ABSTRACT
Crater mapping and counting are critical analyses in many planetary science investigations, as the size-frequency distribution of impact craters can be used to measure the age of a planet's surface and interpret its geologic history. Crater counting is extremely tedious --- counting hundreds to thousands of small features in a small region could take days to months for a trained planetary scientist. Previous work has demonstrated the feasibility of using computer vision techniques to automatically map and count craters in Mars orbital images using semantic segmentation. We present an improved approach for binary and multi-class semantic segmentation of craters in THEMIS daytime thermal infrared images using U2-Net and U-NetFormer with template matching. Our approach is the first method to perform multi-class segmentation of craters using computer vision. Our binary segmentation approach outperforms previous approaches that used semantic segmentation and template matching. A new global high-resolution image mosaic dataset of Mars (CTX, 5 m/px) is now available, but to date, no studies have benchmarked automated crater counting methods for this improved dataset. Toward this goal, we applied the THEMIS-trained model to out-of-domain CTX datasets and evaluated results quantitatively using the DoMars16 benchmark dataset and qualitatively using global mosaic tiles. We show that the THEMIS-trained models effectively segment craters in CTX images without additional fine-tuning. The code can be found here.
- Nadine G Barlow. 1990. Constraints on early events in Martian history as derived from the cratering record. Journal of Geophysical Research: Solid Earth 95, B9 (1990), 14191--14201.Google ScholarCross Ref
- JF Bell III, MC Malin, MA Caplinger, J Fahle, MJ Wolff, BA Cantor, PB James, T Ghaemi, LV Posiolova, MA Ravine, et al. 2013. Calibration and performance of the Mars reconnaissance orbiter context camera (CTX). International Journal of Mars Science and Exploration 8 (2013), 1--14.Google Scholar
- GK Benedix, Anthony Lagain, Kevin Chai, S Meka, S Anderson, C Norman, PA Bland, Jonathan Paxman, MC Towner, and Tele Tan. 2020. Deriving surface ages on Mars using automated crater counting. Earth and Space Science 7, 3 (2020), e2019EA001005.Google Scholar
- G. Bradski. 2000. The OpenCV Library. Dr. Dobb's Journal of Software Tools (2000).Google Scholar
- California Institute of Technology - Division of Geological and Planetary Sciences. [n. d.]. The Bruce Murray Laboratory for Planetary Visualization. http://murray-lab.caltech.edu/CTX/.Google Scholar
- Clark R Chapman and Kenneth L Jones. 1977. Cratering and obliteration history of Mars. Annual Review of Earth and Planetary Sciences 5, 1 (1977), 515--538.Google ScholarCross Ref
- Dong Chen, Fan Hu, P Takis Mathiopoulos, Zhenxin Zhang, and Jiju Peethambaran. 2023. MC-UNet: Martian Crater Segmentation at Semantic and Instance Levels Using U-Net-Based Convolutional Neural Network. Remote Sensing 15, 1 (2023), 266.Google ScholarCross Ref
- Philip R Christensen, Bruce M Jakosky, Hugh H Kieffer, Michael C Malin, Harry Y McSween, Kenneth Nealson, Greg L Mehall, Steven H Silverman, Steven Ferry, Michael Caplinger, et al. 2004. The thermal emission imaging system (THEMIS) for the Mars 2001 Odyssey Mission. Space Science Reviews 110 (2004), 85--130.Google ScholarCross Ref
- Danielle DeLatte, Sarah T. Crites, Nicholas Guttenberg, Elizabeth J. Tasker, and Takehisa Yairi. 2019. Segmentation Convolutional Neural Networks for Automatic Crater Detection on Mars. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12 (2019), 2944--2957.Google ScholarCross Ref
- Kaichang Di, Wei Li, Zongyu Yue, Yiwei Sun, and Yiliang Liu. 2014. A machine learning approach to crater detection from topographic data. Advances in Space Research 54, 11 (2014), 2419--2429.Google ScholarCross Ref
- JL Dickson, LA Kerber, CI Fassett, and BL Ehlmann. 2018. A global, blended CTX mosaic of Mars with vectorized seam mapping: A new mosaicking pipeline using principles of non-destructive image editing. In Lunar and planetary science conference, Vol. 49. Lunar and Planetary Institute The Woodlands TX, USA, 1--2.Google Scholar
- CS Edwards, KJ Nowicki, PR Christensen, J Hill, N Gorelick, and K Murray. 2011. Mosaicking of global planetary image datasets: 1. Techniques and data processing for Thermal Emission Imaging System (THEMIS) multi-spectral data. Journal of Geophysical Research: Planets 116, E10 (2011).Google Scholar
- William K Hartmann and Gerhard Neukum. 2001. Cratering chronology and the evolution of Mars. In Chronology and evolution of Mars: Proceedings of an ISSI Workshop, 10-14 April 2000, Bern, Switzerland. Springer, 165--194.Google Scholar
- Zhonghua Hong, Ziyang Fan, Ruyan Zhou, Haiyan Pan, Yun Zhang, Yanling Han, Jing Wang, Shuhu Yang, and Yanmin Jin. 2022. Pyramidal Image Segmentation Based on U-Net for Automatic Multiscale Crater Extraction. Sensors and Materials 34, 1 (2022), 237--250.Google ScholarCross Ref
- Pavel Iakubovskii. 2019. Segmentation Models Pytorch. https://github.com/qubvel/segmentation_models.pytorch.Google Scholar
- Boris A Ivanov. 2001. Mars/Moon cratering rate ratio estimates. Space Science Reviews 96, 1-4 (2001), 87--104.Google ScholarCross Ref
- Yutong Jia, Lei Liu, and Chenyang Zhang. 2021. Moon impact crater detection using nested attention mechanism based UNet++. IEEE Access 9 (2021), 44107--44116.Google ScholarCross Ref
- Anthony Lagain, Sylvain Bouley, David Baratoux, Chiara Marmo, François Costard, O Delaa, A Pio Rossi, M Minin, GK Benedix, M Ciocco, et al. 2021. Mars Crater Database: A participative project for the classification of the morphological characteristics of large Martian craters. (2021).Google Scholar
- Anthony Lagain, Konstantinos Servis, GK Benedix, Christopher Norman, Seamus Anderson, and PA Bland. 2021. Model age derivation of large martian impact craters, using automatic crater counting methods. Earth and Space Science 8, 2 (2021), e2020EA001598.Google Scholar
- Christopher Lee. 2019. Automated crater detection on Mars using deep learning. Planetary and Space Science (2019).Google Scholar
- Michael C Malin, James F Bell III, Bruce A Cantor, Michael A Caplinger, Wendy M Calvin, R Todd Clancy, Kenneth S Edgett, Lawrence Edwards, Robert M Haberle, Philip B James, et al. 2007. Context camera investigation on board the Mars Reconnaissance Orbiter. Journal of Geophysical Research: Planets 112, E5 (2007).Google Scholar
- Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R Zaiane, and Martin Jagersand. 2020. U2-Net: Going deeper with nested U-structure for salient object detection. Pattern recognition 106 (2020), 107404.Google Scholar
- Stuart J Robbins and Brian M Hynek. 2012. A new global database of Mars impact craters ≥ 1 km: 1. Database creation, properties, and parameters. Journal of Geophysical Research: Planets 117, E5 (2012).Google Scholar
- Ari Silburt, Mohamad Ali-Dib, Chenchong Zhu, Alan P. Jackson, Diana Valencia, Yevgeni Kissin, Daniel Tamayo, and Kristen Menou. 2018. Lunar crater identification via deep learning. Icarus (2018).Google Scholar
- David E Smith, Maria T Zuber, Herbert V Frey, James B Garvin, James W Head, Duane O Muhleman, Gordon H Pettengill, Roger J Phillips, Sean C Solomon, H Jay Zwally, et al. 2001. Mars Orbiter Laser Altimeter: Experiment summary after the first year of global mapping of Mars. Journal of Geophysical Research: Planets 106, E10 (2001), 23689--23722.Google ScholarCross Ref
- TF Stepinski, Wei Ding, and R Vilalta. 2012. Detecting impact craters in planetary images using machine learning. In Intelligent data analysis for real-life applications: Theory and practice. IGI Global, 146--159.Google Scholar
- Robert G Strom, Steven K Croft, and Nadine G Barlow. 1992. The Martian impact cratering record. Mars (1992), 383--423.Google Scholar
- THEMIS Science Team. 2006. THEMIS Day IR Global Mosaic. https://www.mars.asu.edu/data/thm_dir/ (2006).Google Scholar
- THEMIS Science Team. 2014. THEMIS Day IR Global Mosaic. https://www.mars.asu.edu/data/thm_dir/ (2014).Google Scholar
- T. A. Vinogradova, M. Burl, and Eric Mjolsness. 2002. Training of a crater detection algorithm for Mars crater imagery. Proceedings, IEEE Aerospace Conference 7 (2002), 7--7.Google ScholarCross Ref
- Libo Wang, Rui Li, Ce Zhang, Shenghui Fang, Chenxi Duan, Xiaoliang Meng, and Peter M Atkinson. 2022. UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS Journal of Photogrammetry and Remote Sensing 190 (2022), 196--214.Google ScholarCross Ref
- SC Werner and KL Tanaka. 2011. Redefinition of the crater-density and absolute-age boundaries for the chronostratigraphic system of Mars. Icarus 215, 2 (2011), 603--607.Google ScholarCross Ref
- Philipp Georg Wetzler, Rie Honda, Brian L. Enke, William J. Merline, Clark R. Chapman, and Michael C. Burl. 2005. Learning to Detect Small Impact Craters. 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1 1 (2005), 178--184.Google ScholarDigital Library
- Thorsten Wilhelm, Melina Geis, Jens Püttschneider, Timo Sievernich, Tobias Weber, Kay Wohlfarth, and Christian Wöhler. 2020. Domars16k: A diverse dataset for weakly supervised geomorphologic analysis on mars. Remote Sensing 12, 23 (2020), 3981.Google ScholarCross Ref
- Sudong Zang, Lingli Mu, Lina Xian, and Wei Zhang. 2021. Semi-supervised deep learning for lunar crater detection using ce-2 dom. Remote Sensing 13, 14 (2021), 2819.Google ScholarCross Ref
Index Terms
- Automated Multi-class Crater Segmentation in Mars Orbital Images
Recommendations
UAV On-Board Emergency Safe Landing Spot Detection System Combining Classical and Deep Learning-Based Segmentation Methods
Intelligent Information and Database SystemsAbstractThis article proposes the system designed for automatic detection of emergency landing sites for horizontally landing unmanned aerial vehicles (UAV). The presented solution combines the classic computer vision algorithms and novel segmentation ...
Power Line Segmentation in Aerial Images Using Convolutional Neural Networks
Pattern Recognition and Machine IntelligenceAbstractVisual inspection of transmission and distribution networks is often carried out by various electricity companies on a regular basis to maintain the reliability, availability, and sustainability of electricity supply. Till date the widely used ...
A real-time efficient object segmentation system based on U-Net using aerial drone images
AbstractReal-time object detection and segmentation are considered as one of the fundamental but challenging problems in remote sensing and surveillance applications (including satellite and aerial). Consequently, it performs a crucial role in various ...
Comments