https://www.um.edu.mt/library/oar/handle/123456789/2068 Tue, 15 Sep 2026 13:54:02 GMT 2026-09-15T13:54:02Z https://www.um.edu.mt/library/oar/handle/123456789/149091 Title: Iterative hybrid discrete-continuous viewpoint planning for UAV photogrammetry Authors: Grech, Alan; Pisani, Daniel; Grima, Andre; Debono, Carl James; Formosa, Saviour; Seychell, Dylan Abstract: Unmanned aerial vehicle (UAV) photogrammetry requires camera networks that provide sufficient surface coverage, image overlap, parallax, and resolution, yet conventional flight patterns are often poorly adapted to scene geometry, resulting in local reconstruction errors. This paper proposes an iterative hybrid discrete-continuous viewpoint planning method for targeted UAV photogrammetry from a proxy reconstruction. The method scores sampled surface points using photogrammetric heuristics based on frontality, imaging distance, parallax, and multi-view observation count, while also evaluating the full viewpoint set in terms of visibility, pairwise overlap, and graph connectivity. Candidate viewpoints are generated around weakly observed regions, refined using clustered Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimisation, and removed when redundant. The final flight path combines close-range detail viewpoints with wider model-coverage viewpoints, balancing local reconstruction quality with global image-network robustness. Evaluation on three synthetic scenes shows that the proposed method improves both reconstruction accuracy and completeness compared with prior UAV path-planning methods. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149091 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/149083 Title: Enhancing object detection with privileged information : a model-agnostic teacher-student approach Authors: Bartolo, Matthias; Seychell, Dylan; Hili, Gabriel; Montebello, Matthew; Debono, Carl James; Formosa, Saviour; Makantasis, Konstantinos Abstract: This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149083 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/149047 Title: Adult learners' perception on whether educational technology can augment, limit or replace the human element Authors: Camilleri, Christian; Camilleri, Rebecca Abstract: This research aims to study whether educational technology is enhancing or limiting the human element. A quantitative survey, in the form of a self-administered questionnaire, was conducted amongst 134 adult learners following Level 6 part-time courses offered at MCAST, aged ≥21 & ≤ 56 years. The first part of the questionnaire consisted of a descriptive analysis whilst in the second part, linear multiple regression analysis was performed to assess the students overall learning experience (dependent variable) vis-à-vis different teaching scenarios consisting of different levels of technological usage. Primarily, it resulted that all the participants (n=134) are connected to the world of digital information via their smartphones and other telecommunication devices. Moreover, the vast majority (40%) of the students spend more than four hours a day on the web. Nonetheless, the results indicate that the participants strongly rejected the idea of minimizing or replacing the role of the educator. In the second part of the questionnaire, blended learning (mixed mode) emerged as the strongest predictor. Lastly, none of the students (p >0.05) opted for the traditional face-to-face lecturing without use of technological tools thereby indicating that the mode of teaching has become obsolete. Fri, 01 Jan 2021 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149047 2021-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/149046 Title: Automated generation of multi-tenant database systems based upon system design diagrams Authors: Camilleri, Rebecca; Vella, Joseph G. Abstract: Energetic technological advancements in the past decade have led to an exponential increase in the amount of data being stored. Consequently, the need for effective Database Management Systems (DBMSs) which embody security considerations from the initial stages of database design is imperative in modern information systems development. This prerequisite is further accentuated by the recent transitioning from single tenant information systems to multi-tenant based on public cloud infrastructures. Within this context, this paper proposes a Computer-Aided Software Engineering (CASE) tool capable of generating secure database related structures and processes. A comprehensive overview of a specific information system design is provided to the CASE tool by means of entity-relationship diagram, entity life history and dataflow diagram. Subsequently, crucial security controls targeted towards the protection of database objects are incorporated by means of discretionary and role-based access controls. Following the encoding of the system's design data is adorned with the required security elements, the CASE tool performs an in-depth analysis that aids in the detection of potential security pitfalls. Provided that the database design enhanced with security elements is satisfactory, i.e., all checks conducted are successful, the CASE tool generates Structured Query Language (SQL) language constructs for well-known multi-tenant scenarios. Sun, 01 Jan 2023 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149046 2023-01-01T00:00:00Z