ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-06102020-135605


Tipo di tesi
Tesi di laurea magistrale
Autore
VILLELLA, MARCO FEDERICO
URN
etd-06102020-135605
Titolo
AI-based Alarm Generator in Video Survelliance Applications: Analysis and Algorithmic Design and Real-time Implementation in High-performance Embedded Platforms
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
INGEGNERIA ROBOTICA E DELL'AUTOMAZIONE
Relatori
relatore Prof. Saponara, Sergio
correlatore Dott. Gagliardi, Alessio
Parole chiave
  • video surveillance
  • real-time
  • embedded
  • cnn
  • raspberry
  • nvidia jetson
  • xilinx
  • fpga
  • deep learning
  • computer vision
  • object detection
  • alarm generator
  • neural networks
  • ai
Data inizio appello
16/07/2020
Consultabilità
Non consultabile
Data di rilascio
16/07/2090
Riassunto
The aim of this work is to design and develop a neural network for video surveiilance applications, in particular smoke and fire detections. In particular, two neural networks have been developed: the first one is a regressor which has the task of identifying in the image space the ROIs that contain the possible anomalies while the second one is a classifier that has the task of deciding whether the anomaly is true or not. In addition there is an alarm generator algorithm based on the persistence of the anomaly over time. This architecture was then successfully implemented on several embedded systems like Raspberry Pi 3 and 4, NVIDIA Jetson nano and AGX Xavier and Xilinx ZCU104. A performance analysis was performed on each platform and in general the algorithm was more robust and efficient than the current state of the art considering both neural networks based techniques and classical techniques.
File