research-article

Using Clustering and Metric Learning to Improve Science Return of Remote Sensed Imagery

Authors:

David S. Hayden,

David R. Thompson,

Rebecca CastañoAuthors Info & Claims

ACM Transactions on Intelligent Systems and Technology (TIST), Volume 3, Issue 3

Article No.: 51, Pages 1 - 19

https://doi.org/10.1145/2168752.2168765

Published: 01 May 2012 Publication History

Abstract

Current and proposed remote space missions, such as the proposed aerial exploration of Titan by an aerobot, often can collect more data than can be communicated back to Earth. Autonomous selective downlink algorithms can choose informative subsets of data to improve the science value of these bandwidth-limited transmissions. This requires statistical descriptors of the data that reflect very abstract and subtle distinctions in science content. We propose a metric learning strategy that teaches algorithms how best to cluster new data based on training examples supplied by domain scientists. We demonstrate that clustering informed by metric learning produces results that more closely match multiple scientists’ labelings of aerial data than do clusterings based on random or periodic sampling. A new metric-learning strategy accommodates training sets produced by multiple scientists with different and potentially inconsistent mission objectives. Our methods are fit for current spacecraft processors (e.g., RAD750) and would further benefit from more advanced spacecraft processor architectures, such as OPERA.

References

[1]

Arthur, D., Manthey, B., and Roglin, H. 2009. k-Means has polynomial smoothed complexity. In Proceedings of the 50th Annual IEEE Symposium on Foundations of Computer Science. IEEE, 405--414.

Digital Library

[2]

Averbuch, A., Gabber, E., Gordissky, B., and Medan, Y. 1990. A parallel FFT on an MIMD machine* 1. Parall. Comput. 15, 1--3, 61--74.

[3]

Burghouts, G. and Geusebroek, J. 2009. Performance evaluation of local colour invariants. Comput. Vision Image Understand. 113, 1, 48--62.

Digital Library

[4]

Calderon, F., Thompson, D. R., and Wettergreen, D. 2008. Autonomous rover reflectance spectroscopy with dozens of targets. In Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space (iSAIRAS).

[5]

Castano, A., Fukunaga, A., Biesiadecki, J., Neakrase, L., Whelley, P., Greeley, R., Lemmon, M., Castano, R., and Chien, S. 2008. Automatic detection of dust devils and clouds on Mars. Machine Vision Appl. 19, 5--6, 467--482.

Digital Library

[6]

Castaño, R., Judd, M., Anderson, R., and Estlin, T. 2003. Machine learning challenges in Mars rover traverse science. In Proceedings of the ICML Workshop on Machine Learning Technologies for Autonomous Space.

[7]

Castaño, R., Estlin, T., Anderson, R. C., Gaines, D. M., Castano, A., Bornstein, B., Chouinard, C., and Judd, M. 2007. Oasis: Onboard autonomous science investigation system for opportunistic rover science. J. Field Robotics, 379--397.

Digital Library

[8]

Chen, J., Zhao, Z., Ye, J., and Liu, H. 2007. Nonlinear adaptive distance metric learning for clustering. In Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 123--132.

Digital Library

[9]

Chen, L., Liao, H., Ko, M., Lin, J., and Yu, G. 2000. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recog. 33, 10, 1713--1726.

[10]

Chien, S., Sherwood, R., Tran, D., Cichy, B., Rabideau, G., Castano, R., Davies, A., Mandl, D., Frye, S., Trout, B., et al. 2005. Using autonomy flight software to improve science return on Earth Observing One. J. Aerospace Comput. Infor. Comm. 2, 4, 196--216.

[11]

Clough, B. 2002. Metrics, schmetrics! How the heck do you determine a UAV’s autonomy anyway. In Proceedings of the Performance Metrics for Intelligent Systems Workshop.

[12]

Duda, R., Hart, P., and Stork, D. 2000. Pattern Classification. Wiley-Interscience, New York, NY.

Digital Library

[13]

Duin, R. and Loog, M. 2004. Linear dimensionality reduction via a heteroscedastic extension of LDA: The Chernoff criterion. IEEE Trans. Pattern Anal. Machine Intell. 26, 6, 732--739.

