Aerial sequential frame decimation for scene reconstruction

摘要: Micro aerial vehicle (MAV) can be used as an efficient image acquiring tool. However, video sequence has a large amount of redundant information, which will delay the scene reconstruction process and decrease structure accuracy. Meanwhile conventional frame decimation approaches normally have time-consuming feature matching step. This paper proposes hierarchical approach for video-based from motion with sequential frames. For preliminary decimation, both MAV's parameters quality are incorporated, sharply number detailed degenerate situations width baseline considered. The proposed is tested several datasets. results show that our promotes efficiency accuracy three dimensional outdoor reconstructions