A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is proposed. Rotational-invariant neighborhood-based textural representations are extracted and used to learn a set of representative texture atoms for defining a sparse texture model for the image. Based on the learnt sparse texture model, a weighted graphical model is constructed to characterize the statistical textural distinctiveness between all representative texture atom pairs. Finally, the saliency of each pixel in the image is computed based on the probability of occurrence of the representative texture atoms, their respective statistical textural distinctiveness based on the constructed graphical model, and general visual attentive constraints. Experimental results using a public natural image dataset and a variety of performance evaluation metrics show that the proposed approach provides interesting and promising results when compared to existing saliency detection methods.

Extensive research in the field of monocular SLAM for the past fifteen years has yielded workable systems that found their way into various applications in robotics and augmented reality. Although filter-based monocular SLAM systems were common at some time, the more efficient keyframe-based solutions are becoming the de facto methodology for building a monocular SLAM system. The objective of this paper is threefold: first, the paper serves as a guideline for people seeking to design their own monocular SLAM according to specific environmental constraints. Second, it presents a survey that covers the various keyframebased monocular SLAM systems in the literature, detailing the components of their implementation, and critically assessing the specific strategies made in each proposed solution. Third, the paper provides insight into the direction of future research in this field, to address the major limitations still facing monocular SLAM; namely, in the issues of illumination changes, initialization, highly dynamic motion, poorly textured scenes, repetitive textures, map maintenance, and failure recovery.

No abstract

A prototype of a device that relays navigational information to a person who is visually impaired using a portable tactile glove and a wearable computer and camera system was demonstrated and tested. The results of preliminary tests using the glove as a navigational device show that the paths traversed by subjects negotiating an obstacle course using the glove were not qualitatively different from the paths produced with existing wayfinding devices and that hitting probabilities, the measure of the likelihood of hitting an obstacle, are minimized from goal-directed random walks.

Video surveillance systems are playing an increasing role in preventing and investigating crime, protecting public safety, and safeguarding national security. In a typical surveillance installation, a human operator has to constantly monitor a large array of video feeds for suspicious behaviour. As the number of cameras increases, information overload makes manual surveillance increasingly difficult, adding to other confounding factors like human fatigue and boredom.The objective of an intelligent vision-based surveillance system is to automate the monitoring and event detection components of surveillance, alerting the operator only when unusual behaviour or other events of interest are detected. While most traditional methods for trajectory-based unusual behaviour detection rely on low-level trajectory features, this thesis improves a recently introduced approach that makes use of higher-level features of intentionality. Individuals in a scene are modelled as intentional agents instead of simply objects. Unusual behaviour detection then becomes a task of determining whether an agent's trajectory is explicable in terms of learned spatial goals. The proposed method extends the original goal-based approach in three ways: first, the spatial scene structure is learned in a training phase; second, a region transition model is learned to describe normal movement patterns between spatial regions; and third, classification of trajectories in progress is performed in a probabilistic framework using particle filtering. Experimental validation on three published third-party datasets demonstrates the validity of the proposed approach.iii