<p>Emerging mobile mapping systems include a wide range of platforms, for instance, manned aircraft, unmanned aerial vehicles (UAV), terrestrial systems like trucks, tractors, robots, and backpacks, that can carry multiple sensors including LiDAR scanners, cameras, and georeferencing units. Such systems can maneuver in the field to quickly collect high-resolution data, capturing detailed information over an area of interest. With the increased volume and distinct characteristics of the data collected, practical quality control procedures that assess the agreement within/among datasets acquired by various sensors/systems at different times are crucial for accurate, robust interpretation. Moreover, the ability to derive semantic information from acquired data is the key to leveraging the complementary information captured by mobile mapping systems for diverse applications. This dissertation addresses these challenges for different systems (airborne and terrestrial), environments (urban and rural), and applications (agriculture, archaeology, hydraulics/hydrology, and transportation).</p> <p>In this dissertation, quality control procedures that utilize features automatically identified and extracted from acquired data are developed to evaluate the relative accuracy between multiple datasets. The proposed procedures do not rely on manually deployed ground control points or targets and can handle challenging environments such as coastal areas or agricultural fields. Moreover, considering the varying characteristics of acquired data, this dissertation improves several data processing/analysis techniques essential for meeting the needs of various applications. An existing ground filtering algorithm is modified to deal with variation in point density; digital surface model (DSM) smoothing and seamline control techniques are proposed for improving the orthophoto quality in agricultural fields. Finally, this dissertation derives semantic information for diverse applications, including 1) shoreline retreat quantification, 2) automated row/alley detection for plant phenotyping, 3) enhancement of orthophoto quality for tassel/panicle detection, and 4) point cloud semantic segmentation for mapping transportation corridors. The proposed approaches are tested using multiple datasets from UAV and wheel-based mobile mapping systems. Experimental results verify that the proposed approaches can effectively assess the data quality and provide reliable interpretation. This dissertation highlights the potential of modern mobile mapping systems to map challenging environments for a variety of applications.</p>

Thesis (MSc)--Stellenbosch University, 2015. / ENGLISH ABSTRACT: Urban planning and management require up-to-date information about urban land cover. Producing such geospatial information is time consuming as it is usually done manually. The classification of such information from satellite imagery is challenging owing to the difficulties associated with distinguishing urban features having similar spectral properties. Therefore, this study evaluates the combination of a digital surface model (DSM) derived from LiDAR data and very high-resolution GeoEye-1 satellite imagery for classifying urban land cover in Cape Town. The value of the DSM was assessed by comparing a land cover product obtained from the GeoEye-1 image to a map produced using both the GeoEye-1 image and the DSM. A systematic segmentation procedure for the two classifications scenarios preceded a supervised (using a support vector machine, K nearest neighbour and classification and regression algorithm tree classifiers) and rule-based classification. The various approaches were evaluated using a combination of methods. When including the DSM in the supervised and rule-based classifications, the overall accuracy and kappa vary between 80% to 83% and 0.74 to 0.77 respectively. When the DSM is excluded, the overall accuracy ranges between 49 to 64% whereas kappa ranges between 0.32 to 0.53 for the two classification approaches. The accuracies obtained are always about 20% higher when the DSM is included. The normalised DSM (nDSM) enabled accurate discrimination of elevated (e.g. buildings) and non-elevated (e.g. paved surfaces) urban features having similar spectral characteristics. The nDSM of at least one-metre resolution and one metre vertical accuracy influenced the accuracy of the results by correctly differentiating elevated from non-elevated. The rule-based approach was more effective than the supervised classification, particularly for extracting water bodies (dams and swimming pools) and bridges. Consequently, a rule-based approach using very high spatial resolution (EHSR) satellite imagery and a LiDAR-derived DSM is recommended for mapping urban land cover. / AFRIKAANSE OPSOMMING: Stedelike beplanning- en bestuur vereis dat inligting oor grondbedekking (land cover) op datum moet wees. Die vervaardiging van hierdie georuimtelike inligting is tydrowend omdat dit gewoonlik met die hand gedoen word. Die onttrekking van sulke inligting vanuit satellietbeelde bied ʼn groot uitdaging omdat stedelike voorwerpe met soortgelyke spektrale eienskappe moeilik is om van mekaar te onderskei. Hierdie studie evalueer die kombinasie van ʼn digitale oppervlak model (DOM) afkomstig van LiDAR-data en ʼn baie hoë resolusie GeoEye-1-satellietbeeld om stedelike grondbedekking in Kaapstad te klassifiseer. Die waarde van die DOM word bepaal deur ʼn grondbesettingsproduk wat vanuit ʼn GeoEye-1-beeld verkry is te vergelyk met ʼn grondbesettingsproduk wat verkry is deur beide die GeoEye-1-beeld en die DOM te gebruik. Sistematiese segmentasie word op die twee benaderings uitgeoefen en dit word gevolg deur ʼn gekontroleerde klassifikasie (steunvektormasjiene, k-naaste aangrensende waarde en klassifikasie en regressie algoritme) en ʼn reël-gebaseerde algoritme. Hierdie verskeie benaderings is geëvalueer met behulp van ʼn kombinasie van kwalitatiewe en kwantitatiewe metodes. Toe die DOM in die gekontroleerde en reël-gebaseerde klassifikasie ingesluit is, het die algehele akkuraatheid en kappa tussen 80% en 83%, en 74% en 77% gewissel. Toe die DOM uitgesluit is, het die algehele akkuraatheid en kappa tussen 49% en 64%, en 32% en 53% vir die twee klassifikasiebenaderings gewissel. Die behaalde akkurraatheidswaardes is altyd 20% hoër as die DOM ingesluit word. Dit is hoofsaaklik omdat die DOM akkurate onderskeiding tussen hoë (bv. geboue) en plat (bv. geplaveide oppervlaktes) stedelike bakens met gelyksoortige spektrale eienskappe in staat stel. Die kwaliteit van die DOM beïnvloed die akkuraatheid van die resultate. ʼn DOM van ten minste een meter resolusie, met een meter of beter vertikale akkuraatheid, word benodig om te verseker dat geboue en ander beboude bakens korrek van mekaar onderskei kan word. Die reël-gebaseerde benadering was meer effektief as die gekontroleerde klassifikasie, veral om waterliggame (damme en swembaddens) en brûe te identifiseer. Gevolglik word ʼn reël-gebaseerde benadering met die hoë resolusie satellietbeelde en ʼn LiDAR-afgeleide DOM aanbeveel om stedelike grondbesetting te karteer.