A hardware accelerator for ORB-SLAM
Simultaneous Localization And Mapping (SLAM) is a key component of self-driving cars. We study ORB-SLAM, a SLAM state-of-the-art solution, and develop a hardware accelerator for a critical part of it: ORB feature extraction. The accelerator achieve 8x speedup and 2000x energy consumption reduction.
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/176803 |
| Acceso en línea: | https://hdl.handle.net/2117/176803 |
| Access Level: | acceso abierto |
| Palabra clave: | Computer architecture Software engineering orb slam orb-slam accelerador hardware hardware accelerator Arquitectura d'ordinadors Enginyeria de programari Àrees temàtiques de la UPC::Informàtica |
| Sumario: | Simultaneous Localization And Mapping (SLAM) is a key component of self-driving cars. We study ORB-SLAM, a SLAM state-of-the-art solution, and develop a hardware accelerator for a critical part of it: ORB feature extraction. The accelerator achieve 8x speedup and 2000x energy consumption reduction. |
|---|