Anshuman Razdan

Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints

In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

3D face authentication and recognition based on bilateral symmetry analysis

We present a novel and computationally fast method for automatic human face authentication. Taking a 3D triangular facial mesh as input, the approach first automatically extracts the bilateral symmetry plane of the facial surface. The intersection between the symmetry plane and the facial surface, namely the symmetry profile, is then computed. Using both the mean curvature plot of the facial surface and the curvature plot of the symmetry profile curve, three essential points of the nose on the symmetry profile are automatically extracted. The three essential points uniquely determine a Face Intrinsic Coordinate System (FICS). Different faces are aligned based on the FICS. The symmetry profile, together with two transverse profiles, composes a compact representation, called the SFC representation, of a 3D face surface. The face authentication and recognition steps are finally performed by comparing the SFC representations of the faces. The proposed method was tested on 382 face surfaces, which come from 166 individuals and cover a wide ethnic and age variety. The equal error rate (EER) of face authentication on scans with variable facial expressions is 10.8%. For scans with normal expression, the ERR is 0.8%.

Generating 3D Building Models from Architectural Drawings: A Survey

Automatically generating 3D building models from 2D architectural drawings has many useful applications in the architecture engineering and construction community. This survey of model generation from paper and CAD-based architectural drawings covers the common pipeline and compares various algorithms for each step of the process.

Curve matching for open 2D curves

We present a curve matching framework for planar open curves under similarity transform based on a new scale invariant signature. The signature is derived from the concept of integral of unsigned curvatures. If one input curve as a whole can be aligned with some part in the second curve then the algorithm will find the requisite starting and end positions and will estimate the similarity transform in O(Nlog(N)) time. We extend our frame work to a more general case where some part of the first input curve can be aligned with some part of the second input curve. This is a more difficult problem that we solve in O(N^3) time. The contributions of the paper are the new signature as well as faster algorithms for matching open 2D curves. We present examples from diverse application set to show that our algorithm can work across several domains.

A hybrid approach to feature segmentation of triangle meshes

Abstract Segmentation of a polygonal mesh is a method of breaking the mesh down into ‘meaningful’ connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9] , [10] . Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops. We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.

Curvature estimation scheme for triangle meshes using biquadratic Bézier patches

When dealing with triangle meshes, it is often important to compute curvature information for the purposes of feature recognition, segmentation, or shape analysis. Since a triangle mesh is a piecewise linear surface, curvature has to be estimated. Several different schemes have been proposed, both discrete and continuous, i.e. based on fitting surfaces locally. This paper compares commonly used discrete and continuous curvature estimation schemes. We also present a novel method which uses biquadratic Bezier patches as a local surface fitting technique.

Dart throwing on surfaces

In this paper we present dart throwing algorithms to generate maximal Poisson disk point sets directly on 3D surfaces. We optimize dart throwing by efficiently excluding areas of the domain that are already covered by existing darts. In the case of triangle meshes, our algorithm shows dramatic speed improvement over comparable sampling methods. The simplicity of our basic algorithm naturally extends to the sampling of other surface types, including spheres, NURBS, subdivision surfaces, and implicits. We further extend the method to handle variable density points, and the placement of arbitrary ellipsoids without overlap. Finally, we demonstrate how to adapt our algorithm to work with geodesic instead of Euclidean distance. Applications for our method include fur modeling, the placement of mosaic tiles and polygon remeshing.

Interactive Hyperspectral Image Visualization Using Convex Optimization

In this paper, we propose a new framework to visualize hyperspectral images. We present three goals for such a visualization: 1) preservation of spectral distances; 2) discriminability of pixels with different spectral signatures; 3) and interactive visualization for analysis. The introduced method considers all three goals at the same time and produces higher quality output than existing methods. The technical contribution of our mapping is to derive a simplified convex optimization from a complex nonlinear optimization problem. During interactive visualization, we can map the spectral signature of pixels to red, green, and blue colors using a combination of principal component analysis and linear programming. In the results, we present a quantitative analysis to demonstrate the favorable attributes of our algorithm.

Adaptive Subdivision Schemes for Triangular Meshes

Of late we have seen an increase in the use of subdivision techniques for both modeling and animation. They have given rise to a new surface called the subdivision surface which has many advantages over traditional Non Uniform Rational B-spline (NURB) surfaces. Subdivision surfaces easily address the issues related to multiresolution, refinement, scalability and representation of meshes. Many schemes have been introduced that take a coarse mesh and refine it using subdivision. They can be mainly classified as Approximating — in which the original coarse mesh is not preserved, or Interpolating — wherein the subdivision forces the refined mesh to pass through the original points of the coarse mesh. The schemes used for triangular meshes are chiefly the Loop scheme, which is approximating in nature and the Modified Butterfly scheme which is interpolating. Subdivision schemes are cost intensive at higher levels of subdivision. In this paper we introduce two methods of adaptive subdivision for triangular meshes that make use of the Loop scheme or theModified Butterfly scheme to get approximating or interpolating results respectively. The results are obtained at a lower cost when compared with those obtained by regular subdivision schemes. The first method uses the angles between the normal of a face and the normals of its adjacent faces to develop an adaptive method of subdivision. The other method relies on user input, i.e. the user specifies which parts of the mesh should be subdivided. This process can be automated by segmentation techniques, e.g. watershed segmentation, to get the areas in the mesh that need to be subdivided. We compare our methods for various triangular meshes and present our results.

Route Visualization Using Detail Lenses

We present a method designed to address some limitations of typical route map displays of driving directions. The main goal of our system is to generate a printable version of a route map that shows the overview and detail views of the route within a single, consistent visual frame. Our proposed visualization provides a more intuitive spatial context than a simple list of turns. We present a novel multifocus technique to achieve this goal, where the foci are defined by points of interest (POI) along the route. A detail lens that encapsulates the POI at a finer geospatial scale is created for each focus. The lenses are laid out on the map to avoid occlusion with the route and each other, and to optimally utilize the free space around the route. We define a set of layout metrics to evaluate the quality of a lens layout for a given route map visualization. We compare standard lens layout methods to our proposed method and demonstrate the effectiveness of our method in generating aesthetically pleasing layouts. Finally, we perform a user study to evaluate the effectiveness of our layout choices.