Michael Gschwandtner

BlenSor: blender sensor simulation toolbox

This paper introduces a novel software package for the simulation of various types of range scanners. The goal is to provide researchers in the fields of obstacle detection, range data segmentation, obstacle tracking or surface reconstruction with a versatile and powerful software package that is easy to use and allows to focus on algorithmic improvements rather than on building the software framework around it. The simulation environment and the actual simulations can be efficiently distributed with a single compact file. Our proposed approach facilitates easy regeneration of published results, hereby highlighting the value of reproducible research.

Experimental study on the impact of endoscope distortion correction on computer-assisted celiac disease diagnosis

The impact of applying barrel distortion correction to endoscopic imagery in the context of automated celiac disease diagnosis is experimentally investigated. For a large set of feature extraction techniques, it is found that contrasting to intuition, no improvement but even significant result degradation of classification accuracy can be observed. For techniques relying on geometrical properties of the image material (“shape”), moderate improvements of classification accuracy can be achieved. Reasons for this somewhat unexpected results are discussed and ways how to exploit potential distortion correction benefits are sketched.

Improved endoscope distortion correction does not necessarily enhance mucosa-classification based medical decision support systems

Distortion correction in two variants is applied to endoscopic duodenal imagery aiming at an improvement of automated classification of celiac disease affected mucosa patches. In a set of heterogeneous feature extraction techniques, only geometry and shape related ones are able to benefit from distortion correction, while for others, even a decrease of classification accuracy is observed. Different types of distortion correction do not lead to significantly different behaviour in the observed application scenario.

Infrared camera calibration for dense depth map construction

In this paper, we introduce a novel and cost effective approach to calibrate the geometric properties of a far-infrared (IR) sensor. We further demonstrate that fully automatic sensor-to-sensor calibration is feasible in a setup involving a laser range scanner, IR cameras as well as conventional cameras. The calibration result then serves as a basis for upsampling range measurements to the resolution of the IR or visible-light camera images. Since our approach allows to rely on IR information instead of visible-light information for upsampling, bad light conditions or even no visible light at all are no limitation. From a practical point of view, we only require one calibration board of relatively small size which facilitates application in outdoor environments and further allows seamless integration of the IR camera in an existing multi-sensor platform. Our experimental results demonstrate that IR images are particularly useful to obtain reasonable depth information for living objects, when visible-light cameras are either blind or require impractical exposure times. In fact, our approach provides a convenient solution to IR camera calibration and integration, an issue which is particularly important in scenarios where sensors are not permanently mounted on vehicles and consequently require on-site adjustment and calibration.

Track detection for autonomous trains

This paper presents a way to efficiently use lane detection techniques - known from driver assistance systems - to assist in obstacle detection for autonomous trains. On the one hand, there are several properties that can be exploited to improve conventional lane detection algorithms when used for railway applications. The heavily changing visual appearance of the tracks is compensated by very effective geometric constraints. On the other hand there are additional challenges that are less problematic in classical lane detection applications. This work is part of a sensor system for an autonmous train application that aims at creating an environmentally friendly public transportation system.

Transmission error and compression robustness of 2D chaotic map image encryption schemes

This paper analyzes the robustness properties of 2D chaotic map image encryption schemes. We investigate the behavior of such block ciphers under different channel error types and find the transmission error robustness to be highly dependent on on the type of error occurring and to be very different as compared to the effects when using traditional block ciphers like AES. Additionally, chaotic-mixing-based encryption schemes are shown to be robust to lossy compression as long as the security requirements are not too high. This property facilitates the application of these ciphers in scenarios where lossy compression is applied to encrypted material, which is impossible in case traditional ciphers should be employed. If high security is required chaotic mixing loses its robustness to transmission errors and compression, still the lower computational demand may be an argument in favor of chaotic mixing as compared to traditional ciphers when visual data is to be encrypted.

Compression of encrypted visual data

Chaotic mixing based encryption schemes for visual data are shown to be robust to lossy compression as long as the security requirements are not too high. This property facilitates the application of these ciphers in scenarios where lossy compression is applied to encrypted material – which is impossible in case traditional ciphers should be employed. If high security is required chaotic mixing loses its robustness to compression, still the lower computational demand may be an argument in favor of chaotic mixing as compared to traditional ciphers when visual data is to be encrypted.

PCL and ParaView — Connecting the dots

We introduce a novel open-source framework for analyzing and exploring point cloud datasets and algorithms. This is done by integrating the Point Cloud Library (PCL) within ParaView, a parallel scientific visualization tool. In particular, we demonstrate that by wrapping PCL algorithms as VTK1 filters, we can leverage PCLs functionality in an interactive, easy-to-use manner within ParaView. The proposed approach enables rapid algorithm development in a coherent framework without the need to write custom visualization code. We illustrate the advantages of the framework with usage examples such as segmentation, data annotation and Python integration. Additionally, we build upon ParaViews inherent parallelization capabilities and present two strong scaling experiments that demonstrate near-linear scaling performance gains in a multi-processor setup.

Assessing Out-of-the-box Software for Automated Hippocampus Segmentation

A comparison of four out-of-the-box software packages for automated hippocampus segmentation reveals that AHEAD and Freesurfer deliver the most satisfying results in terms of software usability and segmentation reliability and are thus recommended to be used in a fused manner.

Toward DRM for 3D geometry data

Computationally efficient encryption techniques for polygonal mesh data are proposed which exploit the prioritization of data in progressive meshes. Significant reduction of computational demand can be achieved as compared to full encryption, but it turns out that different techniques are required to support both privacy-focussed applications and try-and-buy scenarios.