Dr Peyman Moghadam

Adjunct Senior Fellow

School of Information Technology and Electrical Engineering
Faculty of Engineering, Architecture and Information Technology

Overview

Dr Peyman Moghadam is leading Deep Learning for Robotics research at the CSIRO Robotics and Autonomous Systems group. He is a senior Research Scientist and the AgTech Cluster Leader for Robotics and Autonomous Systems, CSIRO, Data61. He is an Adjunct Professor at the Queensland University of Technology and Adjunct Senior Fellow at the University of Queensland. He received his PhD in Robotics from the Nanyang Technological University (Singapore) in 2011. Before joining CSIRO, he has worked in number of top leading organizations such as the Deutsche Telekom Laboratories (Germany), the Singapore-MIT Alliance for Research and Technology (Singapore). His current research interests focus on Self-Supervised Learning and Embodied Intelligence for Robotics. Professor Moghadam has led several large-scale multidisciplinary projects and he has won numerous awards for his innovations including CSIRO Julius Career award, National and Queensland iAward for Research and Development, the Lord Mayor’s Budding Entrepreneurs Award.

Research Interests

  • Beyond visible Spectrum Perception (Hyperspectral, Thermal)
  • Robotics, Computer Vision, Machine Learning, Deep Learning
  • Embodied Intelligence; Self-Supervised Learning; spatiotemporal learning
  • 3D LiDAR SLAM; 3D Scene understanding; 3D Segmentation

Publications

  • Park, Chanoh, Moghadam, Peyman, Kim, Soohwan, Sridharan, Sridha and Fookes, Clinton (2020) Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach. IEEE Robotics and Automation Letters, 5 2: 1556-1563. doi:10.1109/lra.2020.2969164

  • Park, Chanoh, Kim, Soohwan, Moghadam, Peyman, Guo, Jiadong, Sridharan, Sridha and Fookes, Clinton (2019) Robust photogeometric localization over time for map-centric loop closure. IEEE Robotics and Automation Letters, 4 2: 1768-1775. doi:10.1109/lra.2019.2895262

  • Ward, Daniel, Moghadam, Peyman and Hudson, Nicolas (2019). Deep leaf segmentation using synthetic data. In: British Machine Vision Conference 2018, BMVC 2018, Newcastle, United Kingdom, (). 3 - 6 September 2018.

View all Publications

Available Projects

  • Potential impact of deep learning is limited due to the lack of large, annotated, and high-quality datasets in domains of interest. Annotating such datasets is laborious, costly and time-consuming. This project proposes to develop self-supervised learning systems to extract and use the relevant context given by strong prior spatio-temporal models (e.g. dense 3D reconstructions) as supervisory signals in training. This new concept will investigate model structures that encodes spatio-temporal data, and show rapid adaptation of models to new domains (few-shot learning) using trained embeddings layers (self-supervised, or prior data).

  • Simultaneous Localization and Mapping (SLAM) is a key enabling component of driverless vehicles, robotics and augmented reality. The SLAM goal is to estimate pose of the vehicle and simultaneously generate dense 3D scene reconstruction. At CSIRO we have developed and deployed state-of-the-art 3D LiDAR-based SLAM systems for the past decade. There is a new direction of research at the intersection of deep learning and geometry-based 3D SLAM. The research in this PhD programme will develop algorithms for geometry-based Deep Learning SLAM in a dynamic and unstructured environment. The PhD programme will involve the development of self or semi-supervised learning methods to address the significant weakness of most current deep networks.

  • Hyperspectral cameras are currently undergoing a change from bulky and expensive equipment towards mobile and portable devices. A hyperspectral camera comprises of hundreds of bands with shortwave dependencies. Compared to conventional colour cameras (RGB bands), one could use these shortwave dependencies to design and develop a deep network for object classification, semantic segmentation and scene understanding. Both spectral and spatial relationship needs to be modelled by the deep networks simultaneously. The research in this PhD programme will develop algorithms for hyperspectral deep learning. The PhD programme will involve the development of learning with self-supervision algorithms to address the significant weakness of most current deep networks.

View all Available Projects

Publications

Journal Article

Conference Publication

  • Ward, Daniel, Moghadam, Peyman and Hudson, Nicolas (2019). Deep leaf segmentation using synthetic data. In: British Machine Vision Conference 2018, BMVC 2018, Newcastle, United Kingdom, (). 3 - 6 September 2018.

  • Park, Chanoh, Moghadam, Peyman, Kim, Soohwan, Elfes, Alberto, Fookes, Clinton and Sridharan, Sridha (2018). Elastic LiDAR fusion: Dense map-centric continuous-time SLAM. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia, (). 21-25 May 2018. doi:10.1109/icra.2018.8462915

  • Elanattil, Shafeeq, Moghadam, Peyman, Sridharan, Sridha, Fookes, Clinton and Cox, Mark (2018). Non-rigid Reconstruction with a Single Moving RGB-D Camera. In: 2018 24th International Conference on Pattern Recognition (ICPR). 24th International Conference on Pattern Recognition (ICPR), Beijing, China, (1049-1055). 20-24 August, 2018. doi:10.1109/icpr.2018.8546201

  • Elanattil, Shafeeq, Moghadam, Peyman, Denman, Simon, Sridharan, Sridha and Fookes, Clinton (2018). Skeleton driven non-rigid motion tracking and 3D reconstruction. In: 2018 Digital Image Computing: Techniques and Applications (DICTA). Digital Image Computing: Techniques and Applications (DICTA), Canberra, Australia, (). 10-13 December, 2018. doi:10.1109/dicta.2018.8615797

  • Moghadam, Peyman, Ward, Daniel, Goan, Ethan, Jayawardena, Srimal, Sikka, Pavan and Hernandez, Emili (2017). Plant disease detection using hyperspectral imaging. In: Guo, Y, Li, H, Cai, W, Murshed, M, Wang, Z, Gao, J and Feng, DD, 2017 International Conference On Digital Image Computing - Techniques and Applications (Dicta). International Conference on Digital Image Computing - Techniques and Applications (DICTA), Sydney, Australia, (384-391). 29 November - 1 December 2017.

  • Park, Chanoh, Kim, Soohwan, Moghadam, Peyman, Fookes, Clinton and Sridharan, Sridha (2017). Probabilistic surfel fusion for dense LiDAR mapping. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). 16th IEEE International Conference on Computer Vision (ICCV 2017), Venice, Italy, (2418-2426). 22-29 October 2017. doi:10.1109/ICCVW.2017.285

  • Hoerger, Marcus, Kottege, Navinda, Bandyopadhyay, Tirthankar, Elfes, Alberto and Moghadam, Peyman (2016). Real-Time Stabilisation for Hexapod Robots. In: Hsieh, MA, Khatib, O and Kumar, V, 14th International Symposium on Experimental Robotics (ISER), Morocco, (729-744). 15-18 June 2014 . doi:10.1007/978-3-319-23778-7_48

  • Williamson, Dylan, Kottege, Navinda and Moghadam, Peyman (2016). Terrain characterisation and gait adaptation by a hexapod robot. In: Australasian Conference on Robotics and Automation, ACRA. Australasian Conference on Robotics and Automation, ACRA, Brisbane, Australia, (20-29). 5-7 December 2016.

  • Moghadam, Peyman (2015). 3D medical thermography device. In: SJ Hsieh and JN Zalameda, SPIE Conference on Thermosense - Thermal Infrared Applications XXXVII, Baltimore, MD, United States, (). 20-23 April, 2015. doi:10.1117/12.2177880

  • Cunningham-Nelson, Samuel, Moghadam, Peyman, Roberts, Jonathan and Elfes, Alberto (2015). Coverage-based next best view selection. In: Australasian Conference on Robotics and Automation, ACRA. Australasian Conference on Robotics and Automation, ACRA, Canberra, Australia, (). 2-4 December 2015.

  • Kottege, Navinda, Parkinson, Callum, Moghadam, Peyman, Elfes, Alberto and Singh, Surya P.N (2015). Energetics-informed hexapod gait transitions across terrains. In: 2015 IEEE International Conference on Robotics and Automation, ICRA 2015. 2015 IEEE International Conference on Robotics and Automation, ICRA 2015, Washington State Convention Center Seattle, Washington, United States, (5140-5147). 26-30 May 2015. doi:10.1109/ICRA.2015.7139915

  • Best, Graeme and Moghadam, Peyman (2014). An evaluation of multi-modal user interface elements for tablet-based robot teleoperation. In: Australasian Conference on Robotics and Automation, ACRA. Australasian Conference on Robotics and Automation, ACRA, Melbourne, Australia, (). 2-4 December 2014.

