In this contribution new results in the field of video processing regarding the problem of obstacle detection will be presented.
Video sequences obtained from a camera mounted in a driving car are used as the input to a CNN and different templates are applied to extract multiple features from video sequences. Thereby, CNN with nonlinear weight functions have been considered allowing a reliable feature extraction. A detailed discussion of the algorithms and obtained results will be given in this paper.
Cellular Neural Network-Universal Machines (CNN-UM) are analog devices, which are excellently suited for image processing. A big challenge thereby is the determination of CNN templates for special image processing tasks. In many cases appropriate templates can only be found by a parameter optimization. The determination of templates for complex applications in the area of CNN is usually performed by using a CNN software simulator. Unfortunately, in many cases the determined templates cannot be used in hardware realizations of CNN caused by realization effects. In order to find robust templates, which are not only working on CNN simulators, but also on hardware implementations, we present in this contribution a new kind of on-chip-multi-template-training. Furthermore, as a possible application, we will also present a CNN-based solution of the problem of Pattern Matching, which is a processing step in many areas of image processing, like e.g. in Motion Estimation, Image- and Video-Compression.