A software defined radio based radar system with applications in the detection of wildlife poaching

Simple item page
dc.contributor.advisorNiesler, Thomasen_ZA
dc.contributor.authorVan Zyl, Christiaanen_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Electrical and Electronic Engineering.en_ZA
dc.date.accessioned2023-11-20T09:25:58Zen_ZA
dc.date.accessioned2024-01-08T19:05:38Zen_ZA
dc.date.available2023-11-20T09:25:58Zen_ZA
dc.date.available2024-01-08T19:05:38Zen_ZA
dc.date.issued2023-12en_ZA
dc.descriptionThesis (MEng)--Stellenbosch University, 2023.en_ZA
dc.description.abstractENGLISH ABSTRACT: This thesis presents the development and testing of a low-cost and low-power software-defined r adio ( SDR) b ased r adar p latform f or u se i n anti-poaching applications. A low frequency of 1.1 GHz is specifically selected to investigate the viability of classifying human activity, whilst enabling foliage penetration. A software interface and control tool for the SDR was developed to enable the rapid development and testing of radar techniques, and the collecting and storing of data in the form of I/Q samples. A signal processing pipeline was implemented using the Julia programming language to generate range-Doppler maps from these I/Q samples. Existing non-linear frequency modulated pulse compression waveforms did not yield satisfactory performance due to the low time-bandwidth product regime in which the radar system operates. A pulse compression waveform based on optimised Bézier curves was therefore developed and shown to offer improved performance over existing methods that require a higher time bandwidth product. The best Bézier vertices were determined by a particle swarm optimisation method, which is also presented. A dataset was collected to evaluate the system’s ability to classify targets based on micro-Doppler frequencies. A novel convolutional neural network configuration t hat u ses t emporal D oppler f rames i s p resented a nd s hown to achieve a classification accuracy of 91.6% when testing on a dataset containing a single person. Therefore, it may be concluded that SDR-based radar merits further consideration as a low-cost and low-power approach to the detection of poachers in automated anti-poaching systems.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Hierdie tesis bied die ontwikkeling en toetsing van ’n lae koste en lae kragverbruik sagteware-gedefinieerde r adio ( SGR) g ebaseerde r adarplatform a an vir gebruik in anti-stropery toepassings. ’n Lae frekwensie van 1.1 GHz is spesifiek gekies om die lewensvatbaarheid van die klassifisering van menslike aktiwiteite te ondersoek en terselfdetyd penetrasie deur plantegroei te fasiliteer. ’n Sagteware koppelvlak- en beheerinstrument vir die SGR is ontwikkel om die vinnige ontwikkeling en toetsing van radartegnieke moontlik te maak, sowel as die versameling van data in die vorm van I/Q-monsters. ’n Seinverwerkingstelsel is geïmplementeer met behulp van die Julia-programmeringstaal om afstand-Doppler-beelde uit die I/Q-monsters te genereer. Bestaande nie-lineˆere frekwensie-gemoduleerde pulskompressie-golfvorms het nie bevredigende prestasie gelewer nie as gevolg van die lae tyd-bandwydte produk waarin die radarstelsel werk. ’n Pulskompressie-golfvorm gebaseer op geoptimeerde Bézier krommes was ontwikkel en geïllustreer om verbeterde prestasie te bied in vergelyking met bestaande metodes wat ’n hoër tydbandwydte produk vereis. Die beste Bézier hoekpunte was gevind deur ’n partikelswerm-optimeringsmetode te gebruik en word voorgestel. ’n Datastel is ingesamel om die vermoë van die stelsel om teikens te klassifiseer o p g rond van mikro-Doppler-frekwensies t e e valueer. ’ n Nuwe konvolutiewe neurale-netwerk-konfigurasie, w at t yddomain D oppler-rame gebruik, word voorgestel en geïllustreer om ’n klassifikasie a kkuraatheid van 9 1.6% te behaal tydens toetsing op ’n datastel wat ’n enkele persoon bevat.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxxiv, 158 pages : illustrationsen_ZA
dc.identifier.urihttps://scholar.sun.ac.za/handle/10019.1/129009
dc.language.isoen_ZAen_ZA
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subject.lcshSoftware radioen_ZA
dc.subject.lcshRadar -- Automatic detectionen_ZA
dc.subject.lcshSignal processing -- Digital techniquesen_ZA
dc.subject.lcshDoppler trackingen_ZA
dc.titleA software defined radio based radar system with applications in the detection of wildlife poachingen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
vanzyl_software_2023.pdf
Size:
32.35 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Graduation - 2023 - December (Open Access)