L'interprétation automatique d'images de télédétection à très haute résolution spatiale est une tâche complexe mais nécessaire. Les méthodes basées objet sont couramment employées pour traiter ce type d'images. Elles consistent à construire les objets d'intérêt au moyen d'une étape de segmentation puis à les classifier en utilisant des méthodes de fouille de données. La majorité des travaux entrepris dans ce domaine considèrent la segmentation et la classification de manière indépendante. Or, ces deux étapes cruciales du processus sont fortement liées. Dans cette thèse, nous proposons deux approches différentes basées sur la qualité des données et des connaissances, pour initialiser, guider et évaluer un processus collaboratif de manière objective: 1. Une première approche basée sur une stratégie d'extraction mono-classe qui permet de se focaliser sur les propriétés particulières d'une classe donnée afin de mieux labelliser les objets de cette classe par rapport au reste. 2. Une deuxième approche multi-classe offrant deux stratégies différentes d'agrégation d'extracteurs mono-classes qui permet l'obtention d'une image entièrement labellisée de manière automatique. / Automatic interpretation of very high spatial resolution remotely sensed images is a complex but necessary task. Object-based image analysis approaches are commonly used to deal with this kind of images. They consist in applying an image segmentation algorithm in order to construct the abjects of interest, and then classifying them using data-mining methods. Most of the existing work in this domain consider the segmentation and the classification independently. However, these two crucial steps are closely related. ln this thesis, we propose two different approaches which are based on data and knowledge quality in order to initialize, guide, and evaluate a segmentation and classification collaborative process. 1. The first approach is based on a mono-class extraction strategy allowing us to focus on the particular properties of a given thematic class in order to accurately label the abjects of this class. 2. The second approach deals with multi-class extraction and offers two strategies to aggregate several mono-class extractors to get a final and completely labelled image.

The underlying philosophy of patient-centred care (PCC) advocates for patients to have an active role in all areas of their care, including broader areas of the health care system such as planning and evaluation. Despite efforts made in the past decade that would see greater patient engagement, conventional evaluation approaches continue to dominate the landscape in health services evaluation. To date, limited empirical research has examined the effects of patient engagement or the best approach to engage patients (Abelson et al., 2015; Baker, 2014; Baker, Judd, Fancott, & Maika, 2016). Furthermore, a relative lack of collaboration and shared knowledge exists between the evaluation community and health sector in the rapidly developing area of patient engagement and the development of best practices. Consequently, health organizations continue to struggle with how best to involve patients (i.e., process) in health service improvement initiatives, as well as learn from patient experience (Baker, 2014; Baker, Judd, et al., 2016; Luxford et al., 2011). This dissertation responded to some of these challenges and through this intervention study, the specific purpose of the thesis study was to gain a better understanding of the process of patient engagement in planning and evaluation by addressing the following research questions: 1. What are the facilitators and barriers of engaging patients in planning and evaluation of health services and why? 2. What did the process of engagement look like with respect to Cousins and Whitmore’s (1998) three dimensions of collaborative inquiry? 3. What are the observed effects of the engagement process? This longitudinal qualitative case study began with the creation of the Patient and Family Engagement Committee (PFEC) at the Ottawa Hospital Psychosocial Oncology Program (PSOP) and completed an evaluation project over a period of six months. The research study occurred in parallel with the evaluation project and was designed to gain a better understanding of the process of patient engagement and the role that evaluation plays in this context. The study consisted of three phases and data collection relied on multiple sources. Facilitators that influenced the patient engagement process include: accommodating participant needs, commitment, orientation meeting, designated lead with evaluation skills, homework between meetings, and mutual respect. Having a designated lead, mutual respect, and commitment to the project were the three most highly endorsed facilitators at the end of the project. Conversely, barriers identified include time and resources, imbalanced participation, change in health status, and living at a distance. Time and resources was endorsed as the most significant barrier to the patient engagement process across all three phases of the study. Motivations for participant involvement revolved around giving back, improving health services, learning, commitment to research/evaluation, and providing or hearing a unique perspective. The study examined participatory aspects of the focal evaluation using Cousins and Whitmore’s (1998) three fundamental dimensions of process in collaborative approaches to evaluation: stakeholder diversity, control of evaluation process, and depth of participation. Findings revealed that intended benefits of participant involvement included reach to decision-makers, improved health services, increased diffusion of patient/family engagement, improved access/awareness of services, and a follow-up to assess influence of engagement. Participants’ experiences of being involved invoked enthusiasm for the project, were personally rewarding, instilled a sense of optimism that the project would have an influence, closed the loop on healing, contributed to a shift from a personal to broader health care focus, and contributed to learning. Further research is needed to gain a better understanding of the processes involved or evaluation approaches that could contribute to translating patient engagement into improved outcomes. The findings of this study have enhanced understanding of key contributions that patients, family members, health professionals, and evaluators bring to the patient engagement process, and enriched understanding of key facilitators and barriers to ensure successful patient engagement.

It is still recognized as a challenge task while blind and visually impaired people travel outdoor independently, even if there are a number of assistive mobility aids available. In addition to building universal facilities in urban and rural environments for them, it is essential to develop novel mobility assistive technologies and systems to satisfy their increasing demands for mobility. To investigate those demands, an international survey with 106 blind and visually impaired people from 13 countries is undertaken within this work, with regarding to outdoor mobility experiences, usages of mobile devices and collaborative approaches. From the field of Human-Computer Interaction (HCI) and Accessibility, the dissertation focuses on enhancing blind people’s capabilities of acquisition of spatial environmental information from tactile displays. The spatial environmental information, in this study, is in terms of clusters of surrounding obstacles, geographic information on city maps, and information on environmental accessibility. In order to non-visual representation of the clusters of surroundings obstacles detected by a 3D Time-of-Flight (ToF) infrared camera, a portable pin-matrix display with a matrix of 30 x 32 pins is employed and a pre-designed set of tactile obstacle symbols is used to render the properties of obstacles (e.g., type, size). Additionally, aiming at helping blind people access geographic information, a desktop based pin-matrix display (an array of 60 x 120 pins) and a mobile pin-matrix display (an array of 30 x 32 pins) are used to represent a large-scale city map and a location-aware city map, respectively. A set of tactile map symbols rendered with the raised and lowered pins, has been designed for rendering various map features. To allow blind and visually impaired people to acquire information on environmental accessibility, besides a traditional web browser client and a popular smart phone client, an audio-haptic client on a tactile display with 7200 pins is developed. Users are able to create and share collaborative annotations on environmental accessibility across the 3 clients. The proposed approaches about non-visual representation of obstacles and map features by tactile symbols on pin-matrix displays, will contribute to the fields of accessible tactile graphic well, especially in the coming era of affordable pin-matrix displays. Meanwhile, the collaborative approach for improving environmental accessibility will encourage the society to raise the floor of accessibility for all. A number of further studies can be continued based on the current findings within this work, aiming at enhancing mobility aids for blind and visually impaired people gradually.

It is still recognized as a challenge task while blind and visually impaired people travel outdoor independently, even if there are a number of assistive mobility aids available. In addition to building universal facilities in urban and rural environments for them, it is essential to develop novel mobility assistive technologies and systems to satisfy their increasing demands for mobility. To investigate those demands, an international survey with 106 blind and visually impaired people from 13 countries is undertaken within this work, with regarding to outdoor mobility experiences, usages of mobile devices and collaborative approaches. From the field of Human-Computer Interaction (HCI) and Accessibility, the dissertation focuses on enhancing blind people’s capabilities of acquisition of spatial environmental information from tactile displays. The spatial environmental information, in this study, is in terms of clusters of surrounding obstacles, geographic information on city maps, and information on environmental accessibility. In order to non-visual representation of the clusters of surroundings obstacles detected by a 3D Time-of-Flight (ToF) infrared camera, a portable pin-matrix display with a matrix of 30 x 32 pins is employed and a pre-designed set of tactile obstacle symbols is used to render the properties of obstacles (e.g., type, size). Additionally, aiming at helping blind people access geographic information, a desktop based pin-matrix display (an array of 60 x 120 pins) and a mobile pin-matrix display (an array of 30 x 32 pins) are used to represent a large-scale city map and a location-aware city map, respectively. A set of tactile map symbols rendered with the raised and lowered pins, has been designed for rendering various map features. To allow blind and visually impaired people to acquire information on environmental accessibility, besides a traditional web browser client and a popular smart phone client, an audio-haptic client on a tactile display with 7200 pins is developed. Users are able to create and share collaborative annotations on environmental accessibility across the 3 clients. The proposed approaches about non-visual representation of obstacles and map features by tactile symbols on pin-matrix displays, will contribute to the fields of accessible tactile graphic well, especially in the coming era of affordable pin-matrix displays. Meanwhile, the collaborative approach for improving environmental accessibility will encourage the society to raise the floor of accessibility for all. A number of further studies can be continued based on the current findings within this work, aiming at enhancing mobility aids for blind and visually impaired people gradually.

No description available.