Representing Knowledge of Large-Scale Space

This dissertation presents a model of the knowledge a person has about the spatial structure of a large-scale environment: the "cognitive map". The functions of the cognitive map are to assimilate new information about the environment, to represent the current position, and to answer route-finding and relative-position problems. This model (called the TOUR model) analyzes the cognitive map in terms of symbolic descriptions of the environment and operations on those descriptions. Knowledge about a particular environment is represented in terms of route descriptions, a topological network of paths and places, multiple frames of reference for relative positions, dividing boundaries, and a structure of containing regions. The current position is described by the "You Are Here" pointer, which acts as a working memory and a focus of attention. Operations on the cognitive map are performed by inference rules which act to transfer information among different descriptions and the "You Are Here" pointer. The TOUR model shows how the particular descriptions chosen to represent spatial knowledge support assimilation of new information from local observations into the cognitive map, and how the cognitive map solves route-finding and relative-position problems. A central theme of this research is that the states of partial knowledge supported by a representation are responsible for its ability to function with limited information of computational resources. The representations in the TOUR model provide a rich collection of states of partial knowledge, and therefore exhibit flexible, "common-sense" behavior.

Stereo correspondence estimation using multiwavelets scale-space representation-based multiresolution analysis

A multiresolution technique based on multiwavelets scale-space representation for stereo correspondence estimation is presented. The technique uses the well-known coarse-to-fine strategy, involving the calculation of stereo correspondences at the coarsest resolution level with consequent refinement up to the finest level. Vector coefficients of the multiwavelets transform modulus are used as corresponding features, where modulus maxima defines the shift invariant high-level features (multiscale edges) with phase pointing to the normal of the feature surface. The technique addresses the estimation of optimal corresponding points and the corresponding 2D disparity maps. Illuminative variation that can exist between the perspective views of the same scene is controlled using scale normalization at each decomposition level by dividing the details space coefficients with approximation space. The problems of ambiguity, explicitly, and occlusion, implicitly, are addressed by using a geometric topological refinement procedure. Geometric refinement is based on a symbolic tagging procedure introduced to keep only the most consistent matches in consideration. Symbolic tagging is performed based on probability of occurrence and multiple thresholds. The whole procedure is constrained by the uniqueness and continuity of the corresponding stereo features. The comparative performance of the proposed algorithm with eight famous existing algorithms, presented in the literature, is shown to validate the claims of promising performance of the proposed algorithm.

Depth estimation of metallic objects using multiwavelets scale-space representation

The problem of dimensional defects in aluminum die-castings is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic with highly reflective nature, it is extremely hard to estimate true dimensionality of these metallic parts, autonomously. Some existing vision systems are capable of estimating depth to high accuracy, however are very much hardware dependent, involving the use of light and laser pattern projectors, integrated into vision systems or laser scanners. However, due to the reflective nature of these metallic parts and variable factory environments, the aforementioned vision systems tend to exhibit unpromising performance. Moreover, hardware dependency makes these systems cumbersome and costly. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a pair of stereo cameras and a defused fluorescent light. The proposed vision system is capable of estimating surface depths within the accuracy of 0.5mm. In addition, the system is invariant to illuminative variations as well as orientation and location of the objects on the input image space, making the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup. The proposed system is a major part of quality inspection system for the automotive manufacturing industry.

Stereo image matching using wavelet scale-space representation

A multi-resolution technique for matching a stereo pair of images based on translation invariant discrete multi-wavelet transform is presented. The technique uses the well known coarse to fine strategy, involving the calculation of matching points at the coarsest level with consequent refinement up to the finest level. Vector coefficients of the wavelet transform modulus are used as matching features, where modulus maxima defines the shift invariant high-level features (multiscale edges) with phase pointing to the normal of the feature surface. The technique addresses the estimation of optimal corresponding points and the corresponding 2D disparity maps. Illuminative variation that can exist between the perspective views of the same scene is controlled using scale normalization at each decomposition level by dividing the details space coefficients with approximation space and then using normalized correlation. The problem of ambiguity, explicitly, and occlusion, implicitly, is addressed by using a geometric topological refinement procedure and symbolic tagging.

A scale-space aproach to nonlocal optical flow calculations

[EN] This paper presents an interpretation of a classic optical flow method by Nagel and Enkelmann as a tensor-driven anisotropic diffusion approach in digital image analysis. We introduce an improvement into the model formulation, and we establish well-posedness results for the resulting system of parabolic partial differential equations. Our method avoids linearizations in the optical flow constraint, and it can recover displacement fields which are far beyond the typical one-pixel limits that are characteristic for many differential methods for optical flow recovery. A robust numerical scheme is presented in detail. We avoid convergence to irrelevant local minima by embedding our method into a linear scale-space framework and using a focusing strategy from coarse to fine scales. The high accuracy of the proposed method is demonstrated by means of a synthetic and a real-world image sequence.

