arXiv subjects

Andreas Kolb

Publications and source records attributed to Andreas Kolb.

26 records · Page 2Linked to original sources

arXiv2018

Residuum-Condition Diagram and Reduction of Over-Complete Endmember-Sets

Extracting reference spectra, or endmembers (EMs) from a given multi- or hyperspectral image, as well as estimating the size of the EM set, plays an important role in multispectral image processing. In this paper, we present condition-residuum-diagrams. By plotting the residuum resulting from the unmixing and reconstruction and the condition number of various EM sets, the resulting diagram provides insight into the behavior of the spectral unmixing under a varying amount of endmembers (EMs). Furthermore, we utilize condition-residuum-diagrams to realize an EM reduction algorithm that starts with an initially extracted, over-complete EM set. An over-complete EM set commonly exhibits a good unmixing result, i.e. a lower reconstruction residuum, but due to its partial redundancy, the unmixing gets numerically unstable, i.e. the unmixed abundances values are less reliable. Our greedy reduction scheme improves the EM set by reducing the condition number, i.e. enhancing the set's stability, while keeping the reconstruction error as low as possible. The resulting set sequence gives hint to the optimal EM set and its size. We demonstrate the benefit of our condition-residuum-diagram and reduction scheme on well-studied datasets with known reference EM set sizes for several well-known EE algorithms.

cs.CV↗

arXiv2016

Preoperative Volume Determination for Pituitary Adenoma

The most common sellar lesion is the pituitary adenoma, and sellar tumors are approximately 10-15% of all intracranial neoplasms. Manual slice-by-slice segmentation takes quite some time that can be reduced by using the appropriate algorithms. In this contribution, we present a segmentation method for pituitary adenoma. The method is based on an algorithm that we have applied recently to segmenting glioblastoma multiforme. A modification of this scheme is used for adenoma segmentation that is much harder to perform, due to lack of contrast-enhanced boundaries. In our experimental evaluation, neurosurgeons performed manual slice-by-slice segmentation of ten magnetic resonance imaging (MRI) cases. The segmentations were compared to the segmentation results of the proposed method using the Dice Similarity Coefficient (DSC). The average DSC for all datasets was 75.92% +/- 7.24%. A manual segmentation took about four minutes and our algorithm required about one second.

cs.CV↗

arXiv2015

Kinect Range Sensing: Structured-Light versus Time-of-Flight Kinect

Recently, the new Kinect One has been issued by Microsoft, providing the next generation of real-time range sensing devices based on the Time-of-Flight (ToF) principle. As the first Kinect version was using a structured light approach, one would expect various differences in the characteristics of the range data delivered by both devices. This paper presents a detailed and in-depth comparison between both devices. In order to conduct the comparison, we propose a framework of seven different experimental setups, which is a generic basis for evaluating range cameras such as Kinect. The experiments have been designed with the goal to capture individual effects of the Kinect devices as isolatedly as possible and in a way, that they can also be adopted, in order to apply them to any other range sensing device. The overall goal of this paper is to provide a solid insight into the pros and cons of either device. Thus, scientists that are interested in using Kinect range sensing cameras in their specific application scenario can directly assess the expected, specific benefits and potential problem of either device.

cs.CV↗

arXiv2013

User Interface for Volume Rendering in Virtual Reality Environments

Volume Rendering applications require sophisticated user interaction for the definition and refinement of transfer functions. Traditional 2D desktop user interface elements have been developed to solve this task, but such concepts do not map well to the interaction devices available in Virtual Reality environments. In this paper, we propose an intuitive user interface for Volume Rendering specifically designed for Virtual Reality environments. The proposed interface allows transfer function design and refinement based on intuitive two-handed operation of Wand-like controllers. Additional interaction modes such as navigation and clip plane manipulation are supported as well. The system is implemented using the Sony PlayStation Move controller system. This choice is based on controller device capabilities as well as application and environment constraints. Initial results document the potential of our approach.

cs.GR↗

arXiv2011

Hand Tracking based on Hierarchical Clustering of Range Data

Fast and robust hand segmentation and tracking is an essential basis for gesture recognition and thus an important component for contact-less human-computer interaction (HCI). Hand gesture recognition based on 2D video data has been intensively investigated. However, in practical scenarios purely intensity based approaches suffer from uncontrollable environmental conditions like cluttered background colors. In this paper we present a real-time hand segmentation and tracking algorithm using Time-of-Flight (ToF) range cameras and intensity data. The intensity and range information is fused into one pixel value, representing its combined intensity-depth homogeneity. The scene is hierarchically clustered using a GPU based parallel merging algorithm, allowing a robust identification of both hands even for inhomogeneous backgrounds. After the detection, both hands are tracked on the CPU. Our tracking algorithm can cope with the situation that one hand is temporarily covered by the other hand.

cs.CV↗

arXiv2011

A Comparison of Two Human Brain Tumor Segmentation Methods for MRI Data

The most common primary brain tumors are gliomas, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the preoperative tumor volume is essential. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming process that can be overcome with the help of computerized segmentation methods. In this contribution, two methods for World Health Organization (WHO) grade IV glioma segmentation in the human brain are compared using magnetic resonance imaging (MRI) patient data from the clinical routine. One method uses balloon inflation forces, and relies on detection of high intensity tumor boundaries that are coupled with the use of contrast agent gadolinium. The other method sets up a directed and weighted graph and performs a min-cut for optimal segmentation results. The ground truth of the tumor boundaries - for evaluating the methods on 27 cases - is manually extracted by neurosurgeons with several years of experience in the resection of gliomas. A comparison is performed using the Dice Similarity Coefficient (DSC), a measure for the spatial overlap of different segmentation results.

cs.CV↗

arXiv2011

Glioblastoma Multiforme Segmentation in MRI Data with a Balloon Inflation Approach

Gliomas are the most common primary brain tumors, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the preoperative tumor volume is essential. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming process that can be overcome with the help of computer-assisted segmentation methods. In this paper, a semi-automatic approach for World Health Organization (WHO) grade IV glioma segmentation is introduced that uses balloon inflation forces, and relies on the detection of high-intensity tumor boundaries that are coupled by using contrast agent gadolinium. The presented method is evaluated on 27 magnetic resonance imaging (MRI) data sets and the ground truth data of the tumor boundaries - for evaluation of the results - are manually extracted by neurosurgeons.

cs.GR↗

arXiv2009

A Neural Network Classifier of Volume Datasets

Many state-of-the art visualization techniques must be tailored to the specific type of dataset, its modality (CT, MRI, etc.), the recorded object or anatomical region (head, spine, abdomen, etc.) and other parameters related to the data acquisition process. While parts of the information (imaging modality and acquisition sequence) may be obtained from the meta-data stored with the volume scan, there is important information which is not stored explicitly (anatomical region, tracing compound). Also, meta-data might be incomplete, inappropriate or simply missing. This paper presents a novel and simple method of determining the type of dataset from previously defined categories. 2D histograms based on intensity and gradient magnitude of datasets are used as input to a neural network, which classifies it into one of several categories it was trained with. The proposed method is an important building block for visualization systems to be used autonomously by non-experts. The method has been tested on 80 datasets, divided into 3 classes and a "rest" class. A significant result is the ability of the system to classify datasets into a specific class after being trained with only one dataset of that class. Other advantages of the method are its easy implementation and its high computational performance.

cs.GR↗