A Distributed and Parallel Method for Fusion of Remote Sensing Images Based on Tucker Decomposition

Tensor decomposition based fusion methods for hyperspectral and multi-spectral images have recently demonstrated decent fusion performance in the context of remote sensing applications. Considering the huge volume of today’s remote sensing datasets and the involved heavy computation loads, traditional single-machine fusion methods can no longer serve the purpose due to limited storage, communication, and computation capacities. To this end, we propose a distributed and parallel method for Tucker decomposition model based on Apache Spark. Our primary focus is to (i) enhance the generation and update methods for modal matrices to eliminate the bottleneck of insufficient memory; (ii) redesign the initialization and updating procedures of core tensors to adapt to distributed computing and enhance computational efficiency; and (iii) implement group updates to accelerate the overall fusion flow while maintaining fusion accuracy. Experimental results demonstrate that our distributed and parallel fusion method achieves significant speedups over the original model with decent fusion performance.