cuRCD: Region covariance descriptor CUDA implementation
| Autor: | M. Ali Asan, Adnan Ozsoy |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Speedup
Computer Networks and Communications Computer science Covariance matrix Computation 020207 software engineering 02 engineering and technology Covariance Image (mathematics) CUDA Hardware and Architecture Feature (computer vision) Robustness (computer science) Metric (mathematics) 0202 electrical engineering electronic engineering information engineering Media Technology Algorithm Software |
| Zdroj: | Multimedia Tools and Applications. 80:19737-19751 |
| ISSN: | 1573-7721 1380-7501 |
| DOI: | 10.1007/s11042-021-10644-2 |
| Popis: | Region covariance is a robust feature descriptor that allows the use of even the simplest image features like intensity and gradient combined to form a well-performing descriptor for regions on the image. Beyond its robustness, it requires many identical heavy computations on different parts of input data which makes it a good candidate for parallel execution. In this manuscript, we present a real-time parallel implementation of the region covariance which, to our best knowledge, is the first in the literature. We experimented against existing implementations and achieved 6 times faster execution time over vectorized CPU parallel implementation that provides necessary speed up for real-time processing. Additionally, we improved the existing integral image calculation method on CUDA, reducing memory usage by 50%, achieving the fastest computation speed compared to exist- ing solutions, and improved the covariance matrix comparison metric by using a distance metric that is lightweight to compute and easy to implement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink