A fast detection method for changed land using UAV remote sensing image

Abstract

Abstract. This paper proposes a fast detection method for changed land using UAV remote sensing image. Firstly, a series of SURF feature points on the old time phase orthoimage are retrieved and stored into a matching database. Secondly, through the establishment of coarsefine double matching recursive model to quickly match the new and old time phase images, Whether the change of land use is preliminarily determined by the matching of feature points. Finally, it can be accurately determined whether the suspicious land is appeared through comparative analysis which based on the spectrum and texture of the dual mode comprehensive contrast detection method .Compared to the traditional technology, this method does not need to lay a large number of ground control points, and does not need to splice the UAV images, but can realize the rapid automatic discovery of suspicious objects, which is not only high precision but also saves time and effort.

Abandoned terrace recognition based on deep learning and change detection on the Loess Plateau in China

“…In addition, feature extraction based on NDVI time series data depends on the temporal and spatial resolution of remote sensing data when applied on a large or national scale (Shi, 2020). Computer technology has enabled remote sensing technology, machine learning (Low et al, 2015; Wang et al, 2020), and change detection (Cheng et al, 2011; Kuemmerle et al, 2008; Witmer, 2008; Yang et al, 2019; Zhang, 2010). The most important part of decision tree classification is the establishment of discriminant rules, using differences in the reflection spectral curves of different objects.…”