Digital Library

[14]

Dvorak, D. et al. 2009. NASA study on flight software complexity.

[15]

Elfes, A., Hall, J., Kulczycki, E., Clouse, D., Morfopoulos, A., Montgomery, J., Cameron, J., Ansar, A., and Machuzak, R. 2008. Autonomy architecture for aerobot exploration of Saturnian moon Titan. IEEE Aerospace and Electronic Systems Mag. 23, 7, 16--24.

[16]

Elkan, C. 2003. Using the triangle inequality to accelerate k-means. In Proceedings of the Internatinoal Conference on Machine Learning. Vol. 20, 147--153.

[17]

Estlin, T., Bornstein, B., Gaines, D., Thompson, D., Castaño, R., Anderson, R., de Granville, C., Burl, M., Judd, M., and Chien, S. 2010. Aegis automated targeting for the MER opportunity rover. In Proceedings of the International Symposium on Space Artificial Intelligence, Robotics, and Automation for Space.

[18]

Friedman, J. 1989. Regularized discriminant analysis. J. Amer. Stat. Assoc. 84, 405, 165--175.

[19]

Gersho, A. and Gray, R. 1992. Vector Quantization and Signal Compression. Springer, Berlin.

Digital Library

[20]

Gilmore, M., Castaño, R., Mann, T., Anderson, R., Mjolsness, E., Manduchi, R., and Saunders, R. 2000. Strategies for autonomous rovers at Mars. J. Geophysical Res.-Planets.

[21]

Goldberger, J., Roweis, S., Hinton, G., and Salakhutdinov, R. 2005. Neighbourhood components analysis. In Advances in Neural Information Processing Systems 17, L. K. Saul, Y. Weiss, and L. Bottou Eds., MIT Press, Cambridge, MA, 513--520.

Digital Library

[22]

Grigorescu, S., Petkov, N., and Kruizinga, P. 2002. Comparison of texture features based on gabor filters. IEEE Trans. Image Process. 11, 10, 1160--1167.

Digital Library

[23]

Guo, Y., Hastie, T., and Tibshirani, R. 2007. Regularized linear discriminant analysis and its application in microarrays. Biostatistics 8, 1, 86.

[24]

Hamsici, O. and Martinez, A. 2007. Bayes optimality in linear discriminant analysis. IEEE Trans. Pattern Anal. Mach. Intell. 647--657.

Digital Library

[25]

Hayden, D. S., Chien, S., Thompson, D. R., and Castano, R. 2010. Onboard clustering of aerial data for selective data return. In Proceedings of the 10th International Symposium on Artificial Intelligence, Robotics, and Automation in Space.

[26]

Howland, P., Jeon, M., and Park, H. 2004. Structure preserving dimension reduction for clustered text data based on the generalized singular value decomposition. SIAM J. Matrix Anal. Appl. 25, 1, 165--179.

Digital Library

[27]

Huang, J., Kumar, S., Mitra, M., Zhu, W., and Zabih, R. 1997. Image indexing using color correlograms. In Proceedings of the Computer Vision and Pattern Recognition. IEEE Computer Society, 762.

Digital Library

[28]

Hubert, L. and Arabie, P. 1985. Comparing partitions. J. Classification 2, 193--218.

[29]

Jain, P., Kulis, B., Dhillon, I. S., and Grauman, K. 2009. Online metric learning and fast similarity search. In Advances in Neural Information Processing Systems 21, D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou Eds., 761--768.

[30]

Julesz, B. 1981. Textons, the elements of texture perception, and their interactions. Nature 290, 5802, 91.

[31]

Kinsey, J., Eustice, R., and Whitcomb, L. 2006. A survey of underwater vehicle navigation: Recent advances and new challenges. In Proceedings of the 7th Conference on Manuevering and Control of Marine Craft (MCMC’06).

[32]

Liu, S. and Jernigan, M. 1990. Texture analysis and discrimination in additive noise. Comput. Vision Graph. Image Process. 49, 1, 52--67.

