Dr. Stefan Becker Profile

Dr. Stefan Becker

at Fraunhofer IOSB

SPIE Involvement:

Conference Program Committee | Author

Proceedings Article | 17 October 2023 Presentation + Paper

Center point-based feature representation for tracking

Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens

Proceedings Volume 12742, 127420D (2023) https://doi.org/10.1117/12.2680065

KEYWORDS: Object detection, Feature extraction, Machine learning, Visualization, Design and modelling, Image processing, Video surveillance, Motion models

Read Abstract +

Proceedings Article | 7 October 2019 Presentation + Paper

A comparison study of deep visual tracking on infrared imagery in a maritime environment

Stéphane Vujasinović, Stefan Becker, Norbert Scherer-Negenborn, Michael Arens

Proceedings Volume 11166, 111660P (2019) https://doi.org/10.1117/12.2532805

KEYWORDS: Video, Optical tracking, Visualization, Infrared radiation, Infrared imaging, Feature extraction, Infrared search and track, Failure analysis

Read Abstract +

Proceedings Article | 5 October 2017 Paper

Robust visual object tracking with interleaved segmentation

Peter Abel, Hilke Kieritz, Stefan Becker, Michael Arens

Proceedings Volume 10441, 104410B (2017) https://doi.org/10.1117/12.2275259

KEYWORDS: Optical tracking, Visualization, Image segmentation, Video, Cameras, Statistical modeling

Read Abstract +

Proceedings Article | 24 October 2016 Presentation + Paper

The effects of camera jitter for background subtraction algorithms on fused infrared-visible video streams

Stefan Becker, Norbert Scherer-Negenborn, Pooja Thakkar, Wolfgang Hübner, Michael Arens

Proceedings Volume 9995, 99950I (2016) https://doi.org/10.1117/12.2239884

KEYWORDS: Image fusion, Cameras, Infrared imaging, Sensors, Infrared radiation, Image processing, Infrared cameras, Video, Statistical modeling, Fuzzy logic

Read Abstract +

Proceedings Article | 24 October 2016 Presentation + Paper

MAD for visual tracker fusion

Stefan Becker, Sebastian Krah, Wolfgang Hübner, Michael Arens

Proceedings Volume 9995, 99950L (2016) https://doi.org/10.1117/12.2243473

KEYWORDS: Image fusion, Sensors, Tin, Factor analysis, Error analysis, Automatic tracking, Image processing, Visualization, Detection and tracking algorithms, Optical tracking

Read Abstract +

Proceedings Article | 24 October 2016 Paper

Detection of infrastructure manipulation with knowledge-based video surveillance

David Muench, Barbara Hilsenbeck, Hilke Kieritz, Stefan Becker, Ann-Kristin Grosselfinger, Wolfgang Huebner, Michael Arens

Proceedings Volume 9995, 99950P (2016) https://doi.org/10.1117/12.2240304

KEYWORDS: Video surveillance, Visualization, Surveillance, Skin, Video, Cameras, Sensors, Image filtering, RGB color model, Light

Read Abstract +

Proceedings Article | 21 October 2015 Paper

Detecting abandoned objects using interacting multiple models

Stefan Becker, David Münch, Hilke Kieritz, Wolfgang Hübner, Michael Arens

Proceedings Volume 9652, 96520G (2015) https://doi.org/10.1117/12.2195224

KEYWORDS: Image processing, Motion models, Systems modeling, Positron emission tomography, Video surveillance, Sensors, Surveillance, Video, Cameras, Data modeling

Read Abstract +

Proceedings Article | 17 October 2014 Paper

Independent motion detection with a rival penalized adaptive particle filter

Stefan Becker, Wolfgang Hübner, Michael Arens

Proceedings Volume 9248, 92480J (2014) https://doi.org/10.1117/12.2066635

KEYWORDS: Particles, Motion models, Cameras, Motion detection, Motion estimation, Sensors, Imaging systems, Particle filters, Video, Motion measurement

