People often have difficulties finding specific information in video because of its linear and unstructured nature. Segmenting long videos into small clips by topics and providing browsing and search functionalities is beneficial for information searching. However, manual segmentation is labor intensive and existing automated segmentation methods are not effective for plenty of amateur made and unedited lecture videos. The objectives of this dissertation are to develop 1) automated segmentation algorithms to extract the topic structure of a lecture video, and 2) retrieval algorithms to identify the relevant video segments for user queries.Based on an extensive literature review, existing segmentation features and approaches are summarized and research challenges and questions are presented. Manual segmentation studies are conducted to understand the content structure of a lecture video and a set of potential segmentation features and methods are extracted to facilitate the design of automated segmentation approaches. Two static algorithms are developed to segment a lecture video into a list of topics. Features from multimodalities and various knowledge sources (e.g. electronic slides) are used in the segmentation algorithms. A dynamic segmentation method is also developed to retrieve relevant video segments of appropriate sizes based on the questions asked by users. A series of evaluation studies are conducted and results are presented to demonstrate the effectiveness and usefulness of the automated segmentation approaches.

This study set out to develop a framework within which the use of Geographical Information Technologies (GITs) can be enhanced in Road Infrastructure Maintenance (RIM) in Uganda. Specifically it was guided by 3 objectives; 1. To assess the gaps in the use of GITs for RIM in Uganda and the limitations to accessing these technologies, 2. To develop a methodological framework to enhance the use of GITs in RIM and 3. To develop a Geographical Information Systems for Transportation (GIS-T) data model based on the road maintenance data requirements. A participatory approach through a series of interviews, focus group discussions, workshop & conferences, document reviews, field observations & measurements and GIS analysis were employed. Based on the Spatial Data Infrastructure (SDI) concept and the principle of Causality, the gaps and limitations were established to mainly be concerned with data and organisational constraints as opposed to technical issues. They were classified to include; inadequate involvement of GITs in organisational activities, inappropriate institutional arrangements, absence of data sharing frameworks, budget constraints, insufficient geospatial capacity, digital divide in the perception, adoption & affordability of GITs among the stakeholders and the absence of a road maintenance Spatial Data Infrastructure (SDI). A methodological framework, comprising of 6 strategic components was developed to enhance the use of GITs in RIM. This included enactment of relevant policy components to guide GIT use, continuous capacity building, establishment of a road maintenance SDI, fostering collaboration and spatial data sharing frameworks, budgetary allocation based on defined activities inclusive of GIT initiatives, and adoption of a dynamic segmentation data model. Conceptual and logical data models were developed and proposed for the Sector. The conceptual model, presented using an entity relationship diagram, relates the road network to the point and line events occurring on it. The logical object relational model developed using the ESRI provided template represents the road and the point and line events in a total of 19 object classes. The Study concludes that in order to ground GIT benefits in the sector; technical, data and organisational concerns involved in GIT undertakings should be accorded equal emphasis. Institutionalisation and diffusion of GITs as aspects of the component strategies are regarded capacity building mechanisms earmarked to boost success in GIT initiatives. Further research on diffusion and funding models for GIT initiatives is recommended. It is suggested that aspects of the proposed model be considered when establishing GIT standards for the sector. The RIM sector is encouraged to embrace Science and Technology and to participate in Research and Development and particularly to adopt the culture of innovation considering the ready availability of off the shelf equipment, freeware and open source software that can foster informed decision making.