[IP3-11-3] Dynamic Time Warping

Dynamic Time Warping (DTW) works by comparing the similarity between two temporal sequences and finds their optimal alignment, resulting in a dissimilarity measure. In the case of remote sensing data, DTW can deal with temporal distortions, and can compare shifted evolution profiles and irregular sampling thanks to its ability to align radiometric profiles in an optimal manner

External resources

• Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE transactions on acoustics, speech, and signal processing, 26, 43-49

Learning outcomes

• 1188 - Understand the way in which Dynamic Time Warping can align shifted temporal sequences

  Understand the way in which Dynamic Time Warping can align shifted temporal sequences

Self assessment

Outgoing relations

• [IP3-11-3] Dynamic Time Warping subclassof [IP3-11] Time series analysis

Contributors

• Florian Albrecht
  https://www.researchgate.net/profile/Florian_Albrecht
• Mariana Belgiu
  https://research.utwente.nl/en/persons/mariana-belgiu
• Stefan Lang
  https://www.uni-salzburg.at/index.php?id=32483&L=1