Deep learning networks for selection of persistent scatterer pixels in multi-temporal SAR interferometric processing

no code implementations • 4 Sep 2019 • Ashutosh Tiwari, Avadh Bihari Narayan, Onkar Dikshit

However, pixel selection results, when compared to a combination of R-index and a classified image of the test dataset, reveal that CLSTM-ISS estimates improved the classification of PS and non-PS pixels compared to those of StaMPS and CNN-ISS.

Computational Efficiency Semantic Segmentation