BieColl - Bielefeld eCollections
Not a member yet
1004 research outputs found
Sort by
A Comparison of Classifiers for Prescreening of Honeybee Brood Cells
Get PDFWe report on an image classification task originated from the video observation of beehives. Biologists desire to have an automatic support to identify so called hygienic bees. For this it is important to know which brood cells are in a stadium of initial opening. To find these cells a prescreening process is necessary which classifies three types of cells. To solve this decision problem a number of classification techniques are evaluated. ROC-analysis for the given problem shows that the SVM classifier with RBF kernel outperforms linear discrimance analysis, decision trees, boosted classifiers, and other kernel functions
A Multi-Cue-Based Human Body Tracking System
Get PDFThis paper presents a real-time vision-based system for the tracking of human upper body with both color images and depth maps. We combine the color-histogram-based particle filtering and mean shift algorithm to track face and hands and estimate other body parts by human kinetics. A multi-cue approach that integrates depth information and the color-based method is introduced to handle the rapid and complex motions of human hands. Real-time depth is recovered based on simple hardware configuration, which makes our system easy to be popularized in many real-world applications like digital entertainment. The system runs at 20 fps for images with 320x240 pixels on a 2.8GHz PC
An Attention Based Method For Motion Detection And Estimation
Get PDFThe demand for automated motion detection and object tracking systems has promoted considerable research activity in the field of computer vision. A novel approach to motion detection and estimation based on visual attention is proposed in the paper. Two different thresholding techniques are applied and comparisons are made with Black's motion estimation technique based on the measure of overall derived tracking angle. The method is illustrated on various video data and results show that the new method can extract both motion and shape information
Bowling for Calibration: An Undemanding Camera Calibration Procedure Using a Sphere
Get PDFCamera calibration is a critical problem in computer vision. This paper presents a new method for extrinsic parameters computation: images of a ball rolling on a flat plane in front of the camera are used to compute roll and pitch angles. The calibration is achieved by an iterative Inverse Perspective Mapping (IPM) process that uses an estimation on ball gradient invariant as a stop condition. The method is quick and as easy to use as throw a ball and is particularly suited to be used to quickly calibrate vision systems in unfriendly environments where a grid is not available. The algorithm correctness is demonstrated and its accuracy is computed using both computer generated and real images
Control of Attention by Nonconscious Information: Do Intentions Play a Role?
Get PDFThe present study explores the deployment of attention towards nonconscious information. It is both theoretically and empirically likely that the deployment of attention can be controlled by information which is not consciously registered (attentional priming), similar to the control of sensorimotor responses by nonconscious information (response priming). However, not much is known about the functional basis of attentional priming. The present experiment explore whether and how strongly intentions (current action pans) determine whether attention is allocated towards invisible information (so called direct parameter specification). The results demonstrate that intention-mediated control is possible, but it seems to break down easily, that is to provide a weak and non-robust type of control
Gain Adaptive Real-Time Stereo Streaming
Get PDFThis paper introduces a multi-view stereo matcher that generates depth in real-time from a monocular video stream of a static scene. A key feature of our processing pipeline is that it estimates global camera gain changes in the feature tracking stage and efficiently compensates for these in the stereo stage without impacting the real-time performance. This is very important for outdoor applications where the brightness range often far exceeds the dynamic range of the camera. Real-time performance is achieved by leveraging the processing power of the graphics processing unit (GPU) in addition to the CPU. We demonstrate the effectiveness of our approach on videos of urban scenes recorded by a vehicle-mounted camera with auto-gain enabled
Visual Quality Control in Heat Shrink Tubing
Get PDFIn this contribution a machine vision inspection system is presented which is designed as a length measuring sensor. It is developed to be applied to a range of heat shrink tubes, varying in length, diameter and color. The challenges of this task were the precision and accuracy demands as well as the real-time applicability of the entire approach since it should be realized in regular industrial line production. In production, heat shrink tubes are cut to specific sizes from a continuous tube. A multi-measurement strategy has been developed, which measures each individual tube segment several times with sub pixel accuracy while being in the visual field. The developed approach allows for a contact-free and fully automatic control of 100% of produced heat shrink tubes according to the given requirements with a measuring precision of 0.1mm. Depending on the color, length and diameter of the tubes considered, a true positive rate of 99.99% to 100% has been reached at a true negative rate of > 99.7
Accelerating Relational Clustering Algorithms With Sparse Prototype Representation
Get PDFIn some application contexts, data are better described by a matrix of pairwise dissimilarities rather than by a vector representation. Clustering and topographic mapping algorithms have been adapted to this type of data, either via the generalized Median principle, or more recently with the so called relational approach, in which prototypes are represented by virtual linear combinations of the original observations. One drawback of those methods is their complexity, which scales as the square of the number of observations, mainly because they use dense prototype representations: each prototype is obtained as a virtual combination of all the elements of its cluster (at least). We propose in this paper to use a sparse representation of the prototypes to obtain relational algorithms with sub-quadratic complexity
Emergence in Self Organizing Feature Maps
Get PDFThis paper sheds some light on the differences between SOM and emergent SOM (ESOM). The discussion in philosophy and epistemology about Emergence is summarized in the form of postulates. The properties of SOM are compared to these postulates. SOM fulfill most of the postulates. The epistemological postulates regarding this issue are hard, if not impossible, to prove. An alternative postulate relying on semiotic concepts, called "semiotic irreducibility" is proposed here. This concept is applied to U-Matrix on SOM with many neurons. This leads to the definition of ESOM as SOM producing a nontrivial U-Matrix on which the terms "watershed" and "catchment basin" are meaningful and which are cluster conform. The usefulness of the approach is demonstrated with an ESOM clustering algorithm which exploits the emergent properties of such SOM. Results on synthetic data also in blind studies are convincing. The application of ESOM clustering for a real world problem let to an excellent solution
In the quest of specific-domain ontology components for the semantic web
Get PDFThis paper describes an approach we have been using to identify specific-domain ontology components by using Self-Organizing Maps. These components are clustered together in a natural way according to their similarity. The knowledge maps, as we call them, show colored regions containing knowledge components that may be used to populate an specific-domain ontology. Later, these ontology may be used by software agents to carry out basic reasoning task on our behalf. In particular, we deal with the issue of not constructing the ontology from scratch, our approach helps us to speed up the ontology creation process