SEGMENTASI BAGIAN TUBUH MANUSIA 3D POINT CLOUD BERBASIS SPHERICAL PROJECTION MENGGUNAKAN MASK R-CNN
Abstract
Teknologi sensor yang berkembang pesat, yaitu Light Detection and Ranging (LiDAR), banyak digunakan dalam bidang segmentasi citra dan deteksi objek. Point cloud 3D, yang memvisualisasikan pantulan objek, menjadi hasil dari teknologi ini. Namun, kendala atau tantangan muncul dalam segmentasi point cloud 3D karena struktur data yang tidak beraturan, menyebabkan noise dan tumpang tindih bentuk objek. Hal ini memengaruhi keakuratan segmentasi dan deteksi objek. Untuk mengatasi masalah tersebut, jawabannya ditemukan dalam pendekatan proyeksi bola. Dengan mengubah data point cloud 3D menjadi gambar 2D, proses segmentasi gambar menjadi lebih mudah. Tujuannya adalah untuk segmentasi bagian tubuh dengan menggunakan data 3D point cloud, Saat melakukan segmentasi gambar hasil konversi data 3D ke 2D menggunakan deep learning, model yang efektif untuk mempelajari data tersebut adalah Mask R-CNN. Akurasi 59% berhasil dicapai dalam 200 epoch berdasarkan data pelatihan. Penelitian ini diharapkan dapat membuka jalan untuk penelitian lebih lanjut guna menyempurnakan dan mengembangkan ilmu pengetahuan dibidang computer vision dan kecerdasan buatan.
Kata kunci: LiDAR; Point Cloud; Segmentasi; Spherical Projection
Full Text:
PDFReferences
Bellynza, Ken Ayu, and Hadi Syaputra. 2022. “Objek Deteksi Burung Lovebird Menggunakan Instance Segmentation Mask R-Cnn.” Bina Darma Conference on Computer Science(BDCCS2022) 4 (1).
Chen, Guo Dong, and Fei Fei Wang. 2017. “Medical Data Point Clouds Reconstruction Algorithm Based on Tensor Product B-Spline Approximation in Virtual Surgery.” Journal of Medical and Biological Engineering 37 (2). https://doi.org/10.1007/s40846-016-0211-3.
Dai, Angela, Angel X Chang, Manolis Savva, Maciej Halber, and Thomas Funkhouser. 2017. “ScanNet : Richly-Annotated 3D Reconstructions of Indoor Scenes.” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), no. 10.1109/CVPR.2017.261.
Danielczuk, Michael, Matthew Matl, Saurabh Gupta, Andrew Li, Andrew Lee, Jeffrey Mahler, and Ken Goldberg. 2019. “Segmenting Unknown 3D Objects from Real Depth Images Using Mask R-CNN Trained on Synthetic Data.” Proceedings - IEEE International Conference on Robotics and Automation 2019-May: 7283–90. https://doi.org/10.1109/ICRA.2019.8793744.
He, Kaiming, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. 2017. “Mask R-CNN.”
Hochman, J., H. R. Bourne, P. Coffino, P. A. Insel, L. Krasny, and K. L. Melmon. 1977. “Subunit Interaction in Cyclic AMP Dependent Protein Kinase of Mutant Lymphoma Cells.” Proceedings of the National Academy of Sciences of the United States of America 74 (3). https://doi.org/10.1073/pnas.74.3.1167.
Hong Hai, Hoang, and Tran Bao Long. 2021. “Improve of Mask R-CNN in Edge Segmentation.” JST: Engineering and Technology for Sustainable Development 31 (3): 97–104. https://doi.org/10.51316/jst.151.etsd.2021.31.3.17.
Kadam, Kalyani Dhananjay, Ketan Kotecha, and Swati Ahirrao. 2023. “Retracted: Efficient Approach towards Detection and Identification of Copy Move and Image Splicing Forgeries Using Mask R-CNN with MobileNet V1.” Computational Intelligence and Neuroscience 9786963 (13). https://doi.org/10.1155/2023/9786963.
Kim, Songeun, and Soon Yong Park. 2022. “Expandable Spherical Projection and Feature Concatenation Methods for Real-Time Road Object Detection Using Fisheye Image.” Applied Sciences (Switzerland) 12 (5). https://doi.org/10.3390/app12052403.
Krähenbühl, Philipp, and Vladlen Koltun. 2014. “Geodesic Object Proposals.” European Conference on Computer Vision (ECCV) 8693. https://doi.org/10.1007/978-3-319-10602-1_47.
Krawczyk, Damian, and Robert Sitnik. 2023. “Segmentation of 3D Point Cloud Data Representing Full Human Body Geometry: A Review.” Pattern Recognition 139: 109444. https://doi.org/10.1016/j.patcog.2023.109444.
Le, Van Hung, and Rafal Scherer. 2021. “Human Segmentation and Tracking Survey on Masks for Mads Dataset.” Sensors 21 (24): 1–22. https://doi.org/10.3390/s21248397.
Lin, Kailian, Huimin Zhao, Jujian Lü, Jin Zhan, Xiaoyong Liu, and Rongjun Chen. 2020. “Face Detection and Segmentation Method Based on Mask R-CNN.” Jisuanji Gongcheng/Computer Engineering 46 (6). https://doi.org/10.19678/j.issn.1000-3428.0054566.
Lin, Tsung-Yi, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. “Microsoft COCO: Common Objects in Context.” Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland 8693 (10.1007/978-3-319-10602-1_48).
Liu, Maohua, Yue Shao, Ruren Li, Yan Wang, Xiubo Sun, Jingkuan Wang, and Yingchun You. 2020. “Method for Extraction of Airborne LiDAR Point Cloud Buildings Based on Segmentation.” PLoS ONE 15 (5). https://doi.org/10.1371/journal.pone.0232778.
Marpaung, Faridawaty, Arnita, Fitrahuda Aulia, Nita Suryani, and Rinjani Cyra Nabila. 2022. COMPUTER VISION DAN PENGOLAHAN CITRA DIGITAL.
Plagemann, Christian, and Daphne Koller. 2010. “Real-Time Identification and Localization of Body Parts from Depth Images.” IEEE International Conference on Robotics and Automation, Anchorage, AK, USA 3108–3 (10.1109/ROBOT.2010.5509559).
Rao, Deepak, Quoc V Le, Thanathorn Phoka, Morgan Quigley, Attawith Sudsang, and Andrew Y Ng. 2010. “Grasping Novel Objects with Depth Segmentation.” 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, Taiwan 2578 (10.1109/IROS.2010.5650493).
Ryselis, Karolis, Tomas Blažauskas, Robertas Damaševičius, and Rytis Maskeliūnas. 2022. “Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images.” Sensors 22 (9). https://doi.org/10.3390/s22093531.
Schult, Jonas, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, and Bastian Leibe. 2023. “Mask3D: Mask Transformer for 3D Semantic Instance Segmentation.” Proceedings - IEEE International Conference on Robotics and Automation 2023. https://doi.org/10.1109/ICRA48891.2023.10160590.
Takmaz, Ayça, Jonas Schult, Irem Kaftan, Mertcan Akçay, Bastian Leibe, Robert Sumner, Francis Engelmann, and Siyu Tang. 2022. “3D Segmentation of Humans in Point Clouds with Synthetic Data.” http://arxiv.org/abs/2212.00786.
Uckermann, Andre, Christof Elbrechter, Robert Haschke, and Helge Ritter. 2012. “3D Scene Segmentation for Autonomous Robot Grasping.” IEEE International Conference on Intelligent Robots and Systems, no. October 2012. https://doi.org/10.1109/IROS.2012.6385692.
Wood, Erroll, Tadas Baltruˇ, Hewitt Sebastian, Matthew Johnson, Virginia Estellers, Thomas J Cashman, and Jamie Shotton. 2021. “Fake It till You Make It : Face Analysis in the Wild Using Synthetic Data Alone.” IEEE/CVF International Conference on Computer Vision (ICCV), no. 10.1109/ICCV48922.2021.00366.
Wu, Xin, Shiguang Wen, and Yuan ai Xie. 2019. Improvement of Mask-RCNN Object Segmentation Algorithm. Intelligent Robotics and Applications. ICIRA 2019. Vol. 11740. Springer International Publishing. https://doi.org/10.1007/978-3-030-27526-6_51.
Xu, Jiaxin, Rui Wang, Vaibhav Rakheja, and Computing Science. 2019. “Literature Review: Human Segmentation with Static Camera.” Computer Vision and Pattern Recognition 1 (https://doi.org/10.48550/arXiv.1910.12945).
Yao, R U I, Guosheng Lin, Shixiong Xia, Jiaqi Zhao, and Yong Zhou. 2019. “Video Object Segmentation and Tracking : A Survey.” ACM Transactions on Intelligent Systems and Technology 11 (https://doi.org/10.1145/3391743).
Zhang, Song-hai, Ruilong Li, Xin Dong, Paul Rosin, Zixi Cai, Xi Han, Dingcheng Yang, Haozhi Huang, and Shi-min Hu. 2019. “Pose2Seg : Detection Free Human Instance Segmentation.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 898 (10.1109/CVPR.2019.00098).
Refbacks
- There are currently no refbacks.
==============================================================================================================
Prosiding SEMNASTEK Fakultas Teknik
Universitas Muhammadiyah Jakarta
Jl. Cempaka Putih Tengah 27
Jakarta Pusat 10510
T. 021.4256024, 4244016 / F. 021.4256023
ISSN : 2407 – 1846
e-ISSN : 2460 – 8416
==============================================================================================================