  • Borges, Paulo Vinicius Koerich and Moghadam, Peyman (2014). Combining motion and appearance for scene segmentation. In: Proceedings - IEEE International Conference on Robotics and Automation. 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, (1028-1035). 31 May - 7 June. doi:10.1109/ICRA.2014.6906980

  • Moghadam, Peyman and Vidas, Stephen (2014). HeatWave: the next generation of thermography devices. In: FP Colbert and SJ Hsieh, Conference on Thermosense - Thermal Infrared Applications XXXVI, Baltimore, MD, United States, (). 5-7 May, 2014. doi:10.1117/12.2053950

  • Roshandel, Mehran, Munjal, Aarti, Moghadam, Peyman, Tajik, Shahin and Ketabdar, Hamed (2014). Multi-sensor Based Gestures Recognition with a Smart Finger Ring. In: Kurosu, M, 16th International Conference on Human-Computer Interaction (HCI), Heraklion Greece, (316-324). Jun 22-27, 2014.

  • Roshandel, Mehran, Munjal, Aarti, Moghadam, Peyman, Tajik, Shahin and Ketabdar, Hamed (2014). Multi-sensor finger ring for authentication based on 3D signatures. In: Masaaki Kurosu, Proceedings of the 16th International Conference, HCI International 2014. 16th International Conference on Human-Computer Interaction (HCI), Heraklion, Greece, (131-138). 22 - 27 June 2014.

  • Moghadam, Peyman, Vidas, Stephen and Lam, Obadiah (2014). Spectra: 3D multispectral fusion and visualization toolkit. In: Australasian Conference on Robotics and Automation, ACRA. Australasian Conference on Robotics and Automation, ACRA, Melbourne, Australia, (). 2-4 December 2014.

  • Vidas, Stephen and Moghadam, Peyman (2013). Ad Hoc Radiometric Calibration of a Thermal-Infrared Camera. In: DeSouza, P, Engelke, U and Rahman, A, 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA). International Conference on Digital Image Computing - Techniques and Applications (DICTA), Hobart Australia, (125-132). Nov 26-28, 2013. doi:10.1109/dicta.2013.6691478

  • Vidas, Stephen, Moghadam, Peyman and Bosse, Michael (2013). 3D thermal mapping of building interiors using an RGB-D and thermal camera. In: Proceedings - IEEE International Conference on Robotics and Automation. 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, (2311-2318). 6-10 May 2013. doi:10.1109/icra.2013.6630890

  • Moghadam, Peyman, Bosse, Michael and Zlot, Robert (2013). Line-based extrinsic calibration of range and image sensors. In: Proceedings - IEEE International Conference on Robotics and Automation. 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, (3685-3691). 6-10 May 2013. doi:10.1109/icra.2013.6631095

  • Best, Graeme, Moghadam, Peyman, Kottege, Navinda and Kleeman, Lindsay (2013). Terrain classification using a hexapod robot. In: 2013 Australasian Conference on Robotics and Automation, ACRA 2013. Australasian Conference on Robotics and Automation, ACRA , Sydney, Australia, (). 2-4 December 2013.

  • Moghadam, Peyman and Dong, Jun Feng (2012). Road direction detection based on vanishing-point tracking. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. 25th IEEE\RSJ International Conference on Intelligent Robots and Systems (IROS), Algarve Portugal, (1553-1560). Oct 07-12, 2012. doi:10.1109/iros.2012.6386089

  • Shirazi, Alireza Sahami, Moghadam, Peyman, Ketabdar, Hamed and Schmidt, Albrecht (2012). Assessing the vulnerability of magnetic gestural authentication to video-based shoulder surfing attacks. In: Proceedings of the 30th ACM Conference on Human Factors in Computing Systems, CHI 2012. 30th ACM Conference on Human Factors in Computing Systems, CHI 2012, Austin, TX, United States, (2045-2048). 5 - 10 May 2012. doi:10.1145/2207676.2208352

  • Ketabdar, Hamed, Chang, Hengwei, Moghadam, Peyman, Roshandel, Mehran and Naderi, Babak (2012). Magi Guitar: A Guitar that is Played in Air!. In: 14th ACM International Conference on Human Computer Interaction with Mobile Devices and Services (MobileHCI), San Francisco Ca, (181-184). Sep 21-24, 2012.

