Praćenje gibajućih objekata pomoću filtra gustoće vjerojatnosti hipoteza

undergraduate thesis

• Title (english): Moving object tracking via probability hypotheses density filter
• Author: Marko Peroš
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Marković (član povjerenstva)
• Committee member: Borna Bićanić (član povjerenstva)
• Committee member: Luka Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Praćenje više gibajućih objekata odnosi na problem estimiranja broja objekata i njihovih stanja ili krivulja kretanja na osnovu mjerenja dobivenih od strane senzora. Jedna od poteškoća s kojima se praćenje objekata susreće je pridjeljivanje mjerenja odgovarajućim objektima. U ovom radu dan je kratak uvid u Kalmanov filtar koji je često prisutan u algoritmima praćenja više objekata te kratak pregled različitih pristupa problemu praćenja gibajućih objekata. Također opisano je rješenje za praćenje gibajućih objekata s linearnim dinamičkim sustavima pomoću filtra gustoće vjerojatnosti hipoteza Gaussovih mješavina koji predstavlja zatvoren oblik PHD rekurziji. Cilj ovog rada je i programska implementacija GMPHD filtra u Pythonu i testiranje istog na simulacijama.

Abstract (english)

Multiple object tracking refers to the problem of estimating the number of objects and their states or trajectories based on measurements obtained by sensors. One of the difficulties object tracking faces is assigning measurements to the appropriate objects. This thesis provides a brief insight into the Kalman filter, which is often present in multi-object tracking algorithms and a brief overview of different approaches to the problem of tracking moving objects. Also described is a solution for tracking moving objects with linear dynamical systems using a Gaussian mixture hypothesis probability density filter that represents a closed form of PHD recursion. The goal of this work is to implement the GMPHD filter in Python and test it on simulations.

• Keywords: Kalmanov filtar; Praćenje više objekata; Slučajni konačni skupovi; PHD Filtar; GMPHD Filtar
• Keywords (english): Kalman filter; Multiple object tracking; Random finite sets; PHD Filter; GMPHD Filter
• Language: croatian
• URN:NBN: urn:nbn:hr:168:003436
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-07-13 10:27:35