多維度集合經驗模態拆解 (MEEMD) 常用於拆解影像,但其時間複雜度較高,在這裡介紹一個新方法:「空間頻率擷取使用類梯度運算子」,將運算時間減少十倍以上,且很適合平行化運算,在GPGPU版本中,將近有500 倍的效能提升!我們的新穎方法使用類梯度運算子評估不同半徑下的空間頻率,並且將梯度運算的結果積分到空間幀,其結果很類似於MEEMD 的成果。
The multi-dimensional ensemble empirical mode decomposition (MEEMD) is usually used for temporal-spatial data decomposition. One of the major issue is its high time complexity. A new gradient-liked approach to mimic similar spatial data decomposition results with more than 10x speedup. The GPGPU version of our approach can reach 500x speedup. Our novel approach use gradient-liked operator to evaluate the spatial frequency on different radius and integral the gradient result to spatial frame which is similar to BIMFs of MEEMD.