<p>Dynamic changes of Martian north polar scarps present a valuable insight into the planet's natural climate cycles (Byrne, 2009; Head et al., 2003)<sup>1,2</sup>. Annual avalanches and block falls are amongst the most noticeable surface processes that can be directly linked with the extent of the latter dynamics (Fanara et al, 2020)<sup>3</sup>. New remote sensing approaches based on machine learning allow us to make precise records of the aforementioned mass wasting activity by automatically extracting and analyzing bulk information obtained from satellite imagery.&#160; Previous studies have concluded that a Support Vector Machine (SVM) classifier trained using Histograms of Oriented Gradients (HOG) can be used to efficiently detect block falls, even against backgrounds with increased complexity (Fanara et al., 2020)<sup>4</sup>. We hypothesise that this pretrained model can now be utilized to generate an extended dataset of labelled image data, sufficient in size to opt for a deep learning approach. On top of improving the detection model we also attempt to address the image co-registration protocol. Prior research has suggested this to be a substantial bottleneck, which reduces the amounts of suitable images. We plan to overcome these limitations either by extending our model to include multi-sensor data, or by deploying improved methods designed for exclusively optical data (e.g.&#160; COSI-CORR software (Ayoub, Leprince and Avouac, 2017)<sup>5</sup>).&#160; The resulting algorithm should be a robust solution capable of improving on the already established baselines of 75.1% and 8.5% for TPR and FDR respectively (Fanara et al., 2020)4. The NPLD is our primary area of interest due to it&#8217;s high levels of activity and good satellite image density, yet we also plan to apply our pipeline to different surface changes and Martian regions as well as on other celestial objects.</p><p>&#160;</p><p>1. Head, J.W., Mustard, J.F., Kreslavsky, M.A., Milliken, R.E., Marchant, D.R., 2003. Recent ice ages on Mars. Nature 426, 797&#8211;802</p><p>2. Byrne, S., 2009. The polar deposits of Mars. Annu. Rev. Earth Planet. Sci. 37, 535&#8211;560.</p><p>3. Fanara, K. Gwinner, E. Hauber, J. Oberst, Present-day erosion rate of north polar scarps on Mars due to active mass wasting; Icarus,Volume 342, 2020; 113434, ISSN 0019-1035.</p><p>4. Fanara, K. Gwinner, E. Hauber, J. Oberst, Automated detection of block falls in the north polar region of Mars; Planetary and Space Science, Volume 180, 2020; 104733, ISSN 0032-0633.</p><p>5. Ayoub, F.; Leprince, S.; Avouac, J.-P. User&#8217;s Guide to COSI-CORR Co-registration of Optically Sensed Images and Correlation; California Institute of Technology: Pasadena, CA, USA, 2009; pp. 1&#8211;49.</p>
<div> <p><strong>1.&#160;&#160;&#160;&#160; </strong><strong>Introduction</strong></p> </div> <p>The north polar region of Mars is one of the most active places of the planet with avalanches<sup>[1]</sup> and ice block falls<sup>[2]</sup> being observed every year on High Resolution Imaging Science Experiment (HiRISE) data. Both phenomena originate at the steep icy scarps surrounding the north polar plateau, Planum Boreum. The exposed layers of ice and dust contain important information about the climate cycles of the planet<sup>[3]</sup>. We are interested in monitoring how the current scarp erosion rate (quantified through analysing block falls) is linked to these periodic changes in temperature. The large scale of the region of interest, combined with a growing amount of available satellite data makes automation key for this project. Our goal is to monitor robustly the whole north polar region for ice block falls throughout the entire Mars Reconnaissance Orbiter (MRO) mission. The active scarps of the north polar region contain two main geological units, the older and darker Planum Boreum Cavi unit, also called Basal Unit (BU) and the younger and brighter Planum Boreum 1 unit, which is a part of the so called North Polar Layered Deposits (NPLD)<sup>[4]</sup>. These geologic units are mapped by Tanaka et al. (2012), however the scale of this map is not sufficient for our work, as it is based on coarse resolution data. For our project it is important to segment the HiRISE images of the steep scarps in NPLD and BU regions with high precision, both to restrict the area where the algorithm will look for fallen blocks and to differentiate between the activity originating in the NPLD<sup>[5]</sup> from that originating in the BU.&#160;Here we present our algorithm for automated scarp mapping &#8211; the first completed step towards a fully streamlined monitoring pipeline.</p> <p><img src="data:image/png;base64, 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
<p>The north polar region of Mars is one of the most active places of the planet with avalanches<sup>[1] </sup>and ice block falls<sup>[2]</sup> being observed every year on High Resolution Imaging Science Experiment (HiRISE) data. Both phenomena originate at the steep icy scarps surrounding the north polar plateau, Planum Boreum. The exposed layers of ice and dust contain important information about the climate cycles of the planet<sup>[3]</sup>. We are interested in monitoring how the current scarp erosion rate (quantified through analyzing blockfalls) is linked to these periodic changes in temperature. The large scale of the region of interest, combined with a growing amount of available satellite data makes automation key for this project. Our goal is to robustly monitor the whole north polar region for ice block falls throughout the entire Mars ReconnaissanceOrbiter (MRO) mission.&#160;</p> <p>&#160;</p> <p>Deep Learning networks are widely used for object detection problems, the YOLO family being particularly popular among researchers and commercial users. Although the baseline performance of its most recent iteration (v5) is satisfactory for most generic applications, HiRISE images of NPLD (North Polar Layered Deposits) present a greater challenge. Large boulders are usually easy to identify due to their well differentiated visual features, e.g. longer shadows and edges, greater surface area and less crowded backgrounds. As the blocks get smaller features&#160; become less pronounced and margins between different object instances shrink beyond the default resolution of&#160; YOLOv5 thus noticeably hindering the network&#8217;s overall efficiency. To boost the detection rate we propose the following modifications to the currently available build<em> (fig1)</em>:</p> <p>&#160;</p> <ul> <li aria-level="1"><strong>Super Resolution module</strong><sup>[4]</sup> - before the images are fed into the network backbone they are stretched out to 640x640p using simple bicubic interpolation. An alternative approach utilizes DASR (domain-distance aware super-resolution)&#160; as a preprocessing step. This super-resolution model can be trained on analogous Earth data (e.g. Svalbard) and then deployed to intelligently upscale the HiRISE dataset, adding an extra layer of textures and sharpening the images.&#160;</li> </ul> <p>&#160;</p> <ul> <li aria-level="1"><strong>Better anchor grid</strong><sup>[5]</sup> - anchor grid parameters should be based on the size of the objects we expect to observe in our dataset. The closer the initial guess, the less adjustments are subsequently&#160; performed by the network. We suggest that automatically deriving the anchors prior to training is extremely beneficial to the overall performance.&#160;</li> </ul> <p>&#160;</p> <ul> <li aria-level="1"><strong>Additional Fusion Layer and Residual Connections</strong><sup>[6]</sup> - baseline version of&#160; YOLOv5 starts implementing residual connections only at P3 level, ignoring the higher resolution P2 features. To reduce the loss of the feature information of small objects we incorporate the P2 layer into the rest of the network by stacking it on top of the basis formed by the original three layers, i.e. {P3, P4, P5}.&#160;</li> </ul> <p>&#160;</p> <ul> <li aria-level="1"><strong>Attention Module</strong><sup>[6] </sup>- this enhancement helps the network learn the spatial correlation between features much like the human visual mechanism, which enables the eye to focus on more important feature regions and suppresses irrelevant regions. There are different options available, yet we use a combination of ECA-Net and CBAM contributing channel attention and spatial attention mechanisms respectively.</li> </ul> <p>&#160;</p> <ul> <li aria-level="1"><strong>Position of attention modules within the network</strong><sup>[6]</sup><strong> </strong>- the insertion point of the aforementioned modules is not location invariant. We have chosen to incorporate it into the fusion layers right after every CSP (i.e.C3) block.&#160;</li> </ul> <p><img src="" alt="" /></p> <p><em>Figure 1.</em> A<em> diagram of the improved YOLOv5 architechture. The input tesnors are already upscaled by DASR and presprocessed to derive the best posible anchor grid parameters. C3 (CSP) -&#160; cross-stage partial network; SPPF - spatial pyramid pooling fast; ECBAM - ECANet + CBAM attention modules.&#160;</em></p> <p>The boost in performance is most noticeable in ice boulder dense areas, where detection is highly dependent on resolving separate compactly stacked objects. The exact figure is yet to be confirmed experimentally but preliminary testing shows at least a 3% improvement. We hypothesize that integrating the DASR module with the main training routine instead of performing upscaling as a separate preprocessing step might boost the performance even further. The NPLD remains our primary area of interest due to its high levels of activity and good satellite image density, yet we also plan to apply our pipeline to different surface changes and Martian regions as well as other celestial objects.</p> <p><br /><br /></p> <ul> <li aria-level="1">Russell P., Thomas, N. Byrne, S. Herkenhoff, K.Fishbaugh, K. Bridges, N. Okubo, C. Milazzo, M. Daubar, I. Hansen. Seasonally active frost-dust avalanches on a north polar scarp of Mars captured by HiRISE, Geophys. Res. Lett. 35, L23204 (2008).</li> <li aria-level="1">L. Fanara, K. Gwinner, E. Hauber, J. Oberst. Present-day erosion rate of north polar scarps on Mars due to active mass wasting, Icarus, Volume 342, (2020),113434, ISSN 0019-1035.</li> <li aria-level="1">Smith I.B., Putzig N.E., Holt J.W. and Phillips R.J. An ice age recorded in the polar deposits of Mars, Science, 352, 1075&#8211;1078 (2016).</li> <li aria-level="1">Yunxuan Wei, Shuhang Gu, Yawei Li, Longcun Jin. Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training (2021).</li> <li aria-level="1">Zhan, W., Sun, C., Wang, M. <em>et al.</em> An improved Yolov5 real-time detection method for small objects captured by UAV. <em>Soft Comput</em> 26, 361&#8211;373 (2022)</li> <li aria-level="1">Linlin Zhu, Xun Geng, Zheng Li and Chun Liu. Improving YOLO v5 with Attention Mechanism for Detecting Boulders from Planetary Images. <em>Remote Sens. </em>, <em>13</em>(18), 3776 (2021).</li> </ul>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.