结合影像一致性检测的无人机真正射影像处理

Real Projective Processing of UAV Based on Image Consistency Detection

为更好地解决无人机影像真正射微分纠正过程中存在的影像"拖影"现象,提出了一种基于影像一致性检测的无人机真正射处理技术。该技术在对微分纠正区域格网划分基础上,结合哈希感知算法进行原始微分纠正影像块一致性检测,快速定位建筑物影像遮蔽区块格网,根据地底点辐射距精准探测出建筑物遮蔽区域,通过地底点距离最优选择最优影像进行遮蔽区域补偿。试验证明,文中算法针对无人机小像幅、大视场角影像具有很强的适应性。

To solve the image "ghosting"problem existing in differential correction of unmanned aerial vehicle (UAV)TDOM image processing,this research puts forward a UAV TDOM image rectification based on image consistency.On the basis of grid division on differential correction region,and taking in the hash image consistency detection algorithm,this technology accurately detect and fast position the masking area of construction images based on the underground point radiation,and select the best image through the optimal underground point distance to compensate the masking area.The experimental results show that the algorithm is adaptable to the UAV small image and large field Angle image.