Martian Surface Image Segmentation Dataset and Performance Evaluation

doi:10.19678/j.issn.1000-3428.0065910

Abstract

Abstract: As part of the continuous progress being made in deep space exploration technology，the “Zhurong Mars ”rover carried by China's first Mars exploration mission，Tianwen-1，has successfully landed on Mars and collects images of the Martian surface.Rocks are the main obstacle on the surface of Mars，with rocks of different shapes and sizes having an impact on the path planning of the rover during scientific exploration missions. Accurate rock segmentation is of great significance for obstacle avoidance and path planning.Because there are few applications for the image datasets captured by Tianwen-1，the segmentation datasets from most Mars images are restricted to the non-public state，essentially hindering the research into the algorithms related to Mars rock segmentation.Therefore，the images of the Martian surface，captured by the Navigation and Terrain Cameras（NaTeCam） mounted on the “Zhurong” Mars rover，were manually screened and annotated to establish the Martian surface image segmentation dataset，TWMARS.The dataset contained 336 Martian surface images，which were randomly divided into the training，validation，and test sets according to their required proportions.Performance evaluation tests were conducted on the existing semantic segmentation algorithms of the dataset.The TWMARS data set were run using the MobileNet and ResNet Convolutional Neural Network（CNN） models achieved the highest mean pixel accuracy and mean intersection over union values of 83.0% and 77.4%，respectively.The experimental results show that the classical semantic segmentation algorithms of the dataset achieved a high accuracy and can be applied further to the research regarding the Mars rock detection algorithm.

Key words: Tianwen-1 mission, Mars rover, Navigation and Terrain Cameras（NaTeCam）, Martian surface image, segmentation dataset

摘要： 随着深空探测技术的不断进步，中国火星探测任务天问一号搭载的“祝融号”火星车成功着陆火星，并开展火星表面影像采集工作。火星表面的主要障碍物是岩石，这些形状、大小不同的岩石将会影响火星车在科学探索任务中的路径规划。准确的岩石分割对于火星车避障和路径规划具有重要意义。由于目前对于天问一号所拍摄的图像数据集应用较少，且多数火星图像的分割数据集处于非公开状态，在一定程度上阻碍了火星岩石分割相关算法的研究。为此，面向“祝融号”火星车上搭载的导航地形相机所拍摄的火星表面影像，通过人工进行图像筛选和标记，建立一个火星表面影像分割数据集TWMARS。该数据集共包含336张火星图像，将其按比例随机划分为训练集、验证集和测试集，在现有的语义分割算法上进行数据集性能评估实验，结果表明，在MobileNet、ResNet等系列卷积神经网络模型上运行TWMARS数据集，平均像素精度和平均交并比最高分别可达83.0%和77.4%，在经典语义分割算法上获得较高的准确率，可应用于火星岩石检测算法的相关研究。

关键词: 天问一号任务, 火星车, 导航地形相机, 火星表面影像, 分割数据集

CLC Number:

TP391

Lü Weikun, WEI Linhui, ZHENG Dian, LIU Yu, WANG Yumei. Martian Surface Image Segmentation Dataset and Performance Evaluation[J]. Computer Engineering, 2023, 49(5): 262-268.

吕炜琨, 魏琳慧, 郑殿, 刘雨, 望育梅. 火星表面影像分割数据集及性能评估[J]. 计算机工程, 2023, 49(5): 262-268.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0065910