Digital Library

[33]

Lloyd, S. 1982. Least square quantization in pcm. IEEE Trans. Inform. Theor. 28.

Digital Library

[34]

Lowe, D. 1999. Object recognition from local scale-invariant features. In Proceedings of the International Conference on Computer Vision. IEEE Computer Society, 1150.

Digital Library

[35]

MacQueen, J. et al. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. Vol. 1, 14.

[36]

Manjunath, B. and Ma, W. 2002. Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18, 8, 837--842.

Digital Library

[37]

NASA. 2006. 2006 solar system exploration roadmap. Tech. rep., NASA, Washington, D.C.

[38]

Qin, A., Suganthan, P., and Loog, M. 2005. Uncorrelated heteroscedastic LDA based on the weighted pairwise Chernoff criterion. Pattern Recog. 38, 4, 613--616.

Digital Library

[39]

Rubner, Y., Tomasi, C., and Guibas, L. 2000. The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vision 40, 2, 99--121.

Digital Library

[40]

Saegusa, T. and Maruyama, T. 2007. An FPGA implementation of k-means clustering for color images based on Kd-tree. In Proceedings of the International Conference on Field Programmable Logic and Applications (FPL’06). IEEE, 1--6.

[41]

Stoffel, K. and Belkoniene, A. 1999. Parallel k/h-means clustering for large data sets. In Proceedings of the Euro-Par’99 Conference on Parallel Processing. 1451--1454.

Digital Library

[42]

Thompson, D., Smith, T., and Wettergreen, D. 2008. Information-optimal selective data return for autonomous rover traverse science and survey. In Proceedings of the International Conference on Robotics and Automation (ICRA’08). IEEE, 968--973.

[43]

Thrun, S., Thayer, S., Whittaker, W., Baker, C., Burgard, W., Ferguson, D., Hahnel, D., Montemerlo, D., Morris, A., Omohundro, Z., et al. 2005.Autonomous exploration and mapping of abandoned mines. IEEE Robot. Automation Mag. 11, 4, 79--91.

[44]

Tuytelaars, T. and Mikolajczyk, K. 2008. Local invariant feature detectors: A survey. Found. Trends® in Comput. Graph. Vision 3, 3, 177--280.

Digital Library

[45]

Vinh, N. X., Epps, J., and Bailey, J. 2009. Information theoretic measures for clusterings comparison: Is a correction for chance necessary? In Proceedings of the 26th International Conference on Machine Learning. L. Bottou and M. Littman Eds., 1073--1080.

Digital Library

[46]

Weinberger, K., Blitzer, J., and Saul, L. 2006. Distance metric learning for large margin nearest neighbor classification. In Advances in Neural Information Processing Systems 18, Y. Weiss, B. Schölkopf, and J. Platt Eds., MIT Press, Cambridge, MA, 1473--1480.

[47]

Wettergreen, D., Wagner, M. D., Jonak, D., Baskaran, V., Deans, M., Heys, S., Pane, D., Smith, T., Teza, J., Thompson, D. R., Tompkins, P., and Williams, C. 2008. Long-distance autonomous survey and mapping in the robotic investigation of life in the atacama desert. In Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space (iSAIRAS).

[48]

Xing, E., Ng, A., Jordan, M., and Russell, S. 2002. Distance metric learning, with application to clustering with side-information. In Advances in Neural Information Processing Systems 16, S. Becker, S. Thrun, and K. Obermayer Eds., MIT Press, Cambridge, MA, 521--528.

[49]

Xu, R. and Wunsch, D. 2005. Survey of clustering algorithms. IEEE Trans. Neural Netw. 16, 3, 645--678.

Digital Library

[50]

Yang, L. 2007. An overview of distance metric learning. In Proceedings of the Computer Vision and Pattern Recognition Conference.

[51]

Yang, L. and Jin, R. 2007. Bayesian active distance metric learning. In Proceedings of the Uncertainty in Artificial Intelligence.

[52]

Ye, J. 2006. Characterization of a family of algorithms for generalized discriminant analysis on undersampled problems. J. Mach. Learn. Res. 6, 1, 483.

Digital Library

Cited By

Kim KKim KLee S(2024)PRISM: Deep metric learning based personal grouping method to reduce intersubject variability for motor imagery brain-computer interfaceNeurocomputing10.1016/j.neucom.2024.127805(127805)Online publication date: May-2024
https://doi.org/10.1016/j.neucom.2024.127805
Grande MGuo LBlanc MAlves JMakaya AAsmar SAtkinson DBourdon AChabert PChien SDay JFairén AFreeman AGenova AHerique AKofman WLazio JMousis OOri GParro VPreston RRodriguez-Manfredi JJ. Sterken VStephenson KHook JWaite JZine S(2023)Enabling technologies for planetary explorationPlanetary Exploration Horizon 206110.1016/B978-0-323-90226-7.00002-7(249-329)Online publication date: 2023
https://doi.org/10.1016/B978-0-323-90226-7.00002-7
Chien SWagstaff K(2017)Robotic space exploration agentsScience Robotics10.1126/scirobotics.aan48312:7Online publication date: 28-Jun-2017
https://doi.org/10.1126/scirobotics.aan4831
Show More Cited By

Index Terms

Using Clustering and Metric Learning to Improve Science Return of Remote Sensed Imagery
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Robotics
      1. Robotic autonomy

Recommendations

Enabling Onboard Detection of Events of Scientific Interest for the Europa Clipper Spacecraft
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Data analysis and machine learning methods have great potential to aid in planetary exploration. Spacecraft often operate at great distances from the Earth, and the ability to autonomously detect features of interest onboard can enable content-sensitive ...
Using Onboard Clustering to Summarize Remotely Sensed Imagery

Many current and future space missions can collect far more data than can be returned to Earth for analysis by scientists. To address this situation, the Jet Propulsion Laboratory has developed computationally efficient algorithms for analyzing science ...
Self-Organizing-Map Based Clustering Using a Local Clustering Validity Index

Classical clustering methods, such as partitioning and hierarchical clustering algorithms, often fail to deliver satisfactory results, given clusters of arbitrary shapes. Motivated by a clustering validity index based on inter-cluster and intra-cluster ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Intelligent Systems and Technology

ACM Transactions on Intelligent Systems and Technology Volume 3, Issue 3

May 2012

384 pages

ISSN:2157-6904

EISSN:2157-6912

DOI:10.1145/2168752

Issue’s Table of Contents

Copyright © 2012 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 May 2012

Accepted: 01 September 2011

Revised: 01 July 2011

Received: 01 January 2011

Published in TIST Volume 3, Issue 3

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
212
Total Downloads

Downloads (Last 12 months)10
Downloads (Last 6 weeks)0

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Kim KKim KLee S(2024)PRISM: Deep metric learning based personal grouping method to reduce intersubject variability for motor imagery brain-computer interfaceNeurocomputing10.1016/j.neucom.2024.127805(127805)Online publication date: May-2024
https://doi.org/10.1016/j.neucom.2024.127805
Grande MGuo LBlanc MAlves JMakaya AAsmar SAtkinson DBourdon AChabert PChien SDay JFairén AFreeman AGenova AHerique AKofman WLazio JMousis OOri GParro VPreston RRodriguez-Manfredi JJ. Sterken VStephenson KHook JWaite JZine S(2023)Enabling technologies for planetary explorationPlanetary Exploration Horizon 206110.1016/B978-0-323-90226-7.00002-7(249-329)Online publication date: 2023
https://doi.org/10.1016/B978-0-323-90226-7.00002-7
Chien SWagstaff K(2017)Robotic space exploration agentsScience Robotics10.1126/scirobotics.aan48312:7Online publication date: 28-Jun-2017
https://doi.org/10.1126/scirobotics.aan4831
Zhao ZJiao LZhao JGu JZhao J(2017)Discriminant deep belief network for high-resolution SAR image classificationPattern Recognition10.1016/j.patcog.2016.05.02861:C(686-701)Online publication date: 1-Jan-2017
https://dl.acm.org/doi/10.1016/j.patcog.2016.05.028

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents