ENHANCING UAV COASTAL MAPPING USING INFRARED PANSHARPENING

Abstract. Ecosystems must now cope with climate change such as rising sea levels. These major changes have a direct impact on the coastal fringe. However, in recent years, ecosystems saltmarshes proven their adaptive capacity. Unmanned Aerial Vehicles (UAV) are an inexpensive and easily deployable alternative which offer us possibility to monitor these geomorphological ecological systems, been perfected over making it possible achieve high or even very (VH) spectral spatial resolution. Detection of at VH temporal resolution coastline evolution seasonal monitoring plant communities is facilitated. The red-green-blue (RGB) camera basic equipment low-cost UAVs. Many studies demonstrated interest infrared sensors for vegetation water detection. In this original study, pansharpening method has developed generate red-edge (RE) near channel based RGB. Out three different algorithms tested, Gram-Schmidt showed correlation (0.61 0.63 RE NIR channels respectively), followed by nearest neighbor diffusion finally, principal component pansharpening. maximum likelihood, support vector machine convolutional neural network classifiers were used discriminate main objects study area. classification results revealed that classifier scale ML outperforms others overall accuracy 80.75%. At band scale, obtains best performances 80.04% OA 78.34% SVM.