BieColl - Bielefeld eCollections
Not a member yet
1004 research outputs found
Sort by
EyeScreen: A Vision-Based Desktop Interaction System
Get PDFEyeScreen provides a natural HCI interface with vision-based hand tracking and gesture recognition techniques. Multi-view video images captured from two cameras facing a computer screen are used to track and recognize finger and hand motions. Finger tracking is achieved by skin color detection and particle filtering, and is greatly enhanced by the proposed screen background subtraction method that removes the screen images in advance. Finger click on the screen can also be detected from multi-view information. Gesture recognition based on binocular vision is presented to improve the recognition rate. The experimental results show that EyeScreen is able to perform natural and robust interaction in desktop environment
Gaze Control in a Multiple-Task Active-Vision System
Get PDFVery little attention has been devoted to the problem of modular composition of vision capabilities in perception-action systems. While new algorithms and techniques have paved the way for important developments, the majority of vision systems are still designed and integrated in a very primitive way according to modern software engineering principles. This paper describes the architecture of an active vision system that has been conceived to ease the concurrent utilization of the system by several visual tasks. We describe in detail the functional architecture of the system and provide several solutions to the problem of sharing the visual attention of the system when several visual tasks need to be interleaved. The system's design hides this complexity to client processes that can be designed as if they were exclusive users of the visual system. Some preliminary results on a real robotic platform are also provided
Monitoring surrounding areas of truck-trailer combinations
Get PDFDrivers of trucks and buses are not able to survey the surrounding area of their vehicles. In this paper a system is presented that provides a bird's-eye view of the surrounding area of a truck-trailer combination to the driver. This view enables the driver to maneuver the vehicle easily in complicated environments. The system consists of four omnidirectional cameras mounted on a truck and trailer. The omnidirectional images are combined in such a way that a bird's-eye view image is generated. A sensor measures the angle between truck and trailer, thus the bird's-eye view image is constructed appropriate to this angle
Registering Conventional Images with Low Resolution Panoramic Images
Get PDFThis paper addresses the problem of registering high-resolution, small field-of-view images with low-resolution panoramic images provided by an panoramic catadioptric video sensor. Such systems may find application in surveillance and telepresence systems that require a large field of view and high resolution at selected locations. Although image registration has been studied in more conventional applications, the problem of registering panoramic and conventional video has not previously been addressed, and this problem presents unique challenges due to (i) the extreme differences in resolution between the sensors (more than a 16:1 linear resolution ratio in our application), and (ii) the resolution inhomogeneity of panoramic images. The main contributions of this paper are as follows. First, we introduce our foveated panoramic sensor design. Second, we describe an automatic and near real-time registration between the two image streams. This registration is based on minimizing the intensity discrepancy allowing the direct recovery of both the geometric and the photometric transforms. Registration examples using the developed methods are presented
Visual Person Searches for Retail Loss Detection : Application and Evaluation
Get PDFWe describe a novel computer-vision based system for facilitating the search for people across multiple non-overlapping cameras. The system has been applied in a retail environment most specifically for returns fraud prevention. The system detects and tracks people in multiple cameras and enables rapid cross-camera association of tracks. The system has been tested in a real store environment and we present results with a breakdown of error types
Composition of Self Organizing Maps for Adaptive Mesh Construction on Complex-shaped Domains
Get PDFIn this paper, an important application of Self-Organizing Maps (SOM) to construction of adaptive meshes is considered. It is shown that application of the basic SOM model leads to a number of problems like inaccurate fitting the border of a physical domain, mesh self-crossings, etc. The composite SOM model is proposed which is based on the composition of a number of SOM models interacting in a special way and self-organizing over their own set of input data. A core of the composite SOM model is the colored SOM model with nonadjustable neurons which provides us a technique to control the neuron weights adjustment taking into account the fixed ones and the general layout of the mesh. As a result, the composite SOM model allows us to approximate an arbitrary complex physical domains with well topology preservation
Intraday trading rules based on Self Organizing Maps
Get PDFWorking with five minutes data, we have studied a number of trading rules based on the responses of Kohonen's Self Organizing Maps, evaluating the results with both financial and statistical indicators, as well as by comparison with classical buy and hold strategy. At the current stage our major findings may be summarized as follows: a) Kohonen's maps are helpful to localize profitable intraday patterns, and b) they generally make possible to achieve higher performances than common buy and hold strategy
Local Adaptive Receptive Field Self-Organizing Map for Image Segmentation
Get PDFA new self-organizing map with variable topology is introduced for image segmentation. The proposed network, called Local Adaptive Receptive Field Self-Organizing Map (LARFSOM-RBF), is a two-stage network capable of both color and border segment images. The color segmentation stage is responsibility of LARFSOM which is characterized by adaptive number of nodes, fast convergence and variable topology. For border segmentation RBF nodes are included to determine the border pixels using previously learned information of LARFSOM. LARFSOM-RBF was tested to segment images with different degrees of complexity showing promising results
Self-Organizing Word Map for Context-Based Document Classification
Get PDFIn this paper, a novel SOM-based system for document organization is presented. The purpose of the system is the classification of a document collection in terms of document content. The system possesses a two-level hybrid connectionist architecture that comprises (i) an automatically created word map using a SOM, which functions as a feature extraction module and (ii) a supervised MLP-based classifier, which provides the final classification result. The experiments, which have been performed on Modern Greek text documents, indicate that the proposed system separates effectively the different types of text
Speaker Identification by BYY Automatic Local Factor Analysis based Three-Level Voting Combination
Get PDFLocal Factor Analysis (LFA) is known as more general and powerful than Gaussian Mixture Model (GMM) in unsupervised learning with local subspace structure analysis. In the literature of text-independent speaker identification, GMM has been widely used and investigated, with some preprocessing or postprocessing approaches, while there still lacks efforts on LFA for this task. In pursuit of fast implementation for LFA modeling, this paper focuses on the Bayesian Ying-Yang automatic learning with data smoothing based regularization (BYY-A), which makes automatic model selection during parameter learning. Furthermore for sequence classification, based on trained LFA models, we design and analyze a three-level combination, namely sequence, classifier and committee, respectively. Different combination approaches are designed with variant sequential topologies and voting schemes. Experimental results on the KING speech corpus demonstrate the proposed approaches' effectiveness and potentials