A Robust Multispectral Point Cloud Generation Method Based on 3-D Reconstruction From Multispectral Images

Multispectral point cloud is a novel type of data rich in spectral and spatial information. The 3-D reconstruction is a low-cost solution for acquiring multispectral point cloud. However, most of the existing methods have been developed for RGB images, which are inapplicable to multispectral images due to the special structure of multispectral sensors and the nonlinear intensity differences. In this article, a robust 3-D reconstruction method for multispectral images is proposed to generate multispectral point cloud by harnessing their spatial and spectral information. Considering the characteristics of multispectral image acquisition, reflectance correction and band alignment steps are introduced into the proposed method, aiming to reduce the impact of band differences and spatial errors on 3-D reconstruction. Subsequently, a fused multispectral feature extraction is employed to provide more potential reconstruction feature points. To reduce the mismatched feature points induced by the spectra of vegetation regions, a normalized digital vegetation index (NDVI)-guided feature matching algorithm is proposed that provides accurate correspondence calculation for multispectral image reconstruction. The experiments compared with several well-known methods and commercial software on two datasets have shown superior reconstruction performance.

Automated summary

In this article, a robust 3-D reconstruction method for multispectral images is proposed, which improves the accuracy and performance of reconstruction by using reflectance correction, band alignment, and multispectral feature extraction.