Spatio-temporal pattern recognition using hidden Markov models

Fielding, Kenneth H.; Ruck, Dennis W.

doi:10.1109/7.464351

Cited by 18 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since hidden states do not necessarily correspond to a physical phenomenon, the number is often empirical. In order for the Baum-Welsh learning algorithm to acquire enough data to assign meaningful probabilities to state transition and observation matrices, each state should be associated with several observations before undergoing a transition to another state [25]. In addition, the estimated log likelihoods p(X|λ d ) and p(X|λ f ) should have a large separation, indicating good discrimination between models.…”

Section: B Hmm Experiments and Resultsmentioning

confidence: 99%

Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning

Williams

Ray

Lever

et al. 2014

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

This paper presents methods to automatically classify ground penetrating radar (GPR) images of crevasses on ice sheets. We use a combination of support vector machines (SVMs) and hidden Markov models (HMMs) with down sampling, a preprocessing step that is unbiased and suitable for real-time analysis and detection. We perform modified crossvalidation experiments with 129 examples of Greenland GPR imagery from 2012, collected by a lightweight robot towing a GPR. In order to minimize false positives, an HMM classifier is trained to prescreen the data and mark locations in the GPR files to evaluate with an SVM, and we evaluate the classification results with a similar modified cross-validation technique. The combined HMM-SVM method retains all of the correct classifications by the SVM, and reduces the false positive rate to 0.0007. This method also reduces the computational burden in classifying GPR traces because the SVM is evaluated only on select prescreened traces. Our experiments demonstrate the promise, robustness, and reliability of real-time crevasse detection and classification with robotic GPR surveys.Index Terms-Geophysical signal processing, ground penetrating radar (GPR), robotic sensing systems.

show abstract

Section: B Hmm Experiments and Resultsmentioning

confidence: 99%

Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning

Williams

Ray

Lever

et al. 2014

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Eleven views sufficed not only for synthetically generated views of the military vehicles, but also for actual video data recorded from a truck and a tank [5]. Using Hidden Markov Models trained using synthetic data, Fielding was able to classify with 100% accuracy the tank and truck, using in each case features extracted from only eleven frames of video.…”

Section: Resultsmentioning

confidence: 99%

“…Fielding has recently implemented a spatio-temporal classifier based on the Hidden Markov Model technique [9] that identifies 3D objects in 2D image sequences [3,5,4,2]. A "viewer centered" approach is adopted placing the object of interest in the center of a transparent sphere [11].…”

Section: Introductionmentioning

confidence: 99%

An application of embedology to spatio-temporal pattern recognition

Stright

Rogers

Quinn

et al. 1996

IEEE Trans. Aerosp. Electron. Syst.

Self Cite

View full text Add to dashboard Cite

The theory of embedded time series is shown applicable for determining a reasonable lower bound on the length of test sequence required for accurate classification of moving objects. Sequentially recorded feature vectors of a moving object form a training trajectory in feature space. Each of the sequences of feature vector components is a time series, and under certain conditions, each of these time series has approximately the same fractal dimension. The embedding theorem may be applied to this fractal dimension to establish a sufficient number of observations to determine the feature space trajectory of the object. It is argued that this number is a reasonable lower bound on test sequence length for use in object classification. Experiments with data corresponding to five military vehicles (observed following a projected Lorenz trajectory on a viewing sphere) show that this bound is indeed adequate.

show abstract

“…Recently, Fielding and Ruck [3,4] demonstrated the use of the 11MM as a spatio-temporal image sequence classifier. The 11MM is a statistical approach that classifies an image sequence based on the probability that this sequence was produced by a given model.…”

Section: Hidden Markov Model (11mm) Classifiermentioning

confidence: 99%

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

Brandstrom¹,

Ruck²,

Rogers³

et al. 1996

SPIE Proceedings

View full text Add to dashboard Cite

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.

show abstract

Spatio-temporal pattern recognition using hidden Markov models

Cited by 18 publications

References 26 publications

Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning

Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning

An application of embedology to spatio-temporal pattern recognition

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

Contact Info

Product

Resources

About