http://www.ecice06.com/EN/Y2023/V49/I5/262

Figures/Tables 8

References

[1] National Aeronautics and Space Administration(NASA).Mars exploration program[EB/OL].[2022-09-01].https://mars.nasa.gov/.
[2] LI C L,ZHANG R Q,YU D Y,et al.China's Mars exploration mission and science investigation[J].Space Science Reviews,2021,217(4):57.
[3] 中国国家航天局.中国月球与深空探测工程地面应用系统[EB/OL].[2022-09-01].http://moon.bao.ac.cn. China National Space Administration(CNSA).Ground application system of China lunar and deep space exploration project[EB/OL].[2022-09-01].http://moon.bao.ac.cn.(in Chinese)
[4] KUANG B Y,WISNIEWSKI M,RANA Z A,et al.Rock segmentation in the navigation vision of the planetary rovers[J].Mathematics,2021,9(23):3048.
[5] XIAO X M,CUI H T,YAO M B,et al.Auto rock detection via sparse-based background modeling for Mars rover[C]//Proceedings of IEEE Congress on Evolutionary Computation.Washington D.C.,USA:IEEE Press,2018:1-6.
[6] DI K C,YUE Z Y,LIU Z Q,et al.Automated rock detection and shape analysis from Mars rover imagery and 3D point cloud data[J].Journal of Earth Science,2013,24(1):125-135.
[7] 景庄伟,管海燕,彭代峰,等.基于深度神经网络的图像语义分割研究综述[J].计算机工程,2020,46(10):1-17. JING Z W,GUAN H Y,PENG D F,et al.Survey of research in image semantic segmentation based on deep neural network[J].Computer Engineering,2020,46(10):1-17.(in Chinese)
[8] COATES A,NG A Y.Learning feature representations with k-means[M].Berlin,Germany:Springer,2012.
[9] 汪海洋,潘德炉,夏德深.二维Otsu自适应阈值选取算法的快速实现[J].自动化学报,2007,33(9):968-971. WANG H Y,PAN D L,XIA D S.A fast algorithm for two-dimensional Otsu adaptive threshold algorithm[J].Acta Automatica Sinica,2007,33(9):968-971.(in Chinese)
[10] SHOTTON J,JOHNSON M,CIPOLLA R.Semantic TextOn forests for image categorization and segmentation[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8.
[11] LATEEF F,RUICHEK Y.Survey on semantic segmentation using deep learning techniques[J].Neurocomputing,2019,338:321-348.
[12] LIU D Q,BOBER M,KITTLER J.Visual semantic information pursuit:a survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(4):1404-1422.
[13] MINAEE S,BOYKOV Y,PORIKLI F,et al.Image segmentation using deep learning:a survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3523-3542.
[14] LI H C,QIU L W,LI Z,et al.Automatic rocks segmentation based on deep learning for planetary rover images[J].Natural Science,2021,18(11):755-761.
[15] SWAN R M,ATHA D,LEOPOLD H A,et al.AI4Mars:a dataset for terrain-aware autonomous driving on Mars[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2021:1982-1991.
[16] 李春来,刘建军,耿言,等.中国首次火星探测任务科学目标与有效载荷配置[J].深空探测学报,2018,5(5):406-413. LI C L,LIU J J,GENG Y,et al.Scientific objectives and payload configuration of China's first Mars exploration mission[J].Journal of Deep Space Exploration,2018,5(5):406-413.(in Chinese)
[17] LIANG X,CHEN W L,CAO Z X,et al.The navigation and terrain cameras on the Tianwen-1 Mars rover[J].Space Science Reviews,2021,217(3):37.
[18] HUGHES J S,CRICHTON D,HARDMAN S,et al.PDS4:a model-driven planetary science data architecture for long-term preservation[C]//Proceedings of the 30th IEEE International Conference on Data Engineering.Washington D.C.,USA:IEEE Press,2014:134-141.
[19] TAN X,LIU J J,ZHANG X X,et al.Design and validation of the scientific data products for China's Tianwen-1 mission[J].Space Science Reviews,2021,217(5):69.
[20] RUSSELL B C,TORRALBA A,MURPHY K P,et al.LabelMe:a database and web-based tool for image annotation[J].International Journal of Computer Vision,2008,77(1):157-173.
[21] QIU L W,LI H C,LI Z,et al.Residual grounding transformer network for terrain recognition on the lunar surface[J].Applied Optics,2021,60(21):6002-6014.
[22] SANDLER M,HOWARD A,ZHU M L,et al.MobileNetV2:inverted residuals and linear bottlenecks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:4510-4520.
[23] HOWARD A,SANDLER M,CHEN B,et al.Searching for MobileNetV3[C]//Proceedings of IEEE/CVF International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2020:1314-1324.
[24] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
[25] IBTEHAZ N,RAHMAN M S.MultiResUNet:rethinking the U-Net architecture for multimodal biomedical image segmentation[J].Neural Networks,2020,121:74-87.

Please choose a citation manager

Content to export