基于Laplacian算子的航飞影像预处理分析

Preprocessing Analysis of Aerial Images Based on Laplacian Operator

模糊影像会直接影响空中三角测量解算的结果,因此需要对无人机航飞影像进行预处理。分别使用Soble算子和Laplacian算子对航飞影像中模糊的照片进行边缘检测,识别出模糊照片。分析2种算子在航片预处理中的适用性,并编译软件自动分离出模糊和无效的照片。结果表明:Sobel和Laplacian算子均可以准确地分离出模糊影像,影像识别率可达100%。其中,Laplacian算子对航飞影像的边缘检测敏感度高于Sobel算子,Laplacian算子得到的方差值更大,判定影像清晰与模糊的界限更准确。最后通过快速检索算法与Laplacian算法相结合,编译完成无人机航飞影像预处理模块,提高无人机航片预处理效率。

The blurred image affects the result of aerial triangulation solution.It is necessary to preprocess the UAV aerial images.Soble operator and Laplacian operator are used to detect the edge of blurred photos in aerial images respectively.This paper analyzes the applicability of the two operators in aerial image preprocessing,and compiles the software to automatically separate blurred and invalid photos.The results show that both Sobel and Laplacian operators can accurately separate blurred images,and the image recognition rate can reach 100%.Laplacian operator is more sensitive to the edge detection of aerial images than Sobel operator.The variance value obtained by Laplacian operator is larger,and the boundary between clear and blurred image is more obvious.Finally,through the combination of fast retrieval algorithm and Laplacian algorithm,the UAV aerial image preprocessing module is compiled,which improves the efficiency of UAV aerial image preprocessing.