Read Abstract +

Aggregation of pixel based motion detection into regions of interest, which include views of single moving objects in a scene is an essential pre-processing step in many vision systems. Motion events of this type provide significant information about the object type or build the basis for action recognition. Further, motion is an essential saliency measure, which is able to effectively support high level image analysis. When applied to static cameras, background subtraction methods achieve good results. On the other hand, motion aggregation on freely moving cameras is still a widely unsolved problem. The image flow, measured on a freely moving camera is the result from two major motion types. First the ego-motion of the camera and second object motion, that is independent from the camera motion. When capturing a scene with a camera these two motion types are adverse blended together. In this paper, we propose an approach to detect multiple moving objects from a mobile monocular camera system in an outdoor environment. The overall processing pipeline consists of a fast ego-motion compensation algorithm in the preprocessing stage. Real-time performance is achieved by using a sparse optical flow algorithm as an initial processing stage and a densely applied probabilistic filter in the post-processing stage. Thereby, we follow the idea proposed by Jung and Sukhatme. Normalized intensity differences originating from a sequence of ego-motion compensated difference images represent the probability of moving objects. Noise and registration artefacts are filtered out, using a Bayesian formulation. The resulting a posteriori distribution is located on image regions, showing strong amplitudes in the difference image which are in accordance with the motion prediction. In order to effectively estimate the a posteriori distribution, a particle filter is used. In addition to the fast ego-motion compensation, the main contribution of this paper is the design of the probabilistic filter for real-time detection and tracking of independently moving objects. The proposed approach introduces a competition scheme between particles in order to ensure an improved multi-modality. Further, the filter design helps to generate a particle distribution which is homogenous even in the presence of multiple targets showing non-rigid motion patterns. The effectiveness of the method is shown on exemplary outdoor sequences.

Proceedings Article | 1 November 2013 Paper

Automated generation of high-quality training data for appearance-based object models

Stefan Becker, Arno Voelker, Hilke Kieritz, Wolfgang Hübner, Michael Arens

Proceedings Volume 8899, 889916 (2013) https://doi.org/10.1117/12.2028714

KEYWORDS: Sensors, Cameras, Data modeling, Sensor performance, Statistical modeling, Motion detection, Video surveillance, Video, Electroluminescent displays, Detection and tracking algorithms

Read Abstract +

Methods for automated person detection and person tracking are essential core components in modern security and surveillance systems. Most state-of-the-art person detectors follow a statistical approach, where prototypical appearances of persons are learned from training samples with known class labels. Selecting appropriate learning samples has a significant impact on the quality of the generated person detectors. For example, training a classifier on a rigid body model using training samples with strong pose variations is in general not effective, irrespective of the classifiers capabilities. Generation of high-quality training data is, apart from performance issues, a very time consuming process, comprising a significant amount of manual work. Furthermore, due to inevitable limitations of freely available training data, corresponding classifiers are not always transferable to a given sensor and are only applicable in a well-defined narrow variety of scenes and camera setups. Semi-supervised learning methods are a commonly used alternative to supervised training, in general requiring only few labeled samples. However, as a drawback semi-supervised methods always include a generative component, which is known to be difficult to learn. Therefore, automated processes for generating training data sets for supervised methods are needed. Such approaches could either help to better adjust classifiers to respective hardware, or serve as a complement to existing data sets. Towards this end, this paper provides some insights into the quality requirements of automatically generated training data for supervised learning methods. Assuming a static camera, labels are generated based on motion detection by background subtraction with respect to weak constraints on the enclosing bounding box of the motion blobs. Since this labeling method consists of standard components, we illustrate the effectiveness by adapting a person detector to cameras of a sensor network. While varying the training data and keeping the detection framework identical, we derive statements about the sample quality.

Proceedings Article | 24 October 2012 Paper

IR-videostream rendering based on high-level object information

Stefan Becker, Wolfgang Hübner, Michael Arens

Proceedings Volume 8541, 85410W (2012) https://doi.org/10.1117/12.973721

KEYWORDS: Sensors, Visualization, Image compression, Quantization, Electroluminescence, Electroluminescent displays, Signal attenuation, High dynamic range imaging, Infrared sensors, Image visualization

Read Abstract +

Proceedings Article | 19 May 2011 Paper

An implicit shape model based approach to identify armed persons

Stefan Becker, Kai Jüngling

Proceedings Volume 8049, 80490O (2011) https://doi.org/10.1117/12.883658

KEYWORDS: Weapons, Prototyping, Sensors, Feature extraction, Thermal modeling, Data modeling, Image classification, Visualization, Infrared radiation, Visible radiation

Read Abstract +

Showing 5 of 11 publications

Conference Committee Involvement (9)

Artificial Intelligence for Security and Defence Applications II

17 September 2024 | Edinburgh, United Kingdom

Artificial Intelligence for Security and Defence Applications

4 September 2023 | Amsterdam, Netherlands

Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies VI

5 September 2022 | Berlin, Germany

Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies V

13 September 2021 | Online Only, Spain

Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies IV

22 September 2020 | Online Only, United Kingdom

Showing 5 of 9 Conference Committees

Keywords/Phrases

Search In:

Publication Years