Detekcija pokretnih objekata u inteligentnim videonadzornim sustavima

master's thesis

• Title (english): Detection of moving objects in intelligent video surveillance systems
• Author: Ivana Grgić
• Mentor: Sonja Grgić (mentor)
• Committee member: Sonja Grgić (predsjednik povjerenstva)
• Committee member: Tomislav Kos (član povjerenstva)
• Committee member: Emil Dumić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Ovaj rad bavi se problematikom detekcije pokretnih objekata u inteligentnim videonadzornim sustavima. Obrađena je arhitektura mrežnog videonadzornog sustava te su objašnjene značajke koje takav sustav čine inteligentnim. Navedeni su postupci kompresije koji se primjenjuju u inteligentnim videonadzornim sustavima te su razmotrena njihova obilježja. Dan je pregled i opis postupaka za detekciju pokretnih objekata u videosekvencama snimljenim u inteligentnim videonadzornim sustavima. U programskom paketu MATLAB implementiran je model detekcije kretanja na temelju razlike uzastopnih slika koji omogućava kontinuirano praćenje promjena u slici na temelju postavljenog praga detekcije te su na primjeru snimke jedne mrežne videonadzorne kamere razmotreni rezultati simulacije implementiranog modela.

Abstract (english)

This thesis deals with the problem of moving object detection in intelligent video surveillance systems. Network video surveillance system architecture is reviewed and features that make this system intelligent are explained. Compression formats used in intelligent video surveillance systems are listed and their characteristics are described. Methods for detection of moving objects in a video recorded in an intelligent video surveillance system are explored. A motion detection model based on the difference between current and previous image and set threshold is implemented in computing environment MATLAB. Analysis of the model is conducted using a recording of one network video surveillance camera.

• Keywords: mrežna kamera; videokoder; IP mreža; server; memorija; programska podrška za upravljanje videom; videointeligencija; videokompresija; MJPEG; MPEG-4; H.264; oduzimanje pozadine; razlika uzastopnih slika; optički tok; prag detekcije
• Keywords (english): network camera; video encoder; IP network; server; storage; video management software; video intelligence; video compression; MJPEG; MPEG-4; H.264; background subtraction; frame difference; optical flow; detection threshold
• Language: croatian
• URN:NBN: urn:nbn:hr:168:797962
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 09:01:46