Thesis etd-01142021-002610 |
Link copiato negli appunti
Thesis type
Tesi di laurea magistrale
Author
CITTADINI, EDOARDO
URN
etd-01142021-002610
Thesis title
Real time visual tracking of objects with variable appearance
Department
INGEGNERIA DELL'INFORMAZIONE
Course of study
EMBEDDED COMPUTING SYSTEMS
Supervisors
relatore Prof. Buttazzo, Giorgio C.
Keywords
- real
- time
- visual
- tracking
- objects
- variable
- appearance
- buttazzo
- cittadini
Graduation session start date
19/02/2021
Availability
None
Summary
Un'analisi dettagliata di vari approcci per il tracciamento di oggetti nei moderni sistemi embedded con target real time. Partendo dai filtri di correlazione si passa poi ad approcci più moderni basati su reti neurali e strategie di training più complesse e avanzate fino ad arrivare alle tecnologie dello stato dell'arte utilizzate nei veicoli a guida autonoma.
A detailed analysis of various approaches for object tracking in modern embedded systems with real time constraints. Starting from correlation filters, we then move on to more modern approaches based on neural networks and more complex and advanced training strategies up to state-of-the-art technologies used in self-driving and autonomous vehicles.
A detailed analysis of various approaches for object tracking in modern embedded systems with real time constraints. Starting from correlation filters, we then move on to more modern approaches based on neural networks and more complex and advanced training strategies up to state-of-the-art technologies used in self-driving and autonomous vehicles.
File
| Nome file | Dimensione |
|---|---|
There are some hidden files because of the review of the procedures of theses' publication. |
|