Efficient Implementation of Regional Mutual Information for the Registration of Road Images
| Autor: | Johann Lembach, Horst-Michael Gross, Ronny Stricker |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Similarity (geometry)
Computer science Process (computing) 02 engineering and technology Mutual information 010501 environmental sciences Similarity measure computer.software_genre 01 natural sciences Variable (computer science) Metric (mathematics) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data mining computer Change detection 0105 earth and related environmental sciences |
| Zdroj: | IPTA |
| Popis: | Motivated by recent advancements in the detection and classification of road distress, we aim to align road images from different years to facilitate automated change detection. We present a variable and efficient variant of the Regional Mutual Information (RMI) similarity metric to speed up the registration process while keeping the alignment robust and precise. We propose several modifications to the sampling process of RMI that allow an efficient implementation based on the resulting Hankel-type structures. We analyze the theoretical performance gains and the practical application of the proposed method in the road image domain. The achieved speed-ups significantly reduce the optimization duration while retaining the robust nature of RMI as a similarity measure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|