Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments

• Published in: Neural computation Vol. 18; no. 9; pp. 2122 - 2145
• Main Authors: Unsworth, C. P., Coghill, G.
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.09.2006; MIT Press Journals, The
• Subjects: Applied sciences; Artificial intelligence; Biological and medical sciences; Brain; Computer science; control theory; systems; Electricity; Environment; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; General aspects. Models. Methods; Human subjects; Inference from stochastic processes; time series analysis; Learning and adaptive systems; Letters; Mathematics; Neural networks; Neural Networks (Computer); Neurons; Photic Stimulation - methods; Probability and statistics; Sciences and techniques of general use; Statistics; Tests; Vertebrates: nervous system and sense organs; Human; Motion; Neural computation; Tracking; Multilayer; Error estimation; Multilayer perceptrons; Neural network; Real time system; Multilayer network
• ISSN: 0899-7667; 1530-888X
• DOI: 10.1162/neco.2006.18.9.2122

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 (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.