Labelling 2-D geometric primitives using probabilistic relaxation:reducing the computational requirements

In previous work, an algorithm for matching geometric features was developed. Although the method worked well, it was demanding in computational resources when applied to large problems. The authors now present methods for reducing the computational requirements, without significantly affecting the reliability of the algorithm     

Classification of sets of mixed pixels with the hypothesis-testingHough transform

A new method is presented for mixed pixel classification where the classification of groups of mixed pixels is achieved by using the hypothesis-testing Hough transform. The motivation of the work is that some other estimation methods based on robust statistics, such as the standard Hough transform, have been criticised that, although they can cope with the presence of outliers, they give poor performance in the absence of outliers in comparison to the least-squares-error method. The method proposed in the paper is demonstrated using simulated data and proved to perform equally well in the presence and in the absence of outliers. It is also applied to real Landsat TM data     

2.5D Elastic graph matching

In this paper, we propose novel elastic graph matching (EGM) algorithms for face recognition assisted by the availability of 3D facial geometry. More specifically, we conceptually extend the EGM algorithm in order to exploit the 3D nature of human facial geometry for face recognition/verification. In order to achieve that, first we extend the matching module of the EGM algorithm in order to capitalize on the 2.5D facial data. Furthermore, we incorporate the 3D geometry into the multiscale analysis used and build a novel geodesic multiscale morphological pyramid of dilations/erosions in order to fill the graph jets. We show that the proposed advances significantly enhance the performance of EGM algorithms. We demonstrate the efficiency of the proposed advances in the face recognition/verification problem using photometric stereo.     

Invariant image reconstruction from irregular samples and hexagonal grid splines

We present an algorithm for the reconstruction of images from irregularly placed samples, using linear splines with control points on a hexagonal grid. Several spline approximations are computed for different transformations of the control point grid (e.g. translations and rotations). These approximations are then merged together after compensation of the transformations, yielding a high-quality invariant image reconstruction. Evaluations show that the use of hexagonal grids of the “invariance by integration” principle improves reconstruction quality. An application to image coding is also presented.     

Affine parameter estimation from the trace transform

In this paper, we assume that we are given the images of two segmented objects, one of which may be an affinely distorted version of the other, and wish to recover the values of the parameters of the affine transformation between the two images. The images may also differ by the overall level of illumination. The multiplicative constant of such difference may also be recovered. We present a generic theoretical framework to solve this problem. In terms of this framework, other proposed methods may be interpreted. We show how, in this framework, one can recover the affine parameters in a way that is robust to various effects, such as occlusion and illumination variation. The proposed method is generic enough to be applicable also to matching two images that do not depict the same scene or object.     

The road to intelligence

It is argued that robotic platforms are the way forward towards building intelligent systems, where multiple sensors and manipulation are used for cognitive processes. It is also argued that the cue for developing the right architecture for such a system is human language.     

Effects of superstructure flexibility on strength of reinforced concrete bridge decks

This research studies the impact of the relative rigidity between the concrete bridge deck and the remaining structural components of the bridge superstructure on the behavior of the concrete deck. The study uses non-linear 3-D FEM models, which are developed using ANSYS 5.7 software package. Experimental data from one-span non-composite bridge superstructure are used to validate and calibrate the proposed FEM models. A series of parametric studies is conducted with respect to three parameters: (a) composite action, (b) slenderness ratio, and (c) presence of diaphragms. The analysis results are discussed in detail and conclusions on the behavior of the bridge deck are presented.     

Construction of Minimized Topological Graphs on Occupancy Grid Maps Based on GVD and Sensor Coverage Information

One of the tasks to be carried out during the robot exploration of an unknown environment, is the construction of a complete map of the environment at bounded time interval. In order for the exploration to be efficient, a smart planning method must be implemented so that the robot can cover the space as fast as possible. One of the most important information that an intelligent agent can have, is a representation of the environment, not necessarily in the form of a map, but of a topological graph of the plane, which can be used to perform efficient planning. This work proposes a method to produce a topological graph of an Occupancy Grid Map (OGM) by using a Manhattan distance function to create the Approximate Generalized Voronoi Diagram (AGVD). Several improvements in the AGVD are made, in order to produce a crisp representation of the spaces skeleton, but in the same time to avoid the complex results of other methods. To smooth the final AGVD, morphological operations are performed. A topological graph is constructed from the AGVD, which is minimized by using sensor coverage information, aiming at planning complexity reduction.