Prof. Michael M. Heizmann Profile

Prof. Michael M. Heizmann

Director of the Institute at Karlsruher Institut für Technologie

SPIE Involvement:

Editor | Author

Publications (19)

Proceedings Article | 11 August 2023 Presentation + Paper

Multi-sensor data fusion using deep learning for bulky waste image classification

Manuel Bihler, Lukas Roming, Yifan Jiang, Ahmed Afifi, Jochen Aderhold, Dovilė Čibiraitė-Lukenskienė, Sandra Lorenz, Richard Gloaguen, Robin Gruna, Michael Heizmann

Proceedings Volume 12623, 126230B (2023) https://doi.org/10.1117/12.2673838

KEYWORDS: Data fusion, Sensors, Deep learning, Image classification

Read Abstract +

Proceedings Article | 26 October 2022 Presentation + Paper

Investigating the influence of hyperspectral data compression on spectral unmixing

Jannick Kuester, Johannes Anastasiadis, Wolfgang Middelmann, Michael Heizmann

Proceedings Volume 12267, 122670H (2022) https://doi.org/10.1117/12.2636129

KEYWORDS: Data compression, Remote sensing, Hyperspectral imaging, Machine learning, Feature extraction

Read Abstract +

Proceedings Article | 12 September 2021 Presentation + Paper

Impact of different compression rates for hyperspectral data compression based on a convolutional autoencoder

Jannick Kuester, Wolfgang Gross, Michael Heizmann, Wolfgang Middelmann

Proceedings Volume 11862, 118620H (2021) https://doi.org/10.1117/12.2598010

KEYWORDS: Principal component analysis, Signal to noise ratio, Image compression, Data compression, Signal processing, Data transmission, Hyperspectral imaging, Dimension reduction, Machine learning

Read Abstract +

Proceedings Article | 20 June 2021 Poster + Presentation + Paper

Improving light efficiency in multispectral imaging via complementary notch filters

Theresa Panther, Maximilian Schambach, Michael Heizmann

Proceedings Volume 11787, 117870K (2021) https://doi.org/10.1117/12.2592411

KEYWORDS: Bandpass filters, Signal to noise ratio, Multispectral imaging, Spectral resolution, Linear filtering, Optical filters, Cameras, Photons, Gaussian filters, Standards development

Read Abstract +

Proceedings Article | 20 September 2020 Presentation + Paper

CNN-based augmentation strategy for spectral unmixing datasets considering spectral variability

Johannes Anastasiadis, Michael Heizmann

Proceedings Volume 11533, 115330V (2020) https://doi.org/10.1117/12.2575875

KEYWORDS: Remote sensing, Artificial neural networks, Convolutional neural networks, Data modeling, Neural networks, Error analysis, Matrices, Image processing

Read Abstract +

Spectral unmixing is often relying on a mixing model that is only an approximation. Artificial neural networks have the advantage of not requiring model knowledge. Additional advantages in the domain of spectral unmixing are the easy handling of spectral variability and the possibility to force the sum-to-one and the non-negativity constraints. However, they need a lot of significant training data to achieve good results. To overcome this problem, mainly for classification problems, augmentation strategies are widely used to increase the size of training datasets synthetically. Spectral unmixing can be considered as a regression problem, where data augmentation is also feasible. One intuitive strategy is to generate spectra based on abundances that do not occur in the training dataset, while taking spectral variability into account. For the implementation of this approach, we use a convolutional neural network (CNN), where the input variables are extended by random values. This allows spectral variability to be taken into account. The random inputs are re-sampled for each data point in every epoch. During training the CNN learns the mixing model and the characteristic spectral variability of the training dataset. Additional spectra can be generated afterwards for any given abundances to extend the original training dataset. Because the generative CNN minimizes the error between generated spectra and the corresponding ground truth for the whole dataset during training, the variance of the spectra based on the same abundances is lower than in the training data. We have investigated two approaches for improvement. One is to increase the variance of the random input variables when generating new spectra. For the second, the estimated covariance matrices are considered by the objective function. The presented method is evaluated with real data, which were captured in our image processing laboratory. We found that the augmentation of the training dataset with the presented strategy leads to an improvement for spectral unmixing of the test dataset.

