrecent years due to their greater availability and ability deploy a UAV relatively quickly. Road detection and trackingare important and challenging tasks in many computer vision applications such as surveillance,vehicle navigation.Detection and tracking of road in UAV videos play an important role in automatic UAV navigation, traffic monitoring,and ground vehicle tracking, observe conditions on network of roadways. In this paper, an efficient road detection andtracking framework in UAV videos is proposed. In particular, a graph cut based for detect the road regions duringinitialize stage and homography based road tracking scheme developed to automatically track road areas. The proposedsystem works more efficiently as the road detection and tracking is performed. Thus, the implementation of UAVs inurban areas provides a more efficient of tracking and detection of road conditions and traffic situations in urban areas.Experiments are conducted on UAV videos of road scenes captured and downloaded from the Internet. The promisingresults indicate the effectiveness of of proposed framework.
