Sustav za otkrivanje ukopanih mina

doctoral thesis

• Author: Davor Antonić
• Mentor: Mario Žagar (mentor)
• Committee member: Nikola Bogunović (član povjerenstva)
• Committee member: Mario Žagar (član povjerenstva)
• Committee member: Milan Bajić (član povjerenstva)
• Committee member: Gabro Smiljanić (član povjerenstva)
• Committee member: Ljubo Marangunić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Control and Computer Engineering); Zagreb
• Defense date and country: 2001-10-19, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Process Computing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing ; 623 - Military engineering

Abstract

U ovoj disertaciji opisan je razvoj i implementacija postupaka obrade signala, izdvajanja značajki i klasifikacije te njihovo povezivanje u cjelovit sustav prilagođen potrebama otkrivanja ukopanih mina. Razvijen je postupak automatskog generiranja i redukcije skupa značajki iz spektara signala kao i novi postupci izdvajanja značajki temeljeni na heurističkom pretraživanju stabla i genetskim algoritmima, primjenjivi na široku klasu problema. Svi predloženi postupci provjereni su na stvarnim minama i ostalim objektima. Primjena na skup uzoraka snimljenih sonarom rezultirala je značajnim smanjenjem složenosti klasifikacijskog sustava. Postupci su također ispitani na skupu uzoraka mina i ostalih objekata dobivenih detektorom temeljenim na standardnoj pirotehničarskoj pipalici koji bilježi vibracije nastale dodirom ukopanog predmeta, razvijenog u sklopu ove disertacije. Ispitivanje je pokazalo da predloženi sustav detektora i pripadnog skupa postupaka omogućuje razlikovanje mine od ostalih ukopanih predmeta. Definirana je i odgovarajuća informacijska podrška koja omogućuje prihvat informacija stvorenih na razini detekcije pojedinih mina, uključivanje tih informacija u informacijski sustav humanitarnog razminiranja i ostvarivanje povratne veze koja će omogućiti učenje i kontinuirano poboljšavanje svojstava sustava detekcije. U okviru definiranog sustava također su predloženi postupci praćenja položaja detektora smještenog na daljinski upravljanoj ili autonomnoj robotskoj platformi.

Abstract (english)

This thesis describes development and implementation of algorithms for signal processing, feature extraction and classification, as well as their integration into the system for buried landmine detection. Procedure for automatic generation and reduction of the initial feature set directly from signal spectrums has been developed. Novel feature extraction algorithms based on heuristic tree search and genetic algorithms, which are applicable to the wide range of problems have been proposed. All the algorithms were tested on real mines and other objects. Application to the set of sonar samples resulted in significant reduction of classification system complexity. Algorithms were also tested on mines and other objects samples. Samples were acquired by developed detector, based on standard deminer's prodder which records vibrations produced by touching the buried object. Testing shows that proposed detection system and dedicated set of procedures make mines distinguishable from other buried objects. Appropriate information support has been defined, which makes possible managing information created at the level of individual mines detection. It allows incorporation of the information into the humanitarian demining information system and establishment of feedback which will make possible learning and continuous improvement of detection system features. Methods for position tracking of the detector attached to the remotely controlled or autonomous robotic platform are also described.

• Keywords: Digitalna obrada signala; izdvajanje značajki; heurističko pretraživanje stabla; genetski algoritmi; raspoznavanje uzoraka; neuronske mreže; informacijski sustavi; mobilni roboti; razminiranje
• Keywords (english): Digital signal processing; feature extraction; heuristic tree search; genetic algorithms; pattern recognition; neural networks; information systems; mobile robots; demining
• Language: croatian
• URN:NBN: urn:nbn:hr:168:422954
• Study programme: Title: Computer Science; Study programme type: university; Study level: postgraduate; Academic / professional title: Doktor znanosti (Doktor znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-04-23 07:14:24