We described a video-rate surveillance algorithm to detect and track people from a stationary camera, and to determine if they are carrying objects or moving unencumbered. The contribution of the paper is the shape analysis algorithm that both determines if a person is carrying an object and segments the object from the person so that it can be tracked, e.g., during an exchange of objects betwe...

This paper pursues the idea of understanding shapes of unknown objects through establishing correspondence with points from the surface of known objects. A lot of geometryrelated knowledge, such as functionally correct grasps or object constellations, could thus be transferred from known shapes to novel shapes of the same or a similar category. As one critical module in such a system, this pape...

The fixed mean shape that is built from the statistical shape model produces an erroneous feature extraction result when ASM is applied to multipose faces. To remedy this problem the mean shape vector which is similar to an input face image is needed. In this paper, we propose the adaptive mean shape to extract facial features accurately for non frontal face. It indicates the mean shape vector ...

A character recognition scheme based on structural analysis is presented to deal withunconstrained hand-written characters and degraded samples of multi-font machine-printed characters. It is based on building simplified easy-to-construct shape modelsrepresenting character classes. The scheme is based on employing a general variation anddegradation model to match character sampl...

The Fourier Descriptor (FD) is a powerful tool for shape analysis and many signatures have been proposed to derive Fourier descriptors. These shape signatures lack of important information in articulation and part structures of complex shapes. In this study, the Inner-Centroid Distance (ICDs) signature which is based on the Centroid Distance signature and Inner-Distance is developed to overcome...

The paper describes a method for identification of mechanisms and process trends based on combination of subject-driven document clustering, shape analysis, trends understanding and relevant context retrieval via semantic analysis. The goal is to extract potentially interesting knowledge from a set of technical information based on analysis of graphical information in order to find explanation ...

Shape grammars are, in general, intractable. Even amongst tractable shape grammars, their characteristics vary significantly. This paper describes a paradigm for practical general shape grammar interpreters, which aim to address computational difficulties posed by parameterization. The paradigm is expressed in terms of frameworks each comprising an underlying data structure, manipulation algori...

We present a shape analysis for programs that manipulate overlaid data structures which share sets of objects. The abstract domain contains Separation Logic formulas that (1) combine a per-object separating conjunction with a per-field separating conjunction and (2) constrain a set of variables interpreted as sets of objects. The definition of the abstract domain operators is based on a notion ...

We consider the problem of learning an object model for feature matching. The matching system is Bayesian in nature with separate likelihood and prior parts. The likelihood is based on Gabor filter responses, which are modelled as probability distributions in the filter response vector space. The prior model for the object shape is learnt in two stages: in the first stage we assume only the mea...

Figure 1: We present a view-based convolutional network that produces local, point-based shape descriptors. The network is trained such that geometrically and semantically similar points across different 3D shapes are embedded close to each other in descriptor space (left). Our produced descriptors are quite generic — they can be used in a variety of shape analysis applications, including dense...