MSc. Ihtisham Ali's research focuses on several key areas, including hand-eye calibration and multiview pose estimation. He introduces a novel formulation that addresses these issues with enhanced accuracy, precision, and robustness.
Another area of interest for Ali is visual simultaneous localization and mapping. He proposes a pose estimation and mapping scheme that can track dynamic entities and update the map, enabling autonomous machines to operate in even the most challenging environments.
Shaping the future of machine autonomy
Additionally, Ali introduces the FinnForest dataset, a valuable resource for visual odometry and simultaneous localization and mapping methods in forest environments. In an extension to his work, Ali proposes a solution for autonomous vehicles to localize an observer with extreme perspective changes and achieve bi-directional loop closure on monocular images.
The solution employs deep learning to separate place identification and pose regression and demonstrates the potential for bi-directional loop closure with sufficient training data. With his innovative solutions and cutting-edge research, Ali is helping to shape the future of machine autonomy and making a lasting contribution to this exciting and rapidly evolving field.
Public defence on 24 February
The doctoral dissertation of Ihtisham Ali in the field of machine autonomy titled Methods, Models, and Datasets for Visual Servoing and Vehicle Localisation will be publicly examined in the Faculty of Information Technology and Communication Sciences at Tampere University at 12 o’clock on Friday 24 February 2023 in auditorium TB109 of Tietotalo building (Korkeakoulunkatu 1, Tampere). The Opponents will be Assistant Professor Juho Kannala from Aalto University and Dr Sven Fleck from SmartSurv Vision Systems GmbH in Germany. The Custos will be Professor Atanas Gotchev from Tampere University. The thesis is co-supervised by Dr Sari Peltonen, Tampere University.
The dissertation is available online.
Photo: Zeeshan Waheed