AirCap – Aerial Outdoor Motion Capture (Talk)
In this talk I will present an overview and the latest results of the project Aerial Outdoor Motion Capture (AirCap), running at the Perceiving Systems department. AirCap's goal is to achieve markerless and unconstrained human motion capture (MoCap) in unknown and unstructured outdoor environments. To this end, we have developed a flying MoCap system using a team of autonomous aerial robots with on-board, monocular RGB cameras. Our system is endowed with a range of novel functionalities which was developed by our group over the last 3 years. These include, i) cooperative detection and tracking that enables DNN-based detectors on board flying robots, ii) active cooperative perception in aerial robot teams to minimize joint tracking uncertainty, and iii) markerless human pose and shape estimation using images acquired from multiple views and approximately calibrated cameras. We have conducted several real experiments along with ground truth comparisons to validate our system. Overall, for outdoor scenarios we have demonstrated the first fully autonomous flying MoCap system involving multiple aerial robots.
Biography: Dr. Aamir Ahmad is leading the Robot Perception Group at the Perceiving Systems department of the Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen. He received his PhD in 2013 from the University of Lisbon, Portugal. In 2013 he was awarded the Marie-Curie Intra-European Fellowship for his project 'TRaVERSE', which he conducted at MPI for Biological Cybernetics in Tübingen (2014-2016). He has participated in national and European research projects such as URUS (FP6), PCMMC (Portuguese FCT project) and RoCKIn (FP7). He is also currently leading the team from MPI-IS in the H2020 project DeepField. During his PhD, he was the perception lead in the robot soccer team 'SocRob' and participated in RoboCup 2009, 2011 and 2013 and all Portuguese opens from 2009 to 2013. Two of his papers have received the recognition of being in the top 10 papers presented at the European Conference on Mobile Robotics (2011 and 2015). He was the winner of the Mobility Grant 2011, awarded by the Portuguese Robotics Society. He has published in top robotics journals, such as IEEE Transactions on Robotics (T-RO), IEEE Robotics and Automation Letters (RA-L), Elsevier's Robotics and Autonomous Systems Journal (RAS) and Elsevier's Computer Vision and Image Understanding (CVIU). He has also published in top robotics conferences such as ICRA, IROS and ECMR. His core research interest lies in vision-based robot perception, state estimation, object tracking, formation control of multirobot systems and mobile robot localization, navigation and control.