BRBernd Radig

Bernd Radig

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bernd Radig has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Image Mining: Current Problems in Theory and Applications

    by Igor Gurevich, Davide Moroni, Maria Antonietta Pascali, Bernd Radig, Vera Yashina

  • Automated Visual Large Scale Monitoring of Faunal Biodiversity

    by Bernd Radig, Paul Bodesheim, Dimitri Korsch, Joachim Denzler, Timm Haucke, Morris Klasen, Volker Steinhage

    To observe biodiversity, the variety of plant and animal life in the world or in a particular habitat, human observers make the most common examinations, often assisted by technical equipment. Measuring objectively the number of different species of animals, plants, fungi, and microbes that make up the ecosystem can be difficult. In order to monitor changes in biodiversity, data have to be compared across space and time. Cameras are an essential sensor to determine the species range, abundance, and behavior of animals. The millions of recordings from camera traps set up in natural environments can no longer be analyzed by biologists. We started research on doing this analysis automatically without human interaction. The focus of our present sensor is on image capture of wildlife and moths. Special hardware elements for the detection of different species are designed, implemented, tested, and improved, as well as the algorithms for classification and counting of samples from images and image sequences, e.g., to calculate presence, absence, and abundance values or the duration of characteristic activities related to the spatial mobilities. For this purpose, we are developing stereo camera traps that allow spatial reconstruction of the observed animals. This allows three-dimensional coordinates to be recorded and the shape to be characterized. With this additional feature data, species identification and movement detection are facilitated. To classify and count moths, they are attracted to an illuminated screen, which is then photographed at intervals by a high-resolution color camera. To greatly reduce the volume of data, redundant elements and elements that are consistent from image to image are eliminated. All design decisions take into account that at remote sites and in fully autonomous operation, power supply on the one hand and possibilities for data exchange with central servers on the other hand are limited. Installation at hard-to-reach locations requires a sophisticated and demanding system design with an optimal balance between power requirements, bandwidth for data transmission, required service and operation in all environmental conditions for at least ten years.


  • Detection of Individual Ball Possession in Soccer

    by Martin Hoernig, Daniel Link, Michael Herrmann, Bernd Radig, Martin Lames


  • Real-time segmentation methods for monocular soccer videos

    by M. Hoernig, M. Herrmann, B. Radig

    The analysis of video records of soccer games is a topic of extensive and challenging research in image sequence processing, particularly that of player and field tracking. In this paper, we propose a new approach for detecting players and field lines in monocular TV video data that involves determining the convex field area and grass colors. This is carried out by considering contextual knowledge, together with a new method for color segmentation that selects polyhedrons in a frame-wise manner within the RGB cube. In summary, for every input image, a binary mask of the field area and a background mask are determined. Both mask creation algorithms achieve per pixel F1 scores of about 98% within our representative test set and are real-time capable. Applications like line detection and player tracking are presented.


  • Automatic generation of image analysis programs

    by M. Herrmann, C. Mayer, B. Radig

    In this paper, we introduce a system that generates computer vision programs for a given task, which is specified by regions of interest in a collection of example images. The system relies on a database of operators, which are combined by an automated planning approach in order to create executable programs. We present an early proof-of-concept implementation that relies on a limited database to solve simple tasks, such as finding players in a soccer video or cups on a table. Our experimental evaluation shows that the basic approach is working on relative simple scenarios. Future work will focus on integrating more complex problem descriptions, which require more sophisticated planning strategies in order to compensate for rapidly increasing search spaces.


  • Cross-database evaluation for facial expression recognition

    by C. Mayer, M. Eggers, B. Radig

    We present a system for facial expression recognition that is evaluated on multiple databases. Automated facial expression recognition systems face a number of characteristic challenges. Firstly, obtaining natural training data is difficult, especially for facial configurations expressing emotions like sadness or fear. Therefore, publicly available databases consist of acted facial expressions and are biased by the authors’ design decisions. Secondly, evaluating trained algorithms towards real-world behavior is challenging, again due to the artificial conditions in available image data. To tackle these challenges and since our goal is to train classifiers for an online system, we use several databases in our evaluation. Comparing classifiers across data-bases determines the classifiers capability to generalize more reliable than traditional self-classification.


  • Setup and calibration of a distributed camera system for surveillance of laboratory space

    by M. Eggers, V. Dikov, C. Mayer, C. Steger, B. Radig

    This paper describes the setup and realization of a distributed camera system designed to survey a laboratory area where humans and mobile manipulator robots collaborate jointly. The system consists of 40 industrial grade cameras surveying a 10 m by 10 m area from a top-down perspective, connected via Gigabit Ethernet (GigE) to a cluster of 40 computers for distributed image processing. The cameras were fully calibrated, achieving an average reprojection error of 0.13 pixels for the complete system, which exceeds state-of-the art accuracy. Current long-term testing has the system running with at least 99.994% availability for up to two weeks. Successful application tests of the system were conducted, where it was used to track the movements of robots and humans across the surveyed area.


  • Face model fitting with learned displacement experts and multi-band images

    by Ch. Mayer, B. Radig

    Analyzing human faces is a traditional topic in computer vision research. For this task, model based approaches have been proven adequate to extract high-level information in many applications. However, they require a robust estimation of model parameters to work reliably. To tackle this challenge, we train displacement experts that serve as an update function on initial model parameter configurations. Unfortunately, building displacement experts that work robustly even in unconstrained environments is a non-trivial task. Therefore, we rely on a priori information about the structure of human faces by integrating an image representation that reflects the location of several facial components, so called “multi-band images”. By combining multi-band images and learned displacement experts, we propose a novel face model fitting approach. An evaluation on the “Labeled Faces In The Wild” database demonstrates, that this approach provides robust fitting results even in unconstrained environments.

  • Perception as a key component for cognitive technical systems

    by B. Radig, C. Mayer

    Cognitive capabilities such as perception, reasoning, learning, and planning turn technical systems into systems that “know what they are doing.” Starting from the human brain the Cluster of Excellence “CoTeSys” investigates cognition for technical systems such as vehicles, robots, and factories. Technical systems that are cognitive will be much easier to interact and cooperate with, and will be more robust, flexible, and efficient. For understanding their environment and interacting with humans the cognitive system’s most important sense is the visual one. The talk presents recent results using the visual sensor in building environment models, self localization of autonomous moving robots, navigation, simultaneous tracking of groups of humans and robots, face detection and evaluation of gaze direction and facial expression, and emotional communication between humans and robots.

  • 3D Face Modeling for Multi-Feature Extraction for Intelligent Systems

    by Zahid Riaz, Suat Gedikli, Michael Beetz, Bernd Radig

    3D Face Modeling for Multi-Feature Extraction for Intelligent Systems: 10.4018/978-1-60960-024-2.ch005: In this chapter, we focus on the human robot joint interaction application where robots can extract the useful multiple features from human faces. The idea