Proceedings Article | 21 June 2019 Presentation + Paper

A simulation framework for the design and evaluation of computational cameras

Thomas Nürnberg, Maximilian Schambach, David Uhlig, Michael Heizmann, Fernando Puente León

Proceedings Volume 11061, 1106102 (2019) https://doi.org/10.1117/12.2527599

KEYWORDS: Cameras, Device simulation, Ray tracing, Imaging systems, Computer simulations, Geometrical optics, Computational imaging, Optical simulations, Hyperspectral simulation

Read Abstract +

Proceedings Article | 22 May 2014 Paper

Embedding the results of focussed Bayesian fusion into a global context

Jennifer Sander, Michael Heizmann

Proceedings Volume 9121, 912103 (2014) https://doi.org/10.1117/12.2050323

KEYWORDS: Probability theory, Information fusion, Mathematical modeling, Sensors, Monte Carlo methods, Distortion, Metrology, Calculus, Roads, Statistical analysis

Read Abstract +

Proceedings Article | 24 May 2013 Paper

Model based image restoration for underwater images

Thomas Stephan, Peter Frühberger, Stefan Werling, Michael Heizmann

Proceedings Volume 8791, 87911F (2013) https://doi.org/10.1117/12.2021990

KEYWORDS: Image restoration, Inspection, Sensors, Water, Image processing, Visualization, Imaging systems, Underwater imaging, Scattering, Light scattering

Read Abstract +

Proceedings Article | 28 April 2010 Paper

Global evaluation of focussed Bayesian fusion

Jennifer Sander, Michael Heizmann, Igor Goussev, Jürgen Beyerer

Proceedings Volume 7710, 77100A (2010) https://doi.org/10.1117/12.850028

KEYWORDS: Information fusion, Sensors, Image filtering, Image fusion, Quantitative analysis, Distortion, Sensor fusion, Modeling, Cameras, Reconnaissance

Read Abstract +

Proceedings Article | 29 January 2010 Paper

A novel region-based approach for the fusion of combined stereo and spectral series

I. Gheta, S. Höfer, M. Heizmann, J. Beyerer

Proceedings Volume 7538, 75380G (2010) https://doi.org/10.1117/12.840166

KEYWORDS: Image segmentation, Image fusion, Image registration, Cameras, Optical filters, Fusion energy, RGB color model, Image restoration, Image processing, Visible radiation

Read Abstract +

Proceedings Article | 13 April 2009 Paper

A local approach for focussed Bayesian fusion

Jennifer Sander, Michael Heizmann, Igor Goussev, Jürgen Beyerer

Proceedings Volume 7345, 73450N (2009) https://doi.org/10.1117/12.820165

KEYWORDS: Probability theory, Mathematical modeling, Information fusion, Bayesian inference, Reconnaissance, Computer architecture, Data modeling, Data fusion, Data storage, Criminalistics

Read Abstract +

Proceedings Article | 17 March 2008 Paper

Fusion of combined stereo and spectral series for obtaining 3D information

Ioana Gheta, Markus Mathias, Michael Heizmann, Jürgen Beyerer

Proceedings Volume 6974, 697406 (2008) https://doi.org/10.1117/12.778357

KEYWORDS: Image fusion, Image segmentation, Cameras, Image registration, 3D modeling, Fusion energy, Reconstruction algorithms, Image processing, Optical filters, Matrices

Read Abstract +

Proceedings Article | 18 April 2006 Paper

Fuselets: an agent based architecture for fusion of heterogeneous information and data

Jürgen Beyerer, Michael Heizmann, Jennifer Sander

Proceedings Volume 6242, 62420Q (2006) https://doi.org/10.1117/12.665938

KEYWORDS: Information fusion, Data fusion, Data analysis, Bayesian inference, Reconnaissance, Space reconnaissance, Information architecture, Criminalistics, Signals intelligence, Computer architecture

Read Abstract +

A new architecture for fusing information and data from heterogeneous sources is proposed. The approach takes criminalistics as a model. In analogy to the work of detectives, who attempt to investigate crimes, software agents are initiated that pursue clues and try to consolidate or to dismiss hypotheses. Like their human pendants, they can, if questions beyond their competences arise, consult expert agents. Within the context of a certain task, region, and time interval, specialized operations are applied to each relevant information source, e.g. IMINT, SIGINT, ACINT,..., HUMINT, data bases etc. in order to establish hit lists of first clues. Each clue is described by its pertaining facts, uncertainties, and dependencies in form of a local degree-of-belief (DoB) distribution in a Bayesian sense. For each clue an agent is initiated which cooperates with other agents and experts. Expert agents support to make use of different information sources. Consultations of experts, capable to access certain information sources, result in changes of the DoB of the pertaining clue. According to the significance of concentration of their DoB distribution clues are abandoned or pursued further to formulate task specific hypotheses. Communications between the agents serve to find out whether different clues belong to the same cause and thus can be put together. At the end of the investigation process, the different hypotheses are evaluated by a jury and a final report is created that constitutes the fusion result. The approach proposed avoids calculating global DoB distributions by adopting a local Bayesian approximation and thus reduces the complexity of the exact problem essentially. Different information sources are transformed into DoB distributions using the maximum entropy paradigm and considering known facts as constraints. Nominal, ordinal and cardinal quantities can be treated within this framework equally. The architecture is scalable by tailoring the number of agents according to the available computer resources, to the priority of tasks, and to the maximum duration of the fusion process. Furthermore, the architecture allows cooperative work of human and automated agents and experts, as long as not all subtasks can be accomplished automatically.