  • Ketabdar, Hamed, Moghadam, Peyman, Naderi, Babak and Roshandel, Mehran (2012). Magnetic signatures in air for mobile devices. In: Proceedings of the 14th International Conference on Human Computer Interaction with Mobile Devices and Services (MobileHCI '12). 14th ACM International Conference on Human Computer Interaction with Mobile Devices and Services (MobileHCI '12), San Francisco, CA, United States, (185-188). 21-24 September 2012. doi:10.1145/2371664.2371705

  • Ketabdar, Hamed, Moghadam, Peyman and Roshandel, Mehran (2012). Pingu: a new miniature wearable device for ubiquitous computing environments. In: Proceedings - 2012 6th International Conference on Complex, Intelligent, and Software Intensive Systems, CISIS 2012. Sixth International Conference on Complex, Intelligent, and Software Intensive Systems , Palermo, Italy, (502-506). 4-6 July 2012. doi:10.1109/cisis.2012.123

  • Moghadam, Peyman, Salehi, Saba and Wijesoma, Wijerupage Sardha (2011). Computationally efficient navigation system for unmanned ground vehicles. In: Proceedings of the 2011 IEEE Conference on Technologies for Practical Robot Applications. 2011 IEEE Conference on Technologies for Practical Robot Applications, Woburn, MA, United States, (133-138). 11-12 April 2011. doi:10.1109/tepra.2011.5753495

  • Moratuwage, M. D. P., Wijesoma, W. S., Kalyan, B., Patrikalakis, Nicholas M. and Moghadam, Peyman (2010). Collaborative Multi-Vehicle Localization and Mapping in High Clutter Environments. In: 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010), Singapore Singapore, (1422-1427). Dec 07-10, 2010.

  • Moghadam, Peyman, Wijesoma, Wijerupage Sardha and Moratuwage, M. D. P. (2010). Towards A Fully-Autonomous Vision-based Vehicle Navigation System in Outdoor Environments. In: 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010), Singapore Singapore, (597-602). Dec 07-10, 2010.

  • Moghadam, Peyman and Wijesoma, Wijerupage Sardha (2009). Online, Self-Supervised Vision-Based Terrain Classification in Unstructured Environments. In: IEEE International Conference on Systems, Man and Cybernetics, San Antonio Tx, (3100-3105). Oct 11-14, 2009. doi:10.1109/ICSMC.2009.5345942

  • Moghadam, Peyman, Wijesorna, Wijerupage Sardha and Feng, Dong Jun (2008). Improving Path Planning and Mapping Based on Stereo Vision and Lidar. In: 10th International Conference on Control, Automation, Robotics and Vision, Hanoi Vietnam, (384-389). Dec 17-20, 2008. doi:10.1109/ICARCV.2008.4795550

Possible Research Projects

Note for students: The possible research projects listed on this page may not be comprehensive or up to date. Always feel free to contact the staff for more information, and also with your own research ideas.

  • Potential impact of deep learning is limited due to the lack of large, annotated, and high-quality datasets in domains of interest. Annotating such datasets is laborious, costly and time-consuming. This project proposes to develop self-supervised learning systems to extract and use the relevant context given by strong prior spatio-temporal models (e.g. dense 3D reconstructions) as supervisory signals in training. This new concept will investigate model structures that encodes spatio-temporal data, and show rapid adaptation of models to new domains (few-shot learning) using trained embeddings layers (self-supervised, or prior data).

  • Simultaneous Localization and Mapping (SLAM) is a key enabling component of driverless vehicles, robotics and augmented reality. The SLAM goal is to estimate pose of the vehicle and simultaneously generate dense 3D scene reconstruction. At CSIRO we have developed and deployed state-of-the-art 3D LiDAR-based SLAM systems for the past decade. There is a new direction of research at the intersection of deep learning and geometry-based 3D SLAM. The research in this PhD programme will develop algorithms for geometry-based Deep Learning SLAM in a dynamic and unstructured environment. The PhD programme will involve the development of self or semi-supervised learning methods to address the significant weakness of most current deep networks.

  • Hyperspectral cameras are currently undergoing a change from bulky and expensive equipment towards mobile and portable devices. A hyperspectral camera comprises of hundreds of bands with shortwave dependencies. Compared to conventional colour cameras (RGB bands), one could use these shortwave dependencies to design and develop a deep network for object classification, semantic segmentation and scene understanding. Both spectral and spatial relationship needs to be modelled by the deep networks simultaneously. The research in this PhD programme will develop algorithms for hyperspectral deep learning. The PhD programme will involve the development of learning with self-supervision algorithms to address the significant weakness of most current deep networks.