Automated rock detection and shape analysis from mars rover imagery and 3D point cloud data

Abstract

A new object-oriented method has been developed for the extraction of Mars rocks from Mars rover data. It is based on a combination of Mars rover imagery and 3D point cloud data. First, Navcam or Pancam images taken by the Mars rovers are segmented into homogeneous objects with a mean-shift algorithm. Then, the objects in the segmented images are classified into small rock candidates, rock shadows, and large objects. Rock shadows and large objects are considered as the regions within which large rocks may exist. In these regions, large rock candidates are extracted through ground-plane fitting with the 3D point cloud data. Small and large rock candidates are combined and postprocessed to obtain the final rock extraction results. The shape properties of the rocks (angularity, circularity, width, height, and width-height ratio) have been calculated for subsequent geological studies.

Keywords

Mars rover / rock extraction / rover image / 3D point cloud data.

References

[1] Alexander D A, Deen R G, Andres P M, . Processing of Mars Exploration Rover Imagery for Science and Operations Planning. Journal of Geophysical Research—Planets, 2006, 111 E2 E02S02

[2] Anderson R C, Castano R, Stough T, . Using Scaled Visual Texture for Autonomous Rock Clustering. Lunar and Planetary Science XXXII, Houston, 2001

[3] Castano R, Anderson R C, Fox J, . Automating Shape Analysis of Rocks on Mars. Lunar and Planetary Science XXXIII, Houston, 2002

[4] Castano R, Judd M, Estlin T, . Current Results from a Rover Science Data Analysis System. IEEE Aerospace Conference, Montana, 2005

[5] Castano R, Estlin T, Anderson R C, . Onboard Autonomous Rover Science. Proceedings of IEEE Aerospace Conference, 2007

[6] Cheng Y Z. Mean Shift, Mode Seeking, and Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.

[7] Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects Using Mean Shift. Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, 2000, 142-149.

[8] Comaniciu D, Ramesh V, Meer P. The Variable Bandwidth Mean Shift and Data-Driven Scale Selection. Computer Vision, 2001, 1: 438-445.

[9] Comaniciu D, Meer P. Mean Shift: A Robust Approach toward Feature Space Analysis. Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.

[10] Comaniciu Code for the Edge Detection and Image Segmentation System, 2009

[11] Di K, Xu F, Wang J, . Photogrammetric Processing of Rover Imagery of the 2003 Mars Exploration Rover Mission. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(2): 181-201.

[12] Fitzgibbon A, Pilu M, Fisher R B. Direct Least-Square Fitting of Ellipses. Pattern Analysis and Machine Intelligence, 1999, 21(5): 476-480.

[13] Fox J, Castano R, Anderson R C. Onboard Autonomous Rock Shape Analysis for Mars Rovers. Proceedings of IEEE Aerospace Conference, Montana, 2002, 2036-2052.

[14] Fukanaga K, Hostetler L D. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition. IEEE Transactions on Information Theory, 1975, 21(1): 32-40.

[15] Golombek M P, Huertas A, Marlow J, . Size-Frequency Distributions of Rocks on the Northern Plains of Mars with Special Reference to Phoenix Landing Surfaces. Journal of Geophysical Research—Planets, 2008, 13 E00A09 32.

[16] Gor V, Castano R, Manduchi R, . Autonomous Rock Detection for Mars Terrain. Space 2001, American Institute of Aeronautics and Astronautics, Albuquerque, NM, USA, 2001

[17] Gulick V C, Morris R L, Ruzon M A, . Autonomous Image Analyses during the 1999 Marsokhod Rover Field Test. Journal of Geophysical Research, 2001, 106(E4): 7745-7763.

[18] Hong Y, Yi J, Zhao D. Improved Mean Shift Segmentation Approach for Natural Images. Applied Mathematics and Computation, 2007, 185(2): 940-952.

[19] Li R, Squyres S W, Arvidson R E, . Initial Results of Rover Localization and Topographic Mapping for the 2003 Mars Exploration Rover Mission. Photogrammetric Engineering & Remote Sensing, 2005, 71(10): 1129-1142.

[20] Li R, Di K, Howard A B, . Rock Modeling and Matching for Autonomous Long-Range Mars Rover Localization. Journal of Field Robotics, 2007, 24(3): 187-203.

[21] Manduchi R, Pollara F, Dolinar S, . Onboard Science Processing and Buffer Management for Intelligent Deep Space Communications. Proceedings of IEEE Aerospace Conference Big Sky, Montana, USA, 2000

[22] Ozertem U, Erdogmus D, Jenssen R. Mean Shift Spectral Clustering. Pattern Recognition, 2008, 41(6): 1924-1938.

[23] Peng N S, Yang J, Liu Z, . Automatic Selection of Kernel-Bandwidth for Mean-Shift Object Tracking. Journal of Software, 2005, 16(9): 1542-1550.

[24] Song Y H, Shan J. A Framework for Automated Rock Segmentation of the Mars Exploration Rover Imagery. Proceedings of ASPRS 2006 Annual Conference, Reno, Nevada, USA, 2006

[25] Song Y H, Shan J. Automated Rock Segmentation for Mars Exploration Rover Imagery. Lunar and Planetary Science Conference XXXIX, Houston, USA, 2008

[26] Thompson D R, Niekum S, Smith T, . Automatic Detection and Classification of Features of Geologic Interest. Proceedings of IEEE Aerospace Conference, Montana, USA, 2005

[27] Thompson D R, Smith T, Wettergreen D. Data Mining during Rover Traverse: From Images to Geologic Signatures. Proceedings of 8th International Symposium on Artificial Intelligence, Robotics and Automation in Space, USA, 2005

[28] Thompson D R, Castano R. Performance Comparison of Rock Detection Algorithms for Autonomous Planetary Geology. Aerospace, IEEE, USA, IEEEAC Paper No. 1251, 2007

[29] Wagstaff K L, Castano R, Dolinar S, . Science-Based Region-of-Interest Image Compression. Proceedings of 35th Lunar and Planetary Science Conference, League City, Texas, USA, 2004

[30] Wen Z Q, Cai Z X. Convergence Analysis of Mean Shift Algorithm. Journal of Software, 2007, 18(2): 205-212.

[31] Wu K L, Yang M S. Mean Shift-Based Clustering. Pattern Recognition, 2007, 40(11): 3035-3052.

[32] Xu C Y, Prince J L. Gradient Vector Flow: A New External Force for Snakes. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997, 66-71.