Hierarchical feed-forward network for object detection tasks

Hierarchical feed-forward network for object detection tasks

Ingo Bax Gunther Heidemann Helge Ritter Bielefeld University Neuroinformatics Group Faculty of Technology P.O. Box 10 01 31 D-33501 Bielefeld, Germany E-mail: [email protected] Abstract. Recent research on neocognitron-like neural feed-forward architectures, which have formerly been successfully applied to the recognition of artificial stimuli such as paperclip objects, now also ope...

Hierarchical feed forward models for robust object recognition

Using Feed-Forward Neural Networks for Data Association on Multi-Object Tracking Tasks

This article presents an approach for data association in single camera, multi-object tracking scenarios using feed-forward neural networks (FFNN). The challenges of data association are object occlusions and changing features which are used to describe objects during the process. The presented algorithm within this article can be applied to any kind of object which has to be tracked, e.g. pers...

Sensitive signal detection using a feed-forward oscillator network.

We present the results of an experimental investigation of a network of nonlinear coupled oscillators which are coupled in feed-forward mode. By exploiting the nonlinear response of each oscillator near its intrinsic Hopf bifurcation point, we have found remarkable amplification of small signals over a narrow bandwidth with a large dynamic range. The effect is exploited to extract a small ampli...

A feed-forward neural network approach to edge detection

This paper presents a novel edge detector based on Feed-Forward Neural Networks (FFNNs). The FFNN computing architecture has two stages, which is a feature enhancement stage as well as a structural boundary extraction stage. The first stage is a traditional supervised BP network, and the second one is manually designed without training. Experiments based on both synthetic and natural images sho...