Abstract
In Mars exploration, rocks are good targets for compositional analysis with spectrometers. Their shape, size, and texture could provide a wealth of information for study of planetary geology. However, imitations on communications between Mars and earth lead to operations latencies and slow progress in planetary surface missions. Increasing the autonomy of rovers has become an important research direction. Autonomy is the ability to choose which scientific data to collect and which ones to send back to Earth. One of the aims is to recognize the rocks independently. The AEGIS system adopts the method of edge detection to select potential rock targets for following observation, but the type of rocks cannot be distinguished. Convolutional neural network (CNN) is getting more attention due to its performance in computer vision. However, a common issue of CNN is that it requires large amount of rock images for training, which are difficult to get. Transfer learning provides a good way to overcome the problem of lack of dataset. In this work, CNN based on vgg-16 architecture with deep transfer learning is used to automatically classify 4 groups of Martian rocks. The proposed model achieves accuracy of 100% on Martian rock images we collected from MSL Analyst ‘s Notebook. Moreover, a comparison between the VGG-16 transfer model and other models is made, and it can be found that the proposed model has the best performance in Martian rock classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arp G, Schultz S, Karius V, Head JW (2019) Ries impact crater sedimentary conglomerates: sedimentary particle ‘impact pre-processing’, transport distances and provenance, and implications for Gale crater conglomerates, Mars. ICARUS 321:531–549
Ayhan B, Dao M, Kwan C, Chen HM, Bell JF, Kidd R (2017) A novel utilization of image registration techniques to process mastcam images in mars rover with applications to image fusion, pixel clustering, and anomaly detection. IEEE J Selec Top Appl Earth Observ Rem Sens 10(10):4553–4564
Bell JF III, Godber A, McNair S, Caplinger MA, Maki JN, Lemmon MT, Van Beek J, Malin MC, Wellington D, Kinch KM, Madsen MB, Hardgrove C, Ravine MA, Jensen EH, Harker D, Anderson RB, Herkenhoff KE, Morris RV, Cisneros E, Deen RG (2017) The Mars science laboratory curiosity rover mast camera (Mastcam) instruments: pre-flight and in-flight calibration, validation, and data archiving. Earth and Space Sci 4:396–452
Burl MC, Thompson DR, deGranville C, B.J. (2016) BornsteinRockster: onboard rock segmentation through edge regrouping. J Aerospace Inform Syst 13:329–342. https://doi.org/10.2514/1.i010381
Carrera D, Bandeira L, Santana R, Lozano JA (2019) Detection of sand dunes on Mars using a regular vine-based classification approach. Knowled Bas Syst 163:858–874
Castano R, Estlin T, Anderson R, Gaines D, Castano A, Bormstein B, Chouinard C, Judd M (2007) OASIS: onboard autonomous science investigation system for opportunistic rover science. J Field Robot 24(5):379–397. https://doi.org/10.1007/s11214-012-9892-2
Cousin A, Sautter V (2017) Classification of igneous rocks analyzed by ChemCam at Gale crater, Mars. Icarus 288
Cox R, Lowe DR (1995) A conceptual review of regional-scale controls on the composition of clastic sediment and the co-evolution of continental blocks and their sedimentary cover. J Sediment Res A65:1–12
Estlin T et al. (2009) Automated targeting for the mer rovers. SMC-IT 2009. In: Proceedings of the third IEEE international conference on space Mission challenges for information technology, pp. 257–263. IEEE
Francis R, Estlin T, Doran G, Johnstone S, Gaines D, Verma V et al (2017a) AEGIS autonomous targeting for ChemCam on Mars science laboratory: deployment and results of initial science team use. Sci Robot 2(7):eaan4582
Francis R, Estlin T, Doran G, Johnstone S, Gaines D, Verma V, Burl M, Frydenvang J, Montaño S, Wiens RC, Schaffer S, Gasnault O, DeFores L, Blaney D, Bornstein B (2017b) AEGIS autonomous targeting for ChemCam on Mars science laboratory: deployment & results of initial science team use. Sci Robot 7
