Accurate and efficient localization of facial features is a crucial first step in many face-related computer vision tasks. Some of these tasks include, but not limited to: identity recognition, expression recognition, and head-pose estimation. Most effort in the field has been exerted towards developing better ways of modeling prior appearance knowledge and image observations. Modeling prior shape knowledge, on the other hand, has not been explored as much. In this dissertation I primarily focus on the limitations of the existing methods in terms of modeling the prior shape knowledge. I first introduce a new pose-constrained shape model. I describe my shape model as being "highly flexible yet sufficiently strict". Existing pose-constrained shape models are either too strict, and have questionable generalization power, or they are too loose, and have questionable localization accuracies. My model tries to find a good middle-ground by learning which shape constraints are more "informative" and should be kept, and which ones are not-so-important and may be omitted. I build my pose-constrained facial feature localization approach on this new shape model using a probabilistic graphical model framework. Within this framework, observed and unobserved variables are defined as the local image observations, and the feature locations, respectively. Feature localization, or "probabilistic inference", is then achieved by nonparametric belief propagation. I show that this approach outperforms other popular pose-constrained methods through qualitative and quantitative experiments. Next, I expand my pose-constrained localization approach to unconstrained setting using a multi-model strategy. While doing so, once again I identify and address the two key limitations of existing multi-model methods: 1) semantically and manually defining the models or "guiding" their generation, and 2) not having efficient and effective model selection strategies. First, I introduce an approach based on unsupervised clustering where the models are automatically learned from training data. Then, I complement this approach with an efficient and effective model selection strategy, which is based on a multi-class naive Bayesian classifier. This way, my method can have many more models, each with a higher level of expressive power, and consequently, provides a more effective partitioning of the face image space. This approach is validated through extensive experiments and comparisons with state-of-the-art methods on state-of-the-art datasets. In the last part of this dissertation I discuss a particular application of the previously introduced techniques; facial feature localization in unconstrained videos. I improve the frame-by-frame localization results, by estimating the actual head-movement from a sequence of noisy head-pose estimates, and then using this information for detecting and fixing the localization failures. / text

As the mission field for autonomous vehicles expands into a larger variety of territories, the development of autonomous surface vehicles (ASVs) becomes increasingly important. ASVs have the potential to travel for long periods of time in areas that cannot be reached by aerial, ground, or underwater autonomous vehicles. ASVs are useful for a variety of missions, including bathymetric mapping, communication with other autonomous vehicles, military reconnaissance and surveillance, and environmental data collecting. Critical to an ASV's ability to maneuver without human intervention is its ability to detect obstacles, including the shoreline. Prior topological knowledge of the environment is not always available or, in dynamic environments, reliable. While many existing obstacle detection systems can only detect 3D obstacles at close range via a laser or radar signal, vision systems have the potential to detect obstacles both near and far, including "flat" obstacles such as the shoreline. The challenge lies in processing the images acquired by the vision system and extracting useful information. While this thesis does not address the issue of processing the images to locate the pixel positions of the obstacles, we assume that we have these processed images available. We present an algorithm that takes these processed images and, by incorporating the kinematic model of the ASV, maps the pixel locations of the obstacles into a global coordinate system. An Extended Kalman Filter is used to localize the ASV and the surrounding obstacles. / Master of Science