Planetary Terrain Features Tracking Method Based on Robust Curve Matching

Abstract

A curve description and matching algorithm which utilizes the scale constant is presented for feature tracking and hazard recognition process in planetary landing. The way to form the curve descriptor which is constructed with the curve neighborhood gradients information is introduced. The robustness and the efficiency of our graph matching process is shown in rotation , scale , moderate viewpoint changes and light effects , without knowing the curve geometry or geometrical configuration between the curves. This algorithm can not only be used for edge curve feature tracking with low mismatching,but also effectively identify the craters , rocks and other hazardous or natural landmarks at different scales.

Keywords

planetary landing / obstacle detection / curve matching / edge extraction / curve descriptor

References

[1] 昊伟仁,王大轶,李骥,等.月球软着陆避障段定点着陆导航方法研究[J].中国科学E辑,2011, 41(9):1054一1064.[Wu W R, Wang D Y, Li J, et al. Research of the pinpoint landing navigation method in the hazard avoidance phase of lunar landing}J].Science China E, 2011,41(9);1054一1064.]
[2] Cocaud C, Kubota T. Probabilistic motion estimation for~}1_time navigation and landing on small celestial bodies[C]. The 22ndInternational Symposium on Space Flight Dynamics, 2011.
[3] Dunstan M, Parkes S, Mancuso S. Visual navigation chip for planetary lenders[C].The Data Systems in Aerospace Conference (DASIA),2005.
[4] Johnson A E, Willson R, Goguen J, et al. Field testing of the Mars exploration~descent image motion estimation system[C].IEEE International Conference Robot. Barcelona, Spain,Apr.18一22,2005;4463一4469.
[5] Bakambu J N,Langley C,Pushpanathan G,et al. Field trial results of planetary rover visual motion estimation in Marsanalogue terrain[J].Journal of Field Robotics, 2012, 29(3):413一425.
[6] 冯军华,崔枯涛,崔平远,等.行星表面陨石坑检测与匹配方法[J].航空学报,2010, 31(9):1858一1863.[Feng J H, CuiH T, Cui P Y, et al. Autonomous crater detection and matchingon planetary surface[J].Acta Aeronautica et Astmnautica Sinica. 2010, 31(9):1858一1863.]
[7] Weismuller T, Leinz M, Caballero D, et al. Technology for autonomous optical planetary navigation and precision landing[C].AIAA Space 2007 Conference, 2007:1924一1949.
[8] Bandeira L, Saraiva J, Pina P. Impact crater recognition on Mars based on a probability volume created by template matching[J].IEEE Transactions on Geoscience and Remote Sensing, 2007,45(12):4008一4015.
[9] Ansar A, Cheng Y. An analysis of spacecraft localization firom decent image data for pinpoint landing on Mars and other crateredbodies[J].Photogrammetric Engineeringℜmote Sensing,2005,(10):1197一1204.
[10] 于正提,朱圣英,马冬梅,等.行星表面非规则陨石坑检测与识别方法[J].宇航学报,34(3);320一326.}Yu Z S, Zhu SY, Ma D M, et al. Detection and recognition method for irregular craters on planetary surface[J].Journal of Astronautics, 34(3):320一326.」
[11] Wang Z H, Wu F C, Hu Z Y. MSLD; A robust descriptor for line matching}J]. Pattern Recognition, 2009, 42(5):941-953.
[12] Zhang L L, Reinhard K. An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency[J].Journal of Visual Communication and Image, 2013,7(24);794一805.
[13] Yue Y, Eam K T. A novel 2D shape matching algorithm based on B-spline modeling[C].2004 Image Processing, 2004, 1:409一412.
[14] Armin G, Devrim A. Least squares 3D surface and curve matching[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2005,59(3):151一174.
[15] Gorelick L, Galun M, Sharon E, et al. Shape representation and classification using the Poisson equation[J].IEEE Transactionson Pattern Analysis and Machine Intelligence, 2006, 28(12):1991一2005.
[16] Landa Z, Malah D, Barwhar M. 2D object description and recognition based on contour matching by implicit polynomials[C].The 18th European Signal Processing Conference,Aalborg, Denmark, 2010.
[17] Topal C, Cuneyt A. Edge Drawing:A combined real-time edge and segment detector[J].Visual Communication and Image Representation, 2012, 23(6):862一872.