Neizrazita klasifikacija djelomično preklapajućih objekata u vidnom polju kamere

scientific master's theses

• Title (english): Fuzzy classification of partially occluded objects in the camera’s field of vision
• Author: Darko Homar
• Mentor: Slobodan Ribarić (mentor)
• Committee member: Slobodan Ribarić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronics, Microelectronics, Computer and Intelligent Systems); Zagreb
• Defense date and country: 2003, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering
• Universal decimal classification (UDC): 621.3 - Electrical engineering

Abstract

U radu je predstavljen sustav za raspoznavanje dvodimenzionalnih objekata koji se dodiruju ili prekrivaju. Polazišna osnova sustava je postupak koji podudaranjem linijskih segmenata modela i scene pokušava utvrditi prisutnost i položaj modela u sceni. Nakon što su tim postupkom dobiveni modeli kandidati, promatra se podudaranje njihovih površina sa površinom scene. Rezultati prvog i drugog dijela postupka povezuju se u konačno rješenje korištenjem propozicija neizrazite logike. Sustav je realiziran u objektno orijentiranom programskom jeziku Java i testiran na brojnim primjerima. Rezultati pokazuju da upotreba neizrazite logike i podudaranja površina povećava sigurnost u ispravnost hipoteza, a u slučaju pogrešnih hipoteza, pomaže u postupku njihovog odbacivanja.

Abstract (english)

This paper presents a recognition system for classification of partially occluded two-dimensional objects. The basis of this system is the line segment matching method which tries to establish the existence and position of a given model in the scene. The results of line segment matching are model candidates. Areas of model candidates are matched with the scene. The results of line segment matching and area matching are brought together in the final solution by the use of propositions of fuzzy logic. The system is written in object oriented programming language Java and tested on a number of examples. Results show that the use of fuzzy logic and area matching increases the belief in the trueness of the hypotheses and in the case of an incorrect hypothesis, it helps in the process of its rejection.

• Keywords: Raspoznavanje djelomično prekrivajućih dvodimenzionalnih objekata; podudaranje linijskih segmenata; neizrazita logika
• Keywords (english): Recognition of partially occluded two-dimensional objects; line segment matching; fuzzy logic
• Language: croatian
• URN:NBN: urn:nbn:hr:168:785071
• Study programme: Title: Postgraduate master programme in electrical engineering; Study programme type: university; Study level: postgraduate; Academic / professional title: Magistar znanosti elektrotehnike (Magistar znanosti elektrotehnike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-05-02 10:16:03