Thomas Kalinke

Ruhr-Universität Bochum, Bochum, North Rhine-Westphalia, Germany

Are you Thomas Kalinke?

Claim your profile

Publications (14)5.02 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: . Systems for automated image analysis are useful for a variety
    08/2001;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In previous years, many methods providing the ability to recognize rigid obstacles-sedans and trucks-have been developed. These methods provide the driver with relevant information. They are able to cope reliably with scenarios on motorways. Nevertheless, not much attention has been given to image processing approaches to increase the safety of pedestrians in urban environments. In the paper, a method for the detection, tracking, and final recognition of pedestrians crossing the moving observer's trajectory is suggested. A combination of data- and model-driven approaches is realized. The initial detection process is based on a fusion of texture analysis, model-based grouping of, most likely, the geometric features of pedestrians, and inverse-perspective mapping (binocular vision). Additionally, motion patterns of limb movements are analyzed to determine initial object-hypotheses. The tracking of the quasirigid part of the body is performed by different algorithms that have been successfully employed for the tracking of sedans, trucks, motorbikes, and pedestrians. The final classification is obtained by a temporal analysis of the walking process
    IEEE Transactions on Intelligent Transportation Systems 10/2000; · 3.06 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To reduce the number of traffic accidents and to increase the drivers comfort, the thought of designing driver assistance systems arose in the past years. Fully or partly autonomously guided vehicles, particularly for road traffic, pose high demands on the development of reliable algorithms. Principal problems are caused by having a moving observer in predominantly natural environments. At the Institut fur Neuroinformatik methods for analyzing driving relevant scenes by computer vision are developed in cooperation with several partners from the automobile industry. We present a solution for a driver assistance system. We concentrate on the aspects of video-based scene analysis and organization of behavior
    Image Processing, 2000. Proceedings. 2000 International Conference on; 02/2000
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Systems for automated image analysis are useful for a variety of tasks. Their importance is still growing due to technological advances and increased social acceptance. Especially driver assistance systems have reached a high level of sophistication. Fully or partly autonomously guided vehicles, particularly for road traffic, require highly reliable algorithms due to the conditions imposed by natural environments. At the Institut fur Neuroinformatik, methods for analyzing driving relevant scenes by computer vision are developed in cooperation with several partners from the automobile industry. We present a system extracting important information from an image taken by a CCD camera installed at the rear-view mirror in a car. The approach is divided into a sequential and a parallel phase of sensor and information processing. Three main tasks, namely initial segmentation (object detection), object tracking and object classification are realized by integration in the sequential phase and by fusion in the parallel phase. The main advantage of this approach is integrative coupling of different algorithms providing partly redundant information. q 2000 Elsevier Science B.V. All rights reserved.
    Image and Vision Computing 01/2000; 18:367-376. · 1.96 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Systems for automated image analysis are useful for a variety of tasks and their importance is still increasing due to technological advances and an increase of social acceptance. Especially in the field of driver assistance systems the progress in science has reached a level of high performance. Fully or partly autonomously guided vehicles, particularly for road-based traffic, pose high demands on the development of reliable algorithms due to the conditions imposed by natural environments. At the Institut fur Neuroinformatik, methods for analyzing driving relevant scenes by computer vision are developed in cooperation with several partners from the automobile industry. We introduce a system which extracts the important information from an image taken by a CCD camera installed at the rear view mirror in a car. The approach consists of a sequential and a parallel sensor and information processing. Three main tasks namely the initial segmentation (object detection), the object tracking an...
    Proc SPIE 11/1999;
  • Mustererkennung 1999, 21. DAGM-Symposium, Bonn, 15.-17. September 1999, Proceedings; 01/1999
  • [Show abstract] [Hide abstract]
    ABSTRACT: This work is a part of a vehicle driver assistance system developed at the Institut f#ur Neuroinformatik. It is a concept to expand the driver assistance already existing. In the actual production series of vehicles mainly sensors like radar and sensors for detecting the weather conditions are used to get the driving relevant information. The use of digital image processing expands the spectrum of information signi#cantly. The main goal herein is to detect and classify obstacles in the vehicle environment to assist the driver in his decision process of driving behavior. Images are acquired by a CCD camera installed at the rear view mirror and observes the area in front of the vehicle. Without any constraints the presented method is applicable to the rear view, too. The main goals of object detection and classi#cation are solved. The object detection is based on texture measurements and the determination of object types is done by a matching process. The highly non-linear function betwe...
    12/1998;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Systems for automated image analysis are useful for a vari- ety of tasks and their importance is still growing due to technological advances and an increase of social acceptance. Especially in the eld of driver assistance systems the progress in science has reached a level of high performance. Fully or partly autonomously guided vehicles, par- ticularly for road-based trac, pose high demands on the development of reliable algorithms due to the conditions imposed by natural envi- ronments. At the Institut fur Neuroinformatik methods for analyzing driving relevant scenes by computer vision are developed in cooperation with several partners from the automobile industry. We introduce a sys- tem which extracts the important information from an image taken by a CCD camera installed at the rear view mirror in a car. The approach consists of a sequential and a parallel sensor and information processing. Three main tasks namely the initial segmentation (object detection), the object tracking and the object classication are realized by integration in the sequential branch and by fusion in the parallel branch. The main gain of this approach is given by the integrative coupling of dierent algorithms providing partly redundant information. Some systems presented in ref. (4, 23, 3) show the principal feasibility of driver assistance systems based on computer vision. Although exclusively vision based systems and algorithms are not yet powerful enough to solve all driving rele- vant tasks, a large amount of dierent scenarios can be interpreted suciently. Additionally sensors like RADAR and LIDAR extent the contents of sensor in- formation necessary for building a reliable system. The main focus of our system lies in combining various methods for the analysis and interpretation of images and in the fusion of a large spectrum of sensor data to extract most reliable in- formation for the nal planning and for predicting of behavior of other vehicles. The great variety of dierent scenarios as well as the high degree of reliability necessary for the given task require an encompassing and flexible system ar- chitecture. The requirements concerning the reliability of the reached solution, the variety of geometric appearances of involved objects and the environmen- tal constraints of both deterministic as well as statistical nature necessitate a multitude of partial solutions based on dierent representations of the environ- ment. Consequently, complexity and structure of the overall system have to be
    Mustererkennung 1998, 20. DAGM-Symposium, Stuttgart, 29. September - 1. Oktober 1998, Proceedings; 01/1998
  • Source
    U. Handmann, T. Kalinke
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new approach to object detection based on data fusion of texture and edge information. A self organizing Kohonen map is used as the coupling element of the different representations. Therefore, an extension of the proposed architecture incorporating other features, even features not derived from vision modules, is straight forward. It simplifies to a redefinition of the local feature vectors and a retraining of the network structure. The resulting hypotheses of object locations generated by the detection process are finally inspected by a neural network classifier based on co-occurence matrices
    Intelligent Transportation System, 1997. ITSC '97., IEEE Conference on; 12/1997
  • Thomas Kalinke, Werner von Seelen
    Mustererkennung 1997, 19. DAGM-Symposium, Braunschweig 15.-17. September 1997, Proceedings; 01/1997
  • Source
    Thomas Kalinke, Werner von Seelen
    Mustererkennung 1996, 18. DAGM-Symposium, Heidelberg, 11.-13. September 1996, Proceedings; 01/1996
  • Thomas Kalinke, Werner von Seelen
    Mustererkennung 1996, 18. DAGM-Symposium, Heidelberg, 11.-13. September 1996, Proceedings; 01/1996
  • [Show abstract] [Hide abstract]
    ABSTRACT: Systems for automated image analysis are useful for a variety of tasks and their importance is still growing due to technological advances and an increase of social acceptance. Especially in the field of driver assistance systems the progress in science has reached a level of high performance. Fully or partly autonomously guided vehicles, particularly for road-based traffic, pose high demands on the development of reliable algorithms due to the conditions imposed by natural environments. At the Institut fur Neuroinformatik methods for analyzing driving relevant scenes by computer vision are devel- oped in cooperation with several partners from the au- tomobile industry. We introduce a system which ex- tracts the important information from an image taken by a CCD camera installed at the rear view mirror in a car. The approach consists of a sequential and a paral- lel sensor and information processing. Three main tasks namely the initial segmentation (object detection), the object tracking and the object classification are realized by integration in the sequential branch and by fusion in the parallel branch. The main gain of this approach is given by the integrative coupling of different algorithms providing partly redundant information. Keywords— Driver Assistance, Machine Vision, Data Fusion.
  • T. Kalinke, C. Tzomakas