University of Surrey

About: University of Surrey is a education organization based out in Guildford, Surrey, United Kingdom. It is known for research contribution in the topics: Population & Context (language use). The organization has 17976 authors who have published 44951 publications receiving 1249993 citations. The organization is also known as: Battersea Polytechnic Institute & Battersea College of Technology.

Robust wide baseline stereo from maximally stable extremal regions

Abstract: The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints is studied. A new set of image elements that are put into correspondence, the so called extremal regions , is introduced. Extremal regions possess highly desirable properties: the set is closed under (1) continuous (and thus projective) transformation of image coordinates and (2) monotonic transformation of image intensities. An efficient (near linear complexity) and practically fast detection algorithm (near frame rate) is presented for an affinely invariant stable subset of extremal regions, the maximally stable extremal regions (MSER). A new robust similarity measure for establishing tentative correspondences is proposed. The robustness ensures that invariants from multiple measurement regions (regions obtained by invariant constructions from extremal regions), some that are significantly larger (and hence discriminative) than the MSERs, may be used to establish tentative correspondences. The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes. Significant change of scale (3.5×), illumination conditions, out-of-plane rotation, occlusion, locally anisotropic scale change and 3D translation of the viewpoint are all present in the test problems. Good estimates of epipolar geometry (average distance from corresponding points to the epipolar line below 0.09 of the inter-pixel distance) are obtained.

User acceptance of hedonic information systems

Abstract: This paper studies the differences in user acceptance models for productivity-oriented (or utilitarian) and pleasure-oriented (or hedonic) information systems. Hedonic information systems aim to provide self-fulfilling rather than instrumental value to the user, are strongly connected to home and leisure activities, focus on the fun-aspect of using information systems, and encourage prolonged rather than productive use. The paper reports a cross-sectional survey on the usage intentions for one hedonic information system. Analysis of this sample supports the hypotheses that perceived enjoyment and perceived ease of use are stronger determinants of intentions to use than perceived usefulness. The paper concludes that the hedonic nature of an information system is an important boundary condition to the validity of the technology acceptance model. Specifically, perceived usefulness loses its dominant predictive value in favor of ease of use and enjoyment.

Tracking-Learning-Detection

Abstract: This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object's location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector's errors and updates it to avoid these errors in the future. We study how to identify the detector's errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: (1) P-expert estimates missed detections, and (2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches.