Ground Truth Simulation for Deep Learning Classification of Mid-Resolution Venus Images Via Unmixing of High-Resolution Hyperspectral Fenix Data
This addresses the cost and inconsistency issues in acquiring ground truth for remote sensing classification, though it is incremental as it adapts existing unmixing and CNN methods to a specific domain.
The paper tackles the problem of lacking field data for training deep neural networks in remote sensing by simulating ground truth from high-resolution hyperspectral FENIX images, and successfully transfers the trained CNN to classify mid-resolution VENuS imagery.
Training a deep neural network for classification constitutes a major problem in remote sensing due to the lack of adequate field data. Acquiring high-resolution ground truth (GT) by human interpretation is both cost-ineffective and inconsistent. We propose, instead, to utilize high-resolution, hyperspectral images for solving this problem, by unmixing these images to obtain reliable GT for training a deep network. Specifically, we simulate GT from high-resolution, hyperspectral FENIX images, and use it for training a convolutional neural network (CNN) for pixel-based classification. We show how the model can be transferred successfully to classify new mid-resolution VENuS imagery.