Towards autonomous habitat classification using Gaussian Mixture Models

Robotic agents that can explore and sample in a completely unsupervised fashion could greatly increase the amount of scientific data gathered in dangerous and inaccessible environments. Our application is imaging the benthos using an autonomous underwater vehicle with limited communication to surface craft. Robotic exploration of this nature demands in situ data analysis. To this end, this paper presents results of using a Gaussian Mixture Model (GMM), a Hidden Markov Model (HMM) filter, an Infinite Gaussian Mixture Model (IGMM) and a Variation Dirichlet Process model (VDP) for the classification of benthic habitats. All of the models are trained using unsupervised methods. Furthermore, the IGMM and VDP are trained without knowing the the number of classes in the dataset. It was found that the sequential information the HMM filter provides to the classification process adds lag to the habitat boundary estimates, reducing the classification accuracy. The VDP proved to be the most accurate classifier of the four tested, and also one of the fastest to train. We conclude that the VDP is a powerful model for entirely autonomous labelling of benthic datasets.

[1]  Stefan B. Williams,et al.  Efficient View-Based SLAM Using Visual Loop Closures , 2008, IEEE Transactions on Robotics.

[2]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[3]  O. Pizarro,et al.  Effective Benthic Surveying with Autonomous Underwater Vehicles , 2007, OCEANS 2007.

[4]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[5]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[6]  Max Welling,et al.  Accelerated Variational Dirichlet Process Mixtures , 2006, NIPS.

[7]  O. Zobay.  Mean field inference for the Dirichlet process mixture model , 2009 .

[8]  Pedro Larrañaga,et al.  An Introduction to Probabilistic Graphical Models , 2002, Estimation of Distribution Algorithms.

[9]  Pietro Perona,et al.  Incremental learning of nonparametric Bayesian mixture models , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  Brian Bingham,et al.  Techniques for Deep Sea Near Bottom Survey Using an Autonomous Underwater Vehicle , 2007, Int. J. Robotics Res..

[12]  Yee Whye Teh,et al.  Collapsed Variational Dirichlet Process Mixture Models , 2007, IJCAI.

[13]  Frederic Py,et al.  Adaptive Control for Autonomous Underwater Vehicles , 2008, AAAI.

[14]  Antonio Torralba,et al.  Context-based vision system for place and object recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Erik B. Sudderth.  Graphical models for visual object recognition and tracking , 2006 .

[16]  M. Johnson-Roberson,et al.  Towards Three-Dimensional Heterogeneous Imaging Sensor Correspondence and Registration for Visualization , 2007, OCEANS 2007 - Europe.

[17]  Stefan B. Williams,et al.  Rugosity, slope and aspect from bathymetric stereo image reconstructions , 2010, OCEANS'10 IEEE SYDNEY.

[18]  C. Roman,et al.  Seabed AUV offers new platform for high‐resolution imaging , 2004 .

[19]  Stefan B. Williams,et al.  Dirichlet process mixture models for autonomous habitat classification , 2010, OCEANS'10 IEEE SYDNEY.

[20]  Carl E. Rasmussen,et al.  The Infinite Gaussian Mixture Model , 1999, NIPS.

[21]  Andrea L. Bertozzi,et al.  Environmental boundary tracking and estimation using multiple autonomous vehicles , 2007, 2007 46th IEEE Conference on Decision and Control.

[22]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[23]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[24]  David S. Wettergreen,et al.  Intelligent Maps for Autonomous Kilometer-Scale Science Survey , 2008 .

[25]  M. McCormick,et al.  Comparison of field methods for measuring surface topography and their associations with a tropical reef fish assemblage , 1994 .

[26]  Peter Norvig,et al.  Artificial intelligence - a modern approach, 2nd Edition , 2003, Prentice Hall series in artificial intelligence.

[27]  Babak Shahbaba,et al.  Improving classification models when a class hierarchy is available , 2007 .

[28]  D. Blackwell,et al.  Ferguson Distributions Via Polya Urn Schemes , 1973 .

[29]  C. Antoniak.  Mixtures of Dirichlet Processes with Applications to Bayesian Nonparametric Problems , 1974 .

[30]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[31]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[32]  Michael I. Jordan,et al.  Variational methods for the Dirichlet process , 2004, ICML.

[33]  Michael A. West,et al.  Hierarchical priors and mixture models, with applications in regression and density estimation , 2006 .

[34]  W. Gilks,et al.  Adaptive Rejection Sampling for Gibbs Sampling , 1992 .