From filters to features:Scale-space analysis of edge and blur coding in human vision

To make vision possible, the visual nervous system must represent the most informative features in the light pattern captured by the eye. Here we use Gaussian scale-space theory to derive a multiscale model for edge analysis and we test it in perceptual experiments. At all scales there are two stages of spatial filtering. An odd-symmetric, Gaussian first derivative filter provides the input to a Gaussian second derivative filter. Crucially, the output at each stage is half-wave rectified before feeding forward to the next. This creates nonlinear channels selectively responsive to one edge polarity while suppressing spurious or "phantom" edges. The two stages have properties analogous to simple and complex cells in the visual cortex. Edges are found as peaks in a scale-space response map that is the output of the second stage. The position and scale of the peak response identify the location and blur of the edge. The model predicts remarkably accurately our results on human perception of edge location and blur for a wide range of luminance profiles, including the surprising finding that blurred edges look sharper when their length is made shorter. The model enhances our understanding of early vision by integrating computational, physiological, and psychophysical approaches. © ARVO.

Normal ECG Recognition for Express-Diagnostics Based on Scale-Space Representation and Dynamic Matching

A novel approach of normal ECG recognition based on scale-space signal representation is proposed. The approach utilizes curvature scale-space signal representation used to match visual objects shapes previously and dynamic programming algorithm for matching CSS representations of ECG signals. Extraction and matching processes are fast and experimental results show that the approach is quite robust for preliminary normal ECG recognition.

Automatic ECG Analysis for Preliminary and Detailed Diagnostics Based on Scale-space Representation

A novel approach of automatic ECG analysis based on scale-scale signal representation is proposed. The approach uses curvature scale-space representation to locate main ECG waveform limits and peaks and may be used to correct results of other ECG analysis techniques or independently. Moreover dynamic matching of ECG CSS representations provides robust preliminary recognition of ECG abnormalities which has been proven by experimental results.

Multi scale shape index for 3D object recognition

We present Multi Scale Shape Index (MSSI), a novel feature for 3D object recognition. Inspired by the scale space filtering theory and Shape Index measure proposed by Koenderink & Van Doorn [6], this feature associates different forms of shape, such as umbilics, saddle regions, parabolic regions to a real valued index. This association is useful for representing an object based on its constituent shape forms. We derive closed form scale space equations which computes a characteristic scale at each 3D point in a point cloud without an explicit mesh structure. This characteristic scale is then used to estimate the Shape Index. We quantitatively evaluate the robustness and repeatability of the MSSI feature for varying object scales and changing point cloud density. We also quantify the performance of MSSI for object category recognition on a publicly available dataset. © 2013 Springer-Verlag.

Multi-scale keypoint annotation: a biological approach

The primary visual cortex employs simple, complex and end-stopped cells to create a scale space of 1D singularities (lines and edges) and of 2D singularities (line and edge junctions and crossings called keypoints). In this paper we show first results of a biological model which attributes information of the local image structure to keypoints at all scales, ie junction type (L, T, +) and main line/edge orientations. Keypoint annotation in combination with coarse to fine scale processing facilitates various processes, such as image matching (stereo and optical flow), object segregation and object tracking.

Recognition from appearance subspaces across image sets of variable scale

Linear subspace representations of appearance variation are pervasive in computer vision. In this paper we address the problem of robustly matching them (computing the similarity between them) when they correspond to sets of images of different (possibly greatly so) scales. We show that the naïve solution of projecting the low-scale subspace into the high-scale image space is inadequate, especially at large scale discrepancies. A successful approach is proposed instead. It consists of (i) an interpolated projection of the low-scale subspace into the high-scale space, which is followed by (ii) a rotation of this initial estimate within the bounds of the imposed “downsampling constraint”. The optimal rotation is found in the closed-form which best aligns the high-scale reconstruction of the low-scale subspace with the reference it is compared to. The proposed method is evaluated on the problem of matching sets of face appearances under varying illumination. In comparison to the naïve matching, our algorithm is shown to greatly increase the separation of between-class and within-class similarities, as well as produce far more meaningful modes of common appearance on which the match score is based.

(Tables 1,2) Tracking records and space use statistics of polar bears (Ursus maritimus) in Storfjorden, Svalbard

Arctic sea ice is declining rapidly, making it vital to understand the importance of different types of sea ice for ice-dependent species such as polar bears Ursus maritimus. In this study we used GPS telemetry (25 polar bear tracks obtained in Svalbard, Norway, during spring) and high-resolution synthetic aperture radar (SAR) sea-ice data to investigate fine-scale space use by female polar bears. Space use patterns differed according to reproductive state; females with cubs of the year (COYs) had smaller home ranges and used fast-ice areas more frequently than lone females. First-passage time (FPT) analysis revealed that females with COYs displayed significantly longer FPTs near (<10 km) glacier fronts than in other fast-ice areas; lone females also increased their FPTs in such areas, but they also frequently used drifting pack ice. These results clearly demonstrate the importance of fast-ice areas, in particular close to glacier fronts, especially for females with COYs. Access to abundant and predictable prey (ringed seal pups), energy conservation and reluctance to cross large open water areas are possible reasons for the observed patterns. However, glacier fronts are retracting in Svalbard, and declines in land-fast ice have been notable over the past decade. The eventual disappearance of these important habitats might become critical for the survival of polar bear cubs in Svalbard and other regions with similar habitat characteristics. Given the relatively small size of many fast-ice areas in Svalbard, the results observed in this study would not have been revealed using less accurate location data or lower-resolution sea-ice data.