Proceedings Article | 1 March 2005 Paper

Sampling the parameter domain of image series

Michael Heizmann, Juergen Beyerer

Proceedings Volume 5672, (2005) https://doi.org/10.1117/12.586750

KEYWORDS: Cameras, Image processing, Reflection, Bidirectional reflectance transmission function, Image acquisition, Polarization, Light sources, Solids, Sensors, Modeling

Read Abstract +

SPIE Journal Paper | 1 December 2003

Imaging and analysis of forensic striation marks

Michael Heizmann, Fernando Puente Leon

OE, Vol. 42, Issue 12, (December 2003) https://doi.org/10.1117/12.10.1117/1.1622389

KEYWORDS: Image fusion, Forensic science, Image quality, Image processing, Image enhancement, Optical engineering, Image acquisition, Light sources, Image segmentation, Firearms

Read Abstract +

Proceedings Article | 19 July 2002 Paper

Strategies for the automated recognition of marks in forensic science

Michael Heizmann

Proceedings Volume 4709, (2002) https://doi.org/10.1117/12.474727

KEYWORDS: Forensic science, Databases, Image processing, Optical inspection, Firearms, Image acquisition, Light sources and illumination, Signal detection, Statistical analysis, Data processing

Read Abstract +

Proceedings Article | 19 July 2002 Paper

Automated comparison of striation marks with the system GE/2

Michael Heizmann

Proceedings Volume 4709, (2002) https://doi.org/10.1117/12.474728

KEYWORDS: Image acquisition, Forensic science, Image fusion, Firearms, Databases, Image quality, Feature extraction, Imaging systems, Model-based design, Visualization

Read Abstract +

Proceedings Article | 5 October 2001 Paper

Strategies to detect nonlinear similarities by means of correlation methods

Fernando Puente Leon, Michael Heizmann

Proceedings Volume 4572, (2001) https://doi.org/10.1117/12.444222

KEYWORDS: Sensors, Signal detection, Stochastic processes, Image processing, Nonlinear optics, Signal analyzers, Statistical analysis, Switches, Forensic science, Databases

Read Abstract +

Proceedings Article | 21 February 2001 Paper

Model-based analysis of striation patterns in forensic science

Michael Heizmann, Fernando Puente Leon

Proceedings Volume 4232, (2001) https://doi.org/10.1117/12.417572

KEYWORDS: Image fusion, Image quality, Model-based design, Forensic science, Image acquisition, Image processing, Kinematics, Image enhancement, Databases, Visualization

Read Abstract +

Showing 5 of 19 publications

Proceedings Volume Editor (2)

SPIE Conference Volume | 31 August 2023

Automated Visual Inspection and Machine Vision V

SPIE Conference Volume | 30 June 2021

Automated Visual Inspection and Machine Vision IV

Conference Committee Involvement (15)

Automated Visual Inspection and Machine Vision V

28 June 2023 | Munich, Germany

Automated Visual Inspection and Machine Vision IV

21 June 2021 | Online Only, Germany

Automated Visual Inspection and Machine Vision III

27 June 2019 | Munich, Germany

Automated Visual Inspection and Machine Vision

29 June 2017 | Munich, Germany

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2016

21 April 2016 | Baltimore, MD, United States

Automated Visual Inspection and Machine Vision

24 June 2015 | Munich, Germany

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2015

21 April 2015 | Baltimore, MD, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2014

6 May 2014 | Baltimore, MD, United States

Automated Visual Inspection

16 May 2013 | Munich, Germany

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2013

30 April 2013 | Baltimore, Maryland, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2012

25 April 2012 | Baltimore, Maryland, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2011

27 April 2011 | Orlando, Florida, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2010

7 April 2010 | Orlando, Florida, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2009

16 April 2009 | Orlando, Florida, United States

Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2008

19 March 2008 | Orlando, Florida, United States

Showing 5 of 15 Conference Committees

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years