@article {jaehne_02_anspruchsvolle,
title = {F{\"u}r Anspruchsvolle - Multidimensionale Bildverarbeitung in der Produktion},
journal = {Qualit{\"a}t und Zuverl{\"a}ssigkeit},
volume = {47},
year = {2002},
pages = {1154-1159},
author = {Bernd J{\"a}hne and Martin Brocke and H. Eisele and S. Hader and Fred A. Hamprecht and W. Happold and Florian Raisch and J. Restle}
}
@article {jaehne2002g,
title = {Multidimensionale Bildverarbeitung in der Produktion},
journal = {QZ},
volume = {47},
year = {2002},
pages = {1154--1159},
url = {http://www.qz-online.de/qz-zeitschrift/archiv/artikel/multidimensionale-bildverarbeitung-in-der-produktion-fuer-anspruchsvolle-338129.html},
author = {Bernd J{\"a}hne and Martin Brocke and H. Eisele and S. Hader and Fred A. Hamprecht and W. Happold and Florian Raisch and J. Restle}
}
@conference {brocke2002,
title = {Statistical Image Sequence Processing for Temporal Change Detection},
booktitle = {Proceedings of the 24th DAGM Symposium on Pattern Recognition},
volume = {LNCS 2449},
year = {2002},
pages = {215--223},
abstract = {The aim is to detect sudden temporal changes in image sequences, focusing on bright objects that appear in a few consecutive frames. The proposed algorithm detects such outliers by computing a variance weighted deviation from mean values for every pixel. On this result, an object segmentation based on 2D-moments and its invariants is done frame by frame at a 3-sigma threshold. The algorithm was designed for a wide range of tasks in pre-processing as a tool for detection of fast temporal changes such as suddenly appearing or moving objects. Two different applications on noisy sequence data were realized. The entire system proved to fulfill the requirements of industrial environments for online process control and scientific demands for data rejection.},
doi = {10.1007/3-540-45783-6_27},
author = {Martin Brocke}
}
@phdthesis {brocke2002a,
title = {Statistische Ereignisdetektion in Bildfolgen},
year = {2002},
publisher = {IWR, Fakult{\"a}t f{\"u}r Physik und Astronomie, Univ.\ Heidelberg},
abstract = {This thesis presents a technique to detect statistically unlikely changes in noisy image sequences. Methods for outlier detection are well known in statistical data analysis. This work applies these techniques to image processing. Appropriate statistical tests are performed to identify the relevant pixels by hypothesis testing. The image sequence is represented as a separate time series for each image pixel with the assumption that at steady state the scene is static. This assumption is commonly made for many applications in surveillance and spatio-temporal measurements. The significance level related to the hypothesis test remains the only free parameter. This allows an even comparison of the algorithm{\textquoteright}s performance across different data sets. A confidence measure is calculated for each binary decision (inlier vs. outlier). Effects such as occlusion or false positives that occur for multiple outliers are controlled by an iterative extension. The algorithm was put into practice twice 1) A complete computer vision system for an industrial laser welding process control was patented. It replaces human visual inspection for mass production and improves robustness over spatially integrating sensors. 2) The algorithm has been applied to infrared image sequences in order to distinguish events caused by two separate processes. Hence heat flux parameter estimation was improved by an outlier detector module at the beginning of the estimation scheme. The technique presented has proven to be an easy-to-configure, modular, and fast tool for event detection in image sequences.},
url = {http://www.ub.uni-heidelberg.de/archiv/3065/},
author = {Martin Brocke}
}
@mastersthesis {brocke1998,
title = {Bildverarbeitung f{\"u}r Mikrolaserschwei{\ss}en unter Verwendung der Houghtransformation},
year = {1998},
school = {Universit{\"a}t Heidelberg},
author = {Martin Brocke}
}