A stochastic version of the delta rule
CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
Creating artificial neural networks that generalize
Neural Networks
Adaptive filter theory (3rd ed.)
Adaptive filter theory (3rd ed.)
Noise injection: theoretical prospects
Neural Computation
The visual analysis of human movement: a survey
Computer Vision and Image Understanding
Human motion analysis: a review
Computer Vision and Image Understanding
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Principles of Neurocomputing for Science and Engineering
Principles of Neurocomputing for Science and Engineering
3-D model-based tracking of humans in action: a multi-view approach
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Problems, ongoing research and future directions in motion research
Machine Vision and Applications - Special issue: Human modeling, analysis, and synthesis
Hi-index | 0.00 |
In this letter, we demonstrate that the generalization properties of a neural network (NN) can be extended to encompass objects that obscure or segment the original image in its foreground or background. We achieve this by piloting an extension of the noise injection training technique, which we term excessive noise injection (ENI), on a simple feedforward multilayer perceptron (MLP) network with vanilla backward error propagation to achieve this aim. Six tests are reported that show the ability of an NN to distinguish six similar states of motion of a simplified human figure that has become obscured by moving vertical and horizontal bars and random blocks for different levels of obscuration. Four more extensive tests are then reported to determine the bounds of the technique. The results from the ENI network were compared to results from the same NN trained on clean states only. The results pilot strong evidence that it is possible to track a human subject behind objects using this technique, and thus this technique lends itself to a real-time markerless tracking system from a single video stream.