Uncertainty Assessment of Hyperspectral Image Classification: Deep Learning vs. Random Forest
Majid Shadman Roodposhti, Jagannath Aryal, Arko Lucieer, Brett A Bryan
Entropy: international and interdisciplinary journal of entropy and information studies | MDPI | Published : 2019
Uncertainty assessment techniques have been extensively applied as an estimate of accuracy to compensate for weaknesses with traditional approaches. Traditional approaches to mapping accuracy assessment have been based on a confusion matrix, and hence are not only dependent on the availability of test data but also incapable of capturing the spatial variation in classification error. Here, we apply and compare two uncertainty assessment techniques that do not rely on test data availability and enable the spatial characterisation of classification accuracy before the validation phase, promoting the assessment of error propagation within the classified imagery products. We compared the perform..View full abstract
Awarded by Commonwealth Scientific and Industrial Research Organization (CSIRO)
This research was jointly funded by University of Tasmania and Commonwealth Scientific and Industrial Research Organization (CSIRO), grant number RT109121. BAB was funded by Deakin University.