1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	Pedro Emanuel Moura de Castro
Title:	MULTI-CAMERA SYNCHRONIZATION FOR OBJECT DETECTION IN MULTIPLE SCENES BY COMPUTER VISION
Issue Date:	2021-07-16
Description:	In distributed systems, the application of image analysis algorithms to detect connected events captured by different cameras highly depends on the synchronization of their video feeds. Although solutions have been developed to attain frame synchronization, none of them are applicable in scenarios where the cameras are either: 1) not capturing the same scene; 2) a synchronous capture trigger cannot be applied. Both of these characteristics are common in video surveillance where Structural Analysis or Re-ID are used to analyze captures from different scenes or even in image stitching where the views of different cameras are combined to form a panoramic view of the same scene. In this dissertation, a network based solution is proposed to synchronize multiple camera feeds by synchronizing the clocks of the devices through NTP, analyzing the packets sent and adjusting the video frames accordingly.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
DOI:	10.34626/9cfv-f267
TID identifier:	202824519
URI:	https://hdl.handle.net/10216/135762
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.