Ghaffari A, Madani N (2019) Atrial fibrillation identification based on a deep transfer learning approach. Biomed Phys Eng Exp:035015
Gichu R, Ogohara K (2019) Segmentation of dust storm areas on Mars images using principal component analysis and neural network. Prog Earth Planet Sci 6:19
Grotzinger JP et al (2012) Mars Science Laboratory Mission and science investigation. Space Sci Rev 170(2012):5–56. https://doi.org/10.1007/s11214-012-9892-2
He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778
Hiroshi Inoue. (2018). Data augmentation by pairing samples for images classification arXiv:1801.02929v2 [cs.LG]
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Int Conf Learn Represen 2015(2015):1–15 arXiv:1412.6980
Kwan C, Chou B, Bell FJ III (2019) Comparison of deep learning and conventional Demosaicing algorithms for Mastcam images. Electronics 8:308
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel L, Backpropagation D (1989) Applied to handwritten zip code recognition. Neural Comput 1(4):541–551
Liu S, Tian G, Yuan X (2019) A novel scene classification model combining ResNet based transfer learning and data augmentation with a filter. Neurocomputing 338:191–206
Mangold N, Thompson LM, Forni O, Williams AJ, Fabre C, Le Deit L, Wiens RC, Williams R, Anderson RB, Blaney DL, Calef F, Cousin A, Clegg SM, Dromart G, Dietrich WE, Edgett KS, Fisk MR, Gasnault O, Gellert R, Grotzinger JP, Kah L, Le Moue’lic S, McLennan SM, Maurice S, Meslin P-Y, Newsom HE, Palucis MC, Rapin W, Sautter V, Siebach KL, Stack K, Sumner D, Yingst A (2016a) Composition of conglomerates analyzed by the curiosity rover: implications for Gale crater crust and sediment sources. J Geophys Res Planets 121:353–387
Mangold N, Thompson LM, Forni O, Williams AJ, Fabre C, Le Deit L, Wiens RC, Williams R, Anderson RB, Blaney DL, Calef F, Cousin A, Clegg SM, Dromart G, Dietrich WE, Edgett KS, Fisk MR, Gasnault O, Gellert R, Grotzinger JP, Kah L, Le Moue’lic S, McLennan SM, Maurice S, Meslin P-Y, Newsom HE, Palucis MC, Rapin W, Sautter V, Siebach KL, Stack K, Sumner D, Yingst A (2016b) Composition of conglomerates analyzed by the curiosity rover: implications for Gale crater crust and sediment sources. J Geophys Res Planets 121:353–387
McSween H Jr (2015) Petrology on Mars. Am Mineral 100:2380–2395
Pan SJ, Yang Q (Oct. 2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Ran X, Xue L, Zhang Y (2019) Rock Classification from Field Image Patches Analyzed Using a Deep Convolutional Neural Network [J]. Mathematics 7(8)
Seiders VM, Blome CD (1988) Implications for upper Mesozoic con− glomerate for suspect terrane in western California and adjacent areas. Geol Soc Am Bull 100:374–391
Sharif H, Ralchenko M, Samson C, Ellery A (2015) Autonomous rock classification using Bayesian image analysis for rover-based planetary exploration. Comput Geosci 83:153–167
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:preprint arXiv:1409.1556
Sun H, Lv G, Mo J, Lv X, Guoli D, Liu Y (2019) Application of KPCA combined with SVM in Raman spectral discrimination. Optik
Szegedy C, Vanhoucke V, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna (2016). Rethinking the inception architecture for computer vision. cv-foundation.org [Internet]
Talo M, Baloglu UB, Yıldırım O, U.R. (2019) AcharyaApplication of deep transfer learning for automated brain abnormality classification using MR images. Cogn Syst Res 54:176–188
Williams RME et al (2013) Martian fluvial conglomerates at Gale crater. Science 340:1068–1072 https://doi.org/10.1126/science.1237317
Zuo H, Lu J, Zhang G, Liu F (2019) Fuzzy transfer learning using an infinite gaussian mixture model and active learning. IEEE Trans Fuzzy Syst 27(2):291–303
Author information
Authors and Affiliations
Corresponding authors
Additional information
Communicated by: H. Babaie
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, J., Zhang, L., Wu, Z. et al. Autonomous Martian rock image classification based on transfer deep learning methods. Earth Sci Inform 13, 951–963 (2020). https://doi.org/10.1007/s12145-019-00433-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-019-00433-9