<title>Space object identification using spatiotemporal pattern recognition</title>

Abstract

This paper demonstrates the application of new pattern recognition techniques that can be used to characterize space objects. The feature space trajectory neural network (FST NN) was first presented by Leonard Neiberg and David P. Casasent in 1994 as a target identification tool. Kenneth H. Fielding and Dennis W. Ruck recently applied the hidden Markov model (HMM) classifier to a 3D moving light display identification problem and a target recognition problem, using time history information to improve classification results. This paper shows how the FST NN and HMM can be used to automate optical detection of space object anomalies. Time sequenced images produced by a simulation program are used for testing these anomaly detection algorithms. Two data sets are tested. The second data set is tested with various levels of shot noise. The first data set is more difficult to classify, with the best FST NN test achieving a 100% anomaly detection rate with 5% false alarm rate. FST NN and HMM tests on the second data set achieved 100% anomaly detection with no false alarms. With various levels of shot noise added, the FST NN achieves a 100% anomaly detection rate with 4% false alarm rate. A variety of Fourier features are tested with energy normalized low frequency coefficients producing the best consistent results across data sets and noise levels.A new FST NN test is presented that measures how well the order of a test sequence matches other sequences in the database. The original FST NN is based strictly on feature space distance, but when the order of the sequence is important, the new test is useful.

<title>Feature spacing trajectory representation and processing for active vision</title>

“…As the aspect angle (0) changes, the feature point moves from O to 63°, then back to the center of the FST (for 0 = 900), then back to the 63° point for 9 = 900 + 27° = 117°, etc. Other work [11] has shown that FSTs give better P with fewer training set views and perform better in noise compared to aspect graphs using hidden Markov models. we showed that use of 11 aspect views over gives a negligible 3% difference in the values of each feature.…”

Global feature space neural network for active object recognition

“…In the case of socket 1 object in Fig. 1b, the section of the FST for views near 8 6 A is very close to the section of the FST for views around…”

“…There, the emphasis was on classification rather than pose estimation. Prior work showed that the FST gave superior performance compared to other classifiers [7,8], and overcomes problems that other classifiers have including: small training set size, ad hoc parameter selection, poor generalization, selecting the number of hidden layers, estimating distributions etc.…”